机器学习的医疗乳腺癌数据的乳腺癌疾病预测

 #第一步！导入我们需要的工具

    
 import numpy as np 
    
 import pandas as pd 
    
 import matplotlib.pyplot as plt
    
 import seaborn as sns 
    
 %matplotlib inline
    
 from sklearn.linear_model import LogisticRegression 
    
 from sklearn.model_selection import train_test_split 
    
 from sklearn.model_selection import KFold 
    
 from sklearn.model_selection import GridSearchCV
    
 from sklearn.ensemble import RandomForestClassifier
    
 from sklearn.naive_bayes import GaussianNB
    
 from sklearn.neighbors import KNeighborsClassifier
    
 from sklearn.tree import DecisionTreeClassifier
    
 from sklearn import svm
    
 from sklearn import metrics
    
 import warnings
    
 warnings.filterwarnings('ignore')
    
    
    
    
    代码解读

 data.drop("Unnamed: 32",axis=1,inplace=True)

    
 data.drop("id",axis=1,inplace=True)
    
 data.columns
    
    
    
    
    代码解读

 features_mean= list(data.columns[1:11])

    
 features_se= list(data.columns[11:20])
    
 features_worst=list(data.columns[21:31])
    
 print(features_mean)
    
 print("-----------------------------------")
    
 print(features_se)
    
 print("------------------------------------")
    
 print(features_worst)
    
    
    
    
    代码解读

 data['diagnosis']=data['diagnosis'].map({'M':1,'B':0})

    
 data.describe() 
    
    
    
    
    代码解读

 corr = data[features_mean].corr()

    
 plt.figure(figsize=(14,14))
    
 sns.heatmap(corr, cbar = True,  square = True, annot=True, fmt= '.2f',annot_kws={'size': 15},
    
        xticklabels= features_mean, yticklabels= features_mean,
    
        cmap= 'coolwarm')
    
    
    
    
    代码解读