肿瘤预测

import pandas as pd
import numpy as np

#1.读取数据
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']
data=pd.read_csv(path,names=column_name) 

#2.缺失值处理
    #1)替换成np.nan
data=data.replace(to_replace="?",value=np.nan)
    #2)删除缺失样本,原地删除
data.dropna(inplace=True)
    

data.isnull().any() #不存在缺失值

Sample code number             False
Clump Thickness                False
Uniformity of Cell Size        False
Uniformity of Cell Shape       False
Marginal Adhesion              False
Single Epithelial Cell Size    False
Bare Nuclei                    False
Bland Chromatin                False
Normal Nucleoli                False
Mitoses                        False
Class                          False
dtype: bool

from sklearn.model_selection import train_test_split

x=data.iloc[:,1:-1]
y=data["Class"]

x_train,x_test,y_train,y_test=train_test_split(x,y)

#4.标准化
from sklearn.preprocessing import StandardScaler

transfer=StandardScaler()
x_train=transfer.fit_transform(x_train)
x_test=transfer.transform(x_test)

from sklearn.linear_model import LogisticRegression

#5预估器流程.
estimator=LogisticRegression()
estimator.fit(x_train,y_train)

LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,
                   intercept_scaling=1, l1_ratio=None, max_iter=100,
                   multi_class='auto', n_jobs=None, penalty='l2',
                   random_state=None, solver='lbfgs', tol=0.0001, verbose=0,
                   warm_start=False)

#逻辑回归的模型参数：回归系数和偏置
estimator.coef_ #回归系数

array([[ 1.34866956,  0.39407465,  0.95414338,  0.52087229, -0.30587845,
         1.18209596,  0.94562307,  0.95800325,  0.58231319]])

estimator.intercept_ #偏置

array([-1.14018688])

#6.模型评估
#方法1：直接比对真实值和预测值
y_predict=estimator.predict(x_test)
print("y_predict\n",y_predict)
print("直接比对真实值和预测值:\n",y_test==y_predict)
#方法2：计算准确率
score=estimator.score(x_test,y_test)
print("准确率:\n",score)

y_predict
 [2 2 4 2 2 2 4 4 4 2 4 4 2 4 4 4 2 2 2 4 2 2 2 4 2 2 2 2 2 2 2 4 2 2 2 2 4
 2 4 4 2 2 2 2 2 4 2 2 2 4 2 2 2 4 2 2 2 4 4 2 2 4 2 4 4 2 2 4 2 4 4 2 4 2
 4 4 4 4 4 2 4 4 4 2 2 2 2 4 2 2 2 2 2 4 2 4 2 2 2 2 2 4 4 2 2 4 2 2 2 4 2
 4 4 4 2 2 4 2 4 2 4 4 4 4 4 4 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 4 4 4 2 2 2
 4 2 4 4 4 2 4 4 2 4 2 4 4 2 2 4 2 2 2 2 2 2 2]
直接比对真实值和预测值:
 93     True
165    True
670    True
380    True
385    True
       ... 
291    True
370    True
332    True
632    True
492    True
Name: Class, Length: 171, dtype: bool
准确率:
 0.9707602339181286

#7.查看精确率和召回率，F1-score
from sklearn.metrics import classification_report

report=classification_report(y_test,y_predict,labels=[2,4],target_names=['良性','恶性'])
print(report)

              precision    recall  f1-score   support

          良性       0.96      0.99      0.98       102
          恶性       0.98      0.94      0.96        69

    accuracy                           0.97       171
   macro avg       0.97      0.97      0.97       171
weighted avg       0.97      0.97      0.97       171