python基础综合实践

import pandas as pd
df_train=pd.read_csv('/Users/daqi/Downloads/Python机器学习及实践/Datasets/Breast-Cancer/breast-cancer-train.csv')
df_test=pd.read_csv('/Users/daqi/Downloads/Python机器学习及实践/Datasets/Breast-Cancer/breast-cancer-test.csv')

选取‘clump’与‘cell size’作为特征，构建测试集中的正负分类样本。

#良性肿瘤样本点
df_test_negative=df_test.loc[df_test['Type']==0][['Clump Thickness','Cell Size']]
#恶性肿瘤样本点
df_test_positive=df_test.loc[df_test['Type']==1][['Clump Thickness','Cell Size']]

import matplotlib.pyplot as plt
#良性肿瘤样本点，标记为红色的o
plt.scatter(df_test_negative['Clump Thickness'],df_test_negative['Cell Size'],marker='o',s=200,c='red')
#恶性肿瘤样本点，标记为黑色的x
plt.scatter(df_test_positive['Clump Thickness'],df_test_positive['Cell Size'],marker='x',s=150,c='black')

绘制图1-2

#绘制x，y轴
plt.xlabel('Clump Thickness')
plt.ylabel('Cell Size')
plt.show()

import numpy as np
#利用numpy中的random函数随机采样直线的截距和系数
#截距
intercept=np.random.random([1])
#系数
coef=np.random.random([2])
#创建等差数组
lx=np.arange(0,12)
#实际上表达式是：coef[0]*lx + coef[1]*ly + intercept = 0
ly=(-intercept-lx*coef[0])/coef[1]
#绘制一条随机直线
plt.plot(lx,ly,c='yellow')

绘制图1-3

plt.scatter(df_test_negative['Clump Thickness'],df_test_negative['Cell Size'],marker='o',s=200,c='red')
plt.scatter(df_test_positive['Clump Thickness'],df_test_positive['Cell Size'],marker='x',s=150,c='black')
plt.xlabel('Clump Thickness')
plt.ylabel('Cell Size')
plt.show()

导入sklearn中的逻辑斯蒂回归分类器

from sklearn.linear_model import LogisticRegression
lr=LogisticRegression()

使用前10条训练样本学习直线的系数和截距

lr.fit(df_train[['Clump Thickness','Cell Size']][:10],df_train['Type'][:10])
print('Testing accuracy (10 training sample):',lr.score(df_test[['Clump Thickness','Cell Size']],df_test['Type']))

Testing accuracy (10 training sample): 0.868571428571

intercept=lr.intercept_
# 原本这个分类面应该是lx*coef[0] + ly*coef[1] + intercept=0 映射到2维平面上之后，应该是：  
ly = (-intercept - lx * coef[0]) / coef[1]  

绘制图1-4

plt.plot(lx,ly,c='green')
plt.scatter(df_test_negative['Clump Thickness'],df_test_negative['Cell Size'],marker='o',s=200,c='red')
plt.scatter(df_test_positive['Clump Thickness'],df_test_positive['Cell Size'],marker='x',s=150,c='black')
plt.xlabel('Clump Thickness')
plt.ylabel('Cell Size')
plt.show()

lr=LogisticRegression()
# 使用所有训练样本学习直线的系数和截距  
lr.fit(df_train[['Clump Thickness','Cell Size']],df_train['Type'])
print('Testing accuracy (10 training sample):',lr.score(df_test[['Clump Thickness','Cell Size']],df_test['Type']))

Testing accuracy (10 training sample): 0.937142857143

intercept=lr.intercept_
coef=lr.coef_[0,:]
ly = (-intercept - lx * coef[0]) / coef[1]  

绘制图1-5

plt.plot(lx,ly,c='blue')
plt.scatter(df_test_negative['Clump Thickness'],df_test_negative['Cell Size'],marker='o',s=200,c='red')
plt.scatter(df_test_positive['Clump Thickness'],df_test_positive['Cell Size'],marker='x',s=150,c='black')
plt.xlabel('Clump Thickness')
plt.ylabel('Cell Size')
plt.show()