import pandas  as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import classification_report
from sklearn.metrics import roc_auc_score
#ssl用来处理数据权限
import ssl
ssl._create_default_https_context = ssl._create_unverified_context
# 1.获取数据
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']
data = pd.read_csv("https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/breast-cancer-wisconsin.data",
                  names=names)
data.head()
# 2.基本数据处理
# 2.1 缺失值处理(替换为NaN,再处理)
data = data.replace(to_replace="?", value=np.NaN)
data = data.dropna()
# 2.2 确定特征值,目标值
x = data.iloc[:, 1:10]
x.head()
y = data["Class"]
y.head()
# 2.3 分割数据
x_train, x_test, y_train, y_test = train_test_split(x, y, random_state=22)
# 3.特征工程(标准化)
transfer = StandardScaler()
x_train = transfer.fit_transform(x_train)
x_test = transfer.transform(x_test)
# 4.机器学习(逻辑回归)
estimator = LogisticRegression()
estimator.fit(x_train, y_train)
# 5.模型评估
y_predict=estimator.predict(x_test)
print("预测值为：\n",y_predict)
ret=estimator.score(x_test,y_test)
print("准确率为：\n",ret)
6 精确率、召回率指标评价(该部分内容在下一节)
class_ret=classification_report(y_test,y_predict,labels=(2,4),target_names=("良性","恶性"))
print(class_ret)
# AOC指标计算
# 先将2，4转换为0，1
y_test=np.where(y_test>3,1,0)
roc_auc_score(y_test,y_predict)
# print("AUC指标：",roc_auc_score(y_test,y_predict))
在很多分类场景当中我们不一定只关注预测的准确率，比如以这个癌症举例子，我们并不关注预测的准确率，而是关注在所有的样本当中，癌症患者有没有被全部预测（检测）出来。
如果数据中有缺失值，一定要对其进行处理
准确率并不是衡量分类正确的唯一标准