#導入pandas工具包,並且更名爲pd
import pandas as pd
#調用pandas工具包read_csv函數,傳入訓練文件地址參數,獲得返回數據存至變量df_train
df_train = pd.read_csv('../Datasets/Breast-Cancer/breast-cancer-train.csv')
#調用pandas工具包read_csv函數,傳入測試文件地址參數,獲得返回數據存至變量df_test
df_test = pd.read_csv('../Datasets/Breast-Cancer/breast-cancer-test.csv')
print(df_train.head(5))
print(df_test.head(5))
#選取'clump thickness'與’cell size'作爲特徵,構建測試集中的正負分類樣本
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函數隨機採樣直線的截距和係數
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條訓練樣本學習直線的係數和截距
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()
#使用所有訓練樣本學習直線的係數和截距
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()
效果圖如下: