2.1.1.1 线性分类器

import pandas as pd
import numpy as np
#创建特征列表
column_names=['sample code number','clump thickness','uniformity of cell size', \
'uniformity of cell shape','marginal adhesion','single epithelical cell size', \
'bare nuclei','bland chromatin','normal nucleoli','mitoses','class']
#column_names[0]
#数据的列名为以上自己设置好的列名
data=pd.read_csv('https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/breast-cancer-wisconsin.data',names=column_names)

---

#将？替换为nan
data=data.replace(to_replace='?',value=np.nan)

---

#丢弃带有缺失值的数据（只有有一个维度有缺失）
data=data.dropna(how='any')
data.shape

---

from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test=train_test_split(data[column_names[1:10]],data[column_names[10]],test_size=0.25,random_state=33)
#查验训练样本的数量和类别分布
y_train.value_counts()
#查验测试样本的数量和类别分布
y_test.value_counts()

---

from sklearn.preprocessing import StandardScaler
#逻辑回归
from sklearn.linear_model import LogisticRegression
#随机梯度参数估计
from sklearn.linear_model import SGDClassifier

---

#数据标准化
ss=StandardScaler()
X_train=ss.fit_transform(X_train)
X_test=ss.fit_transform(X_test)

---

lr=LogisticRegression()
sgdc=SGDClassifier()
#训练模型
lr.fit(X_train,y_train)
#预测
lr_y_predict=lr.predict(X_test)
sgdc.fit(X_train,y_train)
sgdc_y_predict=sgdc.predict(X_test)

---

#准确率，召回率，精确率，F1指标
from sklearn.metrics import classification_report
lr.score(X_test,y_test)#accuracy
print(classification_report(y_test,lr_y_predict,target_names=['Benign','Malignant']))