心脏病分类预测--逻辑回归

    import numpy as np
    import pandas as pd
    import matplotlib.pyplot as plt
    import seaborn as sns
    from sklearn.model_selection import train_test_split
    from sklearn.preprocessing import StandardScaler
    from sklearn.linear_model import LogisticRegression
    from sklearn.metrics import accuracy_score
    from sklearn.model_selection import GridSearchCV
    from sklearn.metrics import f1_score
    from sklearn.metrics import classification_report
    from sklearn.metrics import confusion_matrix
    from sklearn.metrics import precision_recall_curve
    from sklearn.metrics import roc_curve
    from sklearn.metrics import roc_auc_score  
     
    # 解决matplotlib中文问题
    from pylab import mpl
    mpl.rcParams['font.sans-serif'] = ['SimHei']  # 指定默认字体
    mpl.rcParams['axes.unicode_minus'] = False  # 解决保存图像是负号'-'显示为方块的问题
     
    # 导入数据
    df = pd.read_csv(r'C:\Users\bo.chen\Desktop\heart.csv')
    df.info()
    df.describe()
     
    df.target.value_counts()
    plt.figure()
    sns.countplot(x='target',data=df,palette="muted")
    plt.xlabel("得病/未得病比例")
    plt.Text(0.5,0,'得病/未得病比例')
     
    df.sex.value_counts()
    plt.figure()
    sns.countplot(x='sex',data=df,palette="Set3")
    plt.xlabel("Sex (0 = 女, 1= 男)")
    plt.Text(0.5,0,'Sex (0 = 女, 1= 男)')
     
    # 数据处理，对特征中非连续型数值进行处理
    first = pd.get_dummies(df['cp'], prefix = "cp")
    second = pd.get_dummies(df['slope'], prefix = "slope")
    thrid = pd.get_dummies(df['thal'], prefix = "thal")
    df = pd.concat([df,first,second,thrid], axis = 1)
    df = df.drop(columns = ['cp', 'slope', 'thal'])
    print(df.head(3))
     
    # 将特征与目标分开
    X = df.drop(['target'], axis = 1)
    y = df.target.values
     
    # 分割数据集
    X_train,X_test,y_train,y_test = train_test_split(X,y,random_state=6)  #随机种子6
     
    # 标准化处理
    standardScaler = StandardScaler()
    standardScaler.fit(X_train)
    X_train = standardScaler.transform(X_train)
    X_test = standardScaler.transform(X_test)
     
    # 逻辑回归模型
    log_reg = LogisticRegression(solver='liblinear')
    log_reg.fit(X_train,y_train)
    print(log_reg.score(X_test,y_test))
     
    y_predict = log_reg.predict(X_test)
    # 调用accuracy_score计算分类准确度
    print(accuracy_score(y_test,y_predict))
     
    # 使用网格搜索找出更好的模型参数
    param_grid = [
    {
        'C':[0.01,0.1,1,10,100],
        'penalty':['l2','l1'],
        'class_weight':['balanced',None]
    }
    ]
     
    grid_search = GridSearchCV(log_reg,param_grid,cv=10,n_jobs=-1)
    grid_search.fit(X_train,y_train)
    print(grid_search.best_estimator_)
    print(grid_search.best_score_)
    print(grid_search.best_params_)
    log_reg = grid_search.best_estimator_
    log_reg.score(X_test,y_test)
     
    # 查看F1指标
    print(f1_score(y_test,y_predict))
    print(classification_report(y_test,y_predict))
     
    # 绘制混淆矩阵
    cnf_matrix = confusion_matrix(y_test,y_predict)
     
    def plot_cnf_matirx(cnf_matrix,description):
    class_names = [0,1]
    fig,ax = plt.subplots()
    tick_marks = np.arange(len(class_names))
    plt.xticks(tick_marks,class_names)
    plt.yticks(tick_marks,class_names)
     
    #create a heat map
    sns.heatmap(pd.DataFrame(cnf_matrix), annot = True, cmap = 'OrRd',
               fmt = 'g')
    ax.xaxis.set_label_position('top')
    plt.tight_layout()
    plt.title(description, y = 1.1,fontsize=16)
    plt.ylabel('实际值0/1',fontsize=12)
    plt.xlabel('预测值0/1',fontsize=12)
    plt.show()
    
    plot_cnf_matirx(cnf_matrix,'Confusion matrix -- Logistic Regression')
     
    decision_scores = log_reg.decision_function(X_test)
    precisions,recalls,thresholds = precision_recall_curve(y_test,decision_scores)
    plt.plot(thresholds,precisions[:-1])
    plt.plot(thresholds,recalls[:-1])
    plt.grid()
    plt.show()   
     
    # 绘制ROC曲线
    fprs,tprs,thresholds = roc_curve(y_test,decision_scores)
     
    def plot_roc_curve(fprs,tprs):
    plt.figure(figsize=(8,6),dpi=80)
    plt.plot(fprs,tprs)
    plt.plot([0,1],linestyle='--')
    plt.xticks(fontsize=13)
    plt.yticks(fontsize=13)
    plt.ylabel('TP rate',fontsize=15)
    plt.xlabel('FP rate',fontsize=15)
    plt.title('ROC曲线',fontsize=17)
    plt.show()
    
    plot_roc_curve(fprs,tprs)
     
    # 求面积,相当于求得分
    # auc:area under curve
    print(roc_auc_score(y_test,decision_scores))
    
    
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
    
    AI助手