LogisticRegression 预测分类

import numpy as np
import pandas as pd
path = "breast-cancer-wisconsin.data"
names = ['id','Clump Thickness','Uniformity of Cell Size','Uniformity of Cell Shape',
         'Marginal Adhesion','Single Epithelial Cell Size','Bare Nuclei',
        'Bland Chromatin','Normal Nucleoli','Mitoses','Class']
## 加载数据
data = pd.read_csv(path,na_values='?')
data.columns = names
## 删除为空的数据
data= data.dropna()
data.dtypes
# ## 使用过采样，进行类别平衡
print(data['Class'].value_counts())
appden_data = data[data['Class']==4][:-35]
data =data.append(appden_data)
## 提取X和
Y = data['Class']
X = data.drop(['Class'],axis=1,inplace=False)
## 标准化
from sklearn.preprocessing import StandardScaler
ssCoder = StandardScaler()
X_ss = ssCoder.fit_transform(X)
X = pd.DataFrame