逻辑斯蒂回归LogisticRegression 案例01：良/恶性乳腺癌肿瘤诊断分类（逻辑回归算法模型）

#逻辑斯蒂回归LogisticRegression 案例01：良/恶性乳腺癌肿瘤诊断分类（逻辑回归算法模型）

from sklearn.metrics import classification_report
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

plt.rcParams['font.sans-serif']=['SimHei']
plt.rcParams['axes.unicode_minus']=False

column_names = ['Sample code number', 'Clump Thickness', 'Uniformity of Cell Size', 'Uniformity of Cell Shape',
                'Marginal Adhesion', 'Single Epithelial Cell Size', 'Bare Nuclei', 'Bland Chromatin', 'Normal Nucleoli',
                'Mitoses', 'Class']

breast_cancer = pd.read_csv('breast-cancer-wisconsin.csv',names = column_names)

print(breast_cancer.head())
breast_cancer=breast_cancer.replace(to_replace='?',value=np.nan)
breast_cancer=breast_cancer.dropna(how='any')
X_train, X_test, y_train, y_test = train_test_split(breast_cancer[column_names[1:10]],
                                                    breast_cancer[column_names[10]],
                                                    test_size=0.25,
                                                    random_state=33)

print('训练样本数据集（X_train）:\n{0}'.format(X_train))
print('训练样本标签集（Y_train）:\n{0}'.format(y_train))
print('测试样本数据集（X_test）:\n{0}'.format(X_test))
print('测试样本标签集（Y_test）:\n{0}'.format(y_test))

lr=LogisticRegression()

lr.fit(X_train,y_train)

score=lr.score(X_test,y_test)
print('评估得分：',score)

result=lr.predict(X_test)
report=classification_report(y_test,result,target_names=['良性','恶性'])
print('评估报告：',report)

result=lr.predict([[2,1,1,1,2,1,3,1,1]])

print(result)
result=lr.predict([[10,7,7,3,8,5,7,4,3]])

print(result)