numpy pandas matplotlib

Pandas

import pandas
data = {"Name":["张三","李四","王五"],
        "City":["北京","上海","广州"],
        "Age":["18","20","22"]}
data_frame = pandas.DataFrame(data)
display(data_frame)

import pandas
data = {"Name":["张三","李四","王五"],
        "City":["北京","上海","广州"],
        "Age":["18","20","22"]}
data_frame = pandas.DataFrame(data)
display(data_frame[data_frame.City != "北京"])

matplotlib

%matplotlib inline 
#允许Jupyter Notebook 进行内置实时绘图
#如不添加上一行代码，则需要在最后添加 plt.show() 语句
import matplotlib.pyplot as plt
import numpy as np
x = np.linspace(-20,20,40)
#生成一个从-20到20，元素个数为10的等差数列
y = x**3 + 2*x**2 + 6*x + 5
plt.plot(x,y,marker = ".")

[<matplotlib.lines.Line2D at 0x260f786f280>]

​

Numpy & K临近算法

#导入数据及生成器
from sklearn.datasets import make_blobs
#导入KNN分类器
from sklearn.neighbors import KNeighborsClassifier
#导入画图工具
import matplotlib.pyplot as plt
#导入数据集拆分工具
from sklearn.model_selection import train_test_split
#生成样本数为200,分类为2的数据集
data = make_blobs(n_samples = 200, centers = 2, random_state = 8 )
X,y = data
#将生成的数据集进行可视化
plt.scatter(X[:,0],X[:,1],c=y,cmap = plt.cm.spring, edgecolor = 'k')
plt.show()

import numpy as np
clf = KNeighborsClassifier()
clf.fit(X,y)

#下面的代码用于画图
x_min, x_max =  X[:,0].min() - 1,X[:,0].max() + 1
y_min, x_max =  X[:,1].min() - 1,X[:,1].max() + 1
xx,yy = np.meshgrid(np.arange(x_min, x_max, .02),
                    np.arange(y_min, y_max, .02))
Z = clf.predict(np.c_[xx.ravel(),yy.ravel()])
Z = Z.reshape(xx.shape)
plt.pcolormesh(xx,yy,Z,shading='auto',cmap = plt.cm.Pastel1)
plt.scatter(X[:,0],X[:,1],c=y,cmap = plt.cm.spring, edgecolor = 'k')
plt.xlim(xx.min(), xx.max())
plt.ylim(yy.min(), yy.max())
plt.title("Classifier:KNN")
plt.show()

import numpy as np
clf = KNeighborsClassifier()
clf.fit(X,y)

#下面的代码用于画图
x_min, x_max =  X[:,0].min() - 1,X[:,0].max() + 1
y_min, x_max =  X[:,1].min() - 1,X[:,1].max() + 1
xx,yy = np.meshgrid(np.arange(x_min, x_max, .02),
                    np.arange(y_min, y_max, .02))
Z = clf.predict(np.c_[xx.ravel(),yy.ravel()])
Z = Z.reshape(xx.shape)
plt.pcolormesh(xx,yy,Z,shading='auto',cmap = plt.cm.Pastel1)
plt.scatter(X[:,0],X[:,1],c=y,cmap = plt.cm.spring, edgecolor = 'k')
plt.xlim(xx.min(), xx.max())
plt.ylim(yy.min(), yy.max())
plt.title("Classifier:KNN")
plt.scatter(6.75,4.82, marker= "*",c='red',s=200)
plt.show()

import numpy as np
clf = KNeighborsClassifier()
clf.fit(X,y)

#下面的代码用于画图
x_min, x_max =  X[:,0].min() - 1,X[:,0].max() + 1
y_min, x_max =  X[:,1].min() - 1,X[:,1].max() + 1
xx,yy = np.meshgrid(np.arange(x_min, x_max, .02),
                    np.arange(y_min, y_max, .02))
Z = clf.predict(np.c_[xx.ravel(),yy.ravel()])
Z = Z.reshape(xx.shape)
plt.pcolormesh(xx,yy,Z,shading='auto',cmap = plt.cm.Pastel1)
plt.scatter(X[:,0],X[:,1],c=y,cmap = plt.cm.spring, edgecolor = 'k')
plt.xlim(xx.min(), xx.max())
plt.ylim(yy.min(), yy.max())
plt.title("Classifier:KNN")
plt.scatter(6.75,4.82, marker= "*",c='red',s=200)
plt.show()


print('\n\n')
print("新数据点的分类是:",clf.predict([[6.75,4.82]]))

​
​
​
​ 新数据点的分类是: [1]

#导入数据及生成器
from sklearn.datasets import make_blobs
#导入KNN分类器
from sklearn.neighbors import KNeighborsClassifier
#导入画图工具
import matplotlib.pyplot as plt
#导入数据集拆分工具
from sklearn.model_selection import train_test_split
#生成样本数为200,分类为2的数据集
data2 = make_blobs(n_samples = 200, centers = 5, random_state = 10086 )
X2,y2 = data2
#将生成的数据集进行可视化
plt.scatter(X2[:,0],X2[:,1],c=y2,cmap = plt.cm.spring, edgecolor = 'k')
plt.show()

#导入数据及生成器
from sklearn.datasets import make_blobs
#导入KNN分类器
from sklearn.neighbors import KNeighborsClassifier
#导入画图工具
import matplotlib.pyplot as plt
#导入数据集拆分工具
from sklearn.model_selection import train_test_split
#生成样本数为200,分类为2的数据集
data2 = make_blobs(n_samples = 200, centers = 5, random_state = 8)
X2,y2 = data2

import numpy as np
clf = KNeighborsClassifier()
clf.fit(X2,y2)

#下面的代码用于画图
x_min, x_max =  X2[:,0].min() - 1,X2[:,0].max() + 1
y_min, x_max =  X2[:,1].min() - 1,X2[:,1].max() + 1
xx,yy = np.meshgrid(np.arange(x_min, x_max, .02),
                    np.arange(y_min, y_max, .02))
Z = clf.predict(np.c_[xx.ravel(),yy.ravel()])
Z = Z.reshape(xx.shape)
plt.pcolormesh(xx,yy,Z,shading='auto',cmap = plt.cm.Pastel1)
plt.scatter(X2[:,0],X2[:,1],c=y2,cmap = plt.cm.spring, edgecolor = 'k')
plt.xlim(xx.min(), xx.max())
plt.ylim(yy.min(), yy.max())
plt.title("Classifier:KNN")
plt.show()

print('\n\n')
print("模型正确率:{:.2f}".format(clf.score(X2,y2)))

​
​
模型正确率:0.96