import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import  StandardScaler
from sklearn.linear_model import LogisticRegression
# 獲得數據
names=['Sample code number','Clump Thickness','Uniformity of Cell Size','Uniformity of Cell Shape','Marginal Adhesion','Single Hpithelial Cell Size','Bare Nucle','Bland Chromatin','Normal Nucleoli','Mitomeos','Class']
data=pd.read_csv("https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/breast-cancer-wisconsin.data",names=names)
# 處理數據  處理掉數據里的缺失值
data=data.replace(to_replace="?",value=np.nan)
# 使用dropna刪除替代過的數據
data=data.dropna()
# 分類數據  特征值  標準值
x=data.iloc[:,1:-1]
y=data["Class"]
# 分割數據
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=20)# 標準化數據
transfer =StandardScaler()
x_train=transfer.fit_transform(x_train)
x_test=transfer.fit_transform(x_test)
# 訓練模型
estimator=LogisticRegression()
ret=estimator.fit(x_train,y_train)
print(ret)
# 模型評估
print(estimator.score(x_test,y_test))