Python机器学习基础教程代码记录
from sklearn.datasets import load_iris
import numpy as np
from scipy import sparse
import matplotlib.pyplot as plt
import pandas as pd
from IPython.display import display
import mglearn
from sklearn.model_selection import train_test_split
iris_dataset=load_iris()
import datetime
print('Keys of iris_dataset:\n{}'.format(iris_dataset.keys()))
Keys of iris_dataset:
dict_keys(['data', 'target', 'frame', 'target_names', 'DESCR', 'feature_names', 'filename'])
print(iris_dataset['DESCR'][:193]+'\n...')
.. _iris_dataset:
Iris plants dataset
--------------------
**Data Set Characteristics:**
:Number of Instances: 150 (50 in each of three classes)
:Number of Attributes: 4 numeric, pre
...
print('Target names:{}'.format(iris_dataset['target_names']))
Target names:['setosa' 'versicolor' 'virginica']
print('Feature names:\n{}'.format(iris_dataset['feature_names']))
Feature names:
['sepal length (cm)', 'sepal width (cm)', 'petal length (cm)', 'petal width (cm)']
print('Type of data:{}'.format(type(iris_dataset['data'])))
Type of data:<class 'numpy.ndarray'>
print('Shape of data:{}'.format(iris_dataset['data'].shape))
Shape of data:(150, 4)
print('First five ros of data:\n{}'.format(iris_dataset['data'][:5]))
First five ros of data:
[[5.1 3.5 1.4 0.2]
[4.9 3. 1.4 0.2]
[4.7 3.2 1.3 0.2]
[4.6 3.1 1.5 0.2]
[5. 3.6 1.4 0.2]]
print('Type of target:{}'.format(type(iris_dataset['target'])))
Type of target:<class 'numpy.ndarray'>
print('Shape of target:{}'.format(iris_dataset['target'].shape))
Shape of target:(150,)
print('Target:\n{}'.format(iris_dataset['target']))
Target:
[0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2 2
2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2
2 2]
from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test=train_test_split(iris_dataset['data'],iris_dataset['target'],random_state=0)
print('X_train shape:{}'.format(X_train.shape))
print('y_train shape:{}'.format(y_train.shape))
X_train shape:(112, 4)
y_train shape:(112,)
print('X_test shape:{}'.format(X_test.shape))
print('y_test.shape:{}'.format(y_test.shape))
X_test shape:(38, 4)
y_test.shape:(38,)
import pandas as pd
iris_dataframe=pd.DataFrame(X_train,columns=iris_dataset['feature_names'])
grr=pd.plotting.scatter_matrix(iris_dataframe,c=y_train,figsize=(15,15),marker='o',hist_kwds={'bins':30},s=60,alpha=0.8,cmap=mglearn.cm3)
from sklearn.neighbors import KNeighborsClassifier
knn=KNeighborsClassifier(n_neighbors=1)
knn.fit(X_train,y_train)
KNeighborsClassifier(n_neighbors=1)
X_new=np.array([[5,2.9,1,0.2]])
print('X_new.shape:{}'.format(X_new.shape))
X_new.shape:(1, 4)
prediction=knn.predict(X_new)
print('Prediction:{}'.format(prediction))
print('Prediction target name:{}'.format(iris_dataset['target_names'][prediction]))
Prediction:[0]
Prediction target name:['setosa']
y_pred=knn.predict(X_test)
print('Test set predictions:\n{}'.format(y_pred))
Test set predictions:
[2 1 0 2 0 2 0 1 1 1 2 1 1 1 1 0 1 1 0 0 2 1 0 0 2 0 0 1 1 0 2 1 0 2 2 1 0
2]
print('Test set score:{:.2f}'.format(np.mean(y_pred==y_test)))
Test set score:0.97
print('Test set score:{:.2f}'.format(knn.score(X_test,y_test)))
Test set score:0.97
X,y=mglearn.datasets.make_forge()
mglearn.discrete_scatter(X[:,0],X[:,1],y)
plt.legend(['Class 0','Class 1'],loc=4)
plt.xlabel('First feature')
plt.ylabel('Second feature')
print('X.shape:{}'.format(X.shape))
X.shape:(26, 2)
C:\Users\reion\anaconda3\lib\site-packages\sklearn\utils\deprecation.py:86: FutureWarning: Function make_blobs is deprecated; Please import make_blobs directly from scikit-learn
warnings.warn(msg, category=FutureWarning)
X,y=mglearn.datasets.make_wave(n_samples=40)
plt.plot(X,y,'o')
plt.ylim(-3,3)
plt.xlabel("Feature")
plt.ylabel("Target")
Text(0, 0.5, 'Target')
from sklearn.datasets import load_breast_cancer
cancer=load_breast_cancer()
print('cancer.keys():\n{}'.format(cancer.keys()))
cancer.keys():
dict_keys(['data', 'target', 'frame', 'target_names', 'DESCR', 'feature_names', 'filename'])
print('Shape of cancer data:{}'.format(cancer.data.shape))
Shape of cancer data:(569, 30)
print('Sample counts per class:\n{}'.format({n:v for n,v in zip(cancer.target_names,np.bincount(cancer.target))}))
Sample counts per class:
{'malignant': 212, 'benign': 357}
print('Feature names:{}'.format(cancer.feature_names))
Feature names:['mean radius' 'mean texture' 'mean perimeter' 'mean area'
'mean smoothness' 'mean compactness' 'mean concavity'
'mean concave points' 'mean symmetry' 'mean fractal dimension'
'radius error' 'texture error' 'perimeter error' 'area error'
'smoothness error' 'compactness error' 'concavity error'
'concave points error' 'symmetry error' 'fractal dimension error'
'worst radius' 'worst texture' 'worst perimeter' 'worst area'
'worst smoothness' 'worst compactness' 'worst concavity'
'worst concave points' 'worst symmetry' 'worst fractal dimension']
from sklearn.datasets import load_boston
boston=load_boston()
print('Data shape:{}'.format(boston.data.shape))
Data shape:(506, 13)
mglearn.plots.plot_knn_classification(n_neighbors=1)
C:\Users\reion\anaconda3\lib\site-packages\sklearn\utils\deprecation.py:86: FutureWarning: Function make_blobs is deprecated; Please import make_blobs directly from scikit-learn
warnings.warn(msg, category=FutureWarning)
mglearn.plots.plot_knn_classification(n_neighbors=3)
C:\Users\reion\anaconda3\lib\site-packages\sklearn\utils\deprecation.py:86: FutureWarning: Function make_blobs is deprecated; Please import make_blobs directly from scikit-learn
warnings.warn(msg, category=FutureWarning)
from sklearn.model_selection import train_test_split
X,y=mglearn.datasets.make_forge()
X_train,X_test,y_train,y_test=train_test_split(X,y,random_state=0)
C:\Users\reion\anaconda3\lib\site-packages\sklearn\utils\deprecation.py:86: FutureWarning: Function make_blobs is deprecated; Please import make_blobs directly from scikit-learn
warnings.warn(msg, category=FutureWarning)
from sklearn.neighbors import KNeighborsClassifier
clf=KNeighborsClassifier(n_neighbors=3)
clf.fit(X_train,y_train)
KNeighborsClassifier(n_neighbors=3)
print('Test set predictions :{}'.format(clf.predict(X_test)))
Test set predictions :[1 0 1 0 1 0 0]
print('Test set accuracy:{:.2f}'.format(clf.score(X_test,y_test)))
Test set accuracy:0.86
fig,axes=plt.subplots(1,3,figsize=(10,3))
for n_neighbors ,ax in zip([1,3,9],axes):
clf=KNeighborsClassifier(n_neighbors=n_neighbors).fit(X,y)
mglearn.plots.plot_2d_separator(clf,X,fill=True,eps=0.5,ax=ax,alpha=0.4)
mglearn.discrete_scatter(X[:,0],X[:,1],y,ax=ax)
ax.set_title('{} neighbor(s)'.format(n_neighbors))
ax.set_xlabel('feature 0')
ax.set_ylabel('feature 1')
from sklearn.datasets import load_breast_cancer
cancer=load_breast_cancer()
X_train,X_test,y_train,y_test=train_test_split(cancer['data'],cancer['target'],stratify=cancer.target,random_state=66)
training_accuracy=[]
testing_accuracy=[]
neighbors_setting=range(1,11)
for n_neighbors in neighbors_setting:
clf=KNeighborsClassifier(n_neighbors=n_neighbors)
clf.fit(X_train,y_train)
training_accuracy.append(clf.score(X_train,y_train))
testing_accuracy.append(clf.score(X_test,y_test))
plt.plot(neighbors_setting,training_accuracy,label='training accuracy')
plt.plot(neighbors_setting,testing_accuracy,label='test accuracy')
plt.ylabel('Accuracy')
plt.xlabel('n_neighbors')
plt.legend()
<matplotlib.legend.Legend at 0x2eac8a873a0>
mglearn.plots.plot_knn_regression(n_neighbors=1)
mglearn.plots.plot_knn_regression(n_neighbors=3)
from sklearn.neighbors import KNeighborsRegressor
X,y=mglearn.datasets.make_wave(n_samples=40)
X_train,X_test,y_train,y_test=train_test_split(X,y,random_state=0)
reg=KNeighborsRegressor(n_neighbors=3)
reg.fit(X_train,y_train)
KNeighborsRegressor(n_neighbors=3)
print('Test set predictions:\n{}'.format(reg.predict(X_test)))
Test set predictions:
[-0.05396539 0.35686046 1.13671923 -1.89415682 -1.13881398 -1.63113382
0.35686046 0.91241374 -0.44680446 -1.13881398]
print('Test set R^2: {:.2f}'.format(reg.score(X_test,y_test)))
Test set R^2: 0.83
fig,axes=plt.subplots(1,3,figsize=(15,4))
line=np.linspace(-3,3,1000).reshape(-1,1)
for n_neighbors ,ax in zip([1,3,9],axes):
reg=KNeighborsRegressor(n_neighbors=n_neighbors)
reg.fit(X_train,y_train)
ax.plot(line,reg.predict(line))
ax.plot(X_train,y_train,'^',c=mglearn.cm2(0),markersize=8)
ax.plot(X_test,y_test,c=mglearn.cm2(1),markersize=8)
ax.set_title(
'{} neighbors(s)\n train score:{:.2f} test score:{:.2f}'.format(
n_neighbors,reg.score(X_train,y_train),reg.score(X_test,y_test)
)
)
ax.set_xlabel('Feature')
ax.set_ylabel('Target')
axes[0].legend(['Model predictions','Training data/target','Test data/targrt'],loc='best')
<matplotlib.legend.Legend at 0x2eac8517550>
mglearn.plots.plot_linear_regression_wave()
w[0]: 0.393906 b: -0.031804
from sklearn.linear_model import LinearRegression
X,y=mglearn.datasets.make_wave(n_samples=60)
X_train,X_test,y_train,y_test=train_test_split(X,y,random_state=42)
lr=LinearRegression().fit(X_train,y_train)
print('lr.coef_:{}'.format(lr.coef_))
print('lr.intercept_:{}'.format(lr.intercept_))
lr.coef_:[0.39390555]
lr.intercept_:-0.031804343026759746
print("Training set score:{:.2f}".format(lr.score(X_train,y_train)))
print('Test set score:{:.2f}'.format(lr.score(X_test,y_test)))
Training set score:0.67
Test set score:0.66
X,y=mglearn.datasets.load_extended_boston()
X_train,X_test,y_train,y_test=train_test_split(X,y,random_state=0)
lr=LinearRegression().fit(X_train,y_train)
print("Train set score:{:.2f}".format(lr.score(X_train,y_train)))
print('Test set score:{:.2f}'.format(lr.score(X_test,y_test)))
Train set score:0.95
Test set score:0.61
from sklearn.linear_model import Ridge
ridge=Ridge().fit(X_train,y_train)
print("Training set score:{:.2f}".format(ridge.score(X_train,y_train)))
print("Test set score:{:.2f}".format(ridge.score(X_test,y_test)))
Training set score:0.89
Test set score:0.75
ridge10=Ridge(alpha=10).fit(X_train,y_train)
print("Training set score:{:.2f}".format(ridge10.score(X_train,y_train)))
print("Test set score:{:.2f}".format(ridge10.score(X_test,y_test)))
Training set score:0.79
Test set score:0.64
ridge01=Ridge(alpha=0.1).fit(X_train,y_train)
print("Training set score:{:.2f}".format(ridge01.score(X_train,y_train)))
print("Test set score:{:.2f}".format(ridge01.score(X_test,y_test)))
Training set score:0.93
Test set score:0.77
plt.plot(ridge.coef_,'s',label='Ridge alpha=1')
plt.plot(ridge10.coef_,'^',label='Ridge alpha=10')
plt.plot(ridge01.coef_,'v',label='Ridge alpha=0.1')
plt.plot(lr.coef_,'o',label='LinearRegression')
plt.xlabel('Coefficient index')
plt.ylabel('Coefficient magnitude')
plt.hlines(0,0,len(lr.coef_))
plt.ylim(-25,25)
plt.legend()
<matplotlib.legend.Legend at 0x2eac87cb070>
mglearn.plots.plot_ridge_n_samples()
from sklearn.linear_model import Lasso
lasso=Lasso().fit(X_train,y_train)
print("Training set score:{:.2f}".format(lasso.score(X_train,y_train)))
print("Test set score:{:.2f}".format(lasso.score(X_test,y_test)))
print('Number of features used:{}'.format(np.sum(lasso.coef_!=0)))
Training set score:0.29
Test set score:0.21
Number of features used:4
lasso001=Lasso(alpha=0.01,max_iter=100000).fit(X_train,y_train)
print("Training set score:{:.2f}".format(lasso001.score(X_train,y_train)))
print("Test set score:{:.2f}".format(lasso001.score(X_test,y_test)))
print('Number of features used:{}'.format(np.sum(lasso001.coef_!=0)))
Training set score:0.90
Test set score:0.77
Number of features used:33
lasso00001=Lasso(alpha=0.0001,max_iter=100000).fit(X_train,y_train)
print("Training set score:{:.2f}".format(lasso00001.score(X_train,y_train)))
print("Test set score:{:.2f}".format(lasso00001.score(X_test,y_test)))
print('Number of features used:{}'.format(np.sum(lasso00001.coef_!=0)))
Training set score:0.95
Test set score:0.64
Number of features used:96
plt.plot(lasso.coef_,'s',label='Lasso alpha=1')
plt.plot(lasso001.coef_,'^',label='Lasso alpha=0.01')
plt.plot(lasso00001.coef_,'v',label='Lasso alpha=0.0001')
plt.plot(ridge01.coef_,'o',label='Ridge alpha=0.1')
plt.legend(ncol=2,loc=(0,1.05))
plt.ylim(-25,25)
plt.xlabel('Coefficient index')
plt.ylabel('Coefficient magnitude')
print(lasso.coef_)
[-0. 0. -0. 0. -0. 0.
-0. 0. -0. -0. -0. 0.
-5.3529079 -0. 0. -0. 0. -0.
-0. -0. -0. -0. -0. -0.
-0. -0. 0. 0. 0. 0.
0. 0. 0. 0. 0. 0.
0. 0. -0. 0. -0. -0.
-0. -0. -0. -0. -0. -0.
-0. 0. 0. 0. 0. 0.
0. 0. 0. 0. -0. -0.
-0. -0. -0. -0. -0. -0.
-0. -0. 0. 0. 0. -0.
-0. -0. 0. -0. -0. 0.
-0. -1.05063037 -3.3104274 -0. -0. 0.
-0. -0. -0. 0. -0. -0.41386744
-0. -0. -0. -0. -0. -0.
-0. -0. -0. -0. -0. 0.
-0. -0. ]
from sklearn.linear_model import LogisticRegression
from sklearn.svm import LinearSVC
X,y=mglearn.datasets.make_forge()
fig,axes=plt.subplots(1,2,figsize=(10,3))
for model,ax in zip([LinearSVC(),LogisticRegression()],axes):
clf=model.fit(X,y)
mglearn.plots.plot_2d_separator(clf,X,fill=False,eps=0.5,ax=ax,alpha=0.7)
mglearn.discrete_scatter(X[:,0],X[:,1],y,ax=ax)
ax.set_title('{}'.format(clf.__class__.__name__))
ax.set_xlabel('Feature 0')
ax.set_ylabel('Feature 1')
axes[0].legend()
C:\Users\reion\anaconda3\lib\site-packages\sklearn\utils\deprecation.py:86: FutureWarning: Function make_blobs is deprecated; Please import make_blobs directly from scikit-learn
warnings.warn(msg, category=FutureWarning)
C:\Users\reion\anaconda3\lib\site-packages\sklearn\svm\_base.py:985: ConvergenceWarning: Liblinear failed to converge, increase the number of iterations.
warnings.warn("Liblinear failed to converge, increase "
<matplotlib.legend.Legend at 0x2eacb6e8a90>
mglearn.plots.plot_linear_svc_regularization()
from sklearn.datasets import load_breast_cancer
cancer=load_breast_cancer()
X_train,X_test,y_train,y_test=train_test_split(cancer.data,cancer.target,stratify=cancer.target,random_state=42)
logreg=LogisticRegression().fit(X_train,y_train)
print('Training set score:{:.3f}'.format(logreg.score(X_train,y_train)))
print("Test set score:{:.3f}".format(logreg.score(X_test,y_test)))
Training set score:0.955
Test set score:0.958
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
logreg100=LogisticRegression(C=100).fit(X_train,y_train)
print('Training set score:{:.3f}'.format(logreg100.score(X_train,y_train)))
print("Test set score:{:.3f}".format(logreg100.score(X_test,y_test)))
Training set score:0.944
Test set score:0.958
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
logreg001=LogisticRegression(C=0.01).fit(X_train,y_train)
print('Training set score:{:.3f}'.format(logreg001.score(X_train,y_train)))
print("Test set score:{:.3f}".format(logreg001.score(X_test,y_test)))
Training set score:0.937
Test set score:0.930
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
plt.plot(logreg.coef_.T,'o',label='C=1')
plt.plot(logreg100.coef_.T,'^',label='C=100')
plt.plot(logreg001.coef_.T,'v',label='C=0.01')
print(logreg.coef_.T)
plt.xticks(range(cancer.data.shape[1]),cancer.feature_names,rotation=90)
plt.hlines(0,0,cancer.data.shape[1])
plt.ylim(-5,5)
plt.xlabel('Coefficient index')
plt.ylabel('Coefficient magnitude')
plt.legend()
[[ 1.61353724]
[ 0.05653993]
[-0.0379765 ]
[ 0.00296929]
[-0.07199378]
[-0.31364118]
[-0.43808733]
[-0.18276726]
[-0.11456157]
[-0.02433269]
[ 0.06416621]
[ 0.84241837]
[ 0.35199832]
[-0.10429922]
[-0.00674319]
[-0.06786874]
[-0.09653963]
[-0.0240688 ]
[-0.02813081]
[-0.00614864]
[ 1.57958217]
[-0.26155772]
[-0.16723925]
[-0.02556688]
[-0.12867136]
[-1.01367658]
[-1.26659045]
[-0.36289883]
[-0.35240931]
[-0.10159592]]
<matplotlib.legend.Legend at 0x2eacb685be0>
for C,marker in zip([0.001,1,100],['o','^','v']):
lr_l1=LogisticRegression(C=C,penalty='l1',solver='liblinear').fit(X_train,y_train)
print('Training accuracy of l1 logreg with C={:.3f}:{:.2f}'.format(C,lr_l1.score(X_train,y_train)))
print('Test accuracy of l1 logreg with C={:.3f}:{:.2f}'.format(C,lr_l1.score(X_test,y_test)))
plt.plot(lr_l1.coef_.T,marker,label='C={:.3f}'.format(C))
plt.xticks(range(cancer.data.shape[1]),cancer.feature_names,rotation=90)
plt.hlines(0,0,cancer.data.shape[1])
plt.xlabel("Coefficient index")
plt.ylabel('Coefficient magnitude')
plt.ylim(-5,5)
plt.legend(loc=3)
Training accuracy of l1 logreg with C=0.001:0.91
Test accuracy of l1 logreg with C=0.001:0.92
Training accuracy of l1 logreg with C=1.000:0.96
Test accuracy of l1 logreg with C=1.000:0.96
Training accuracy of l1 logreg with C=100.000:0.99
Test accuracy of l1 logreg with C=100.000:0.98
C:\Users\reion\anaconda3\lib\site-packages\sklearn\svm\_base.py:985: ConvergenceWarning: Liblinear failed to converge, increase the number of iterations.
warnings.warn("Liblinear failed to converge, increase "
<matplotlib.legend.Legend at 0x2eacb8f71f0>
from sklearn.datasets import make_blobs
X,y=make_blobs(random_state=42)
mglearn.discrete_scatter(X[:,0],X[:,1],y)
plt.xlabel('Feature 0')
plt.ylabel('Feature 1')
plt.legend(['Class 0','Class 1','Class 2'])
<matplotlib.legend.Legend at 0x2eacb861640>
from sklearn.svm import LinearSVC
linear_svm=LinearSVC().fit(X,y)
print('Coefficient shape:',linear_svm.coef_.shape)
print('Intercept shape:',linear_svm.intercept_.shape)
Coefficient shape: (3, 2)
Intercept shape: (3,)
mglearn.discrete_scatter(X[:,0],X[:,1],y)
line=np.linspace(-15,15)
for coef ,intercept,color in zip(linear_svm.coef_,linear_svm.intercept_,['b','r','g']):
plt.plot(line,-(line*coef[0]+intercept)/coef[1],c=color)
plt.ylim(-10,15)
plt.xlim(-10,8)
plt.xlabel('Feature 0')
plt.ylabel('Feature 1')
plt.legend(['Class 0','Class 1','Class 2','Linear class 0','Linear class 1','Line class 2'],loc=(1.01,0.3))
print(line)
print(-(line*coef[0]+intercept)/coef[1])
[-15. -14.3877551 -13.7755102 -13.16326531 -12.55102041
-11.93877551 -11.32653061 -10.71428571 -10.10204082 -9.48979592
-8.87755102 -8.26530612 -7.65306122 -7.04081633 -6.42857143
-5.81632653 -5.20408163 -4.59183673 -3.97959184 -3.36734694
-2.75510204 -2.14285714 -1.53061224 -0.91836735 -0.30612245
0.30612245 0.91836735 1.53061224 2.14285714 2.75510204
3.36734694 3.97959184 4.59183673 5.20408163 5.81632653
6.42857143 7.04081633 7.65306122 8.26530612 8.87755102
9.48979592 10.10204082 10.71428571 11.32653061 11.93877551
12.55102041 13.16326531 13.7755102 14.3877551 15. ]
[ 13.48522515 12.91759141 12.34995767 11.78232394 11.2146902
10.64705646 10.07942272 9.51178898 8.94415524 8.37652151
7.80888777 7.24125403 6.67362029 6.10598655 5.53835281
4.97071908 4.40308534 3.8354516 3.26781786 2.70018412
2.13255038 1.56491665 0.99728291 0.42964917 -0.13798457
-0.70561831 -1.27325205 -1.84088579 -2.40851952 -2.97615326
-3.543787 -4.11142074 -4.67905448 -5.24668822 -5.81432195
-6.38195569 -6.94958943 -7.51722317 -8.08485691 -8.65249065
-9.22012438 -9.78775812 -10.35539186 -10.9230256 -11.49065934
-12.05829308 -12.62592681 -13.19356055 -13.76119429 -14.32882803]
mglearn.plots.plot_2d_classification(linear_svm,X,fill=True,alpha=0.7)
mglearn.discrete_scatter(X[:,0],X[:,1],y)
line=np.linspace(-15,15)
for coef ,intercept,color in zip(linear_svm.coef_,linear_svm.intercept_,['b','r','g']):
plt.plot(line,-(line*coef[0]+intercept)/coef[1],c=color)
plt.legend(['Class 0','Class 1','Class 2','Linear class 0','Linear class 1','linear class 2'],loc=(1.01,0.3))
plt.xlabel("Feature 0")
plt.ylabel('Feature 1')
Text(0, 0.5, 'Feature 1')
X=np.array([[0,1,0,1],
[1,0,1,1],[0,0,0,1],[1,0,1,0]])
y=np.array([0,1,0,1])
counts={}
for label in np.unique(y):
counts[label]=X[y==label].sum(axis=0)
print('Feature counts:\n{}'.format(counts))
Feature counts:
{0: array([0, 1, 0, 2]), 1: array([2, 0, 2, 1])}
# mglearn.plots.plot_animal_tree()
from sklearn.tree import DecisionTreeClassifier
cancer=load_breast_cancer()
X_train,X_test,y_train,y_test=train_test_split(cancer.data,cancer.target,random_state=42,stratify=cancer.target)
tree=DecisionTreeClassifier(random_state=0)
tree.fit(X_train,y_train)
print('Accuracy on training set:{:.3f}'.format(tree.score(X_train,y_train)))
print('Accuracy on test set:{:.3f}'.format(tree.score(X_test,y_test)))
Accuracy on training set:1.000
Accuracy on test set:0.937
tree=DecisionTreeClassifier(max_depth=4,random_state=0)
tree.fit(X_train,y_train)
print('Accuracy on training set:{:.3f}'.format(tree.score(X_train,y_train)))
print('Accuracy on test set:{:.3f}'.format(tree.score(X_test,y_test)))
Accuracy on training set:0.988
Accuracy on test set:0.951
from sklearn.tree import export_graphviz
export_graphviz(tree,out_file='tree.dot',class_names=['malignant','benign'],feature_names=cancer.feature_names,impurity=False,filled=True)
# import graphviz
# with open(r'C:\Users\reion\Documents\Python机器学习基础教程\tree.dot') as f:
# dot_graph=f.read()
# graphviz.Source(dot_graph)
print('Feature importance :\n{}'.format(tree.feature_importances_))
Feature importance :
[0. 0. 0. 0. 0. 0.
0. 0. 0. 0. 0.01019737 0.04839825
0. 0. 0.0024156 0. 0. 0.
0. 0. 0.72682851 0.0458159 0. 0.
0.0141577 0. 0.018188 0.1221132 0.01188548 0. ]
def plot_feature_importances_cancer(model):
n_feature=cancer.data.shape[1]
plt.barh(range(n_feature),model.feature_importances_,align='center')
plt.yticks(np.arange(n_feature),cancer.feature_names)
plt.xlabel('Feature importance')
plt.ylabel('Feature')
plot_feature_importances_cancer(tree)
# tree=mglearn.plots.plot_tree_not_monotone()
# display(tree)
from sklearn.ensemble import RandomForestClassifier
from sklearn.datasets import make_moons
X,y=make_moons(n_samples=100,noise=0.25,random_state=3)
X_train,X_test,y_train,y_test=train_test_split(X,y,stratify=y,random_state=42)
forest=RandomForestClassifier(n_estimators=5,random_state=2)
forest.fit(X_train,y_train)
RandomForestClassifier(n_estimators=5, random_state=2)
fig,axes=plt.subplots(2,3,figsize=(20,10))
for i,(ax,tree) in enumerate(zip(axes.ravel(),forest.estimators_)):
ax.set_title('Tree{}'.format(i))
mglearn.plots.plot_tree_partition(X_train,y_train,tree,ax=ax)
mglearn.plots.plot_2d_separator(forest,X_train,fill=True,ax=axes[-1,-1],alpha=0.4)
axes[-1,-1].set_title('RandomForest')
mglearn.discrete_scatter(X_train[:,0],X_train[:,1],y_train)
[<matplotlib.lines.Line2D at 0x2eac8a1d5e0>,
<matplotlib.lines.Line2D at 0x2eac8a1d0d0>]
X_train,X_test,y_train,y_test=train_test_split(cancer.data,cancer.target,stratify=cancer.target,random_state=0)
forest=RandomForestClassifier(n_estimators=100,random_state=0)
forest.fit(X_train,y_train)
print('Accuracy on training set:{:.3f}'.format(forest.score(X_train,y_train)))
print('Accuracy on test set:{:.3f}'.format(forest.score(X_test,y_test)))
Accuracy on training set:0.998
Accuracy on test set:0.944
plot_feature_importances_cancer(forest)
from sklearn.ensemble import GradientBoostingClassifier
X_train,X_test,y_train,y_test=train_test_split(cancer.data,cancer.target,stratify=cancer.target,random_state=0)
gbrt=GradientBoostingClassifier(random_state=0)
gbrt.fit(X_train,y_train)
print('Accuracy on training set:{:.3f}'.format(gbrt.score(X_train,y_train)))
print('Accuracy on test set:{:.3f}'.format(gbrt.score(X_test,y_test)))
Accuracy on training set:1.000
Accuracy on test set:0.958
gbrt=GradientBoostingClassifier(max_depth=1,random_state=0)
gbrt.fit(X_train,y_train)
print('Accuracy on training set:{:.3f}'.format(gbrt.score(X_train,y_train)))
print('Accuracy on test set:{:.3f}'.format(gbrt.score(X_test,y_test)))
Accuracy on training set:0.995
Accuracy on test set:0.965
gbrt=GradientBoostingClassifier(random_state=0,learning_rate=0.01)
gbrt.fit(X_train,y_train)
print('Accuracy on training set:{:.3f}'.format(gbrt.score(X_train,y_train)))
print('Accuracy on test set:{:.3f}'.format(gbrt.score(X_test,y_test)))
Accuracy on training set:0.995
Accuracy on test set:0.944
gbrt=GradientBoostingClassifier(max_depth=1,random_state=0)
gbrt.fit(X_train,y_train)
plot_feature_importances_cancer(gbrt)
X,y=make_blobs(centers=4,random_state=8)
y=y%2
mglearn.discrete_scatter(X[:,0],X[:,1],y)
plt.xlabel('Feature 0')
plt.ylabel('Feature 1')
Text(0, 0.5, 'Feature 1')
from sklearn.svm import LinearSVC
linear_svm=LinearSVC().fit(X,y)
mglearn.discrete_scatter(X[:,0],X[:,1],y)
mglearn.plots.plot_2d_separator(linear_svm,X,fill=False)
plt.xlabel('Feature 0')
plt.ylabel('Feature 1')
C:\Users\reion\anaconda3\lib\site-packages\sklearn\svm\_base.py:985: ConvergenceWarning: Liblinear failed to converge, increase the number of iterations.
warnings.warn("Liblinear failed to converge, increase "
Text(0, 0.5, 'Feature 1')
X_new=np.hstack([X,X[:,1:]**2])
from mpl_toolkits.mplot3d import Axes3D,axes3d
figure=plt.figure()
ax=Axes3D(figure,elev=-152,azim=-26)
mask=y==0
ax.scatter(X_new[mask,0],X_new[mask,1],X_new[mask,2],c='b',cmap=mglearn.cm2,s=60)
ax.scatter(X_new[~mask,0],X_new[~mask,1],X_new[~mask,2],c='r',cmap=mglearn.cm2,s=60)
ax.set_xlabel('feature 0')
ax.set_ylabel('feature 1')
ax.set_zlabel('feature1**2')
Text(0.5, 0, 'feature1**2')
linear_svm_3d=LinearSVC().fit(X_new,y)
coef,intercept=linear_svm_3d.coef_.ravel(),linear_svm_3d.intercept_.ravel()
figure=plt.figure()
ax=Axes3D(figure,elev=-152,azim=-26)
xx=np.linspace(X_new[:,0].min()-2,X_new[:,0].max()+2,50)
yy=np.linspace(X_new[:,1].min()-2,X_new[:,1].max()+2,50)
XX,YY=np.meshgrid(xx,yy)
ZZ=(coef[0]*XX+coef[1]*YY+intercept)/-coef[2]
ax.plot_surface(XX,YY,ZZ,rstride=8,cstride=8,alpha=0.8)
ax.scatter(X_new[mask,0],X_new[mask,1],X_new[mask,2],c='b',cmap=mglearn.cm2,s=60)
ax.scatter(X_new[~mask,0],X_new[~mask,1],X_new[~mask,2],c='r',cmap=mglearn.cm2,s=60)
ax.set_xlabel('feature 0')
ax.set_ylabel('feature 1')
ax.set_zlabel('feature**2')
C:\Users\reion\anaconda3\lib\site-packages\sklearn\svm\_base.py:985: ConvergenceWarning: Liblinear failed to converge, increase the number of iterations.
warnings.warn("Liblinear failed to converge, increase "
Text(0.5, 0, 'feature**2')
ZZ=YY**2
dec=linear_svm_3d.decision_function(np.c_[XX.ravel(),YY.ravel(),ZZ.ravel()])
plt.contourf(XX,YY,dec.reshape(XX.shape),levels=[dec.min(),0,dec.max()],cmap=mglearn.cm2,alpha=0.5)
mglearn.discrete_scatter(X[:,0],X[:,1],y)
plt.xlabel('Feature 0')
plt.ylabel('Feature 1')
Text(0, 0.5, 'Feature 1')
from sklearn.svm import SVC
X,y=mglearn.tools.make_handcrafted_dataset()
svm=SVC(kernel='rbf',C=10,gamma=0.1).fit(X,y)
mglearn.plots.plot_2d_separator(svm,X,eps=0.5)
mglearn.discrete_scatter(X[:,0],X[:,1],y)
sv=svm.support_vectors_
sv_labels=svm.dual_coef_.ravel()>0
print(sv)
mglearn.discrete_scatter(sv[:,0],sv[:,1],sv_labels,s=10,markeredgewidth=3)
plt.xlabel('Feature 0')
plt.ylabel('Feature 1')
[[ 8.1062269 4.28695977]
[ 9.50169345 1.93824624]
[11.563957 1.3389402 ]
[10.24028948 2.45544401]
[ 7.99815287 4.8525051 ]]
Text(0, 0.5, 'Feature 1')
fig,axes=plt.subplots(3,3,figsize=(15,10))
for ax,C in zip(axes,[-1,0,3]):
for a ,gamma in zip(ax,range(-1,2)):
mglearn.plots.plot_svm(log_C=C,log_gamma=gamma,ax=a)
axes[0,0].legend(['Class 0',' Class 1','sv class 0','sv class1'],ncol=4,loc=(0.9,1.2))
<matplotlib.legend.Legend at 0x2eacbc03640>
X_train,X_test,y_train,y_test=train_test_split(cancer.data,cancer.target,stratify=cancer.target,random_state=0)
svc=SVC()
svc.fit(X_train,y_train)
print('Accuracy on training set:{:.3f}'.format(svc.score(X_train,y_train)))
print('Accuracy on test set:{:.3f}'.format(svc.score(X_test,y_test)))
Accuracy on training set:0.923
Accuracy on test set:0.916
plt.plot(X_train.min(axis=0),'o',label='min')
plt.plot(X_train.max(axis=0),'^',label='max')
plt.legend(loc=4)
plt.xlabel('Feature Max')
plt.ylabel('Feature magnitude')
plt.yscale('log')
min_on_training=X_train.min(axis=0)
max_on_training=X_train.max(axis=0)
range_on_training=(X_train-min_on_training).max(axis=0)
X_train_scaled=(X_train-min_on_training)/range_on_training
print('Minimum for each feature\n{}'.format(X_train_scaled.min(axis=0)))
print('Maximum for each feature\n{}'.format(X_train_scaled.max(axis=0)))
Minimum for each feature
[0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.
0. 0. 0. 0. 0. 0.]
Maximum for each feature
[1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1.
1. 1. 1. 1. 1. 1.]
X_test_scaled=(X_test-min_on_training)/range_on_training
svc=SVC()
svc.fit(X_train_scaled,y_train)
print('Accuracy on training set:{:.3f}'.format(svc.score(X_train_scaled,y_train)))
print('Accuracy on test set:{:.3f}'.format(svc.score(X_test_scaled,y_test)))
Accuracy on training set:0.991
Accuracy on test set:0.944
svc=SVC(C=1000)
svc.fit(X_train_scaled,y_train)
print('Accuracy on training set:{:.3f}'.format(svc.score(X_train_scaled,y_train)))
print('Accuracy on test set:{:.3f}'.format(svc.score(X_test_scaled,y_test)))
Accuracy on training set:1.000
Accuracy on test set:0.951
# display(mglearn.plots.plot_logistic_regression_graph())
display(mglearn.plots.plot_single_hidden_layer_graph())
---------------------------------------------------------------------------
FileNotFoundError Traceback (most recent call last)
~\anaconda3\lib\site-packages\graphviz\backend.py in run(cmd, input, capture_output, check, encoding, quiet, **kwargs)
163 try:
--> 164 proc = subprocess.Popen(cmd, startupinfo=get_startupinfo(), **kwargs)
165 except OSError as e:
~\anaconda3\lib\subprocess.py in __init__(self, args, bufsize, executable, stdin, stdout, stderr, preexec_fn, close_fds, shell, cwd, env, universal_newlines, startupinfo, creationflags, restore_signals, start_new_session, pass_fds, encoding, errors, text)
857
--> 858 self._execute_child(args, executable, preexec_fn, close_fds,
859 pass_fds, cwd, env,
~\anaconda3\lib\subprocess.py in _execute_child(self, args, executable, preexec_fn, close_fds, pass_fds, cwd, env, startupinfo, creationflags, shell, p2cread, p2cwrite, c2pread, c2pwrite, errread, errwrite, unused_restore_signals, unused_start_new_session)
1310 try:
-> 1311 hp, ht, pid, tid = _winapi.CreateProcess(executable, args,
1312 # no special security
FileNotFoundError: [WinError 2] 系统找不到指定的文件。
During handling of the above exception, another exception occurred:
ExecutableNotFound Traceback (most recent call last)
~\anaconda3\lib\site-packages\IPython\core\formatters.py in __call__(self, obj)
343 method = get_real_method(obj, self.print_method)
344 if method is not None:
--> 345 return method()
346 return None
347 else:
~\anaconda3\lib\site-packages\graphviz\files.py in _repr_svg_(self)
142
143 def _repr_svg_(self):
--> 144 return self.pipe(format='svg').decode(self._encoding)
145
146 def pipe(self, format=None, renderer=None, formatter=None, quiet=False):
~\anaconda3\lib\site-packages\graphviz\files.py in pipe(self, format, renderer, formatter, quiet)
167 data = text_type(self.source).encode(self._encoding)
168
--> 169 out = backend.pipe(self._engine, format, data,
170 renderer=renderer, formatter=formatter,
171 quiet=quiet)
~\anaconda3\lib\site-packages\graphviz\backend.py in pipe(engine, format, data, renderer, formatter, quiet)
246 """
247 cmd, _ = command(engine, format, None, renderer, formatter)
--> 248 out, _ = run(cmd, input=data, capture_output=True, check=True, quiet=quiet)
249 return out
250
~\anaconda3\lib\site-packages\graphviz\backend.py in run(cmd, input, capture_output, check, encoding, quiet, **kwargs)
165 except OSError as e:
166 if e.errno == errno.ENOENT:
--> 167 raise ExecutableNotFound(cmd)
168 else:
169 raise
ExecutableNotFound: failed to execute ['dot', '-Kdot', '-Tsvg'], make sure the Graphviz executables are on your systems' PATH
<graphviz.dot.Digraph at 0x2eacbb0c160>
line=np.linspace(-3,3,100)
plt.plot(line,np.tanh(line),label='tanh')
plt.plot(line,np.maximum(line,0),label='relu')
plt.legend(loc='best')
plt.xlabel('x')
plt.ylabel('relu(x),tanh(x)')
print(len(np.maximum(line,0)))
100
mglearn.plots.plot_two_hidden_layer_graph()
---------------------------------------------------------------------------
FileNotFoundError Traceback (most recent call last)
~\anaconda3\lib\site-packages\graphviz\backend.py in run(cmd, input, capture_output, check, encoding, quiet, **kwargs)
163 try:
--> 164 proc = subprocess.Popen(cmd, startupinfo=get_startupinfo(), **kwargs)
165 except OSError as e:
~\anaconda3\lib\subprocess.py in __init__(self, args, bufsize, executable, stdin, stdout, stderr, preexec_fn, close_fds, shell, cwd, env, universal_newlines, startupinfo, creationflags, restore_signals, start_new_session, pass_fds, encoding, errors, text)
857
--> 858 self._execute_child(args, executable, preexec_fn, close_fds,
859 pass_fds, cwd, env,
~\anaconda3\lib\subprocess.py in _execute_child(self, args, executable, preexec_fn, close_fds, pass_fds, cwd, env, startupinfo, creationflags, shell, p2cread, p2cwrite, c2pread, c2pwrite, errread, errwrite, unused_restore_signals, unused_start_new_session)
1310 try:
-> 1311 hp, ht, pid, tid = _winapi.CreateProcess(executable, args,
1312 # no special security
FileNotFoundError: [WinError 2] 系统找不到指定的文件。
During handling of the above exception, another exception occurred:
ExecutableNotFound Traceback (most recent call last)
~\anaconda3\lib\site-packages\IPython\core\formatters.py in __call__(self, obj)
343 method = get_real_method(obj, self.print_method)
344 if method is not None:
--> 345 return method()
346 return None
347 else:
~\anaconda3\lib\site-packages\graphviz\files.py in _repr_svg_(self)
142
143 def _repr_svg_(self):
--> 144 return self.pipe(format='svg').decode(self._encoding)
145
146 def pipe(self, format=None, renderer=None, formatter=None, quiet=False):
~\anaconda3\lib\site-packages\graphviz\files.py in pipe(self, format, renderer, formatter, quiet)
167 data = text_type(self.source).encode(self._encoding)
168
--> 169 out = backend.pipe(self._engine, format, data,
170 renderer=renderer, formatter=formatter,
171 quiet=quiet)
~\anaconda3\lib\site-packages\graphviz\backend.py in pipe(engine, format, data, renderer, formatter, quiet)
246 """
247 cmd, _ = command(engine, format, None, renderer, formatter)
--> 248 out, _ = run(cmd, input=data, capture_output=True, check=True, quiet=quiet)
249 return out
250
~\anaconda3\lib\site-packages\graphviz\backend.py in run(cmd, input, capture_output, check, encoding, quiet, **kwargs)
165 except OSError as e:
166 if e.errno == errno.ENOENT:
--> 167 raise ExecutableNotFound(cmd)
168 else:
169 raise
ExecutableNotFound: failed to execute ['dot', '-Kdot', '-Tsvg'], make sure the Graphviz executables are on your systems' PATH
<graphviz.dot.Digraph at 0x2eacd37caf0>
from sklearn.neural_network import MLPClassifier
from sklearn.datasets import make_moons
X,y=make_moons(n_samples=100,noise=0.25,random_state=3)
X_train,X_test,y_train,y_test=train_test_split(X,y,random_state=42,stratify=y)
mlp=MLPClassifier(solver='lbfgs',random_state=0).fit(X_train,y_train)
mglearn.plots.plot_2d_separator(mlp,X_train,fill=True,alpha=0.3)
mglearn.discrete_scatter(X_train[:,0],X_train[:,1],y_train)
plt.xlabel('Feature 0')
plt.ylabel('Feature 1')
Text(0, 0.5, 'Feature 1')
mlp=MLPClassifier(solver='lbfgs',random_state=0,hidden_layer_sizes=[10]).fit(X_train,y_train)
mglearn.plots.plot_2d_separator(mlp,X_train,fill=True,alpha=0.3)
mglearn.discrete_scatter(X_train[:,0],X_train[:,1],y_train)
plt.xlabel('Feature 0')
plt.ylabel('Feature 1')
C:\Users\reion\anaconda3\lib\site-packages\sklearn\neural_network\_multilayer_perceptron.py:500: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
self.n_iter_ = _check_optimize_result("lbfgs", opt_res, self.max_iter)
Text(0, 0.5, 'Feature 1')
mlp=MLPClassifier(solver='lbfgs',random_state=0,hidden_layer_sizes=[10,10]).fit(X_train,y_train)
mglearn.plots.plot_2d_separator(mlp,X_train,fill=True,alpha=0.3)
mglearn.discrete_scatter(X_train[:,0],X_train[:,1],y_train)
plt.xlabel('Feature 0')
plt.ylabel('Feature 1')
Text(0, 0.5, 'Feature 1')
mlp=MLPClassifier(solver='lbfgs',random_state=0,hidden_layer_sizes=[10,10],activation='relu').fit(X_train,y_train)
mglearn.plots.plot_2d_separator(mlp,X_train,fill=True,alpha=0.3)
mglearn.discrete_scatter(X_train[:,0],X_train[:,1],y_train)
plt.xlabel('Feature 0')
plt.ylabel('Feature 1')
Text(0, 0.5, 'Feature 1')
mlp=MLPClassifier(solver='lbfgs',random_state=0,hidden_layer_sizes=[10,10],activation='tanh').fit(X_train,y_train)
mglearn.plots.plot_2d_separator(mlp,X_train,fill=True,alpha=0.3)
mglearn.discrete_scatter(X_train[:,0],X_train[:,1],y_train)
plt.xlabel('Feature 0')
plt.ylabel('Feature 1')
C:\Users\reion\anaconda3\lib\site-packages\sklearn\neural_network\_multilayer_perceptron.py:500: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
self.n_iter_ = _check_optimize_result("lbfgs", opt_res, self.max_iter)
Text(0, 0.5, 'Feature 1')
fig,axes=plt.subplots(2,4,figsize=(20,8))
for axx,n_hidden_nodes in zip(axes,[10,100]):
for ax ,alpha in zip(axx,[0.0001,0.01,0.1,1]):
mlp=MLPClassifier(solver='lbfgs',random_state=0,hidden_layer_sizes=[n_hidden_nodes,n_hidden_nodes],alpha=alpha)
mlp.fit(X_train,y_train)
mglearn.plots.plot_2d_separator(mlp,X_train,fill=True,alpha=0.3,ax=ax)
mglearn.discrete_scatter(X_train[:,0],X_train[:,1],y_train,ax=ax)
ax.set_title('n_heidden_layer_size=[{},{}]\nalpha={:.4f}'.format(n_hidden_nodes,n_hidden_nodes,alpha))
C:\Users\reion\anaconda3\lib\site-packages\sklearn\neural_network\_multilayer_perceptron.py:500: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
self.n_iter_ = _check_optimize_result("lbfgs", opt_res, self.max_iter)
C:\Users\reion\anaconda3\lib\site-packages\sklearn\neural_network\_multilayer_perceptron.py:500: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
self.n_iter_ = _check_optimize_result("lbfgs", opt_res, self.max_iter)
fig,axes=plt.subplots(2,4,figsize=(20,8))
for i,ax in enumerate(axes.ravel()):
mlp=MLPClassifier(solver='lbfgs',random_state=i,hidden_layer_sizes=[100,100])
mlp.fit(X_train,y_train)
mglearn.plots.plot_2d_separator(mlp,X_train,fill=True,ax=ax,alpha=0.3)
mglearn.discrete_scatter(X_train[:,0],X_train[:,1],y_train,ax=ax)
C:\Users\reion\anaconda3\lib\site-packages\sklearn\neural_network\_multilayer_perceptron.py:500: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
self.n_iter_ = _check_optimize_result("lbfgs", opt_res, self.max_iter)
print('Cacner data per-feature maxima:\n{}'.format(cancer.data.max(axis=0)))
Cacner data per-feature maxima:
[2.811e+01 3.928e+01 1.885e+02 2.501e+03 1.634e-01 3.454e-01 4.268e-01
2.012e-01 3.040e-01 9.744e-02 2.873e+00 4.885e+00 2.198e+01 5.422e+02
3.113e-02 1.354e-01 3.960e-01 5.279e-02 7.895e-02 2.984e-02 3.604e+01
4.954e+01 2.512e+02 4.254e+03 2.226e-01 1.058e+00 1.252e+00 2.910e-01
6.638e-01 2.075e-01]
X_train,X_test,y_train,y_test=train_test_split(cancer.data,cancer.target,stratify=cancer.target,random_state=0)
mlp=MLPClassifier(random_state=42)
mlp.fit(X_train,y_train)
print('Accuracy on training set:{:.3f}'.format(mlp.score(X_train,y_train)))
print('Accuracy on test set:{:.3f}'.format(mlp.score(X_test,y_test)))
Accuracy on training set:0.939
Accuracy on test set:0.923
mean_on_train=X_train.mean(axis=0)
std_on_train=X_train.std(axis=0)
X_train_scaled=(X_train-mean_on_train)/std_on_train
X_test_scaled=(X_test-mean_on_train)/std_on_train
mlp=MLPClassifier(random_state=0)
mlp.fit(X_train_scaled,y_train)
print('Accuracy on training set:{:.3f}'.format(mlp.score(X_train_scaled,y_train)))
print('Accuracy on test set:{:.3f}'.format(mlp.score(X_test_scaled,y_test)))
Accuracy on training set:0.998
Accuracy on test set:0.951
C:\Users\reion\anaconda3\lib\site-packages\sklearn\neural_network\_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.
warnings.warn(
mlp=MLPClassifier(random_state=0,max_iter=1000)
mlp.fit(X_train_scaled,y_train)
print('Accuracy on training set:{:.3f}'.format(mlp.score(X_train_scaled,y_train)))
print('Accuracy on test set:{:.3f}'.format(mlp.score(X_test_scaled,y_test)))
Accuracy on training set:0.998
Accuracy on test set:0.958
mlp=MLPClassifier(random_state=0,alpha=1,max_iter=1000)
mlp.fit(X_train_scaled,y_train)
print('Accuracy on training set:{:.3f}'.format(mlp.score(X_train_scaled,y_train)))
print('Accuracy on test set:{:.3f}'.format(mlp.score(X_test_scaled,y_test)))
Accuracy on training set:0.991
Accuracy on test set:0.965
plt.figure(figsize=(20,5))
plt.imshow(mlp.coefs_[0],interpolation='none',cmap='viridis')
plt.yticks(range(30),cancer.feature_names)
plt.xlabel('Columns in weight matrix')
plt.ylabel('Input feature')
plt.colorbar()
<matplotlib.colorbar.Colorbar at 0x2ea8245ce20>
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.datasets import make_circles
X,y=make_circles(noise=0.25,factor=0.5,random_state=1)
y_named=np.array(['blue','red'])[y]
print(y_named)
X_train,X_test,y_train_named,y_test_named,y_train,y_test=train_test_split(X,y_named,y,random_state=0)
gbrt=GradientBoostingClassifier(random_state=0)
gbrt.fit(X_train,y_train_named)
['red' 'red' 'blue' 'red' 'red' 'blue' 'blue' 'red' 'red' 'red' 'red'
'blue' 'red' 'red' 'red' 'blue' 'blue' 'blue' 'red' 'blue' 'blue' 'red'
'red' 'red' 'blue' 'blue' 'red' 'blue' 'blue' 'blue' 'red' 'red' 'red'
'red' 'red' 'blue' 'blue' 'red' 'blue' 'blue' 'red' 'red' 'red' 'blue'
'red' 'blue' 'blue' 'red' 'blue' 'red' 'blue' 'red' 'blue' 'blue' 'red'
'blue' 'blue' 'red' 'blue' 'red' 'blue' 'red' 'red' 'blue' 'blue' 'red'
'blue' 'red' 'blue' 'red' 'red' 'blue' 'red' 'red' 'blue' 'red' 'blue'
'red' 'red' 'blue' 'blue' 'blue' 'blue' 'blue' 'blue' 'red' 'blue' 'blue'
'red' 'red' 'blue' 'blue' 'red' 'red' 'blue' 'red' 'blue' 'red' 'blue'
'blue']
GradientBoostingClassifier(random_state=0)
print('X_train.shape:{}'.format(X_train.shape))
print('Decision function shape:{}'.format(gbrt.decision_function(X_test).shape))
X_train.shape:(75, 2)
Decision function shape:(25,)
print('Decision function:\n{}'.format(gbrt.decision_function(X_test)[:6]))
Decision function:
[ 4.13592603 -1.70169917 -3.95106099 -3.62609552 4.28986642 3.66166081]
print('Threshoulded decision function:\n{}'.format(gbrt.decision_function(X_test)>0))
print('Predictions:\n{}'.format(gbrt.predict(X_test)))
Threshoulded decision function:
[ True False False False True True False True True True False True
True False True False False False True True True True True False
False]
Predictions:
['red' 'blue' 'blue' 'blue' 'red' 'red' 'blue' 'red' 'red' 'red' 'blue'
'red' 'red' 'blue' 'red' 'blue' 'blue' 'blue' 'red' 'red' 'red' 'red'
'red' 'blue' 'blue']
greator_zero=(gbrt.decision_function(X_test)>0).astype(int)
pred=gbrt.classes_[greator_zero]
print('pred is equal to predictions :{}'.format(np.all(pred==gbrt.predict(X_test))))
pred is equal to predictions :True
decision_function=gbrt.decision_function(X_test)
print('Decision function minimum:{:.2f},maximum:{:.2f}'.format(np.min(decision_function),np.max(decision_function)))
Decision function minimum:-7.69,maximum:4.29
fig,axes=plt.subplots(1,2,figsize=(13,5))
mglearn.tools.plot_2d_separator(gbrt,X,ax=axes[0],alpha=0.4,fill=True,cm=mglearn.cm2)
score_image=mglearn.tools.plot_2d_scores(gbrt,X,ax=axes[1],alpha=0.4,cm=mglearn.ReBl)
for ax in axes:
mglearn.discrete_scatter(X_test[:,0],X_test[:,1],y_test,markers='^',ax=ax)
mglearn.discrete_scatter(X_train[:,0],X_train[:,1],y_train,markers='o',ax=ax)
ax.set_xlabel('feature 0')
ax.set_ylabel('feature 1')
cbar=plt.colorbar(score_image,ax=axes.tolist())
axes[0].legend(['Test class 0','Test Class 1','Train class 0','Train class 1'],ncol=4,loc=(0.1,1.1))
<matplotlib.legend.Legend at 0x2eacd37c430>
from sklearn.datasets import load_iris
iris=load_iris()
X_train,X_test,y_train,y_test=train_test_split(iris.data,iris.target,random_state=42)
gbrt=GradientBoostingClassifier(learning_rate=0.01,random_state=0)
gbrt.fit(X_train,y_train)
GradientBoostingClassifier(learning_rate=0.01, random_state=0)
print('Descision function shape:{}'.format(gbrt.decision_function(X_test).shape))
print('Decision function:\n{}'.format(gbrt.decision_function(X_test)))
Descision function shape:(38, 3)
Decision function:
[[-1.995715 0.04758267 -1.92720695]
[ 0.06146394 -1.90755736 -1.92793758]
[-1.99058203 -1.87637861 0.09686725]
[-1.995715 0.04758267 -1.92720695]
[-1.99730159 -0.13469108 -1.20341483]
[ 0.06146394 -1.90755736 -1.92793758]
[-1.995715 0.04758267 -1.92720695]
[-1.99677434 -1.87637861 0.09686725]
[-1.995715 0.04758267 -1.92720695]
[-1.995715 0.04758267 -1.92720695]
[-1.99677434 -1.87637861 0.07863156]
[ 0.06146394 -1.90755736 -1.92793758]
[ 0.06146394 -1.90755736 -1.92793758]
[ 0.06146394 -1.90755736 -1.92793758]
[ 0.06146394 -1.90755736 -1.92793758]
[-1.995715 0.04758267 -1.92720695]
[-1.99087515 -1.87637861 0.09686725]
[-1.995715 0.04758267 -1.92720695]
[-1.995715 0.04758267 -1.92720695]
[-1.99087515 -1.87637861 0.09686725]
[ 0.06146394 -1.90755736 -1.92793758]
[-1.99730159 -1.86429671 0.04166049]
[ 0.06146394 -1.90755736 -1.92793758]
[-1.99087515 -1.87637861 0.09686725]
[-1.99087515 -1.87637861 0.07863156]
[-1.99087515 -1.87637861 0.09686725]
[-1.99058203 -1.87637861 0.09686725]
[-1.99087515 -1.87637861 0.07863156]
[ 0.06146394 -1.90755736 -1.92793758]
[ 0.06146394 -1.90755736 -1.92793758]
[ 0.06146394 -1.90755736 -1.92793758]
[ 0.06146394 -1.90755736 -1.92793758]
[-1.995715 0.04758267 -1.92720695]
[ 0.06146394 -1.90755736 -1.92793758]
[ 0.06146394 -1.90755736 -1.92793758]
[-1.99712219 -1.87637861 0.04166049]
[-1.995715 0.04758267 -1.92720695]
[ 0.06146394 -1.90755736 -1.92793758]]
print('Argmax of decision function:\n{}'.format(np.argmax(gbrt.decision_function(X_test),axis=1)))
print('Predictions:\n{}'.format(gbrt.predict(X_test)))
Argmax of decision function:
[1 0 2 1 1 0 1 2 1 1 2 0 0 0 0 1 2 1 1 2 0 2 0 2 2 2 2 2 0 0 0 0 1 0 0 2 1
0]
Predictions:
[1 0 2 1 1 0 1 2 1 1 2 0 0 0 0 1 2 1 1 2 0 2 0 2 2 2 2 2 0 0 0 0 1 0 0 2 1
0]
print('Predictioned probabilities:\n{}'.format(gbrt.predict_proba(X_test)[:6]))
print('Sums{}'.format(gbrt.predict_proba(X_test)[:6].sum(axis=1)))
Predictioned probabilities:
[[0.10217718 0.78840034 0.10942248]
[0.78347147 0.10936745 0.10716108]
[0.09818072 0.11005864 0.79176065]
[0.10217718 0.78840034 0.10942248]
[0.10360005 0.66723901 0.22916094]
[0.78347147 0.10936745 0.10716108]]
Sums[1. 1. 1. 1. 1. 1.]
print("Argmax of predicted probabilities:\n{}".format(np.argmax(gbrt.predict_proba(X_test),axis=1)))
print('Predictions:\n{}'.format(gbrt.predict(X_test)))
Argmax of predicted probabilities:
[1 0 2 1 1 0 1 2 1 1 2 0 0 0 0 1 2 1 1 2 0 2 0 2 2 2 2 2 0 0 0 0 1 0 0 2 1
0]
Predictions:
[1 0 2 1 1 0 1 2 1 1 2 0 0 0 0 1 2 1 1 2 0 2 0 2 2 2 2 2 0 0 0 0 1 0 0 2 1
0]
logreg=LogisticRegression()
named_target=iris.target_names[y_train]
logreg.fit(X_train,named_target)
print('Unqiue classes in training data:{}'.format(logreg.classes_))
print('Predictions:{}'.format(logreg.predict(X_test)[:10]))
argmax_dec_func=np.argmax(logreg.decision_function(X_test)[:10],axis=1)
print('argmax of decision function:{}'.format(argmax_dec_func[:10]))
print('argmax combined with classes_:{}'.format(logreg.classes_[argmax_dec_func][:10]))
Unqiue classes in training data:['setosa' 'versicolor' 'virginica']
Predictions:['versicolor' 'setosa' 'virginica' 'versicolor' 'versicolor' 'setosa'
'versicolor' 'virginica' 'versicolor' 'versicolor']
argmax of decision function:[1 0 2 1 1 0 1 2 1 1]
argmax combined with classes_:['versicolor' 'setosa' 'virginica' 'versicolor' 'versicolor' 'setosa'
'versicolor' 'virginica' 'versicolor' 'versicolor']
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
mglearn.plots.plot_scaling()
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split
cancer=load_breast_cancer()
X_train,X_test,y_train,y_test=train_test_split(cancer.data,cancer.target,stratify=cancer.target,random_state=1)
print(X_train.shape)
print(X_test.shape)
(426, 30)
(143, 30)
from sklearn.preprocessing import MinMaxScaler
scaler=MinMaxScaler()
scaler.fit(X_train)
MinMaxScaler()
X_train_scaled=scaler.transform(X_train)
print('Transformed shape:{}'.format(X_train_scaled.shape))
print('per-feature minimum before scaling:\n{}'.format(X_train.min(axis=0)))
print('per-feature maximun before scaling:\n{}'.format(X_train.max(axis=0)))
print('per_feature after scaling:\n{}'.format(X_train_scaled.min(axis=0)))
print('per_feature after scaling:\n{}'.format(X_train_scaled.max(axis=0)))
Transformed shape:(426, 30)
per-feature minimum before scaling:
[6.981e+00 1.038e+01 4.379e+01 1.435e+02 5.263e-02 2.650e-02 0.000e+00
0.000e+00 1.167e-01 5.025e-02 1.144e-01 3.602e-01 7.570e-01 6.802e+00
2.667e-03 3.746e-03 0.000e+00 0.000e+00 7.882e-03 9.502e-04 7.930e+00
1.249e+01 5.041e+01 1.852e+02 8.409e-02 4.327e-02 0.000e+00 0.000e+00
1.565e-01 5.504e-02]
per-feature maximun before scaling:
[2.811e+01 3.928e+01 1.885e+02 2.501e+03 1.634e-01 3.454e-01 4.264e-01
1.913e-01 2.906e-01 9.575e-02 2.873e+00 3.647e+00 2.198e+01 5.422e+02
3.113e-02 1.354e-01 3.960e-01 5.279e-02 7.895e-02 2.984e-02 3.604e+01
4.954e+01 2.512e+02 4.254e+03 2.226e-01 1.058e+00 1.252e+00 2.910e-01
5.774e-01 2.075e-01]
per_feature after scaling:
[0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.
0. 0. 0. 0. 0. 0.]
per_feature after scaling:
[1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1.
1. 1. 1. 1. 1. 1.]
X_test_scaled=scaler.transform(X_test)
print('per_feature after scaling:\n{}'.format(X_test_scaled.min(axis=0)))
print('per_feature after scaling:\n{}'.format(X_test_scaled.max(axis=0)))
per_feature after scaling:
[ 0.07648256 -0.02318339 0.07117684 0.03295864 0.08919383 -0.02232675
0. 0. -0.06152961 -0.00637363 -0.00105126 0.00079104
0.00067851 0.00079567 -0.0335172 -0.01134793 0. 0.
0.0233157 -0.00191763 0.03635717 -0.01268556 0.03107724 0.01349292
-0.09327846 -0.01574803 0. 0. 0.00023759 0.01252788]
per_feature after scaling:
[0.8173127 0.76435986 0.84589869 0.68610817 0.83118173 0.89338351
1.00093809 1.05175118 1.07705578 1.03714286 0.50554629 1.37665815
0.44117231 0.4224857 0.72596002 0.77972564 0.38762626 0.66054177
0.75389768 0.75839224 0.80896478 0.88852901 0.75696001 0.66869839
0.9075879 0.81108275 0.61717252 0.88487973 1.20527441 0.77371114]
from sklearn.datasets import make_blobs
X,_=make_blobs(n_samples=50,centers=5,random_state=4)
fig,axes=plt.subplots(1,3,figsize=(13,4))
axes[0].scatter(X_train[:,0],X_train[:,1],c=mglearn.cm2(0),label='Training set',s=60)
axes[0].scatter(X_test[:,0],X_test[:,1],c=mglearn.cm2(1),label='Test set',s=60,marker='^')
axes[0].legend(loc='upper left')
axes[0].set_title('Original Data')
scaler=MinMaxScaler()
scaler.fit(X_train)
X_train_scaled=scaler.transform(X_train)
X_test_scaled=scaler.transform(X_test)
axes[1].scatter(X_train_scaled[:,0],X_train_scaled[:,1],c=mglearn.cm2(0),label='Training set',s=60)
axes[1].scatter(X_test_scaled[:,0],X_test_scaled[:,1],c=mglearn.cm2(1),label='Training set',s=60,marker='^')
axes[1].set_title('Scaled Data')
#错误示范
test_scaler=MinMaxScaler()
test_scaler.fit(X_test)
X_test_scaled_badly=test_scaler.transform(X_test)
axes[2].scatter(X_train_scaled[:,0],X_train_scaled[:,1],c=mglearn.cm2(0),label='Training set',s=60)
axes[2].scatter(X_test_scaled_badly[:,0],X_test_scaled_badly[:,1],c=mglearn.cm2(1),label='Training set',s=60,marker='^')
axes[2].set_title('Improperly Sacled Data')
for ax in axes:
ax.set_xlabel('feature 0')
ax.set_ylabel('feature 1')
*c* argument looks like a single numeric RGB or RGBA sequence, which should be avoided as value-mapping will have precedence in case its length matches with *x* & *y*. Please use the *color* keyword-argument or provide a 2-D array with a single row if you intend to specify the same RGB or RGBA value for all points.
*c* argument looks like a single numeric RGB or RGBA sequence, which should be avoided as value-mapping will have precedence in case its length matches with *x* & *y*. Please use the *color* keyword-argument or provide a 2-D array with a single row if you intend to specify the same RGB or RGBA value for all points.
*c* argument looks like a single numeric RGB or RGBA sequence, which should be avoided as value-mapping will have precedence in case its length matches with *x* & *y*. Please use the *color* keyword-argument or provide a 2-D array with a single row if you intend to specify the same RGB or RGBA value for all points.
*c* argument looks like a single numeric RGB or RGBA sequence, which should be avoided as value-mapping will have precedence in case its length matches with *x* & *y*. Please use the *color* keyword-argument or provide a 2-D array with a single row if you intend to specify the same RGB or RGBA value for all points.
*c* argument looks like a single numeric RGB or RGBA sequence, which should be avoided as value-mapping will have precedence in case its length matches with *x* & *y*. Please use the *color* keyword-argument or provide a 2-D array with a single row if you intend to specify the same RGB or RGBA value for all points.
*c* argument looks like a single numeric RGB or RGBA sequence, which should be avoided as value-mapping will have precedence in case its length matches with *x* & *y*. Please use the *color* keyword-argument or provide a 2-D array with a single row if you intend to specify the same RGB or RGBA value for all points.
from sklearn.svm import SVC
svm=SVC(C=100)
svm.fit(X_train,y_train)
print('Test set accuracy:{:.2f}'.format(svm.score(X_test,y_test)))
Test set accuracy:0.93
scaler=MinMaxScaler()
scaler.fit(X_train)
X_train_scaled=scaler.transform(X_train)
X_test_scaled=scaler.transform(X_test)
svm.fit(X_train_scaled,y_train)
print('Test set accuracy:{:.2f}'.format(svm.score(X_test_scaled,y_test)))
Test set accuracy:0.97
from sklearn.preprocessing import StandardScaler
scaler=StandardScaler()
scaler.fit(X_train)
X_train_scaled=scaler.transform(X_train)
X_test_scaled=scaler.transform(X_test)
print(X_train_scaled)
svm.fit(X_train_scaled,y_train)
print('SVM test accuracy:{:.2f}'.format(svm.score(X_test_scaled,y_test)))
[[-1.32273784 -0.24339118 -1.30979447 ... -0.98162332 -0.74451786
-0.17937263]
[-0.57400445 -1.09616357 -0.55701267 ... -0.75814958 -0.27864647
-0.09138928]
[-0.33626585 -0.26650154 -0.29217561 ... -0.0990813 -0.54099725
0.22428432]
...
[ 0.99850751 -0.01228755 0.97416698 ... 1.16019922 0.00914439
-0.32281216]
[-0.38782362 -1.6646785 -0.43967457 ... -0.50778729 -0.23412633
0.52876005]
[ 1.4711204 -0.79341782 1.43690881 ... 0.91820225 -0.76200792
-1.18451579]]
SVM test accuracy:0.97
mglearn.plots.plot_pca_illustration()
fig,axes=plt.subplots(15,2,figsize=(10,20))
malignant=cancer.data[cancer.target==0]
benign=cancer.data[cancer.target==1]
ax=axes.ravel()
for i in range(30):
_,bins=np.histogram(cancer.data[:,i],bins=50)
ax[i].hist(malignant[:,i],bins=bins,color=mglearn.cm3(0),alpha=0.5)
ax[i].hist(benign[:,i],bins=bins,color=mglearn.cm3(1),alpha=0.5)
ax[i].set_title(cancer.feature_names[i])
ax[i].set_yticks(())
ax[0].set_xlabel('Feature magnitude')
ax[0].set_ylabel('Frequency')
ax[0].legend(['malignant','benign'],loc='best')
fig.tight_layout()
scaler=StandardScaler()
scaler.fit(cancer.data)
X_scaled=scaler.transform(cancer.data)
from sklearn.decomposition import PCA
pca=PCA(n_components=2)
pca.fit(X_scaled)
X_pca=pca.transform(X_scaled)
print('Originam shape:{}'.format(str(X_scaled.shape)))
print('Reduced shape:{}',format(str(X_pca.shape)))
Originam shape:(569, 30)
Reduced shape:{} (569, 2)
plt.figure(figsize=(8,8))
mglearn.discrete_scatter(X_pca[:,0],X_pca[:,1],cancer.target)
plt.legend(cancer.target_names,loc='best')
plt.gca().set_aspect('equal')
plt.xlabel('First principal component')
plt.ylabel('Second princial conponent')
Text(0, 0.5, 'Second princial conponent')
print('PCA component shape:{}'.format(pca.components_.shape))
PCA component shape:(2, 30)
print('PCA components:\n{}'.format(pca.components_))
PCA components:
[[ 0.21890244 0.10372458 0.22753729 0.22099499 0.14258969 0.23928535
0.25840048 0.26085376 0.13816696 0.06436335 0.20597878 0.01742803
0.21132592 0.20286964 0.01453145 0.17039345 0.15358979 0.1834174
0.04249842 0.10256832 0.22799663 0.10446933 0.23663968 0.22487053
0.12795256 0.21009588 0.22876753 0.25088597 0.12290456 0.13178394]
[-0.23385713 -0.05970609 -0.21518136 -0.23107671 0.18611302 0.15189161
0.06016536 -0.0347675 0.19034877 0.36657547 -0.10555215 0.08997968
-0.08945723 -0.15229263 0.20443045 0.2327159 0.19720728 0.13032156
0.183848 0.28009203 -0.21986638 -0.0454673 -0.19987843 -0.21935186
0.17230435 0.14359317 0.09796411 -0.00825724 0.14188335 0.27533947]]
plt.matshow(pca.components_,cmap='viridis')
plt.yticks([0,1],['First component','Second component'])
plt.colorbar()
plt.xticks(range(len(cancer.feature_names)),cancer.feature_names,rotation=60,ha='left')
plt.xlabel('Feature')
plt.ylabel('Principal components')
Text(0, 0.5, 'Principal components')
from sklearn.datasets import fetch_lfw_people
people=fetch_lfw_people(min_faces_per_person=20,resize=0.7,download_if_missing=True)
image_shape=people.images[0].shape
print(image_shape)
fig,axes=plt.subplots(2,5,figsize=(15,8),subplot_kw={'xticks':(),'yticks':()})
for target ,image,ax in zip(people.target,people.images,axes.ravel()):
ax.imshow(image)
ax.set_title(people.target_names[target])
(87, 65)
print('People.images.shape:{}'.format(people.images.shape))
print('Number of classes:{}'.format(len(people.target_names)))
People.images.shape:(3023, 87, 65)
Number of classes:62
counts=np.bincount(people.target)
for i,(count,name)in enumerate(zip(counts,people.target_names)):
print('{0:25}{1:3}'.format(name,count),end=' ')
if (i+1)%3==0:
print()
Alejandro Toledo 39 Alvaro Uribe 35 Amelie Mauresmo 21
Andre Agassi 36 Angelina Jolie 20 Ariel Sharon 77
Arnold Schwarzenegger 42 Atal Bihari Vajpayee 24 Bill Clinton 29
Carlos Menem 21 Colin Powell 236 David Beckham 31
Donald Rumsfeld 121 George Robertson 22 George W Bush 530
Gerhard Schroeder 109 Gloria Macapagal Arroyo 44 Gray Davis 26
Guillermo Coria 30 Hamid Karzai 22 Hans Blix 39
Hugo Chavez 71 Igor Ivanov 20 Jack Straw 28
Jacques Chirac 52 Jean Chretien 55 Jennifer Aniston 21
Jennifer Capriati 42 Jennifer Lopez 21 Jeremy Greenstock 24
Jiang Zemin 20 John Ashcroft 53 John Negroponte 31
Jose Maria Aznar 23 Juan Carlos Ferrero 28 Junichiro Koizumi 60
Kofi Annan 32 Laura Bush 41 Lindsay Davenport 22
Lleyton Hewitt 41 Luiz Inacio Lula da Silva 48 Mahmoud Abbas 29
Megawati Sukarnoputri 33 Michael Bloomberg 20 Naomi Watts 22
Nestor Kirchner 37 Paul Bremer 20 Pete Sampras 22
Recep Tayyip Erdogan 30 Ricardo Lagos 27 Roh Moo-hyun 32
Rudolph Giuliani 26 Saddam Hussein 23 Serena Williams 52
Silvio Berlusconi 33 Tiger Woods 23 Tom Daschle 25
Tom Ridge 33 Tony Blair 144 Vicente Fox 32
Vladimir Putin 49 Winona Ryder 24
mask=np.zeros(people.target.shape,dtype=np.bool)
for target in np.unique(people.target):
mask[np.where(people.target==target)[0][:50]]=1
X_people=people.data[mask]
y_people=people.target[mask]
X_people=X_people/255.
