癌症分类预测--良性 / 恶性乳腺癌肿瘤预测

#癌症分类预测 -- 良性 / 恶性乳腺癌肿瘤预测
import pandas as pd
import numpy as np

#获取数据（读取时加上names）
path = "https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/breast-cancer-wisconsin.data"
column_name = ['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']
data1 = pd.read_csv(path,names = column_name)
display(data1.head())
#数据处理（处理缺失值）

data1 = data1.replace(to_replace = "?",value = np.nan)
data1.dropna(inplace = True)
# data1.isnull().any()
#数据集划分
from sklearn.model_selection import train_test_split

x = data1.iloc[:,1:-1]
# display(x)
y = data1["Class"]
# display(y)
x_train,x_test,y_train,y_test = train_test_split(x,y)
#特征工程（标准化）
from sklearn.preprocessing import StandardScaler
transfer = StandardScaler()
x_train = transfer.fit_transform(x_train)
x_test = transfer.transform(x_test)

#逻辑回归预估器
from sklearn.linear_model import LogisticRegression
estimator = LogisticRegression()
estimator.fit(x_train,y_train)
#逻辑回归的模型参数：权重系数和偏置
print("权重系数：\n",estimator.coef_)
print("偏置：\n",estimator.intercept_)
#模型评估
#方法一：直接对比真实值和预测值
y_predict = estimator.predict(x_test)
print("y_predict：\n",y_predict)
print("直接对比真实值和预测值：\n",y_test == y_predict)

#方法二：计算准确率
score = estimator.score(x_test,y_test)
print("准确率为：\n",score)