python LogisticRegressing 实现

最新推荐文章于 2024-09-08 10:54:22 发布

原创最新推荐文章于 2024-09-08 10:54:22 发布 · 728 阅读

0 ·

CC 4.0 BY-SA版权

机器学习--ML 专栏收录该内容

36 篇文章

订阅专栏

本文通过使用Python中的pandas和sklearn库对乳腺癌数据集进行处理，并利用逻辑回归模型进行训练和测试，展示了如何根据细胞厚度和大小来预测癌症类型。

import pandas as pd;

import numpy as np;

import matplotlib.pyplot as plt;

df_train = pd.read_csv('breast-cancer-train.csv')

df_test = pd.read_csv('breast-cancer-test.csv')

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']]

plt.figure(1)

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.title('Cancer data')

plt.xlabel('Clump Thickness')

plt.ylabel('Cell Size')

#plt.show()

intercept = np.random.random([1])

coef = np.random.random([2])

lx = np.arange(0, 12)

ly = (-intercept - lx * coef[0]) / coef[1]

plt.figure(2)

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.title('Cancer data')

plt.xlabel('Clump Thickness')

plt.ylabel('Cell Size')

#plt.show()

from sklearn.linear_model import LogisticRegression

lr = LogisticRegression()

lr.fit(df_train[['Clump Thickness', 'Cell Size']][:10], df_train['Type'][0:10])

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.figure(3)

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')

lr = LogisticRegression()

lr.fit(df_train[['Clump Thickness', 'Cell Size']], df_train['Type'])

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.figure(4)

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')

lr = LogisticRegression()

lr.fit(df_train[['Clump Thickness', 'Cell Size']], df_train['Type'])

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

plt.show()