<ipython-input-151-9dfabe49bc6b>:1: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
mask=np.zeros(people.target.shape,dtype=np.bool)
from sklearn.neighbors import KNeighborsClassifier
X_train,X_test,y_train,y_test=train_test_split(X_people,y_people,stratify=y_people,random_state=0)
knn=KNeighborsClassifier(n_neighbors=1)
knn.fit(X_train,y_train)
print('Test set score of 1-nn:{:.2f}'.format(knn.score(X_test,y_test)))
Test set score of 1-nn:0.20
mglearn.plots.plot_pca_whitening()
pca=PCA(n_components=100,whiten=True,random_state=0).fit(X_train)
X_train_pca=pca.transform(X_train)
X_test_pca=pca.transform(X_test)
print('X_train_pca.shape:{}'.format(X_train_pca.shape))
X_train_pca.shape:(1547, 100)
knn=KNeighborsClassifier(n_neighbors=1)
knn.fit(X_train_pca,y_train)
print("Test set accuracy :{:.2f}".format(knn.score(X_test_pca,y_test)))
Test set accuracy :0.24
print('pca.components_.shape:{}'.format(pca.components_.shape))
pca.components_.shape:(100, 5655)
fix,axes=plt.subplots(3,5,figsize=(15,12),subplot_kw={'xticks':(),'yticks':()})
for i ,(component,ax) in enumerate(zip(pca.components_,axes.ravel())):
ax.imshow(component.reshape(image_shape),cmap='viridis')
ax.set_title("{} component".format((i+1)))
mglearn.plots.plot_pca_faces(X_train,X_test,image_shape)
mglearn.discrete_scatter(X_train_pca[:,0],X_train_pca[:,1],y_train)
plt.xlabel("First principal component")
plt.ylabel('Second principal component')
Text(0, 0.5, 'Second principal component')
mglearn.plots.plot_nmf_illustration()
C:\Users\reion\anaconda3\lib\site-packages\sklearn\decomposition\_nmf.py:312: FutureWarning: The 'init' value, when 'init=None' and n_components is less than n_samples and n_features, will be changed from 'nndsvd' to 'nndsvda' in 1.1 (renaming of 0.26).
warnings.warn(("The 'init' value, when 'init=None' and "
C:\Users\reion\anaconda3\lib\site-packages\sklearn\decomposition\_nmf.py:1090: ConvergenceWarning: Maximum number of iterations 200 reached. Increase it to improve convergence.
warnings.warn("Maximum number of iterations %d reached. Increase it to"
C:\Users\reion\anaconda3\lib\site-packages\sklearn\decomposition\_nmf.py:312: FutureWarning: The 'init' value, when 'init=None' and n_components is less than n_samples and n_features, will be changed from 'nndsvd' to 'nndsvda' in 1.1 (renaming of 0.26).
warnings.warn(("The 'init' value, when 'init=None' and "
C:\Users\reion\anaconda3\lib\site-packages\sklearn\decomposition\_nmf.py:1090: ConvergenceWarning: Maximum number of iterations 200 reached. Increase it to improve convergence.
warnings.warn("Maximum number of iterations %d reached. Increase it to"
from sklearn.decomposition import NMF
nmf=NMF(n_components=15,random_state=0)
nmf.fit(X_train)
X_train_nmf=nmf.transform(X_train)
X_test_nmf=nmf.transform(X_test)
fig,axes=plt.subplots(3,5,figsize=(15,12))
for i,(component,ax) in enumerate(zip(nmf.components_,axes.ravel())):
ax.imshow(component.reshape(image_shape))
ax.set_title('{}.component'.format(i))
C:\Users\reion\anaconda3\lib\site-packages\sklearn\decomposition\_nmf.py:312: FutureWarning: The 'init' value, when 'init=None' and n_components is less than n_samples and n_features, will be changed from 'nndsvd' to 'nndsvda' in 1.1 (renaming of 0.26).
warnings.warn(("The 'init' value, when 'init=None' and "
C:\Users\reion\anaconda3\lib\site-packages\sklearn\decomposition\_nmf.py:1090: ConvergenceWarning: Maximum number of iterations 200 reached. Increase it to improve convergence.
warnings.warn("Maximum number of iterations %d reached. Increase it to"
compn=3
inds=np.argsort(X_train_nmf[:,compn])[::-1]
fig,axes=plt.subplots(2,5,figsize=(15,8))
for i ,(ind,ax)in enumerate(zip(inds,axes.ravel())):
ax.imshow(X_train[ind].reshape(image_shape))
compn=7
inds=np.argsort(X_train_nmf[:,compn])[::-1]
fig,axes=plt.subplots(2,5,figsize=(15,8))
for i,(ind,ax)in enumerate(zip(inds,axes.ravel())):
ax.imshow(X_train[ind].reshape(image_shape))
S=mglearn.datasets.make_signals()
print(S.shape)
plt.figure(figsize=(6,1))
plt.plot(S,'-')
plt.xlabel("True")
plt.ylabel("Siginal")
(2000, 3)
Text(0, 0.5, 'Siginal')
A=np.random.RandomState(0).uniform(size=(100,3))
X=np.dot(S,A.T)
print('Shape of measurements:{}'.format(S.shape))
Shape of measurements:(2000, 3)
nmf=NMF(n_components=3,random_state=42)
S_=nmf.fit_transform(X)
print('Recovered signal shape:{}'.format(S_.shape))
Recovered signal shape:(2000, 3)
C:\Users\reion\anaconda3\lib\site-packages\sklearn\decomposition\_nmf.py:312: FutureWarning: The 'init' value, when 'init=None' and n_components is less than n_samples and n_features, will be changed from 'nndsvd' to 'nndsvda' in 1.1 (renaming of 0.26).
warnings.warn(("The 'init' value, when 'init=None' and "
C:\Users\reion\anaconda3\lib\site-packages\sklearn\decomposition\_nmf.py:1090: ConvergenceWarning: Maximum number of iterations 200 reached. Increase it to improve convergence.
warnings.warn("Maximum number of iterations %d reached. Increase it to"
pca=PCA(n_components=3)
H=pca.fit_transform(X)
models=[X,S,S_,H]
names=['Observation(first three measurements)','True sources','NMF recovered signals','PCA recovered signal']
fig,axes=plt.subplots(4,figsize=(8,4),gridspec_kw={'hspace':0.5},subplot_kw={'xticks':(),'yticks':()})
for model ,name,ax in zip(models,names,axes):
ax.set_title(name)
ax.plot(model[:,:3],'-')
from sklearn.datasets import load_digits
digits=load_digits()
fig,axes=plt.subplots(2,5,figsize=(10,5))
for ax,img in zip(axes.ravel(),digits.images):
ax.imshow(img)
pca=PCA(n_components=2)
pca.fit(digits.data)
digits_pca=pca.transform(digits.data)
colors=['#476A2A','#7851B8','#BD3430','#4A2D4E','#875525','#A83683','#4E655E','#853541','#3A3120','#535D8E']
plt.figure(figsize=(10,10))
plt.xlim(digits_pca[:,0].min(),digits_pca[:,0].max())
plt.ylim(digits_pca[:,1].min(),digits_pca[:,1].max())
for i in range(len(digits.data)):
plt.text(digits_pca[i,0],digits_pca[i,1],str(digits.target[i]),color=colors[digits.target[i]],fontdict={'weight':'bold','size':9})
plt.xlabel('First principal component')
plt.ylabel('Second principal component')
Text(0, 0.5, 'Second principal component')
from sklearn.manifold import TSNE
tsne=TSNE(random_state=42)
digits_tsne=tsne.fit_transform(digits.data)
plt.figure(figsize=(10,10))
plt.xlim(digits_tsne[:,0].min()+1,digits_tsne[:,0].max()+1)
plt.ylim(digits_tsne[:,1].min(),digits_tsne[:,1].max()+1)
for i in range(len(digits.data)):
plt.text(digits_tsne[i,0],digits_tsne[i,1],str(digits.target[i]),fontdict={'weight':'bold','size':9},color=colors[digits.target[i]])
plt.xlabel('t-SNE feature 0')
plt.ylabel('t-SNE feature 1')
Text(0, 0.5, 't-SNE feature 1')
mglearn.plots.plot_kmeans_algorithm()
mglearn.plots.plot_kmeans_boundaries()
from sklearn.datasets import make_blobs
from sklearn.cluster import KMeans
X,y=make_blobs(random_state=1)
kmeans=KMeans(n_clusters=3)
kmeans.fit(X)
KMeans(n_clusters=3)
print('Cluster membership:\n{}'.format(kmeans.labels_))
Cluster membership:
[0 2 2 2 1 1 1 2 0 0 2 2 1 0 1 1 1 0 2 2 1 2 1 0 2 1 1 0 0 1 0 0 1 0 2 1 2
2 2 1 1 2 0 2 2 1 0 0 0 0 2 1 1 1 0 1 2 2 0 0 2 1 1 2 2 1 0 1 0 2 2 2 1 0
0 2 1 1 0 2 0 2 2 1 0 0 0 0 2 0 1 0 0 2 2 1 1 0 1 0]
print(kmeans.predict(X))
[0 2 2 2 1 1 1 2 0 0 2 2 1 0 1 1 1 0 2 2 1 2 1 0 2 1 1 0 0 1 0 0 1 0 2 1 2
2 2 1 1 2 0 2 2 1 0 0 0 0 2 1 1 1 0 1 2 2 0 0 2 1 1 2 2 1 0 1 0 2 2 2 1 0
0 2 1 1 0 2 0 2 2 1 0 0 0 0 2 0 1 0 0 2 2 1 1 0 1 0]
mglearn.discrete_scatter(X[:,0],X[:,1],kmeans.labels_,markers='o')
mglearn.discrete_scatter(kmeans.cluster_centers_[:,0],kmeans.cluster_centers_[:,1],[0,1,2],markers='^',markeredgewidth=3)
[<matplotlib.lines.Line2D at 0x2ea84358e50>,
<matplotlib.lines.Line2D at 0x2ea843681c0>,
<matplotlib.lines.Line2D at 0x2ea843684f0>]
fig,axes=plt.subplots(1,2,figsize=(10,5))
kmeans=KMeans(n_clusters=2)
kmeans.fit(X)
assignments=kmeans.labels_
mglearn.discrete_scatter(X[:,0],X[:,1],assignments,ax=axes[0])
kmeans=KMeans(n_clusters=5)
kmeans.fit(X)
assignments=kmeans.labels_
mglearn.discrete_scatter(X[:,0],X[:,1],assignments,ax=axes[1])
[<matplotlib.lines.Line2D at 0x2ea867484f0>,
<matplotlib.lines.Line2D at 0x2ea86748970>,
<matplotlib.lines.Line2D at 0x2ea8675f1f0>,
<matplotlib.lines.Line2D at 0x2ea8675f520>,
<matplotlib.lines.Line2D at 0x2ea8675f850>]
X_varied,y_varied=make_blobs(n_samples=200,cluster_std=[1.0,2.5,0.5],random_state=170)
y_pred=KMeans(n_clusters=3,random_state=0).fit_predict(X_varied)
mglearn.discrete_scatter(X_varied[:,0],X_varied[:,1],y_pred)
plt.legend(['cluster 0','cluster 1','cluster 2'],loc='best')
plt.xlabel('Feature 0')
plt.ylabel('Feature 1')
Text(0, 0.5, 'Feature 1')
X,y=make_blobs(random_state=170,n_samples=600)
rng=np.random.RandomState(74)
transformation=rng.normal(size=(2,2))
X=np.dot(X,transformation)
kmeans=KMeans(n_clusters=3)
kmeans.fit(X)
y_pred=kmeans.predict(X)
plt.scatter(X[:,0],X[:,1],c=y_pred,cmap=mglearn.cm3)
plt.scatter(kmeans.cluster_centers_[:,0],kmeans.cluster_centers_[:,1],marker='^',c=[0,1,2],s=100,linewidth=2,cmap=mglearn.cm3)
plt.xlabel('Feature 0')
plt.ylabel('Feature 1')
Text(0, 0.5, 'Feature 1')
from sklearn.datasets import make_moons
X,y=make_moons(n_samples=200,noise=0.05,random_state=0)
kmeans=KMeans(n_clusters=2)
kmeans.fit(X)
y_pred=kmeans.predict(X)
plt.scatter(X[:,0],X[:,1],c=y_pred,cmap=mglearn.cm2,s=60)
plt.scatter(kmeans.cluster_centers_[:,0],kmeans.cluster_centers_[:,1],marker='^',c=[mglearn.cm2(0),mglearn.cm2(1)],s=100,linewidth=2)
plt.xlabel('Feature 0')
plt.ylabel('Feature 1')
Text(0, 0.5, 'Feature 1')
X_train,X_test,y_train,y_test=train_test_split(X_people,y_people,stratify=y_people,random_state=0)
nmf=NMF(n_components=100,random_state=0)
nmf.fit(X_train)
pca=PCA(n_components=100,random_state=0)
pca.fit(X_train)
kmeans=KMeans(n_clusters=100,random_state=0)
kmeans.fit(X_train)
X_reconstructed_pca=pca.inverse_transform(pca.transform(X_test))
X_reconstructed_kmeans=pca.inverse_transform(pca.transform(X_test))
X_reconstructed_nmf=np.dot(nmf.transform(X_test),nmf.components_)
C:\Users\reion\anaconda3\lib\site-packages\sklearn\decomposition\_nmf.py:312: FutureWarning: The 'init' value, when 'init=None' and n_components is less than n_samples and n_features, will be changed from 'nndsvd' to 'nndsvda' in 1.1 (renaming of 0.26).
warnings.warn(("The 'init' value, when 'init=None' and "
C:\Users\reion\anaconda3\lib\site-packages\sklearn\decomposition\_nmf.py:1090: ConvergenceWarning: Maximum number of iterations 200 reached. Increase it to improve convergence.
warnings.warn("Maximum number of iterations %d reached. Increase it to"
fig,axes=plt.subplots(3,5,figsize=(8,8),subplot_kw={'xticks':(),'yticks':()})
fig.suptitle('Extracted Components')
for ax,comp_kmeans,comp_pca,comp_nmf in zip(axes.T,kmeans.cluster_centers_,pca.components_,nmf.components_):
ax[0].imshow(comp_kmeans.reshape(image_shape))
ax[1].imshow(comp_pca.reshape(image_shape))
ax[2].imshow(comp_nmf.reshape(image_shape),cmap='viridis')
axes[0,0].set_ylabel('kmeans')
axes[1,0].set_ylabel('pca')
axes[2,0].set_ylabel('nmf')
fig,axes=plt.subplots(4,5,figsize=(8,8),subplot_kw={'xticks':(),'yticks':()})
fig.suptitle('Reconstructions')
for ax,orig,rec_means,rec_pca,rec_nmf in zip(axes.T,X_test,X_reconstructed_kmeans,X_reconstructed_pca,X_reconstructed_nmf):
ax[0].imshow(orig.reshape(image_shape))
ax[1].imshow(rec_means.reshape(image_shape))
ax[2].imshow(rec_pca.reshape(image_shape))
ax[3].imshow(rec_nmf.reshape(image_shape))
axes[0,0].set_ylabel('original')
axes[1,0].set_ylabel('kmeans')
axes[2,0].set_ylabel('pca')
axes[3,0].set_ylabel('nmf')
Text(0, 0.5, 'nmf')
X,y=make_moons(n_samples=200,noise=0.05,random_state=0)
kmeans=KMeans(n_clusters=10,random_state=0)
kmeans.fit(X)
y_pred=kmeans.predict(X)
plt.scatter(X[:,0],X[:,1],c=y_pred,s=60,cmap='Paired')
plt.scatter(kmeans.cluster_centers_[:,0],kmeans.cluster_centers_[:,1],marker='^',c=range(kmeans.n_clusters),linewidth=2,cmap='Paired')
plt.xlabel('Feature 0')
plt.ylabel('Feature 1')
print('Cluster memberships:\n{}'.format(y_pred))
Cluster memberships:
[9 2 5 4 2 7 9 6 9 6 1 0 2 6 1 9 3 0 3 1 7 6 8 6 8 5 2 7 5 8 9 8 6 5 3 7 0
9 4 5 0 1 3 5 2 8 9 1 5 6 1 0 7 4 6 3 3 6 3 8 0 4 2 9 6 4 8 2 8 4 0 4 0 5
6 4 5 9 3 0 7 8 0 7 5 8 9 8 0 7 3 9 7 1 7 2 2 0 4 5 6 7 8 9 4 5 4 1 2 3 1
8 8 4 9 2 3 7 0 9 9 1 5 8 5 1 9 5 6 7 9 1 4 0 6 2 6 4 7 9 5 5 3 8 1 9 5 6
3 5 0 2 9 3 0 8 6 0 3 3 5 6 3 2 0 2 3 0 2 6 3 4 4 1 5 6 7 1 1 3 2 4 7 2 7
3 8 6 4 1 4 3 9 9 5 1 7 5 8 2]
distance_features=kmeans.transform(X)
print('Distance feature shape:{}'.format(distance_features.shape))
print('Distance feature:\n:{}'.format(distance_features))
Distance feature shape:(200, 10)
Distance feature:
:[[0.9220768 1.46553151 1.13956805 ... 1.16559918 1.03852189 0.23340263]
[1.14159679 2.51721597 0.1199124 ... 0.70700803 2.20414144 0.98271691]
[0.78786246 0.77354687 1.74914157 ... 1.97061341 0.71561277 0.94399739]
...
[0.44639122 1.10631579 1.48991975 ... 1.79125448 1.03195812 0.81205971]
[1.38951924 0.79790385 1.98056306 ... 1.97788956 0.23892095 1.05774337]
[1.14920754 2.4536383 0.04506731 ... 0.57163262 2.11331394 0.88166689]]
mglearn.plots.plot_agglomerative_algorithm()
from sklearn.cluster import AgglomerativeClustering
X,y=make_blobs(random_state=1)
agg=AgglomerativeClustering(n_clusters=3)
assignment=agg.fit_predict(X)
mglearn.discrete_scatter(X[:,0],X[:,1],assignment)
plt.xlabel('Feature 0')
plt.ylabel('Feature 1')
Text(0, 0.5, 'Feature 1')
mglearn.plots.plot_agglomerative()
from scipy.cluster.hierarchy import dendrogram,ward
X,y=make_blobs(random_state=0,n_samples=12)
linkage_array=ward(X)
dendrogram(linkage_array)
ax=plt.gca()
bounds=ax.get_xbound()
ax.plot(bounds,[7.25,7.25],'--',c='k')
ax.plot(bounds,[4,4],'--',c='k')
ax.text(bounds[1],7.25,'two clusters',va='center',fontdict={'size':15})
ax.text(bounds[1],4,'theree clusters',va='center',fontdict={'size':15})
plt.xlabel('Sample index')
plt.ylabel('Cluster distance')
Text(0, 0.5, 'Cluster distance')
from sklearn.cluster import DBSCAN
X,y=make_blobs(n_samples=12,random_state=0)
dbscan=DBSCAN()
clusters=dbscan.fit_predict(X)
print('Cluster memberships:\n{}'.format(clusters))
Cluster memberships:
[-1 -1 -1 -1 -1 -1 -1 -1 -1 -1 -1 -1]
mglearn.plots.plot_dbscan()
min_samples: 2 eps: 1.000000 cluster: [-1 0 0 -1 0 -1 1 1 0 1 -1 -1]
min_samples: 2 eps: 1.500000 cluster: [0 1 1 1 1 0 2 2 1 2 2 0]
min_samples: 2 eps: 2.000000 cluster: [0 1 1 1 1 0 0 0 1 0 0 0]
min_samples: 2 eps: 3.000000 cluster: [0 0 0 0 0 0 0 0 0 0 0 0]
min_samples: 3 eps: 1.000000 cluster: [-1 0 0 -1 0 -1 1 1 0 1 -1 -1]
min_samples: 3 eps: 1.500000 cluster: [0 1 1 1 1 0 2 2 1 2 2 0]
min_samples: 3 eps: 2.000000 cluster: [0 1 1 1 1 0 0 0 1 0 0 0]
min_samples: 3 eps: 3.000000 cluster: [0 0 0 0 0 0 0 0 0 0 0 0]
min_samples: 5 eps: 1.000000 cluster: [-1 -1 -1 -1 -1 -1 -1 -1 -1 -1 -1 -1]
min_samples: 5 eps: 1.500000 cluster: [-1 0 0 0 0 -1 -1 -1 0 -1 -1 -1]
min_samples: 5 eps: 2.000000 cluster: [-1 0 0 0 0 -1 -1 -1 0 -1 -1 -1]
min_samples: 5 eps: 3.000000 cluster: [0 0 0 0 0 0 0 0 0 0 0 0]
X,y=make_moons(n_samples=200,noise=0.05,random_state=0)
scaler=StandardScaler()
scaler.fit(X)
X_scaled=scaler.transform(X)
dbscan=DBSCAN()
clusters=dbscan.fit_predict(X_scaled)
plt.scatter(X_scaled[:,0],X_scaled[:,1],c=clusters,cmap=mglearn.cm2,s=60)
plt.xlabel('Feature 0')
plt.ylabel('Feature 1')
Text(0, 0.5, 'Feature 1')
from sklearn.metrics import adjusted_rand_score
X,y=make_moons(n_samples=200,noise=0.05,random_state=0)
scaler=StandardScaler()
scaler.fit(X)
X_scaled=scaler.transform(X)
fig,axes=plt.subplots(1,4,figsize=(15,3),subplot_kw={'xticks':(),'yticks':()})
alogorithms=[KMeans(n_clusters=2),AgglomerativeClustering(n_clusters=2),DBSCAN()]
random_state=np.random.RandomState(seed=0)
random_clusters=random_state.randint(low=0,high=2,size=len(X))
axes[0].scatter(X_scaled[:,0],X_scaled[:,1],c=random_clusters,cmap=mglearn.cm3,s=60)
axes[0].set_title('Random assignment - ARI :{:.2f}'.format(adjusted_rand_score(y,random_clusters)))
for ax ,alogorithm in zip(axes[1:],alogorithms):
clusters=alogorithm.fit_predict(X_scaled)
ax.scatter(X_scaled[:,0],X_scaled[:,1],c=clusters,cmap=mglearn.cm3,s=60)
ax.set_title('{}- ARI:{:.2f}'.format(alogorithm.__class__.__name__,adjusted_rand_score(y,clusters)))
from sklearn.decomposition import PCA
pca=PCA(n_components=100,whiten=True,random_state=0)
pca.fit_transform(X_people)
X_pca=pca.transform(X_people)
dbscan=DBSCAN()
labels=dbscan.fit_predict(X_pca)
print('Unique label:{}'.format(np.unique(labels)))
Unique label:[-1]
dbscan=DBSCAN(min_samples=3)
labels=dbscan.fit_predict(X_pca)
print('Unique labels:{}'.format(np.unique(labels)))
Unique labels:[-1]
dbscan=DBSCAN(min_samples=3,eps=15)
labels=dbscan.fit_predict(X_pca)
print('Unique labels:{}'.format(np.unique(labels)))
Unique labels:[-1 0]
print('Number of points per cluster:{}'.format(np.bincount(labels+1)))
Number of points per cluster:[ 13 2050]
noise=X_people[labels==-1]
fig,axes=plt.subplots(3,9,subplot_kw={'xticks':(),'yticks':()},figsize=(12,4))
for image,ax in zip(noise,axes.ravel()):
ax.imshow(image.reshape(image_shape),vmin=0,vmax=1)#书上有27个噪声，但在新版本上运行只有13个噪声
for eps in [1,3,5,7,9,11,13]:
print('\nesp={}'.format(eps))
dbscan=DBSCAN(eps=eps,min_samples=3)
labels=dbscan.fit_predict(X_pca)
print('Clusters present :{}'.format(np.unique(labels)))
print('Clusters size:{}'.format(np.bincount(labels+1)))
esp=1
Clusters present :[-1]
Clusters size:[2063]
esp=3
Clusters present :[-1]
Clusters size:[2063]
esp=5
Clusters present :[-1]
Clusters size:[2063]
esp=7
Clusters present :[-1 0 1 2 3]
Clusters size:[2042 10 4 3 4]
esp=9
Clusters present :[-1 0]
Clusters size:[1401 662]
esp=11
Clusters present :[-1 0]
Clusters size:[ 459 1604]
esp=13
Clusters present :[-1 0]
Clusters size:[ 83 1980]
dbscan=DBSCAN(min_samples=3,eps=7)
labels=dbscan.fit_predict(X_pca)
for cluster in range(max(labels)+1):
mask=labels==cluster
n_images=np.sum(mask)
fig,axes=plt.subplots(1,n_images,figsize=(n_images*1.5,4),subplot_kw={'xticks':(),'yticks':()})
for image,label,ax in zip(X_people[mask],y_people[mask],axes):
ax.imshow(image.reshape(image_shape))
ax.set_title(people.target_names[label].split()[-1])
km=KMeans(n_clusters=10,random_state=0)
labels_km=km.fit_predict(X_pca)
print('Cluster size k-means:{}'.format(np.bincount(labels_km)))
Cluster size k-means:[124 77 215 177 152 344 78 367 319 210]
fig,axes=plt.subplots(2,5,figsize=(12,4),subplot_kw={'xticks':(),'yticks':()})
for center ,ax in zip(km.cluster_centers_,axes.ravel()):
ax.imshow(pca.inverse_transform(center).reshape(image_shape),vmin=0,vmax=1)
mglearn.plots.plot_kmeans_faces(km,pca,X_pca,X_people,y_people,people.target_names)
agglomerative=AgglomerativeClustering(n_clusters=10)
labels_agg=agglomerative.fit_predict(X_pca)
print('Cluster sizes agglomerative clustering:{}'.format(np.bincount(labels_agg)))
Cluster sizes agglomerative clustering:[279 103 291 102 84 987 59 49 53 56]
print('ARI:{:.2f}'.format(adjusted_rand_score(labels_agg,labels_km)))
ARI:0.06
linkage_array=ward(X_pca)
plt.figure(figsize=(20,5))
dendrogram(linkage_array,p=7,truncate_mode='level',no_labels=True)
plt.xlabel('Sample index')
plt.ylabel('Cluster distance')
Text(0, 0.5, 'Cluster distance')
n_clusters=10
for cluster in range(n_clusters):
mask=labels_agg==cluster
fig,axes=plt.subplots(1,10,subplot_kw={'xticks':(),'yticks':()},figsize=(15,8))
axes[0].set_ylabel(np.sum(mask))
for image,label,asdf,ax in zip(X_people[mask],y_people[mask],labels_agg[mask],axes):
ax.imshow(image.reshape(image_shape),vmin=0,vmax=1)
ax.set_title(people.target_names[label].split()[-1],fontdict={'fontsize':9})
print(labels_agg)
[2 0 4 ... 2 2 2]
agglomerative=AgglomerativeClustering(n_clusters=40)
labels_agg=agglomerative.fit_predict(X_pca)
print('Cluster size agglomerative clustering :{}'.format(np.bincount(labels_agg)))
n_clusters=40
for cluster in [10,13,19,22,36]:
mask=labels_agg==cluster
fig,axes=plt.subplots(1,15,subplot_kw={'xticks':(),'yticks':()},figsize=(15,8))
cluster_size=np.sum(mask)
axes[0].set_ylabel('#{}:{}'.format(cluster,cluster_size))
for image,label,asdf,ax in zip(X_people[mask],y_people[mask],labels_agg[mask],axes):
ax.imshow(image.reshape(image_shape))
ax.set_title(people.target_names[label].split()[-1],fontdict={'fontsize':9})
for i in range(cluster_size,15):
axes[i].set_visible(False)
Cluster size agglomerative clustering :[291 30 94 96 50 62 287 27 64 56 28 40 31 42 40 98 30 55
25 37 22 14 13 19 33 22 14 23 113 50 27 7 48 22 6 53
43 14 18 19]
import pandas as pd
from IPython.display import display
data=pd.read_csv('./adult.csv',header=None,index_col=False,names=['age','workclass','fnlwgt','education','education-num','marital-status'
,'occupation','relationship','race','gender','capital-gain',
'capital-loss','hours-per-week','native-country','income'])
data=data[['age','workclass','education','gender','hours-per-week','occupation','income']]
display(data.head())
| age | workclass | education | gender | hours-per-week | occupation | income | |
|---|---|---|---|---|---|---|---|
| 0 | 39 | State-gov | Bachelors | Male | 40 | Adm-clerical | <=50K |
| 1 | 50 | Self-emp-not-inc | Bachelors | Male | 13 | Exec-managerial | <=50K |
| 2 | 38 | Private | HS-grad | Male | 40 | Handlers-cleaners | <=50K |
| 3 | 53 | Private | 11th | Male | 40 | Handlers-cleaners | <=50K |
| 4 | 28 | Private | Bachelors | Female | 40 | Prof-specialty | <=50K |
print(data.gender.value_counts())
Male 21790
Female 10771
Name: gender, dtype: int64
print('Original features:\n',list(data.columns),'\n')
data_dummies=pd.get_dummies(data)
print("Feature after get_duummies:\n",list(data_dummies.columns))
Original features:
['age', 'workclass', 'education', 'gender', 'hours-per-week', 'occupation', 'income']
Feature after get_duummies:
['age', 'hours-per-week', 'workclass_ ?', 'workclass_ Federal-gov', 'workclass_ Local-gov', 'workclass_ Never-worked', 'workclass_ Private', 'workclass_ Self-emp-inc', 'workclass_ Self-emp-not-inc', 'workclass_ State-gov', 'workclass_ Without-pay', 'education_ 10th', 'education_ 11th', 'education_ 12th', 'education_ 1st-4th', 'education_ 5th-6th', 'education_ 7th-8th', 'education_ 9th', 'education_ Assoc-acdm', 'education_ Assoc-voc', 'education_ Bachelors', 'education_ Doctorate', 'education_ HS-grad', 'education_ Masters', 'education_ Preschool', 'education_ Prof-school', 'education_ Some-college', 'gender_ Female', 'gender_ Male', 'occupation_ ?', 'occupation_ Adm-clerical', 'occupation_ Armed-Forces', 'occupation_ Craft-repair', 'occupation_ Exec-managerial', 'occupation_ Farming-fishing', 'occupation_ Handlers-cleaners', 'occupation_ Machine-op-inspct', 'occupation_ Other-service', 'occupation_ Priv-house-serv', 'occupation_ Prof-specialty', 'occupation_ Protective-serv', 'occupation_ Sales', 'occupation_ Tech-support', 'occupation_ Transport-moving', 'income_ <=50K', 'income_ >50K']
data_dummies.head()
| age | hours-per-week | workclass_ ? | workclass_ Federal-gov | workclass_ Local-gov | workclass_ Never-worked | workclass_ Private | workclass_ Self-emp-inc | workclass_ Self-emp-not-inc | workclass_ State-gov | ... | occupation_ Machine-op-inspct | occupation_ Other-service | occupation_ Priv-house-serv | occupation_ Prof-specialty | occupation_ Protective-serv | occupation_ Sales | occupation_ Tech-support | occupation_ Transport-moving | income_ <=50K | income_ >50K | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 39 | 40 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | ... | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 |
| 1 | 50 | 13 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | ... | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 |
| 2 | 38 | 40 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | ... | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 |
| 3 | 53 | 40 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | ... | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 |
| 4 | 28 | 40 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | ... | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 1 | 0 |
5 rows × 46 columns
features=data_dummies.loc[:,'age':'occupation_ Transport-moving']
X=features.values
y=data_dummies['income_ >50K'].values
print(np.bincount(y))
print(np.bincount(data_dummies['income_ <=50K']))
print('X.shape:{},y.shape:{}'.format(X.shape,y.shape))
[24720 7841]
[ 7841 24720]
X.shape:(32561, 44),y.shape:(32561,)
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test=train_test_split(X,y,random_state=0)
logreg=LogisticRegression()
logreg.fit(X_train,y_train)
print('Test score::{:.2f}'.format(logreg.score(X_test,y_test)))
Test score::0.81
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
demo_df=pd.DataFrame({'Integer Feature':[0,1,2,1],'Categorical feature':['socks','fox','socks','box']})
display(demo_df)
| Integer Feature | Categorical feature | |
|---|---|---|
| 0 | 0 | socks |
| 1 | 1 | fox |
| 2 | 2 | socks |
| 3 | 1 | box |
pd.get_dummies(demo_df)
| Integer Feature | Categorical feature_box | Categorical feature_fox | Categorical feature_socks | |
|---|---|---|---|---|
| 0 | 0 | 0 | 0 | 1 |
| 1 | 1 | 0 | 1 | 0 |
| 2 | 2 | 0 | 0 | 1 |
| 3 | 1 | 1 | 0 | 0 |
demo_df['Inter Feature']=demo_df['Integer Feature'].astype(str)
pd.get_dummies(demo_df,columns=['Integer Feature','Categorical feature'])
| Inter Feature | Integer Feature_0 | Integer Feature_1 | Integer Feature_2 | Categorical feature_box | Categorical feature_fox | Categorical feature_socks | |
|---|---|---|---|---|---|---|---|
| 0 | 0 | 1 | 0 | 0 | 0 | 0 | 1 |
| 1 | 1 | 0 | 1 | 0 | 0 | 1 | 0 |
| 2 | 2 | 0 | 0 | 1 | 0 | 0 | 1 |
| 3 | 1 | 0 | 1 | 0 | 1 | 0 | 0 |
from sklearn.linear_model import LinearRegression
from sklearn.tree import DecisionTreeRegressor
X,y=mglearn.datasets.make_wave(n_samples=100)
line=np.linspace(-3,3,1000,endpoint=False).reshape(-1,1)
reg=DecisionTreeRegressor(min_samples_split=3).fit(X,y)
plt.plot(line,reg.predict(line),label='decision tree')
reg=LinearRegression().fit(X,y)
plt.plot(line,reg.predict(line),label='linear regression')
plt.plot(X[:,0],y,'o',c='k')
plt.ylabel('Regression output')
plt.xlabel('Input feature')
plt.legend(loc='best')
<matplotlib.legend.Legend at 0x2ea8b91d6a0>
bins=np.linspace(-3,3,11)
print('bins:{}'.format(bins))
bins:[-3. -2.4 -1.8 -1.2 -0.6 0. 0.6 1.2 1.8 2.4 3. ]
which_bins=np.digitize(X,bins=bins)
print('\nData points:\n:{}'.format(X[:5]))
print('\nBin membership for data points:\n',which_bins[:5])
Data points:
:[[-0.75275929]
[ 2.70428584]
[ 1.39196365]
[ 0.59195091]
[-2.06388816]]
Bin membership for data points:
[[ 4]
[10]
[ 8]
[ 6]
[ 2]]
from sklearn.preprocessing import OneHotEncoder
encoder=OneHotEncoder(sparse=False)
encoder.fit(which_bins)
X_bined=encoder.transform(which_bins)
print(X_bined[:5])
[[0. 0. 0. 1. 0. 0. 0. 0. 0. 0.]
