In [11]:
%matplotlib inline
#良、恶性肿瘤预测样例
import pandas as pd
import matplotlib.pyplot as plt
#调用pandas工具包读取csv文件
df_train=pd.read_csv('/Users/wizardholy/Documents/pywork/datasets/Breast-Cancer/breast-cancer-train.csv')
df_test=pd.read_csv('/Users/wizardholy/Documents/pywork/datasets/Breast-Cancer/breast-cancer-test.csv')
df_test_negative=df_test.loc[df_test['Type']==0][['Clump Thickness','Cell Size']]
# print 'negative'
# print df_test_negative
df_test_positive=df_test.loc[df_test['Type']==1][['Clump Thickness','Cell Size']]
# print 'positive'
# print df_test_positive
#绘制样本分布
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(u'肿块厚度')
plt.ylabel(u'细胞尺寸')
plt.show()
In [10]:
#随机采样直线的截距和系数
import numpy as np
intercept = np.random.random([1])
coef = np.random.random([2])
lx = np.arange(0, 12)
ly = (-intercept - lx * coef[0]) / coef[1]
#绘制一条直线
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(u'肿块厚度')
plt.ylabel(u'细胞尺寸')
plt.show()
In [24]:
from sklearn.linear_model import LogisticRegression
lr = LogisticRegression()
#使用前10条数据做训练集
lr.fit(df_train[['Clump Thickness', 'Cell Size']][:10], df_train['Type'][:10])
print 'Test accuracy(10 sample)',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(u'肿块厚度')
plt.ylabel(u'细胞尺寸')
plt.show()
In [25]:
#使用所有训练样本学习直线的系数和截距
lr = LogisticRegression()
#使用前10条数据做训练集
lr.fit(df_train[['Clump Thickness', 'Cell Size']][:], df_train['Type'][:])
print 'Test accuracy(10 sample)',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(u'肿块厚度')
plt.ylabel(u'细胞尺寸')
plt.show()
In [ ]: