#导入pandas工具包，并且更名为pd
import pandas as pd
#调用pandas工具包read_csv函数，传入训练文件地址参数，获得返回数据存至变量df_train
df_train = pd.read_csv('../Datasets/Breast-Cancer/breast-cancer-train.csv')
#调用pandas工具包read_csv函数，传入测试文件地址参数，获得返回数据存至变量df_test
df_test = pd.read_csv('../Datasets/Breast-Cancer/breast-cancer-test.csv')
print(df_train.head(5))
print(df_test.head(5))
#选取'clump thickness'与’cell size'作为特征，构建测试集中的正负分类样本
df_test_negative = df_test.loc[df_test['Type'] == 0][['Clump Thickness', 'Cell Size']]
df_test_positive = df_test.loc[df_test['Type'] == 1][['Clump Thickness', 'Cell Size']]
print(df_test_negative.head())
print(df_test_positive.head())
import matplotlib.pyplot as plt
plt.scatter(df_test_negative['Clump Thickness'],df_test_negative['Cell Size'],marker = 'o', s=20, c='green')
plt.scatter(df_test_positive['Clump Thickness'],df_test_positive['Cell Size'], marker = 'x', s=10, c='red')
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
intercept = np.random.random([1])
coef = np.random.random([2])
lx = np.arange(0, 12)
ly = (-intercept - lx * coef[0]) / coef[1]
plt.plot(lx, ly, c='yellow')
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()
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 samples):', lr.score(df_test[['Clump Thickness', 'Cell Size']], df_test['Type']))
intercept = lr.intercept_
coef = lr.coef_[0, :]
ly = (-intercept - lx * coef[0]) / coef[1]
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 (all training samples):', lr.score(df_test[['Clump Thickness', 'Cell Size']], df_test['Type']))
intercept = lr.intercept_
coef = lr.coef_[0, :]
ly = (-intercept - lx * coef[0]) / coef[1]
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()
效果图如下：