[0. 0. 0. 0. 0. 0. 0. 0. 0. 1.]
[0. 0. 0. 0. 0. 0. 0. 1. 0. 0.]
[0. 0. 0. 0. 0. 1. 0. 0. 0. 0.]
[0. 1. 0. 0. 0. 0. 0. 0. 0. 0.]]
print('X_bined.shape:{}'.format(X_bined.shape))
X_bined.shape:(100, 10)
line_bined=encoder.transform(np.digitize(line,bins=bins))
reg=LinearRegression().fit(X_bined,y)
plt.plot(line,reg.predict(line_bined),label='linear regression bined')
reg=DecisionTreeRegressor(min_samples_split=3).fit(X_bined,y)
plt.plot(line,reg.predict(line_bined),label='Decision tree bined')
plt.plot(X[:,0],y,'o',c='k')
plt.vlines(bins,-3,3,linewidth=1,alpha=.2)
plt.legend(loc='best')
plt.ylabel('Regression output')
plt.xlabel('Input feature')
Text(0.5, 0, 'Input feature')
X_combined=np.hstack([X,X_bined])
print(X_combined.shape)
(100, 11)
reg=LinearRegression().fit(X_combined,y)
line_combined=np.hstack([line,line_bined])
plt.plot(line,reg.predict(line_combined),label='linear regression combined')
for bin in bins:
plt.plot([bin,bin],[-3,3],':',c='k')
print(bins)
plt.legend(loc='best')
plt.ylabel('Regression output')
plt.xlabel('Input Feature')
plt.plot(X[:,0],y,'o',c='k')
[-3. -2.4 -1.8 -1.2 -0.6 0. 0.6 1.2 1.8 2.4 3. ]
[<matplotlib.lines.Line2D at 0x2ea8d6cc3a0>]
X_product=np.hstack([X_bined,X * X_bined])
print(X_product.shape)
(100, 20)
reg=LinearRegression().fit(X_product,y)
line_product=np.hstack([line_bined,line*line_bined])
plt.plot(line,reg.predict(line_product),label='linear regression product')
for bin in bins:
plt.plot([bin,bin],[-3,3],':',c='k')
plt.plot(X[:,0],y,'o',c='k')
plt.ylabel('Regression output')
plt.xlabel('Input Feature')
plt.legend(loc='best')
print(X.shape)
print(y.shape)
(100, 1)
(100,)
from sklearn.preprocessing import PolynomialFeatures
poly=PolynomialFeatures(degree=10,include_bias=False)
poly.fit(X)
X_poly=poly.transform(X)
print('X_poly.shape:{}'.format(X_poly.shape))
X_poly.shape:(100, 10)
print('Entries of X:\n{}'.format(X[:5]))
print('Entries of X_poly:\n{}'.format(X_poly[:5]))
Entries of X:
[[-0.75275929]
[ 2.70428584]
[ 1.39196365]
[ 0.59195091]
[-2.06388816]]
Entries of X_poly:
[[-7.52759287e-01 5.66646544e-01 -4.26548448e-01 3.21088306e-01
-2.41702204e-01 1.81943579e-01 -1.36959719e-01 1.03097700e-01
-7.76077513e-02 5.84199555e-02]
[ 2.70428584e+00 7.31316190e+00 1.97768801e+01 5.34823369e+01
1.44631526e+02 3.91124988e+02 1.05771377e+03 2.86036036e+03
7.73523202e+03 2.09182784e+04]
[ 1.39196365e+00 1.93756281e+00 2.69701700e+00 3.75414962e+00
5.22563982e+00 7.27390068e+00 1.01250053e+01 1.40936394e+01
1.96178338e+01 2.73073115e+01]
[ 5.91950905e-01 3.50405874e-01 2.07423074e-01 1.22784277e-01
7.26822637e-02 4.30243318e-02 2.54682921e-02 1.50759786e-02
8.92423917e-03 5.28271146e-03]
[-2.06388816e+00 4.25963433e+00 -8.79140884e+00 1.81444846e+01
-3.74481869e+01 7.72888694e+01 -1.59515582e+02 3.29222321e+02
-6.79478050e+02 1.40236670e+03]]
print('Polynomial feature names:\n{}'.format(poly.get_feature_names()))
Polynomial feature names:
['x0', 'x0^2', 'x0^3', 'x0^4', 'x0^5', 'x0^6', 'x0^7', 'x0^8', 'x0^9', 'x0^10']
reg=LinearRegression().fit(X_poly,y)
line_poly=poly.transform(line)
plt.plot(line,reg.predict(line_poly),label='polynomial linear regression')
plt.plot(X[:,0],y,'o',c='k')
plt.ylabel('Regression output')
plt.xlabel('Input feature')
plt.legend(loc='best')
<matplotlib.legend.Legend at 0x2ea9173edc0>
from sklearn.svm import SVR
for gamma in [1,10]:
svr=SVR(gamma=gamma).fit(X,y)
plt.plot(line,svr.predict(line),label='SVR gamma={}'.format(gamma))
plt.plot(X[:,0],y,'y',c='k')
plt.ylabel('Regression output')
plt.xlabel('Input feature')
plt.legend(loc='best')
<matplotlib.legend.Legend at 0x2ea92d97a60>
from sklearn.datasets import load_boston
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import MinMaxScaler
boston=load_boston()
X_train,X_test,y_train,y_test=train_test_split(boston.data,boston.target,random_state=0)
scaler=MinMaxScaler()
X_train_scaled=scaler.fit_transform(X_train)
X_test_scaled=scaler.transform(X_test)
poly=PolynomialFeatures(degree=2).fit(X_train_scaled)
X_train_poly=poly.transform(X_train_scaled)
X_test_poly=poly.transform(X_test_scaled)
print('X_train.shape:{}'.format(X_train.shape))
print('X_train_poly.shape:{}'.format(X_train_poly.shape))
X_train.shape:(379, 13)
X_train_poly.shape:(379, 105)
print('Polynomial feature names:\n{}'.format(poly.get_feature_names()))
Polynomial feature names:
['1', 'x0', 'x1', 'x2', 'x3', 'x4', 'x5', 'x6', 'x7', 'x8', 'x9', 'x10', 'x11', 'x12', 'x0^2', 'x0 x1', 'x0 x2', 'x0 x3', 'x0 x4', 'x0 x5', 'x0 x6', 'x0 x7', 'x0 x8', 'x0 x9', 'x0 x10', 'x0 x11', 'x0 x12', 'x1^2', 'x1 x2', 'x1 x3', 'x1 x4', 'x1 x5', 'x1 x6', 'x1 x7', 'x1 x8', 'x1 x9', 'x1 x10', 'x1 x11', 'x1 x12', 'x2^2', 'x2 x3', 'x2 x4', 'x2 x5', 'x2 x6', 'x2 x7', 'x2 x8', 'x2 x9', 'x2 x10', 'x2 x11', 'x2 x12', 'x3^2', 'x3 x4', 'x3 x5', 'x3 x6', 'x3 x7', 'x3 x8', 'x3 x9', 'x3 x10', 'x3 x11', 'x3 x12', 'x4^2', 'x4 x5', 'x4 x6', 'x4 x7', 'x4 x8', 'x4 x9', 'x4 x10', 'x4 x11', 'x4 x12', 'x5^2', 'x5 x6', 'x5 x7', 'x5 x8', 'x5 x9', 'x5 x10', 'x5 x11', 'x5 x12', 'x6^2', 'x6 x7', 'x6 x8', 'x6 x9', 'x6 x10', 'x6 x11', 'x6 x12', 'x7^2', 'x7 x8', 'x7 x9', 'x7 x10', 'x7 x11', 'x7 x12', 'x8^2', 'x8 x9', 'x8 x10', 'x8 x11', 'x8 x12', 'x9^2', 'x9 x10', 'x9 x11', 'x9 x12', 'x10^2', 'x10 x11', 'x10 x12', 'x11^2', 'x11 x12', 'x12^2']
from sklearn.linear_model import Ridge
ridge=Ridge().fit(X_train_scaled,y_train)
print('Score without interations:{:.3f}'.format(ridge.score(X_test_scaled,y_test)))
ridge=Ridge().fit(X_train_poly,y_train)
print('Score with interations:{:.3f}'.format(ridge.score(X_test_poly,y_test)))
Score without interations:0.621
Score with interations:0.753
from sklearn.ensemble import RandomForestRegressor
rf=RandomForestRegressor(n_estimators=100).fit(X_train_scaled,y_train)
print('Score without interations:{:.3f}'.format(rf.score(X_test_scaled,y_test)))
rf=RandomForestRegressor(n_estimators=100).fit(X_train_poly,y_train)
print('Score with interations :{:.3f}'.format(rf.score(X_test_poly,y_test)))
Score without interations:0.804
Score with interations :0.777
rnd=np.random.RandomState(0)
X_org=rnd.normal(size=(1000,3))
w=rnd.normal(size=3)
X=rnd.poisson(10*np.exp(X_org))
y=np.dot(X_org,w)
print(w.shape)
print(X.shape)
print(y.shape)
(3,)
(1000, 3)
(1000,)
print('Number of feature appearances:\n{}'.format(np.bincount(X[:,0])))
Number of feature appearances:
[28 38 68 48 61 59 45 56 37 40 35 34 36 26 23 26 27 21 23 23 18 21 10 9
17 9 7 14 12 7 3 8 4 5 5 3 4 2 4 1 1 3 2 5 3 8 2 5
2 1 2 3 3 2 2 3 3 0 1 2 1 0 0 3 1 0 0 0 1 3 0 1
0 2 0 1 1 0 0 0 0 1 0 0 2 2 0 1 1 0 0 0 0 1 1 0
0 0 0 0 0 0 1 0 0 0 0 0 1 1 0 0 1 0 0 0 0 0 0 0
1 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1]
bins=np.bincount(X[:,0])
plt.bar(range(len(bins)),bins,color='r',alpha=.5)
plt.ylabel('Number of appearance')
plt.xlabel('Value')
Text(0.5, 0, 'Value')
from sklearn.linear_model import Ridge
X_train,X_test,y_train,y_test=train_test_split(X,y,random_state=0)
score=Ridge().fit(X_train,y_train).score(X_test,y_test)
print('Test score:{:.3f}'.format(score))
Test score:0.622
X_train_log=np.log(X_train+1)
X_test_log=np.log(X_test+1)
plt.hist(X_train_log[:,0],bins=25,color='gray')
plt.ylabel('Numebr of appearance')
plt.xlabel('value')
Text(0.5, 0, 'value')
score=Ridge().fit(X_train_log,y_train).score(X_test_log,y_test)
print('Test score:{:.3f}'.format(score))
Test score:0.875
from sklearn.datasets import load_breast_cancer
from sklearn.feature_selection import SelectPercentile
from sklearn.model_selection import train_test_split
cancer=load_breast_cancer()
rng=np.random.RandomState(0)
noise=rng.normal(size=(len(cancer.data),50))
X_w_noise=np.hstack([cancer.data,noise])
X_train,X_test,y_train,y_test=train_test_split(X_w_noise,cancer.target,random_state=0,test_size=.5)
select=SelectPercentile(percentile=50)
select.fit(X_train,y_train)
X_train_selected=select.transform(X_train)
print('X_train.shape:{}'.format(X_train.shape))
print('X_train_selected.shape{}'.format(X_train_selected.shape))
X_train.shape:(284, 80)
X_train_selected.shape(284, 40)
mask=select.get_support()
print(mask)
plt.matshow(mask.reshape(1,-1),cmap='gray_r')
plt.xlabel('Sample index')
[ True True True True True True True True True False True False
True True True True True True False False True True True True
True True True True True True False True False True True True
False False False False False True False False False False False False
False False True False True True False False True False True True
False False False False True False True False False False True False
False False False False False False False False]
Text(0.5, 0, 'Sample index')
from sklearn.linear_model import LogisticRegression
X_test_selected=select.transform(X_test)
lr=LogisticRegression()
lr.fit(X_train,y_train)
print('Score with all features:{:.3f}'.format(lr.score(X_test,y_test)))
lr.fit(X_train_selected,y_train)
print('Score with only selected feature:{:.3f}'.format(lr.score(X_test_selected,y_test)))
Score with all features:0.937
Score with only selected feature:0.933
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
from sklearn.feature_selection import SelectFromModel
from sklearn.ensemble import RandomForestClassifier
select=SelectFromModel(RandomForestClassifier(n_estimators=100,random_state=42),threshold='median')
select.fit(X_train,y_train)
X_train_l1=select.transform(X_train)
print('X_train.shape:{}'.format(X_train.shape))
print('X_train_l1.shape:{}'.format(X_train_l1.shape))
X_train.shape:(284, 80)
X_train_l1.shape:(284, 40)
mask=select.get_support()
plt.matshow(mask.reshape(1,-1),cmap='gray_r')
plt.xlabel('Sample index')
Text(0.5, 0, 'Sample index')
from sklearn.feature_selection import RFE
select=RFE(RandomForestClassifier(n_estimators=100,random_state=42),n_features_to_select=40)
select.fit(X_train,y_train)
mask=select.get_support()
plt.matshow(mask.reshape(1,-1),cmap='gray_r')
plt.xlabel('Sample index')
Text(0.5, 0, 'Sample index')
X_train_rfe=select.transform(X_train)
X_test_rfe=select.transform(X_test)
score=LogisticRegression().fit(X_train_rfe,y_train).score(X_test_rfe,y_test)
print('Test score:{:.3f}'.format(score))
Test score:0.926
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
print('Test score :{:.3f}'.format(select.score(X_test,y_test)))
Test score :0.954
citibike=mglearn.datasets.load_citibike()
print('Citi Bike data:\n{}'.format(citibike.head()))
Citi Bike data:
starttime
2015-08-01 00:00:00 3
2015-08-01 03:00:00 0
2015-08-01 06:00:00 9
2015-08-01 09:00:00 41
2015-08-01 12:00:00 39
Freq: 3H, Name: one, dtype: int64
plt.figure(figsize=(10,3))
xticks=pd.date_range(start=citibike.index.min(),end=citibike.index.max())
plt.xticks(xticks,xticks.strftime('%a %m-%d'),rotation=90,ha='left')
plt.plot(citibike,linewidth=1)
plt.xlabel('Date')
plt.ylabel('Rentals')
print(citibike.index)
DatetimeIndex(['2015-08-01 00:00:00', '2015-08-01 03:00:00',
'2015-08-01 06:00:00', '2015-08-01 09:00:00',
'2015-08-01 12:00:00', '2015-08-01 15:00:00',
'2015-08-01 18:00:00', '2015-08-01 21:00:00',
'2015-08-02 00:00:00', '2015-08-02 03:00:00',
...
'2015-08-30 18:00:00', '2015-08-30 21:00:00',
'2015-08-31 00:00:00', '2015-08-31 03:00:00',
'2015-08-31 06:00:00', '2015-08-31 09:00:00',
'2015-08-31 12:00:00', '2015-08-31 15:00:00',
'2015-08-31 18:00:00', '2015-08-31 21:00:00'],
dtype='datetime64[ns]', name='starttime', length=248, freq='3H')
y=citibike.values
X = citibike.index.astype("int64").values.reshape(-1, 1)
X.shape
(248, 1)
n_train=184
def eval_on_features(features,target,regressor):
X_train,X_test=features[:n_train],features[n_train:]
y_train,y_test=target[:n_train],target[n_train:]
regressor.fit(X_train,y_train)
print('Test-set R^2:{:.2f}'.format(regressor.score(X_test,y_test)))
y_pred=regressor.predict(X_test)
y_pred_train=regressor.predict(X_train)
plt.figure(figsize=(10,3))
plt.xticks(range(0,len(X),8),xticks.strftime('%a %m-%d'),rotation=90,ha='left')
plt.plot(range(n_train),y_train,label='train')
plt.plot(range(n_train,len(y_test)+n_train),y_test,'-',label='test')
plt.plot(range(n_train),y_pred_train,'--',label='Prediction train')
plt.plot(range(n_train,len(y_test)+n_train),y_pred,'--',label='prediction test')
plt.legend(loc=(1.01,0))
plt.xlabel('Date')
plt.ylabel('Rentals')
from sklearn.ensemble import RandomForestRegressor
regressor=RandomForestRegressor(n_estimators=100,random_state=0)
plt.figure()
eval_on_features(X,y,regressor)
Test-set R^2:-0.04
<Figure size 432x288 with 0 Axes>
X_hour=citibike.index.hour.values.reshape(-1,1)
eval_on_features(X_hour,y,regressor)
Test-set R^2:0.60
X_hour_week=np.hstack([citibike.index.dayofweek.values.reshape(-1,1),citibike.index.hour.values.reshape(-1,1)])
eval_on_features(X_hour_week,y,regressor)
Test-set R^2:0.84
from sklearn.preprocessing import OneHotEncoder
enc=OneHotEncoder()
X_hour_week_onehot=enc.fit_transform(X_hour_week).toarray()
X_hour_week_onehot
array([[0., 0., 0., ..., 0., 0., 0.],
[0., 0., 0., ..., 0., 0., 0.],
[0., 0., 0., ..., 0., 0., 0.],
...,
[1., 0., 0., ..., 1., 0., 0.],
[1., 0., 0., ..., 0., 1., 0.],
[1., 0., 0., ..., 0., 0., 1.]])
from sklearn.linear_model import Ridge
eval_on_features(X_hour_week_onehot,y,Ridge())
Test-set R^2:0.62
from sklearn.preprocessing import PolynomialFeatures
poly_transform=PolynomialFeatures(degree=2,interaction_only=True,include_bias=False)
X_hour_week_onehot_poly=poly_transform.fit_transform(X_hour_week_onehot)
lr=Ridge()
eval_on_features(X_hour_week_onehot_poly,y,lr)
Test-set R^2:0.85
hour=['%02d:00'% i for i in range(0,24,3)]
day=['Mon','Tue','Wed','Thu','Fri','Sat','Sun']
features=day+hour
print(hour)
print(day)
print(features)
['00:00', '03:00', '06:00', '09:00', '12:00', '15:00', '18:00', '21:00']
['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun']
['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun', '00:00', '03:00', '06:00', '09:00', '12:00', '15:00', '18:00', '21:00']
features_poly=poly_transform.get_feature_names(features)
features_nonzero=np.array(features_poly)[lr.coef_!=0]
coef_nonzero=lr.coef_[lr.coef_!=0]
plt.figure(figsize=(15,2))
plt.plot(coef_nonzero,'o')
plt.xticks(np.arange(len(coef_nonzero)),features_nonzero,rotation=90)
plt.xlabel('Features name')
plt.ylabel('Features magnitude')
Text(0, 0.5, 'Features magnitude')
from sklearn.datasets import make_blobs
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
X,y=make_blobs(random_state=0)
X_train,X_test,y_train,y_test=train_test_split(X,y,random_state=0)
logreg=LogisticRegression().fit(X_train,y_train)
print('Test set score:{:.2f}'.format(logreg.score(X_test,y_test)))
Test set score:0.88
mglearn.plots.plot_cross_validation()
from sklearn.model_selection import cross_val_score
from sklearn.datasets import load_iris
from sklearn.linear_model import LogisticRegression
iris=load_iris()
logreg=LogisticRegression()
scores=cross_val_score(logreg,iris.data,iris.target,cv=3)
print('Cross-validation score:{}'.format(scores))
Cross-validation score:[0.98 0.96 0.98]
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
scores=cross_val_score(logreg,iris.data,iris.target,cv=5)
print('Cross-validation score:{}'.format(scores))
Cross-validation score:[0.96666667 1. 0.93333333 0.96666667 1. ]
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
print('Average cross-validation score:{:.2f}'.format(scores.mean()))
Average cross-validation score:0.97
from sklearn.datasets import load_iris
iris=load_iris()
print('Iris labels:\n{}'.format(iris.target))
Iris labels:
[0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2 2
2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2
2 2]
mglearn.plots.plot_stratified_cross_validation()
from sklearn.model_selection import KFold
kfold=KFold(n_splits=5)
print('Cross_validation scores:\n{}'.format(cross_val_score(logreg,iris.data,iris.target,cv=kfold)))
Cross_validation scores:
[1. 1. 0.86666667 0.93333333 0.83333333]
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
kfold=KFold(n_splits=3)
print('Cross_validation scores:\n{}'.format(cross_val_score(logreg,iris.data,iris.target,cv=kfold)))
Cross_validation scores:
[0. 0. 0.]
