scikit-learn学习笔记

carto@cartoPC:~$ python
Python 2.7.12 (default, Dec  4 2017, 14:50:18) 
[GCC 5.4.0 20160609] on linux2
Type "help", "copyright", "credits" or "license" for more information.
>>> import numpy as np
>>> from sklearn import datasets
>>> from sklearn.cross_validation import train_test_split
/usr/local/lib/python2.7/dist-packages/sklearn/cross_validation.py:41: DeprecationWarning: This module was deprecated in version 0.18 in favor of the model_selection module into which all the refactored classes and functions are moved. Also note that the interface of the new CV iterators are different from that of this module. This module will be removed in 0.20.
  "This module will be removed in 0.20.", DeprecationWarning)
>>> from sklearn.neighbors import KNeighborsClassifier
>>> iris=datasets.load_iris()
>>> iris_X=iris.data
>>> iris_y=iris.target
>>> print(iris_X[:2,:])
[[ 5.1  3.5  1.4  0.2]
 [ 4.9  3.   1.4  0.2]]
>>> print(iris_y)
[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]
>>> X_train,X_test,y_train,y_test=train_test_split(iris_X,iris_y,test_size=0.3)
>>> print(y_train)
[2 1 0 0 0 2 0 0 1 1 2 2 1 1 2 2 2 0 1 0 2 2 1 1 1 1 1 0 1 1 0 2 1 0 0 2 2
 0 0 2 1 0 0 2 1 2 1 2 1 1 1 2 1 2 0 2 0 1 1 2 1 0 1 2 2 0 2 2 1 0 1 1 2 2
 1 0 1 1 2 0 0 1 0 1 0 2 0 1 1 0 2 1 2 0 2 0 2 0 2 1 0 2 0 2 2]
>>> knn=KNeighborsClassifier()
>>> knn.fit()
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
TypeError: fit() takes exactly 3 arguments (1 given)
>>> knn.fit(X_train,y_train)
KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',
           metric_params=None, n_jobs=1, n_neighbors=5, p=2,
           weights='uniform')
>>> print(knn.predict(X_test))
[1 1 2 0 1 1 1 1 2 0 0 2 0 1 0 0 0 1 2 2 2 2 0 1 2 0 1 2 2 0 1 2 0 0 1 0 0
 0 0 1 0 1 1 2 0]
>>> print(y_test)
[1 1 2 0 1 1 1 1 2 0 0 2 0 1 0 0 0 1 2 2 2 2 0 1 2 0 1 2 2 0 2 2 0 0 2 0 0
 0 0 1 0 1 1 2 0]
>>> 

2.SVC的使用

import pandas as pd
import numpy as np
from sklearn import datasets
from sklearn import svm
from sklearn.model_selection import train_test_split
def load_data():
    iris=datasets.load_iris()
    X_train,X_test,y_train,y_test=train_test_split(
    iris.data,iris.target,test_size=0.10,random_state=0)
    return X_train,X_test,y_train,y_test
 
def test_LinearSVC(X_train,X_test,y_train,y_test):
    cls=svm.LinearSVC()
    cls.fit(X_train,y_train)
    print('Coefficients:%s, intercept %s'%(cls.coef_,cls.intercept_))
    print('Score: %.2f' %cls.score(X_test,y_test))
 
if __name__=="__main__":
    X_train,X_test,y_train,y_test=load_data()
    test_LinearSVC(X_train,X_test,y_train,y_test)

调用

carto@cartoPC:~/python_ws$ python svmtest2.py
Coefficients:[[ 0.18424504  0.45123335 -0.80794237 -0.45071267]
 [-0.13381099 -0.75235247  0.57223898 -1.11494325]
 [-0.7943601  -0.95801711  1.31465593  1.8169808 ]], intercept [ 0.10956304  1.86593164 -1.72576407]
Score: 1.00