宫颈癌预测--随机森林

    import sklearn
    print(sklearn.__version__)
    import numpy as np
    import pandas as pd
    import matplotlib.pyplot as plt
    import matplotlib as mpl
     
    from sklearn.impute import SimpleImputer
    from sklearn.preprocessing import MinMaxScaler
    from sklearn.preprocessing import label_binarize
    from sklearn.model_selection import train_test_split
     
    from sklearn import tree
    from sklearn.ensemble import RandomForestClassifier
    from sklearn import metrics
    
    import warnings
    warnings.filterwarnings("ignore")
     
    mpl.rcParams['font.sans-serif'] = [u'SimHei']  # 用来正常显示中文标签
    mpl.rcParams['axes.unicode_minus'] = False  # 用来正常显示负号
     
    names = ['Age', 'Number of sexual partners', 'First sexual intercourse',
       'Num of pregnancies', 'Smokes', 'Smokes (years)',
       'Smokes (packs/year)', 'Hormonal Contraceptives',
       'Hormonal Contraceptives (years)', 'IUD', 'IUD (years)', 'STDs',
       'STDs (number)', 'STDs:condylomatosis',
       'STDs:cervical condylomatosis', 'STDs:vaginal condylomatosis',
       'STDs:vulvo-perineal condylomatosis', 'STDs:syphilis',
       'STDs:pelvic inflammatory disease', 'STDs:genital herpes',
       'STDs:molluscum contagiosum', 'STDs:AIDS', 'STDs:HIV',
       'STDs:Hepatitis B', 'STDs:HPV', 'STDs: Number of diagnosis',
       'STDs: Time since first diagnosis', 'STDs: Time since last diagnosis',
       'Dx:Cancer', 'Dx:CIN', 'Dx:HPV', 'Dx', 'Hinselmann', 'Schiller',
       'Citology', 'Biopsy']
    data = pd.read_csv(r'C:\Users\bo.chen\Desktop\risk_factors_cervical_cancer.csv')
     
    # 查看数据
    print(data.shape)
     
    # 划分数据集中的特征和目标值
    X = data[names[0:-4]]   # X = data.iloc[:,0:-4]
    y = data[names[-4:]]    # Y = data.iloc[:,-4:]
    # 预测的目标有四个目标值：Hiselmann、Schiller、Citlolgy、Biopsy
    print(type(X))
    print(X.head())
    print(y.head())
    # 空值处理
    X = X.replace("?", np.NAN)
    # 使用SimpleImputerr给定缺省值，默认以mean也就是均值替换
    imputer = SimpleImputer(missing_values=np.nan, strategy='mean')
    X = imputer.fit_transform(X,y)
    
    
    # 数据集分割
    X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.2,random_state=0)
    print("训练样本数量:%d,特征属性数目:%d,目标属性数目:%d"\
      %(X_train.shape[0],X_train.shape[1],y_train.shape[1]))
    print ("测试样本数量:%d" % X_test.shape[0])
     
    # 标准化
    ss = MinMaxScaler()
    # 分类模型，经常使用的是minmaxscaler归一化，回归模型经常用standardscaler
    X_train = ss.fit_transform(X_train, y_train)
    X_test = ss.transform(X_test)
     
    # 模型构建
    rf = RandomForestClassifier(n_estimators=50,criterion="gini",max_depth=1,\
                            random_state=10)
    rf.fit(X_train,y_train)
     
    # 模型效果评估
    score = rf.score(X_test, y_test)
    print("准确率：%.2f%%" %(score * 100))
     
    #模型预测
    rf_y_predict = rf.predict_proba(X_test)# prodict_proba输出概率
    # print(rf_y_predict)
     
    #计算ROC值
    forest_fpr1, forest_tpr1, thresholds1 = \
             metrics.roc_curve(label_binarize(y_test[names[-4]],classes=(0,1,2)).\
                               T[0:-1].T.ravel(), rf_y_predict[0].ravel())
    forest_fpr2, forest_tpr2, thresholds2 = \
             metrics.roc_curve(label_binarize(y_test[names[-3]],classes=(0,1,2)).\
                               T[0:-1].T.ravel(), rf_y_predict[1].ravel())
    forest_fpr3, forest_tpr3, thresholds3 = \
             metrics.roc_curve(label_binarize(y_test[names[-2]],classes=(0,1,2)).\
                               T[0:-1].T.ravel(), rf_y_predict[2].ravel())
    forest_fpr4, forest_tpr4, thresholds4 = \
             metrics.roc_curve(label_binarize(y_test[names[-1]],classes=(0,1,2)).\
                               T[0:-1].T.ravel(), rf_y_predict[3].ravel())
    # AUC值
    auc1 = metrics.auc(forest_fpr1, forest_tpr1)
    auc2 = metrics.auc(forest_fpr2, forest_tpr2)
    auc3 = metrics.auc(forest_fpr3, forest_tpr3)
    auc4 = metrics.auc(forest_fpr4, forest_tpr4)
     
    print ("Hinselmann目标属性AUC值：%.2f"%auc1)
    print ("Schiller目标属性AUC值：%.2f"%auc2)
    print ("Citology目标属性AUC值：%.2f"%auc3)
    print ("Biopsy目标属性AUC值：%.2f"%auc4)
     
    # 画图（ROC图）
    plt.figure(figsize=(8, 6), facecolor='w')
    plt.plot(forest_fpr1,forest_tpr1,c='r',lw=2,label=u'Hinselmann目标属性,AUC=%.3f' % auc1)
    plt.plot(forest_fpr2,forest_tpr2,c='b',lw=2,label=u'Schiller目标属性,AUC=%.3f' % auc2)
    plt.plot(forest_fpr3,forest_tpr3,c='g',lw=2,label=u'Citology目标属性,AUC=%.3f' % auc3)
    plt.plot(forest_fpr4,forest_tpr4,c='y',lw=2,label=u'Biopsy目标属性,AUC=%.3f' % auc4)
    plt.plot((0,1),(0,1),c='#a0a0a0',lw=2,ls='--')
    plt.xlim(-0.001, 1.001)
    plt.ylim(-0.001, 1.001)
    plt.xticks(np.arange(0, 1.1, 0.1))
    plt.yticks(np.arange(0, 1.1, 0.1))
    plt.xlabel('False Positive Rate(FPR)', fontsize=16)
    plt.ylabel('True Positive Rate(TPR)', fontsize=16)
    plt.grid(b=True, ls=':')
    plt.legend(loc='lower right', fancybox=True, framealpha=0.8, fontsize=12)
    plt.title(u'随机森林多目标属性分类ROC曲线', fontsize=18)
    plt.show()

    Examples
    --------
    >>> import numpy as np
    >>> from sklearn.impute import SimpleImputer
    >>> imp_mean = SimpleImputer(missing_values=np.nan, strategy='mean')
    >>> imp_mean.fit([[7, 2, 3], [4, np.nan, 6], [10, 5, 9]])
    SimpleImputer()
    >>> X = [[np.nan, 2, 3], [4, np.nan, 6], [10, np.nan, 9]]
    >>> print(imp_mean.transform(X))
    [[ 7.   2.   3. ]
     [ 4.   3.5  6. ]
     [10.   3.5  9. ]]