kfold=KFold(n_splits=3,shuffle=True,random_state=0)
print('Cross_validation scores:\n{}'.format(cross_val_score(logreg,iris.data,iris.target,cv=kfold)))
Cross_validation scores:
[0.98 0.96 0.96]
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
from sklearn.model_selection import LeaveOneOut
loo=LeaveOneOut()
scores=cross_val_score(logreg,iris.data,iris.target,cv=loo)
print('Number of cv iterations:',len(scores))
print('Mean accuracy:{:.2f}'.format(scores.mean()))
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
Number of cv iterations: 150
Mean accuracy:0.97
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
mglearn.plots.plot_shuffle_split()
from sklearn.model_selection import ShuffleSplit
shuffle_split=ShuffleSplit(test_size=.5,train_size=.5,n_splits=10)
scores=cross_val_score(logreg,iris.data,iris.target,cv=shuffle_split)
print('Cross_validation scores:\n{}'.format(scores))
Cross_validation scores:
[0.94666667 0.93333333 0.97333333 0.93333333 0.97333333 0.96
0.97333333 0.94666667 0.96 0.96 ]
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
from sklearn.model_selection import GroupKFold
X,y=make_blobs(n_samples=12,random_state=0)
groups=[0,0,0,1,1,1,1,2,2,3,3,3]
scores=cross_val_score(logreg,X,y,groups,cv=GroupKFold(n_splits=3))
print('Cross_validation scores:\n{}'.format(scores))
Cross_validation scores:
[0.75 0.6 0.66666667]
C:\Users\reion\anaconda3\lib\site-packages\sklearn\utils\validation.py:70: FutureWarning: Pass groups=[0, 0, 0, 1, 1, 1, 1, 2, 2, 3, 3, 3] as keyword args. From version 1.0 (renaming of 0.25) passing these as positional arguments will result in an error
warnings.warn(f"Pass {args_msg} as keyword args. From version "
mglearn.plots.plot_group_kfold()
from sklearn.svm import SVC
X_train,X_test,y_train,y_test=train_test_split(iris.data,iris.target,random_state=0)
print('Size of training set:{} size of test set :{}'.format(X_train.shape[0],X_test.shape[0]))
best_score=0
for gamma in [0.001,0.01,0.1,1,10,100]:
for C in [0.001,0.01,0.1,1,10,100]:
svm=SVC(gamma=gamma,C=C)
svm.fit(X_train,y_train)
score=svm.score(X_test,y_test)
if score>best_score:
best_score=score
best_parameters={'C':C,'gamma':gamma}
print('Best score:{:.2f}'.format(best_score))
print('Best parameters:{}'.format(best_parameters))
Size of training set:112 size of test set :38
Best score:0.97
Best parameters:{'C': 100, 'gamma': 0.001}
mglearn.plots.plot_threefold_split()
from sklearn.svm import SVC
X_trainval,X_test,y_trainval,y_test=train_test_split(iris.data,iris.target,random_state=0)
X_train,X_valid,y_train,y_valid=train_test_split(X_trainval,y_trainval,random_state=1)
print('Size of training set:{} size of validation set:{} size of test set:{}\n'.format(X_train.shape[0],X_valid.shape[0],X_test.shape[0]))
for gamma in [0.001,0.01,0.1,1,10,100]:
for C in [0.001,0.01,0.1,1,10,100]:
svm=SVC(gamma=gamma,C=C)
svm.fit(X_train,y_train)
score=svm.score(X_valid,y_valid)
if score>best_score:
best_score=score
best_parameters={'C':C,'gamma':gamma}
svm=SVC(**best_parameters)
svm.fit(X_trainval,y_trainval)
test_scores=svm.score(X_test,y_test)
print('Best score on validation:{:.2f}'.format(best_score))
print('Best parameters:{}'.format(best_parameters))
print('Test set score with best valiadation{:.2f}'.format(test_scores))
Size of training set:84 size of validation set:28 size of test set:38
Best score on validation:0.97
Best parameters:{'C': 100, 'gamma': 0.001}
Test set score with best valiadation0.97
for gamma in [0.001,0.01,0.1,1,10,100]:
for C in [0.001,0.01,0.1,1,10,100]:
svm=SVC(gamma=gamma,C=C)
svm.fit(X_train,y_train)
scores=cross_val_score(svm,X_trainval,y_trainval,cv=5)
score=np.mean(scores)
if score>best_score:
best_score=score
best_parameters={'C':C,'gamma':gamma}
svm=SVC(**best_parameters)
svm.fit(X_trainval,y_trainval)
test_scores=svm.score(X_test,y_test)
print('Best score on validation:{:.2f}'.format(best_score))
print('Best parameters:{}'.format(best_parameters))
print('Test set score with best valiadation{:.2f}'.format(test_scores))
Best score on validation:0.97
Best parameters:{'C': 100, 'gamma': 0.001}
Test set score with best valiadation0.97
# mglearn.plots.plot_cross_val_selection()
mglearn.plots.plot_grid_search_overview()
param_grid={'C':[0.001,0.01,0.1,1,10,100],'gamma':[0.001,0.01,0.1,1,10,100]}
print('Parameter grid:\n{}'.format(param_grid))
Parameter grid:
{'C': [0.001, 0.01, 0.1, 1, 10, 100], 'gamma': [0.001, 0.01, 0.1, 1, 10, 100]}
from sklearn.model_selection import GridSearchCV
from sklearn.svm import SVC
grid_search=GridSearchCV(SVC(),param_grid,cv=5)
X_train,X_test,y_train,y_test=train_test_split(iris.data,iris.target,random_state=0)
grid_search.fit(X_train,y_train)
GridSearchCV(cv=5, estimator=SVC(),
param_grid={'C': [0.001, 0.01, 0.1, 1, 10, 100],
'gamma': [0.001, 0.01, 0.1, 1, 10, 100]})
print('Test set score:{:.2f}'.format(grid_search.score(X_test,y_test)))
Test set score:0.97
print('Best parameters:{}'.format(grid_search.best_params_))
print('Best cross-validation score:{:.2f}'.format(grid_search.best_score_))
Best parameters:{'C': 10, 'gamma': 0.1}
Best cross-validation score:0.97
print('Best estimator:\n{}'.format(grid_search.best_estimator_))
Best estimator:
SVC(C=10, gamma=0.1)
import pandas as pd
results=pd.DataFrame(grid_search.cv_results_)
display(results)
| mean_fit_time | std_fit_time | mean_score_time | std_score_time | param_C | param_gamma | params | split0_test_score | split1_test_score | split2_test_score | split3_test_score | split4_test_score | mean_test_score | std_test_score | rank_test_score | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 0.000800 | 4.001146e-04 | 0.000200 | 3.993988e-04 | 0.001 | 0.001 | {'C': 0.001, 'gamma': 0.001} | 0.347826 | 0.347826 | 0.363636 | 0.363636 | 0.409091 | 0.366403 | 0.022485 | 22 |
| 1 | 0.000800 | 3.999236e-04 | 0.000200 | 3.996849e-04 | 0.001 | 0.01 | {'C': 0.001, 'gamma': 0.01} | 0.347826 | 0.347826 | 0.363636 | 0.363636 | 0.409091 | 0.366403 | 0.022485 | 22 |
| 2 | 0.000600 | 4.899017e-04 | 0.000000 | 0.000000e+00 | 0.001 | 0.1 | {'C': 0.001, 'gamma': 0.1} | 0.347826 | 0.347826 | 0.363636 | 0.363636 | 0.409091 | 0.366403 | 0.022485 | 22 |
| 3 | 0.000000 | 0.000000e+00 | 0.000800 | 4.000665e-04 | 0.001 | 1 | {'C': 0.001, 'gamma': 1} | 0.347826 | 0.347826 | 0.363636 | 0.363636 | 0.409091 | 0.366403 | 0.022485 | 22 |
| 4 | 0.000800 | 3.999949e-04 | 0.000200 | 3.996849e-04 | 0.001 | 10 | {'C': 0.001, 'gamma': 10} | 0.347826 | 0.347826 | 0.363636 | 0.363636 | 0.409091 | 0.366403 | 0.022485 | 22 |
| 5 | 0.000800 | 4.000666e-04 | 0.000200 | 3.994942e-04 | 0.001 | 100 | {'C': 0.001, 'gamma': 100} | 0.347826 | 0.347826 | 0.363636 | 0.363636 | 0.409091 | 0.366403 | 0.022485 | 22 |
| 6 | 0.000600 | 4.898625e-04 | 0.000000 | 0.000000e+00 | 0.01 | 0.001 | {'C': 0.01, 'gamma': 0.001} | 0.347826 | 0.347826 | 0.363636 | 0.363636 | 0.409091 | 0.366403 | 0.022485 | 22 |
| 7 | 0.000200 | 3.995895e-04 | 0.000200 | 4.005432e-04 | 0.01 | 0.01 | {'C': 0.01, 'gamma': 0.01} | 0.347826 | 0.347826 | 0.363636 | 0.363636 | 0.409091 | 0.366403 | 0.022485 | 22 |
| 8 | 0.001000 | 6.143617e-07 | 0.000000 | 0.000000e+00 | 0.01 | 0.1 | {'C': 0.01, 'gamma': 0.1} | 0.347826 | 0.347826 | 0.363636 | 0.363636 | 0.409091 | 0.366403 | 0.022485 | 22 |
| 9 | 0.000400 | 4.896872e-04 | 0.000200 | 4.000664e-04 | 0.01 | 1 | {'C': 0.01, 'gamma': 1} | 0.347826 | 0.347826 | 0.363636 | 0.363636 | 0.409091 | 0.366403 | 0.022485 | 22 |
| 10 | 0.000801 | 4.005718e-04 | 0.000200 | 3.999710e-04 | 0.01 | 10 | {'C': 0.01, 'gamma': 10} | 0.347826 | 0.347826 | 0.363636 | 0.363636 | 0.409091 | 0.366403 | 0.022485 | 22 |
| 11 | 0.000799 | 3.993803e-04 | 0.000200 | 4.002571e-04 | 0.01 | 100 | {'C': 0.01, 'gamma': 100} | 0.347826 | 0.347826 | 0.363636 | 0.363636 | 0.409091 | 0.366403 | 0.022485 | 22 |
| 12 | 0.000000 | 0.000000e+00 | 0.001000 | 3.989506e-07 | 0.1 | 0.001 | {'C': 0.1, 'gamma': 0.001} | 0.347826 | 0.347826 | 0.363636 | 0.363636 | 0.409091 | 0.366403 | 0.022485 | 22 |
| 13 | 0.001000 | 4.672031e-07 | 0.000000 | 0.000000e+00 | 0.1 | 0.01 | {'C': 0.1, 'gamma': 0.01} | 0.695652 | 0.695652 | 0.681818 | 0.681818 | 0.727273 | 0.696443 | 0.016610 | 17 |
| 14 | 0.001000 | 1.472802e-06 | 0.000000 | 0.000000e+00 | 0.1 | 0.1 | {'C': 0.1, 'gamma': 0.1} | 0.913043 | 0.913043 | 0.909091 | 0.863636 | 0.909091 | 0.901581 | 0.019054 | 16 |
| 15 | 0.001000 | 3.504023e-07 | 0.000000 | 0.000000e+00 | 0.1 | 1 | {'C': 0.1, 'gamma': 1} | 1.000000 | 0.913043 | 1.000000 | 0.909091 | 0.954545 | 0.955336 | 0.039794 | 6 |
| 16 | 0.000800 | 4.001626e-04 | 0.000000 | 0.000000e+00 | 0.1 | 10 | {'C': 0.1, 'gamma': 10} | 0.347826 | 0.347826 | 0.363636 | 0.363636 | 0.409091 | 0.366403 | 0.022485 | 22 |
| 17 | 0.000600 | 4.899014e-04 | 0.000600 | 4.899403e-04 | 0.1 | 100 | {'C': 0.1, 'gamma': 100} | 0.347826 | 0.347826 | 0.363636 | 0.363636 | 0.409091 | 0.366403 | 0.022485 | 22 |
| 18 | 0.001000 | 3.693565e-07 | 0.000000 | 0.000000e+00 | 1 | 0.001 | {'C': 1, 'gamma': 0.001} | 0.695652 | 0.695652 | 0.681818 | 0.681818 | 0.727273 | 0.696443 | 0.016610 | 17 |
| 19 | 0.001000 | 5.223489e-07 | 0.000000 | 0.000000e+00 | 1 | 0.01 | {'C': 1, 'gamma': 0.01} | 0.913043 | 0.913043 | 1.000000 | 0.909091 | 0.954545 | 0.937945 | 0.035211 | 11 |
| 20 | 0.000400 | 4.900379e-04 | 0.000200 | 3.999710e-04 | 1 | 0.1 | {'C': 1, 'gamma': 0.1} | 1.000000 | 0.956522 | 1.000000 | 0.909091 | 0.954545 | 0.964032 | 0.033918 | 3 |
| 21 | 0.000199 | 3.989220e-04 | 0.000200 | 3.997803e-04 | 1 | 1 | {'C': 1, 'gamma': 1} | 0.956522 | 0.913043 | 1.000000 | 0.909091 | 0.954545 | 0.946640 | 0.033305 | 8 |
| 22 | 0.000800 | 4.000669e-04 | 0.000200 | 3.997803e-04 | 1 | 10 | {'C': 1, 'gamma': 10} | 0.913043 | 0.956522 | 1.000000 | 0.818182 | 0.954545 | 0.928458 | 0.061620 | 13 |
| 23 | 0.000800 | 3.999951e-04 | 0.000400 | 4.896875e-04 | 1 | 100 | {'C': 1, 'gamma': 100} | 0.391304 | 0.434783 | 0.545455 | 0.500000 | 0.636364 | 0.501581 | 0.085693 | 21 |
| 24 | 0.000200 | 3.999710e-04 | 0.000200 | 4.000664e-04 | 10 | 0.001 | {'C': 10, 'gamma': 0.001} | 0.913043 | 0.913043 | 1.000000 | 0.909091 | 0.954545 | 0.937945 | 0.035211 | 11 |
| 25 | 0.000400 | 4.899208e-04 | 0.000200 | 4.000664e-04 | 10 | 0.01 | {'C': 10, 'gamma': 0.01} | 1.000000 | 0.956522 | 1.000000 | 0.909091 | 0.954545 | 0.964032 | 0.033918 | 3 |
| 26 | 0.000400 | 4.899208e-04 | 0.000200 | 3.997803e-04 | 10 | 0.1 | {'C': 10, 'gamma': 0.1} | 1.000000 | 0.956522 | 1.000000 | 0.954545 | 0.954545 | 0.973123 | 0.021957 | 1 |
| 27 | 0.000400 | 4.902131e-04 | 0.000200 | 3.998756e-04 | 10 | 1 | {'C': 10, 'gamma': 1} | 0.956522 | 0.956522 | 1.000000 | 0.863636 | 0.954545 | 0.946245 | 0.044708 | 9 |
| 28 | 0.000600 | 4.897067e-04 | 0.000208 | 4.151344e-04 | 10 | 10 | {'C': 10, 'gamma': 10} | 0.869565 | 0.913043 | 1.000000 | 0.818182 | 0.954545 | 0.911067 | 0.063488 | 14 |
| 29 | 0.000795 | 3.974699e-04 | 0.000400 | 4.898624e-04 | 10 | 100 | {'C': 10, 'gamma': 100} | 0.521739 | 0.521739 | 0.590909 | 0.590909 | 0.681818 | 0.581423 | 0.058964 | 19 |
| 30 | 0.000400 | 4.896874e-04 | 0.000200 | 3.997803e-04 | 100 | 0.001 | {'C': 100, 'gamma': 0.001} | 1.000000 | 0.956522 | 1.000000 | 0.909091 | 0.954545 | 0.964032 | 0.033918 | 3 |
| 31 | 0.000400 | 4.898040e-04 | 0.000000 | 0.000000e+00 | 100 | 0.01 | {'C': 100, 'gamma': 0.01} | 1.000000 | 0.913043 | 1.000000 | 0.954545 | 0.954545 | 0.964427 | 0.032761 | 2 |
| 32 | 0.000200 | 3.990173e-04 | 0.000200 | 4.001617e-04 | 100 | 0.1 | {'C': 100, 'gamma': 0.1} | 1.000000 | 0.956522 | 1.000000 | 0.863636 | 0.954545 | 0.954941 | 0.049799 | 7 |
| 33 | 0.000398 | 4.876012e-04 | 0.000305 | 3.986543e-04 | 100 | 1 | {'C': 100, 'gamma': 1} | 0.956522 | 0.956522 | 1.000000 | 0.863636 | 0.954545 | 0.946245 | 0.044708 | 9 |
| 34 | 0.000600 | 4.897458e-04 | 0.000200 | 3.999710e-04 | 100 | 10 | {'C': 100, 'gamma': 10} | 0.869565 | 0.913043 | 1.000000 | 0.818182 | 0.954545 | 0.911067 | 0.063488 | 14 |
| 35 | 0.000800 | 4.002100e-04 | 0.000200 | 4.000664e-04 | 100 | 100 | {'C': 100, 'gamma': 100} | 0.521739 | 0.521739 | 0.590909 | 0.590909 | 0.681818 | 0.581423 | 0.058964 | 19 |
scores=np.array(results.mean_test_score).reshape(6,6)
mglearn.tools.heatmap(scores,xlabel='gamma',xticklabels=param_grid['gamma'],ylabel='C',yticklabels=param_grid['C'],cmap='viridis')
<matplotlib.collections.PolyCollection at 0x2ea8db41f40>
'''错误示范'''
fig,axes=plt.subplots(1,3,figsize=(13,5))
param_grid_linear={'C':np.linspace(1,2,6),'gamma':np.linspace(1,2,6)}
param_grid_one_log={'C':np.linspace(1,2,6),'gamma':np.logspace(-3,2,6)}
param_grid_range={'C':np.logspace(-3,2,6),'gamma':np.logspace(-7,-2,6)}
for param_grid,ax in zip([param_grid_linear,param_grid_one_log,param_grid_range],axes):
grid_search=GridSearchCV(SVC(),param_grid,cv=5)
grid_search.fit(X_train,y_train)
scores=grid_search.cv_results_['mean_test_score'].reshape(6,6)
scores_img=mglearn.tools.heatmap(scores,xlabel='gamma',ylabel='C',xticklabels=param_grid['gamma'],yticklabels=param_grid['C'],cmap='viridis',ax=ax)
plt.colorbar(scores_img,ax=axes.tolist())
<matplotlib.colorbar.Colorbar at 0x2ea86290670>
param_grid=[{'kernel':['rbf'],'C':[0.001,0.01,0.1,1,10,100],'gamma':[0.001,0.01,0.1,1,10,100]},
{'kernel':['linear'],'C':[0.001,0.01,0.1,1,10,100],'gamma':[0.001,0.01,0.1,1,10,100]}]
print('List of grids:\n{}'.format(param_grid))
List of grids:
[{'kernel': ['rbf'], 'C': [0.001, 0.01, 0.1, 1, 10, 100], 'gamma': [0.001, 0.01, 0.1, 1, 10, 100]}, {'kernel': ['linear'], 'C': [0.001, 0.01, 0.1, 1, 10, 100], 'gamma': [0.001, 0.01, 0.1, 1, 10, 100]}]
grid_search=GridSearchCV(SVC(),param_grid,cv=5)
grid_search.fit(X_train,y_train)
print('Best parameters:{}'.format(grid_search.best_params_))
print('Best cross-validation score:{:.2f}'.format(grid_search.best_score_))
Best parameters:{'C': 10, 'gamma': 0.1, 'kernel': 'rbf'}
Best cross-validation score:0.97
results=pd.DataFrame(grid_search.cv_results_)
display(results.T)
| 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | ... | 62 | 63 | 64 | 65 | 66 | 67 | 68 | 69 | 70 | 71 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| mean_fit_time | 0.001 | 0.0002 | 0.000599 | 0.001 | 0.0004 | 0.0006 | 0.0002 | 0.001 | 0.001 | 0.0 | ... | 0.0004 | 0.0 | 0.0004 | 0.0002 | 0.000599 | 0.0002 | 0.000601 | 0.0002 | 0.0004 | 0.000202 |
| std_fit_time | 0.000001 | 0.0004 | 0.000489 | 0.000001 | 0.00049 | 0.00049 | 0.0004 | 0.0 | 0.0 | 0.0 | ... | 0.00049 | 0.0 | 0.00049 | 0.0004 | 0.000489 | 0.0004 | 0.00049 | 0.000401 | 0.00049 | 0.000403 |
| mean_score_time | 0.0002 | 0.0 | 0.000401 | 0.0 | 0.0 | 0.0004 | 0.0008 | 0.0 | 0.0 | 0.0006 | ... | 0.0004 | 0.0002 | 0.0002 | 0.0 | 0.0002 | 0.0002 | 0.000199 | 0.0002 | 0.0002 | 0.0004 |
| std_score_time | 0.0004 | 0.0 | 0.000491 | 0.0 | 0.0 | 0.00049 | 0.0004 | 0.0 | 0.0 | 0.00049 | ... | 0.00049 | 0.0004 | 0.0004 | 0.0 | 0.000399 | 0.0004 | 0.000399 | 0.0004 | 0.0004 | 0.00049 |
| param_C | 0.001 | 0.001 | 0.001 | 0.001 | 0.001 | 0.001 | 0.01 | 0.01 | 0.01 | 0.01 | ... | 10 | 10 | 10 | 10 | 100 | 100 | 100 | 100 | 100 | 100 |
| param_gamma | 0.001 | 0.01 | 0.1 | 1 | 10 | 100 | 0.001 | 0.01 | 0.1 | 1 | ... | 0.1 | 1 | 10 | 100 | 0.001 | 0.01 | 0.1 | 1 | 10 | 100 |
| param_kernel | rbf | rbf | rbf | rbf | rbf | rbf | rbf | rbf | rbf | rbf | ... | linear | linear | linear | linear | linear | linear | linear | linear | linear | linear |
| params | {'C': 0.001, 'gamma': 0.001, 'kernel': 'rbf'} | {'C': 0.001, 'gamma': 0.01, 'kernel': 'rbf'} | {'C': 0.001, 'gamma': 0.1, 'kernel': 'rbf'} | {'C': 0.001, 'gamma': 1, 'kernel': 'rbf'} | {'C': 0.001, 'gamma': 10, 'kernel': 'rbf'} | {'C': 0.001, 'gamma': 100, 'kernel': 'rbf'} | {'C': 0.01, 'gamma': 0.001, 'kernel': 'rbf'} | {'C': 0.01, 'gamma': 0.01, 'kernel': 'rbf'} | {'C': 0.01, 'gamma': 0.1, 'kernel': 'rbf'} | {'C': 0.01, 'gamma': 1, 'kernel': 'rbf'} | ... | {'C': 10, 'gamma': 0.1, 'kernel': 'linear'} | {'C': 10, 'gamma': 1, 'kernel': 'linear'} | {'C': 10, 'gamma': 10, 'kernel': 'linear'} | {'C': 10, 'gamma': 100, 'kernel': 'linear'} | {'C': 100, 'gamma': 0.001, 'kernel': 'linear'} | {'C': 100, 'gamma': 0.01, 'kernel': 'linear'} | {'C': 100, 'gamma': 0.1, 'kernel': 'linear'} | {'C': 100, 'gamma': 1, 'kernel': 'linear'} | {'C': 100, 'gamma': 10, 'kernel': 'linear'} | {'C': 100, 'gamma': 100, 'kernel': 'linear'} |
| split0_test_score | 0.347826 | 0.347826 | 0.347826 | 0.347826 | 0.347826 | 0.347826 | 0.347826 | 0.347826 | 0.347826 | 0.347826 | ... | 1.0 | 1.0 | 1.0 | 1.0 | 0.956522 | 0.956522 | 0.956522 | 0.956522 | 0.956522 | 0.956522 |
| split1_test_score | 0.347826 | 0.347826 | 0.347826 | 0.347826 | 0.347826 | 0.347826 | 0.347826 | 0.347826 | 0.347826 | 0.347826 | ... | 1.0 | 1.0 | 1.0 | 1.0 | 0.956522 | 0.956522 | 0.956522 | 0.956522 | 0.956522 | 0.956522 |
| split2_test_score | 0.363636 | 0.363636 | 0.363636 | 0.363636 | 0.363636 | 0.363636 | 0.363636 | 0.363636 | 0.363636 | 0.363636 | ... | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
| split3_test_score | 0.363636 | 0.363636 | 0.363636 | 0.363636 | 0.363636 | 0.363636 | 0.363636 | 0.363636 | 0.363636 | 0.363636 | ... | 0.909091 | 0.909091 | 0.909091 | 0.909091 | 0.909091 | 0.909091 | 0.909091 | 0.909091 | 0.909091 | 0.909091 |
| split4_test_score | 0.409091 | 0.409091 | 0.409091 | 0.409091 | 0.409091 | 0.409091 | 0.409091 | 0.409091 | 0.409091 | 0.409091 | ... | 0.954545 | 0.954545 | 0.954545 | 0.954545 | 0.954545 | 0.954545 | 0.954545 | 0.954545 | 0.954545 | 0.954545 |
| mean_test_score | 0.366403 | 0.366403 | 0.366403 | 0.366403 | 0.366403 | 0.366403 | 0.366403 | 0.366403 | 0.366403 | 0.366403 | ... | 0.972727 | 0.972727 | 0.972727 | 0.972727 | 0.955336 | 0.955336 | 0.955336 | 0.955336 | 0.955336 | 0.955336 |
| std_test_score | 0.022485 | 0.022485 | 0.022485 | 0.022485 | 0.022485 | 0.022485 | 0.022485 | 0.022485 | 0.022485 | 0.022485 | ... | 0.036364 | 0.036364 | 0.036364 | 0.036364 | 0.028764 | 0.028764 | 0.028764 | 0.028764 | 0.028764 | 0.028764 |
| rank_test_score | 52 | 52 | 52 | 52 | 52 | 52 | 52 | 52 | 52 | 52 | ... | 8 | 8 | 8 | 8 | 18 | 18 | 18 | 18 | 18 | 18 |
16 rows × 72 columns
scores=cross_val_score(GridSearchCV(SVC(),param_grid,cv=5),iris.data,iris.target)
print('Cross-validation scores',scores)
print('Mean cross-validation score:',scores.mean())
Cross-validation scores [0.96666667 1. 0.9 0.96666667 1. ]
Mean cross-validation score: 0.9666666666666668
def nested_cv(X,y,inner_cv,outer_cv,Classifier,parameter_grid):
outer_scores=[]
for training_samples,test_samples in outer_cv.split(X,y):
best_parms=[]
best_score=-np.inf
for parameters in parameter_grid:
cv_scores=[]
for inner_train,inner_test in inner_cv.split(X[training_samples],y[training_samples]):
clf=Classifier(**parameters)
clf.fit(X[inner_train],y[inner_train])
score=clf.score(X[inner_train],y[inner_train])
cv_scores.append(score)
mean_score=np.mean(cv_scores)
if mean_score>best_score:
best_score=mean_score
best_params=parameters
clf=Classifier(**best_params)
clf.fit(X[training_samples],y[training_samples])
outer_scores.append(clf.score(X[test_samples],y[test_samples]))
return np.array(outer_scores)
from sklearn.model_selection import ParameterGrid,StratifiedKFold
scores=nested_cv(iris.data,iris.target,StratifiedKFold(5),StratifiedKFold(5),SVC,ParameterGrid(param_grid))
print('Cross-validation scores:{}'.format(scores))
Cross-validation scores:[0.96666667 1. 0.9 0.96666667 1. ]
from sklearn.datasets import load_digits
digits=load_digits()
y=digits.target==9
X_train,X_test,y_train,y_test=train_test_split(digits.data,y,random_state=0)
from sklearn.dummy import DummyClassifier
dummy_majority=DummyClassifier(strategy='most_frequent').fit(X_train,y_train)
pred_most_frequent=dummy_majority.predict(X_test)
print('Unique predicted labels:{}'.format(np.unique(pred_most_frequent)))
print('Test score{:.2f}'.format(dummy_majority.score(X_test,y_test)))
Unique predicted labels:[False]
Test score0.90
from sklearn.tree import DecisionTreeClassifier
tree=DecisionTreeClassifier(max_depth=2).fit(X_train,y_train)
pred_tree=tree.predict(X_test)
print('Test score:{:.2f}'.format(tree.score(X_test,y_test)))
Test score:0.92
from sklearn.linear_model import LogisticRegression
dummy=DummyClassifier().fit(X_train,y_train)
pred_dummy=dummy.predict(X_test)
print('Dummy score{:.2f}'.format(dummy.score(X_test,y_test)))
logreg=LogisticRegression(C=0.1).fit(X_train,y_train)
pred_logreg=logreg.predict(X_test)
print('logreg score{:.2f}'.format(logreg.score(X_test,y_test)))
Dummy score0.90
logreg score0.98
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
from sklearn.metrics import confusion_matrix
confusion=confusion_matrix(y_test,pred_logreg)
print('Confusion matrix:\n{}'.format(confusion))
Confusion matrix:
[[402 1]
[ 6 41]]
mglearn.plots.plot_confusion_matrix_illustration()
mglearn.plots.plot_binary_confusion_matrix()
print('\nMost frequent class:')
print(confusion_matrix(y_test,pred_most_frequent))
print('\nDummy model:')
print(confusion_matrix(y_test,pred_dummy))
print('\nDecision tree:')
print(confusion_matrix(y_test,pred_tree))
print('\nLogisticRegression regression')
print(confusion_matrix(y_test,pred_logreg))
Most frequent class:
[[403 0]
[ 47 0]]
Dummy model:
[[403 0]
[ 47 0]]
Decision tree:
[[390 13]
[ 24 23]]
LogisticRegression regression
[[402 1]
[ 6 41]]
from sklearn.metrics import f1_score
print('f1 score most frequent:{:.2f}'.format(f1_score(y_test,pred_most_frequent)))
print('f1 score dummy{:.2f}'.format(f1_score(y_test,pred_dummy)))
print('f1 score tree{:.2f}'.format(f1_score(y_test,pred_tree)))
print('f1 score logreg{:.2f}'.format(f1_score(y_test,pred_logreg)))
f1 score most frequent:0.00
f1 score dummy0.00
f1 score tree0.55
f1 score logreg0.92
from sklearn.metrics import classification_report
print(classification_report(y_test,pred_most_frequent,target_names=['not nine','nine']))
precision recall f1-score support
not nine 0.90 1.00 0.94 403
nine 0.00 0.00 0.00 47
accuracy 0.90 450
macro avg 0.45 0.50 0.47 450
weighted avg 0.80 0.90 0.85 450
C:\Users\reion\anaconda3\lib\site-packages\sklearn\metrics\_classification.py:1248: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
_warn_prf(average, modifier, msg_start, len(result))
C:\Users\reion\anaconda3\lib\site-packages\sklearn\metrics\_classification.py:1248: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
_warn_prf(average, modifier, msg_start, len(result))
C:\Users\reion\anaconda3\lib\site-packages\sklearn\metrics\_classification.py:1248: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
_warn_prf(average, modifier, msg_start, len(result))
print(classification_report(y_test,pred_dummy,target_names=['not nine','nine']))
precision recall f1-score support
not nine 0.90 1.00 0.94 403
nine 0.00 0.00 0.00 47
accuracy 0.90 450
macro avg 0.45 0.50 0.47 450
weighted avg 0.80 0.90 0.85 450
C:\Users\reion\anaconda3\lib\site-packages\sklearn\metrics\_classification.py:1248: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
_warn_prf(average, modifier, msg_start, len(result))
C:\Users\reion\anaconda3\lib\site-packages\sklearn\metrics\_classification.py:1248: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
_warn_prf(average, modifier, msg_start, len(result))
C:\Users\reion\anaconda3\lib\site-packages\sklearn\metrics\_classification.py:1248: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
_warn_prf(average, modifier, msg_start, len(result))
print(classification_report(y_test,pred_logreg,target_names=['not nine','nine']))
precision recall f1-score support
not nine 0.99 1.00 0.99 403
nine 0.98 0.87 0.92 47
accuracy 0.98 450
macro avg 0.98 0.93 0.96 450
weighted avg 0.98 0.98 0.98 450
from mglearn.datasets import make_blobs
from sklearn.svm import SVC
X,y=make_blobs(n_samples=(400,50),centers=2,cluster_std=[7.0,2],random_state=42)
X_train,X_test,y_train,y_test=train_test_split(X,y,random_state=0)
svc=SVC(gamma=.05).fit(X_train,y_train)
print(X.shape)
(450, 2)
C:\Users\reion\anaconda3\lib\site-packages\sklearn\utils\deprecation.py:86: FutureWarning: Function make_blobs is deprecated; Please import make_blobs directly from scikit-learn
warnings.warn(msg, category=FutureWarning)
mglearn.plots.plot_decision_threshold()
from sklearn.metrics import classification_report
print(classification_report(y_test,svc.predict(X_test)))
precision recall f1-score support
0 0.99 0.93 0.96 107
1 0.42 0.83 0.56 6
accuracy 0.93 113
macro avg 0.70 0.88 0.76 113
weighted avg 0.96 0.93 0.94 113
y_pred_low_threshold=svc.decision_function(X_test)>-.8
print(classification_report(y_test,y_pred_low_threshold))
precision recall f1-score support
0 1.00 0.89 0.94 107
1 0.33 1.00 0.50 6
accuracy 0.89 113
macro avg 0.67 0.94 0.72 113
weighted avg 0.96 0.89 0.92 113
from sklearn.metrics import precision_recall_curve,f1_score
precision,recall,thresholds=precision_recall_curve(y_test,svc.decision_function(X_test))
X,y=make_blobs(n_samples=(4000,500),centers=2,cluster_std=[7.0,2],random_state=22)
X_train,X_test,y_train,y_test=train_test_split(X,y,random_state=0)
svc=SVC(gamma=.05).fit(X_train,y_train)
precision,recall,theresholds=precision_recall_curve(y_test,svc.decision_function(X_test))
close_zero=np.argmin(np.abs(thresholds))
plt.plot(precision[close_zero],recall[close_zero],'o',markersize=10,label='threshold zero',fillstyle='none',c='k',mew=2)
plt.plot(precision,recall,label='precision recall curve')
plt.xlabel('Precision')
plt.ylabel('Recall')
C:\Users\reion\anaconda3\lib\site-packages\sklearn\utils\deprecation.py:86: FutureWarning: Function make_blobs is deprecated; Please import make_blobs directly from scikit-learn
warnings.warn(msg, category=FutureWarning)
Text(0, 0.5, 'Recall')
from sklearn.ensemble import RandomForestClassifier
rf=RandomForestClassifier(n_estimators=100,random_state=0,max_features=2)
rf.fit(X_train,y_train)
precision_rf,recall_rf,thresholds_rf=precision_recall_curve(y_test,rf.predict_proba(X_test)[:,1])
plt.plot(precision,recall,label='svc')
plt.plot(precision[close_zero],recall[close_zero],'o',markersize=10,label='thresholds zero svc',fillstyle='none',c='k',mew=2)
plt.plot(precision_rf,recall_rf,label='rf')
close_default_rf=np.argmin(np.abs(thresholds_rf-0.5))
plt.plot(precision_rf[close_default_rf],recall_rf[close_default_rf],'^',c='k',markersize=10,label='threshold 0.5 rf',fillstyle='none',mew=2)
plt.xlabel('Precision')
plt.ylabel('Recall')
plt.legend(loc='best')
<matplotlib.legend.Legend at 0x2ea95b7f940>
print('f1 score of random forest:{:.3f}'.format(f1_score(y_test,rf.predict(X_test))))
print('f1 score of svc:{:.3f}'.format(f1_score(y_test,svc.predict(X_test))))
f1 score of random forest:0.610
f1 score of svc:0.656
from sklearn.metrics import average_precision_score
ap_rf=average_precision_score(y_test,rf.predict_proba(X_test)[:,1])
ap_svc=average_precision_score(y_test,svc.decision_function(X_test))
print('Average precision of random forest:{:.3f}'.format(ap_rf))
print('Average precision of svc:{:.3f}'.format(ap_svc))
Average precision of random forest:0.660
Average precision of svc:0.666
from sklearn.metrics import roc_curve
fpr,tpr,thresholds=roc_curve(y_test,svc.decision_function(X_test))
plt.plot(fpr,tpr,label='ROC Curve')
plt.xlabel('FPR')
plt.ylabel('TPR(recall)')
close_zero=np.argmin(np.abs(thresholds))
plt.plot(fpr[close_zero],tpr[close_zero],'o',markersize=10,label='threshold zero',fillstyle='none',c='k',mew=2)
plt.legend()
<matplotlib.legend.Legend at 0x2ea838e29d0>
from sklearn.metrics import roc_curve
fpr_rf,tpr_rf,thresholds_rf=roc_curve(y_test,rf.predict_proba(X_test)[:,1])
plt.plot(fpr,tpr,label='ROC Curve SVC')
plt.plot(fpr_rf,tpr_rf,label='ROC Curve RF')
plt.xlabel('FPR')
plt.ylabel('TPR(RECALL)')
plt.plot(fpr[close_zero],tpr[close_zero],'o',markersize=10,label='threshold zero',fillstyle='none',c='k',mew=2)
close_default_rf=np.argmin(np.abs(thresholds_rf-0.5))
plt.plot(fpr_rf[close_default_rf],tpr_rf[close_default_rf],'^',markersize=10,label='threshold 0.5 RF',fillstyle='none',c='k',mew=2)
[<matplotlib.lines.Line2D at 0x2ea91679ca0>]
from sklearn.metrics import roc_auc_score
rf_auc=roc_auc_score(y_test,rf.predict_proba(X_test)[:,1])
svc_auc=roc_auc_score(y_test,svc.decision_function(X_test))
print('AUC for Random Forest:{:.3f}'.format(rf_auc))
print('AUC for SVC :{:.3f}'.format(svc_auc))
AUC for Random Forest:0.937
AUC for SVC :0.916
from sklearn.datasets import load_digits
from sklearn.model_selection import train_test_split
from sklearn.svm import SVC
from sklearn.metrics import roc_auc_score,roc_curve
digits=load_digits()
y=digits.target==9
X_train,X_test,y_train,y_test=train_test_split(digits.data,y,random_state=0)
plt.figure()
for gamma in [1,0.05,0.01]:
svc=SVC(gamma=gamma).fit(X_train,y_train)
accuracy=svc.score(X_test,y_test)
auc=roc_auc_score(y_test,svc.decision_function(X_test))
fpr,tpr,_=roc_curve(y_test,svc.decision_function(X_test))
print('gamma={:.2f} accuracy={:.2f} AUC={:.2f}'.format(gamma,accuracy,auc))
plt.plot(fpr,tpr,label='gamma={:.3f}'.format(gamma))
plt.xlabel('FPR')
plt.ylabel('TPR')
plt.xlim(-0.01,1)
plt.ylim(0,1.02)
plt.legend(loc='best')
gamma=1.00 accuracy=0.90 AUC=0.50
gamma=0.05 accuracy=0.90 AUC=1.00
gamma=0.01 accuracy=0.90 AUC=1.00
<matplotlib.legend.Legend at 0x2ea916a4820>
from sklearn.metrics import accuracy_score
from sklearn.metrics import confusion_matrix
from sklearn.linear_model import LogisticRegression
X_train,X_test,y_train,y_test=train_test_split(digits.data,digits.target,random_state=0)
lr=LogisticRegression().fit(X_train,y_train)
pred=lr.predict(X_test)
print('Accuracy :{:.3f}'.format(accuracy_score(y_test,pred)))
print('Confusion matrix:\n{}'.format(confusion_matrix(y_test,pred)))
Accuracy :0.951
Confusion matrix:
[[37 0 0 0 0 0 0 0 0 0]
[ 0 40 0 0 0 0 0 0 2 1]
[ 0 1 40 3 0 0 0 0 0 0]
[ 0 0 0 43 0 0 0 0 1 1]
[ 0 0 0 0 37 0 0 1 0 0]
[ 0 0 0 0 0 46 0 0 0 2]
[ 0 1 0 0 0 0 51 0 0 0]
[ 0 0 0 1 1 0 0 46 0 0]
[ 0 3 1 0 0 0 0 0 43 1]
[ 0 0 0 0 0 1 0 0 1 45]]
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
score_image=mglearn.tools.heatmap(
confusion_matrix(y_test,pred),xlabel='Predicted label',ylabel='True label',xticklabels=digits.target_names,
yticklabels=digits.target_names,cmap=plt.cm.gray_r,fmt='%d')
plt.title('Confusion matrix')
plt.gca().invert_yaxis()
print(classification_report(y_test,pred))
precision recall f1-score support
0 1.00 1.00 1.00 37
1 0.89 0.93 0.91 43
2 0.98 0.91 0.94 44
3 0.91 0.96 0.93 45
4 0.97 0.97 0.97 38
5 0.98 0.96 0.97 48
6 1.00 0.98 0.99 52
7 0.98 0.96 0.97 48
8 0.91 0.90 0.91 48
9 0.90 0.96 0.93 47
accuracy 0.95 450
macro avg 0.95 0.95 0.95 450
weighted avg 0.95 0.95 0.95 450
print('Micro average f1 score :{:.3f}'.format(f1_score(y_test,pred,average='micro')))
print('Macro average f1 score:{:.3f}'.format(f1_score(y_test,pred,average='macro')))
Micro average f1 score :0.951
Macro average f1 score:0.952
from sklearn.model_selection import cross_val_score,GridSearchCV
print('Default scoring:{}'.format(cross_val_score(SVC(),digits.data,digits.target==9)))
explicit_accuracy=cross_val_score(SVC(),digits.data,digits.target==9,scoring='accuracy')
print('Explicit accuracy scoring:{}'.format(explicit_accuracy))
roc_auc=cross_val_score(SVC(),digits.data,digits.target==9,scoring='roc_auc')
print('AUC scoring:{}'.format(roc_auc))
Default scoring:[0.975 0.99166667 1. 0.99442897 0.98050139]
Explicit accuracy scoring:[0.975 0.99166667 1. 0.99442897 0.98050139]
AUC scoring:[0.99717078 0.99854252 1. 0.999828 0.98400413]
X_train,X_test,y_train,y_test=train_test_split(digits.data,digits.target==9,random_state=0)
param_grid={'gamma':[0.0001,0.001,0.1,1,10]}
grid=GridSearchCV(SVC(),param_grid=param_grid)
grid.fit(X_train,y_train)
print('Grid-Seach with accuracy')
print('Best parameters:',grid.best_params_)
print('Best cross_val_validation score(accuracy)):{:.3f}'.format(grid.best_score_))
print('Test set AUC:{:.3f}'.format(roc_auc_score(y_test,grid.decision_function(X_test))))
print('Test set accuracy :{:.3f}'.format(grid.score(X_test,y_test)))
Grid-Seach with accuracy
Best parameters: {'gamma': 0.001}
Best cross_val_validation score(accuracy)):0.996
Test set AUC:1.000
Test set accuracy :0.991
grid=GridSearchCV(SVC(),param_grid=param_grid,scoring='roc_auc')
grid.fit(X_train,y_train)
print('\nGrid-Search with AUC')
print('Best parameters:',grid.best_params_)
print('Best cross_val_validation score(accuracy)):{:.3f}'.format(grid.best_score_))
print('Test set AUC:{:.3f}'.format(roc_auc_score(y_test,grid.decision_function(X_test))))
print('Test set accuracy :{:.3f}'.format(grid.score(X_test,y_test)))
Grid-Search with AUC
Best parameters: {'gamma': 0.001}
Best cross_val_validation score(accuracy)):0.999
Test set AUC:1.000
Test set accuracy :1.000
# from sklearn.metrics.scorer import SCORERS
# print('Available scores:\n{}'.format(sorted(SCORRES.keys())))
from sklearn.svm import SVC
from sklearn.datasets import load_breast_cancer
from sklearn.preprocessing import MinMaxScaler
from sklearn.model_selection import train_test_split
cancer=load_breast_cancer()
X_train,X_test,y_train,y_test=train_test_split(cancer.data,cancer.target,random_state=0)
scaler=MinMaxScaler().fit(X_train)
X_train_scaled=scaler.transform(X_train)
X_test_scaled=scaler.transform(X_test)
svm=SVC()
svm.fit(X_train_scaled,y_train)
print('Test score:{:.3f}'.format(svm.score(X_test_scaled,y_test)))
Test score:0.972
from sklearn.model_selection import GridSearchCV
param_grid={'C':[0.001,0.01,0.1,1,10,100],
'gamma':[0.001,0.01,0.1,1,101,100]}
grid=GridSearchCV(SVC(),param_grid=param_grid,cv=5)
grid.fit(X_train_scaled,y_train)
print('Best cross_val_validation score(accuracy)):{:.3f}'.format(grid.best_score_))
print('Best set accuracy :{:.3f}'.format(grid.score(X_test_scaled,y_test)))
print('Best parameters:',grid.best_params_)
Best cross_val_validation score(accuracy)):0.981
Best set accuracy :0.972
Best parameters: {'C': 1, 'gamma': 1}
mglearn.plots.plot_improper_processing()
from sklearn.pipeline import Pipeline
pipe=Pipeline([('scaler',MinMaxScaler()),('svm',SVC())])
pipe.fit(X_train,y_train)
Pipeline(steps=[('scaler', MinMaxScaler()), ('svm', SVC())])
print('Test score:{:.2f}'.format(pipe.score(X_test,y_test)))
Test score:0.97
param_grid={'svm__C':[0.001,0.01,0.1,1,10,100],'svm__gamma':[0.001,0.01,0.1,1,10,100]}
grid=GridSearchCV(pipe,param_grid=param_grid,cv=5)
grid.fit(X_train,y_train)
print('Best cross_validation accuracy:{:.2f}'.format(grid.best_score_))
print('Test set score:{:.2f}'.format(grid.score(X_test,y_test)))
print('Best parameters:{}'.format(grid.best_params_))
Best cross_validation accuracy:0.98
Test set score:0.97
Best parameters:{'svm__C': 1, 'svm__gamma': 1}
mglearn.plots.plot_proper_processing()
def fit(self,X,y):
X_transformed=X
for name,estimator in self.steps[:-1]:
X_transformed=estimator.fit_transform(X_transformed,y)
self.steps[:-1][1].fit(X_tranformed,y)
return self
def predict(self,X):
X_transformede=X
for step in self.steps[:-1]:
X_transformed=step[1].transform(X_transformed)
return self.steps[-1][1].predict(X_transformed)
from sklearn.pipeline import make_pipeline
pipe_log=Pipeline([('scaler',MinMaxScaler()),('svm',SVC(C=100))])
pipe_short=make_pipeline(MinMaxScaler(),SVC(C=100))
print('Pipeline steps:\n{}'.format(pipe_short.steps))
Pipeline steps:
[('minmaxscaler', MinMaxScaler()), ('svc', SVC(C=100))]
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA
pipe=make_pipeline(StandardScaler(),PCA(n_components=2),StandardScaler())
print('Pipeline steps:\n{}'.format(pipe.steps))
Pipeline steps:
[('standardscaler-1', StandardScaler()), ('pca', PCA(n_components=2)), ('standardscaler-2', StandardScaler())]
pipe.fit(cancer.data)
components=pipe.named_steps['pca'].components_
print('components.shape{}'.format(components.shape))
components.shape(2, 30)
from sklearn.linear_model import LogisticRegression
pipe=make_pipeline(StandardScaler(),LogisticRegression())
param_grid={'logisticregression__C':[0.01,0.1,1,10,100]}
X_train,X_test,y_train,y_test=train_test_split(cancer.data,cancer.target,random_state=4)
grid=GridSearchCV(estimator=pipe,param_grid=param_grid,cv=5)
grid.fit(X_train,y_train)
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
GridSearchCV(cv=5,
estimator=Pipeline(steps=[('standardscaler', StandardScaler()),
('logisticregression',
LogisticRegression())]),
param_grid={'logisticregression__C': [0.01, 0.1, 1, 10, 100]})
print('Best estimator:\n{}'.format(grid.best_estimator_))
Best estimator:
Pipeline(steps=[('standardscaler', StandardScaler()),
('logisticregression', LogisticRegression(C=1))])
print('Logistic regression step:\n{}'.format(grid.best_estimator_.named_steps['logisticregression']))
Logistic regression step:
LogisticRegression(C=1)
print('Logistic regression cofficients:\n{}'.format(grid.best_estimator_.named_steps['logisticregression'].coef_))
Logistic regression cofficients:
[[-0.43570655 -0.34266946 -0.40809443 -0.5344574 -0.14971847 0.61034122
-0.72634347 -0.78538827 0.03886087 0.27497198 -1.29780109 0.04926005
-0.67336941 -0.93447426 -0.13939555 0.45032641 -0.13009864 -0.10144273
0.43432027 0.71596578 -1.09068862 -1.09463976 -0.85183755 -1.06406198
-0.74316099 0.07252425 -0.82323903 -0.65321239 -0.64379499 -0.42026013]]
from sklearn.datasets import load_boston
from sklearn.linear_model import Ridge
boston=load_boston()
X_train,X_test,y_train,y_test=train_test_split(boston.data,boston.target,random_state=0)
from sklearn.preprocessing import PolynomialFeatures
pipe=make_pipeline(StandardScaler(),PolynomialFeatures(),Ridge())
param_grid={'polynomialfeatures__degree':[1,2,3],'ridge__alpha':[0.001,0.01,0.1,1,10,100]}
grid=GridSearchCV(estimator=pipe,param_grid=param_grid,cv=5,n_jobs=-1)
grid.fit(X_train,y_train)
GridSearchCV(cv=5,
estimator=Pipeline(steps=[('standardscaler', StandardScaler()),
('polynomialfeatures',
PolynomialFeatures()),
('ridge', Ridge())]),
n_jobs=-1,
param_grid={'polynomialfeatures__degree': [1, 2, 3],
'ridge__alpha': [0.001, 0.01, 0.1, 1, 10, 100]})
plt.matshow(grid.cv_results_['mean_test_score'].reshape(3,-1),vmin=0,cmap='viridis')
plt.xlabel('ridge__alpha')
plt.ylabel('polynomialfeatures__degree')
plt.xticks(range(len(param_grid['ridge__alpha'])),param_grid['ridge__alpha'])
plt.yticks(range(len(param_grid['polynomialfeatures__degree'])),param_grid['polynomialfeatures__degree'])
plt.colorbar()
<matplotlib.colorbar.Colorbar at 0x2ea92bbd7f0>
print('Best parameters:{}'.format(grid.best_params_))
Best parameters:{'polynomialfeatures__degree': 2, 'ridge__alpha': 10}
print('Test-set score:{:.2f}'.format(grid.score(X_test,y_test)))
Test-set score:0.77
param_grid={'ridge__alpha':[0.001,0.01,0.1,1,10,100]}
pipe=make_pipeline(StandardScaler(),Ridge())
grid=GridSearchCV(pipe,param_grid,cv=5)
grid.fit(X_train,y_train)
print('Score without poly features:{:.2f}'.format(grid.score(X_test,y_test)))
Score without poly features:0.63
pipe=Pipeline([('preprocessing',StandardScaler()),('classifier',SVC())])
from sklearn.ensemble import RandomForestClassifier
param_grid=[{'classifier':[SVC()],'preprocessing':[StandardScaler(),None],
'classifier__gamma':[0.001,0.01,0.1,1,10,100],
'classifier__C':[0.001,0.01,0.1,1,10,100]},
{'classifier':[RandomForestClassifier(n_estimators=100)],
'preprocessing':[None],'classifier__max_features':[1,2,3]}]
X_train,X_test,y_train,y_test=train_test_split(cancer.data,cancer.target,random_state=0)
grid=GridSearchCV(pipe,param_grid,cv=5)
grid.fit(X_train,y_train)
print('Best params:\n{}\n'.format(grid.best_params_))
print('Best cross_validation score:{:.2f}'.format(grid.best_score_))
print('Test set score:{:.2f}'.format(grid.score(X_test,y_test)))
Best params:
{'classifier': SVC(C=10, gamma=0.01), 'classifier__C': 10, 'classifier__gamma': 0.01, 'preprocessing': StandardScaler()}
Best cross_validation score:0.99
Test set score:0.98
%%time
from sklearn.datasets import load_files
reviews_train=load_files(r'./aclImdb/train/')
text_train,y_train=reviews_train.data[:25000],reviews_train.target[reviews_train.target!=2]
print('type of text_trian:{}'.format(type(text_train)))
print('length of text text_train:{}'.format(len(text_train)))
print('text_train[1]:\n{}'.format(text_train[1]))
type of text_trian:<class 'list'>
length of text text_train:25000
text_train[1]:
b"Amount of disappointment I am getting these days seeing movies like Partner, Jhoom Barabar and now, Heyy Babyy is gonna end my habit of seeing first day shows.<br /><br />The movie is an utter disappointment because it had the potential to become a laugh riot only if the d\xc3\xa9butant director, Sajid Khan hadn't tried too many things. Only saving grace in the movie were the last thirty minutes, which were seriously funny elsewhere the movie fails miserably. First half was desperately been tried to look funny but wasn't. Next 45 minutes were emotional and looked totally artificial and illogical.<br /><br />OK, when you are out for a movie like this you don't expect much logic but all the flaws tend to appear when you don't enjoy the movie and thats the case with Heyy Babyy. Acting is good but thats not enough to keep one interested.<br /><br />For the positives, you can take hot actresses, last 30 minutes, some comic scenes, good acting by the lead cast and the baby. Only problem is that these things do not come together properly to make a good movie.<br /><br />Anyways, I read somewhere that It isn't a copy of Three men and a baby but I think it would have been better if it was."
Wall time: 19.4 s
text_train=[doc.replace(b"<br />",b" ")for doc in text_train]
print('sample per class(training):{}'.format(np.bincount(y_train)))
sample per class(training):[12500 12500]
reviews_test=load_files(r'./aclImdb/test/')
text_test,y_test=reviews_test.data,reviews_test.target
print('Number of documents in test data:{}'.format(len(text_test)))
print('Samples per class (test):{}'.format(np.bincount(y_test)))
text_test=[doc.replace(b"<br />",b" ")for doc in text_test]
Number of documents in test data:25000
Samples per class (test):[12500 12500]
bards_words=['The fool doth think he is wise','but the wise man knows himself to be a fool']
from sklearn.feature_extraction.text import CountVectorizer
vect=CountVectorizer()
vect.fit(bards_words)
CountVectorizer()
print('Vocabulary size:{}'.format(len(vect.vocabulary_)))
print('Vocabulary content:\n{}'.format(vect.vocabulary_))
Vocabulary size:13
Vocabulary content:
{'the': 9, 'fool': 3, 'doth': 2, 'think': 10, 'he': 4, 'is': 6, 'wise': 12, 'but': 1, 'man': 8, 'knows': 7, 'himself': 5, 'to': 11, 'be': 0}
bag_of_words=vect.transform(bards_words)
print('bag_of_words:{}'.format(repr(bag_of_words)))
print(bag_of_words)
bag_of_words:<2x13 sparse matrix of type '<class 'numpy.int64'>'
with 16 stored elements in Compressed Sparse Row format>
(0, 2) 1
(0, 3) 1
(0, 4) 1
(0, 6) 1
(0, 9) 1
(0, 10) 1
(0, 12) 1
(1, 0) 1
(1, 1) 1
(1, 3) 1
(1, 5) 1
(1, 7) 1
(1, 8) 1
(1, 9) 1
(1, 11) 1
(1, 12) 1
print('Dense representation of bag_of_words:\n{}'.format(bag_of_words.toarray()))
Dense representation of bag_of_words:
[[0 0 1 1 1 0 1 0 0 1 1 0 1]
[1 1 0 1 0 1 0 1 1 1 0 1 1]]
vect=CountVectorizer().fit(text_test)
X_test=vect.transform(text_test)
print('X_test:\n{}'.format(repr(text_test)))
IOPub data rate exceeded.
The notebook server will temporarily stop sending output
to the client in order to avoid crashing it.
To change this limit, set the config variable
`--NotebookApp.iopub_data_rate_limit`.
Current values:
NotebookApp.iopub_data_rate_limit=1000000.0 (bytes/sec)
NotebookApp.rate_limit_window=3.0 (secs)
feature_names=vect.get_feature_names()
print('Number of features :{}'.format(len(feature_names)))
print('First 20 features:\n{}'.format(feature_names[:20]))
print('Features 20010 to 20030:\n{}'.format(feature_names[20010:20030]))
print('Every 2000th feature:\n{}'.format(feature_names[::2000]))
Number of features :73822
First 20 features:
['00', '000', '00000000000', '00000001', '000dm', '001', '0069', '007', '0079', '007s', '0083', '009', '00am', '00o', '00pm', '00s', '00schneider', '01', '0126', '0148']
Features 20010 to 20030:
['drought', 'drove', 'drover', 'droves', 'drowing', 'drown', 'drowned', 'drowning', 'drownings', 'drowns', 'drowsy', 'dru', 'drubbed', 'drubbing', 'drudge', 'drudgery', 'drudges', 'drudging', 'druedain', 'drug']
Every 2000th feature:
['00', 'afflicted', 'ardal', 'basket', 'boiled', 'calculating', 'chitty', 'congealed', 'cushioned', 'devoted', 'droplet', 'envogue', 'felled', 'frontline', 'gorman', 'header', 'hypnotism', 'intruments', 'kerchiefs', 'leos', 'malerie', 'microwaves', 'mutually', 'oedipus', 'pasts', 'polaroids', 'pushtun', 'remnar', 'runner', 'sentencing', 'slips', 'starkly', 'swiches', 'tings', 'ulloa', 'venice', 'widen']
from sklearn.model_selection import cross_val_score
from sklearn.linear_model import LogisticRegression
scores=cross_val_score(LogisticRegression(),X_test,y_test,cv=5)
print('Mean cross_validation accuracy:{:.2f}'.format(np.mean(scores)))
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
Mean cross_validation accuracy:0.89
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
%%time
from sklearn.model_selection import GridSearchCV
param_grid={'C':[0.001,0.01,0.1,1,10]}
grid=GridSearchCV(LogisticRegression(),param_grid,cv=5,n_jobs=-1)
grid.fit(X_test,y_test)
print('Best cross_valiadtion score:{:.2f}'.format(grid.best_score_))
print('Best parameters:',grid.best_params_)
Best cross_valiadtion score:0.89
Best parameters: {'C': 0.1}
Wall time: 22.9 s
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
vect=CountVectorizer(min_df=5).fit(text_test)
X_test=vect.transform(text_test)
print('X_test with min_df:{}'.format(repr(X_test)))
X_test with min_df:<25000x26749 sparse matrix of type '<class 'numpy.int64'>'
with 3289577 stored elements in Compressed Sparse Row format>
feature_names=vect.get_feature_names()
print('First 50 features:\n{}'.format(feature_names[:50]))
print('Feature 20010 to 20030:\n{}'.format(feature_names[20010:20030]))
print('Every 700th feature:\n{}'.format(feature_names[::700]))
First 50 features:
['00', '000', '007', '01', '02', '03', '04', '05', '06', '07', '08', '09', '10', '100', '1000', '100th', '101', '102', '105', '107', '108', '109', '10th', '11', '110', '111', '116', '117', '11th', '12', '120', '125', '12th', '13', '130', '13th', '14', '140', '14th', '15', '150', '1500', '15th', '16', '16mm', '16s', '16th', '17', '170', '1700']
Feature 20010 to 20030:
['riddler', 'riddles', 'ride', 'rider', 'riders', 'rides', 'ridge', 'ridgemont', 'ridges', 'ridicule', 'ridiculed', 'ridicules', 'ridiculous', 'ridiculously', 'ridiculousness', 'riding', 'ridley', 'riefenstahl', 'rife', 'riff']
Every 700th feature:
['00', 'affiliates', 'arbitrary', 'baritone', 'boats', 'caddy', 'childless', 'completist', 'crazily', 'delinquents', 'distinguishable', 'egged', 'exceptionally', 'fink', 'gain', 'grimace', 'hesitate', 'immune', 'invasions', 'king', 'lips', 'marthy', 'mistaking', 'netherworld', 'othello', 'permeate', 'pratfall', 'quip', 'renant', 'rotund', 'selfless', 'skilled', 'spoon', 'succinctly', 'terminator', 'treasures', 'uns', 'warhol', 'yearning']
grid=GridSearchCV(LogisticRegression(),param_grid,cv=5)
grid.fit(X_test,y_test)
print('Best cross_validation score:{:.2f}'.format(grid.best_score_))
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
Best cross_validation score:0.89
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
from sklearn.feature_extraction.text import ENGLISH_STOP_WORDS
print('Number of stop words:{}'.format(len(ENGLISH_STOP_WORDS)))
print('Every 10th stopword:\n{}'.format(list(ENGLISH_STOP_WORDS)[::10]))
Number of stop words:318
Every 10th stopword:
['bottom', 'bill', 'indeed', 'except', 'therein', 'made', 'during', 'am', 'whoever', 'via', 'across', 'beforehand', 'after', 'on', 'otherwise', 'be', 'three', 'she', 'without', 'never', 'him', 'most', 'the', 'elsewhere', 'must', 'wherein', 'describe', 'nobody', 'two', 'whole', 'ltd', 'seems']
vect=CountVectorizer(min_df=5,stop_words='english').fit(text_test)
X_test=vect.transform(text_test)
print('X_test with stop words:\n{}'.format(repr(X_test)))
X_test with stop words:
<25000x26445 sparse matrix of type '<class 'numpy.int64'>'
with 2101629 stored elements in Compressed Sparse Row format>
grid=GridSearchCV(LogisticRegression(),param_grid,cv=5,n_jobs=-1)
grid.fit(X_test,y_test)
print('Best cross_validation score:{:.2f}'.format(grid.best_score_))
Best cross_validation score:0.89
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.pipeline import make_pipeline
pipe=make_pipeline(TfidfVectorizer(min_df=5),LogisticRegression())
param_grid={'logisticregression__C':[0.001,0.01,0.1,1,10]}
grid=GridSearchCV(pipe,param_grid,cv=5,n_jobs=-1)
grid.fit(text_test,y_test)
print('Best cross_validation score:{:.2f}'.format(grid.best_score_))
Best cross_validation score:0.90
C:\Users\reion\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
vectorizer=grid.best_estimator_.named_steps['tfidfvectorizer']
X_test=vectorizer.transform(text_train)
max_value=X_test.max(axis=0).toarray().ravel()
sorted_by_tfidf=max_value.argsort()
feature_names=np.array(vectorizer.get_feature_names())
print('Features with lowest tfidf:\n{}'.format(feature_names[sorted_by_tfidf[:20]]))
print('Features with highest tfidf :\n{}'.format(feature_names[sorted_by_tfidf[-20:]]))
Features with lowest tfidf:
['exorbitant' 'dillane' 'strangeland' 'dicamillo' 'strother' 'desecrate'
'stuey' 'dengler' 'demeter' 'stéphanois' 'subjugation' 'delair' 'dekalog'
'deepa' 'davidians' 'daulton' 'darwyn' 'darvi' 'darkhunters'
'summerville']
Features with highest tfidf :
['autism' 'botched' 'mrs' 'didn' 'godzilla' 'dev' 'lupin' 'rocky'
'amityville' 'weller' 'bye' 'bambi' 'frasier' 'pokemon' 'othello' 'yadda'
'lucy' 'ha' 'click' 'wicked']
sorted_by_idf=np.argsort(vectorizer.idf_)
print('Features with lowest idf:\n{}'.format(feature_names[sorted_by_idf[:100]]))
Features with lowest idf:
['the' 'and' 'of' 'to' 'this' 'is' 'it' 'in' 'that' 'but' 'for' 'with'
'was' 'as' 'on' 'movie' 'not' 'one' 'have' 'be' 'film' 'you' 'are' 'all'
'at' 'an' 'by' 'so' 'from' 'like' 'who' 'if' 'they' 'there' 'out' 'his'
'just' 'or' 'about' 'he' 'what' 'has' 'some' 'can' 'good' 'when' 'more'
'up' 'time' 'very' 'even' 'see' 'only' 'my' 'would' 'no' 'well' 'really'
'which' 'me' 'story' 'had' 'much' 'their' 'than' 'other' 'were' 'get'
'do' 'been' 'don' 'most' 'also' 'how' 'great' 'into' 'will' 'first'
'because' 'make' 'her' 'people' 'made' 'bad' 'way' 'could' 'them' 'we'
'any' 'after' 'then' 'too' 'watch' 'movies' 'seen' 'acting' 'think' 'she'
'characters' 'many']
mglearn.tools.visualize_coefficients(
grid.best_estimator_.named_steps['logisticregression'].coef_,feature_names,n_top_features=40)
%%time
from sklearn.model_selection import GridSearchCV
# from tune_sklearn import TuneSearchCV
pipe=make_pipeline(TfidfVectorizer(min_df=5),LogisticRegression())
param_grid={'logisticregression__C':[0.001,0.01,0.1,1,10,100],'tfidfvectorizer__ngram_range':[(1,1),(1,2),(1,3)]}
grid=GridSearchCV(pipe,param_grid=param_grid,n_jobs=-1)
grid.fit(text_test,y_test)
print('Best cross_validation score:{:.2f}'.format(grid.best_score_))
print('Best parameters:\n{}'.format(grid.best_params_))
Best cross_validation score:0.91
Best parameters:
{'logisticregression__C': 10, 'tfidfvectorizer__ngram_range': (1, 3)}
Wall time: 3min 38s
scores=grid.cv_results_['mean_test_score'].reshape(-1,3).T
heatmap=mglearn.tools.heatmap(scores,xlabel='C',ylabel='ngram_range',cmap='viridis',
fmt='%.3f',
xticklabels=param_grid['logisticregression__C'],
yticklabels=param_grid['tfidfvectorizer__ngram_range'])
plt.colorbar(heatmap)
<matplotlib.colorbar.Colorbar at 0x2ea84da4f40>
vect=grid.best_estimator_.named_steps['tfidfvectorizer']
feature_names=np.array(vect.get_feature_names())
coef=grid.best_estimator_.named_steps['logisticregression'].coef_
mglearn.tools.visualize_coefficients(coef,feature_names,n_top_features=40)
mask=np.array([len(feature.split(' '))for feature in feature_names])==3
mglearn.tools.visualize_coefficients(coef.ravel()[mask],feature_names[mask],n_top_features=40)
import spacy
import nltk
en_nlp=spacy.load('en_core_web_sm')
stemmer=nltk.stem.PorterStemmer()
def compare_normalization(doc):
doc_spacy=en_nlp(doc)
print('Lemmatization')
print([token.lemma_ for token in doc_spacy])
print('Stemming:')
print([stemmer.stem(token.norm_.lower())for token in doc_spacy])
compare_normalization(u"Our meeting today was worse than yesterday,""I'm scared of meeting the clients tomorrow.")
Lemmatization
['our', 'meeting', 'today', 'be', 'bad', 'than', 'yesterday', ',', "i'm", 'scare', 'of', 'meet', 'the', 'client', 'tomorrow', '.']
Stemming:
['our', 'meet', 'today', 'wa', 'wors', 'than', 'yesterday', ',', "i'm", 'scare', 'of', 'meet', 'the', 'client', 'tomorrow', '.']
import re
regexp=re.compile('(?u)\\b\\w\\w+\\b')
en_nlp=spacy.load('en_core_web_sm')
old_tokenizer=en_nlp.tokenizer
en_nlp.tokenizer=lambda string: old_tokenizer.tokens_from_list(regexp.findall(string))
def custom_tokenizer(document):
doc_spacy=en_nlp(document,entity=False,parse=False)
return [token.lemma_ for token in doc_spacy]
lemma_vect=CountVectorizer(tokenizer=custom_tokenizer,min_df=5)
X_test_lemma=lemma_vect.fit_transform(text_test)
print('X_test_lemma.shape{}'.format(X_test_lemma.shape))
'''.tokens_from_list报错，暂时先跳过'''
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-404-5d08729e20e8> in <module>
----> 1 X_test_lemma=lemma_vect.fit_transform(text_test)
2 print('X_test_lemma.shape{}'.format(X_test_lemma.shape))
3 '''.tokens_from_list报错，暂时先跳过'''
4
~\anaconda3\lib\site-packages\sklearn\feature_extraction\text.py in fit_transform(self, raw_documents, y)
1200 max_features = self.max_features
1201
-> 1202 vocabulary, X = self._count_vocab(raw_documents,
1203 self.fixed_vocabulary_)
1204
~\anaconda3\lib\site-packages\sklearn\feature_extraction\text.py in _count_vocab(self, raw_documents, fixed_vocab)
1112 for doc in raw_documents:
1113 feature_counter = {}
-> 1114 for feature in analyze(doc):
1115 try:
1116 feature_idx = vocabulary[feature]
~\anaconda3\lib\site-packages\sklearn\feature_extraction\text.py in _analyze(doc, analyzer, tokenizer, ngrams, preprocessor, decoder, stop_words)
104 doc = preprocessor(doc)
105 if tokenizer is not None:
--> 106 doc = tokenizer(doc)
107 if ngrams is not None:
108 if stop_words is not None:
<ipython-input-403-79450082e040> in custom_tokenizer(document)
5 en_nlp.tokenizer=lambda string: old_tokenizer.tokens_from_list(regexp.findall(string))
6 def custom_tokenizer(document):
----> 7 doc_spacy=en_nlp(document,entity=False,parse=False)
8 return [token.lemma_ for token in doc_spacy]
9 lemma_vect=CountVectorizer(tokenizer=custom_tokenizer,min_df=5)
TypeError: __call__() got an unexpected keyword argument 'entity'
vect=CountVectorizer(max_features=10000,max_df=.15)
X=vect.fit_transform(text_test)
from sklearn.decomposition import LatentDirichletAllocation
lda=LatentDirichletAllocation(n_components=10,learning_method='batch',max_iter=25,random_state=0)
document_topics=lda.fit_transform(X)
lda.components_.shape
(10, 10000)
sorting=np.argsort(lda.components_,axis=1)[:,::-1]
feature_names=np.array(vect.get_feature_names())
mglearn.tools.print_topics(topics=range(10),feature_names=feature_names,sorting=sorting,topics_per_chunk=5,
n_words=10)
topic 0 topic 1 topic 2 topic 3 topic 4
-------- -------- -------- -------- --------
us didn role war action
world nothing performance american role
family worst girl world cast
own actually cast us murder
each re played our robert
between minutes actress history plays
real going young german performance
human actors book years john
young guy plays country actor
without pretty women soldiers director
topic 5 topic 6 topic 7 topic 8 topic 9
-------- -------- -------- -------- --------
car horror show music sex
back effects funny dvd italian
gets monster comedy work violence
guy fi series version performance
old sci tv actors dr
down space episode director director
big special now original quite
town evil saw game gore
kids alien years years woman
around series watched sound shakespeare
lda100=LatentDirichletAllocation(n_components=100,learning_method='batch',max_iter=25,random_state=0)
document_topics100=lda100.fit_transform(X)
topics=np.array([7,16,24,25,28,36,37,45,51,53,54,63,89,97])
sorting=np.argsort(lda100.components_,axis=1)[:,::-1]
feature_names=np.array(vect.get_feature_names())
mglearn.tools.print_topics(topics=topics,feature_names=feature_names,sorting=sorting,topics_per_chunk=7,n_words=20)
topic 7 topic 16 topic 24 topic 25 topic 28 topic 36 topic 37
-------- -------- -------- -------- -------- -------- --------
robin noir box british game years jackson
doctor robert darkness london games wonderful michael
de spanish heart disaster play old black
murphy murder button tv jason again tale
williams young rose water played loved blues
hood racism mary mr lloyd saw videos
jackie detective conrad vegas oscar excellent samuel
tv anti gulliver old award today music
eddie crime diaz jordan hoffman now justin
part ryan kurtz local matthau beautiful ricci
showtime carmen interesting uk billy every abuse
niro police massacre hamilton academy since thriller
role picture find las graphics amazing christina
got mitchum marlow day won ago daughters
russo drama party minister kramer 10 generation
now crossfire travels crocodile ted disney south
played femme joseph tree golf perfect us
actor spain production look playing recommend vincent
robert against however cinema greatest favorite nanny
old fine based set marty always plays
topic 45 topic 51 topic 53 topic 54 topic 63 topic 89 topic 97
-------- -------- -------- -------- -------- -------- --------
death wax reality kids alien sex christmas
wife torture mark children vampire women books
human trap kevin school space men queen
own macbeth real kid aliens female am
both tourist allen parents earth woman mini
self terrorist jennifer year effects male novels
hospital rendition caine old vampires sexual stanwyck
yet terrorists virtual child fi porn barbara
now desert woody adults sci nudity morgan
us director michael young ship sexy lestat
himself cia spacey high predator naked vice
without museum mentally age planet girl damned
becomes streep cronenberg family special soft magazine
seems andreas sense adult hero girls snow
however el away show star core read
left government fiction college action lesbian fanny
our another human barney human looking portray
lives meryl makes fun evil having cook
between mannequins challenged girl our erotic completely
emotional arab dream new crew beautiful listening
death=np.argsort(document_topics100[:,45])[::-1]
for i in death[:10]:
print(b'.'.join(text_test[i].split(b'.')[:2])+b'.\n')
b'Francis Ford Coppola\'s "Apocalypse Now" is not a Vietnam War film. Do not confuse it with one.\n'
b"Dead Man Walking, absolutely brilliant, in tears by the end! You can not watch this film and not think about the issues it raises; how can you justify killing (whether it be murder or the death penalty) and to what point is forgiveness possible (not just in a spiritual way). Don't watch this film when your down! But WATCH IT!!!.\n"
b'The Hospital is a movie that was made ahead of its time. This film, produced by screenwriter Paddy Chayefsky, who gave us the Oscar-Winning film, "Network", deals with overworked staff, gross incompetence, and bureaucratic corruption at a large conglomerate hospital in Manhattan.\n'
b"What a self-indulgent mess! Duncan Roy's film is apparently autobiographical, however it's impossible to find any glimmer of emotional truth in this chaotic, badly acted and woefully amateurish fiasco. In a way, you have to admire the balls of a man who through grim determination and a very generous benefactor manages to make a film about his own rise and fall - from abused, working class lad to criminal English lord.\n"
b"I've been intending to write a review of this film for some time, but only now have I actually managed to get my thoughts down for the perusal of others. I never had the pleasure of seeing this film on the `big screen' which is a shame, as it is often visually stunning, but I have revisited it on video numerous times over the years, enjoying it immensely every time.\n"
b'Spoilers. This review has been edited due to word limit.\n'
b"Although the acting was excellent, I spent the whole movie waiting for the nasty boy who caused so much grief to so many of the characters, get his final nemesis, and instead everyone else suffered except him and he gets the job of the husband whose wife's death he causes by running away from his friends, wins the girl he gave an overdose to and tried to rape. Even his friend gives money to his father, but the butterfly effect completely fails to return to its cause.\n"
b'Chen Kaige lost his sense of tempo. I envy Europeans and Americans who can watch the film without following the dialog with their ears, because it is painful to do: slow, unnaturally heavy, and over-deliberate.\n'
b"Francis Ford Coppola's first 'personal' film, completed and released in 1969, was the last movie he made as a mostly unknown, up and coming director before The Godfather, and is in stark contrast to both that film, and the rest of his uneven career. It's ostensibly a road movie involving a disconnected young woman bored with domestic life, and pregnant with a child she isn't sure she wants, fleeing the trappings her dull marriage and hitting the open road in search of freedom.\n"
b"I don't remember too much about this movie except that there was a distinctly gratuitous destruction of luminaires (lamps). Almost every fight scene included the unnecessary and wanton destruction of useful light fixtures, even if outfitted with cheesy, '70's-style, cylindrical shades to keep with the time setting of the story.\n"
fig,ax=plt.subplots(1,2,figsize=(10,10))
topic_names=["{:>2}".format(i)+''.join(words)for i ,words in enumerate(feature_names[sorting[:,:2]])]
for col in [0,1]:
start=col*50
end=(col+1)*50
ax[col].barh(np.arange(50),np.sum(document_topics100,axis=0)[start:end])
ax[col].set_yticks(np.arange(50))
ax[col].set_yticklabels(topic_names[start:end],ha='left',va='top')
ax[col].invert_yaxis()
ax[col].set_xlim(0,2000)
yax=ax[col].get_yaxis()
yax.set_tick_params(pad=130)
plt.tight_layout()
