Keras搭建神经网络进行二分类预测是否存款，带运行效果及评测图

痛定思痛。 2022-04-03 18:24 262阅读 0赞

数据来源：[http://archive.ics.uci.edu/ml/datasets/Bank+Marketing][http_archive.ics.uci.edu_ml_datasets_Bank_Marketing]

开发工具：Jupyter notebook

语言版本：python 3.6

1.数据读入及特征工程

import numpy as np
    import pandas as pd
    from sklearn import preprocessing
    %matplotlib inline
    from matplotlib import pyplot as plt
    
    data = pd.read_csv("D:\\bank-full.csv",sep = ';')
    test = pd.read_csv("D:\\bank.csv",sep = ';')
    
    
    def get_y_train():
        y_train = np.array(data['y'])
        y_train = np.where(y_train == 'yes', 0, 1) #将预测值转换成01
        return y_train
    
    def get_y_test():
        y_test = np.array(test['y'])
        y_test = np.where(y_test == 'yes', 0, 1) #将预测值转换成01
        return y_test
    
    def get_X_train():
        oh_data = pd.get_dummies(data) #对非数值数据进行ont-hot编码
        columns_size = oh_data.columns.size
        X_train = oh_data.iloc[:,0:columns_size-2] #取特征
        X_train = preprocessing.scale(X_train) #归一化
        return X_train
    
    def get_X_test():
        oh_test = pd.get_dummies(test) #对非数值数据进行ont-hot编码
        columns_size = oh_test.columns.size
        X_test = oh_test.iloc[:,0:columns_size-2] #取特征
        X_test= preprocessing.scale(X_test) #归一化
        return X_test
    X_test = get_X_test()
    X_train = get_X_train()
    y_test = get_y_test()
    y_train = get_y_train()

2.模型建立

from keras.layers import Dense,LSTM,Dropout
    from keras.models import Sequential
    from keras import optimizers
    from sklearn import metrics
    
    
    model = Sequential()
    model.add(Dense(51, input_dim = 51, activation = 'relu'))
    model.add(Dropout(0.2))
    model.add(Dense(128, activation = 'relu'))
    model.add(Dropout(0.2))
    model.add(Dense(64, activation = 'relu'))
    model.add(Dense(1, activation = 'sigmoid'))
    model.compile(optimizer = optimizers.adam(lr = 0.006),
        loss = 'binary_crossentropy',
        metrics = ['accuracy'])
    
    history = model.fit(X_train, y_train, nb_epoch = 20, batch_size = 512, validation_data = (X_test, y_test))

3.模型运行情况作图

y_pred = model.predict_classes(X_test, batch_size = 20, verbose = 1)
    target_names = ['1', '0']
    print(metrics.classification_report(y_test, y_pred,
        target_names = target_names))
    
    history_dict = history.history
    loss, accuracy = model.evaluate(X_test, y_test)
    
    print('test loss: ', loss)
    print('test accuracy: ', accuracy)
    
    history_dict = history.history
    loss_values = history_dict['loss']
    val_loss_values = history_dict['val_loss']
    acc = history_dict['acc']
    epochs = range(1, len(acc) + 1)
    
    plt.plot(epochs, loss_values, 'bo', label = 'Training loss')
    plt.plot(epochs, val_loss_values, 'b', label = 'Validation loss')
    plt.title('Training and validation loss')
    plt.xlabel('Epochs')
    plt.ylabel('Loss')
    plt.legend()
    plt.show()# 
    acc_values = history_dict['acc']
    val_acc_values = history_dict['val_acc']
    
    plt.plot(epochs, acc_values, 'bo', label = 'Training acc')
    plt.plot(epochs, val_acc_values, 'b', label = 'Validation acc')
    plt.title('Training and validation accuracy')
    plt.xlabel('Epochs')
    plt.ylabel('Acc')
    plt.legend()
    plt.show()

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3hpYW9jeHljemg_size_16_color_FFFFFF_t_70][]

4.模型AUC评测

from sklearn.metrics import roc_curve, auc 
    
    y_pred_keras = model.predict(X_test).ravel()
    fpr, tpr, threshold = roc_curve(y_test, y_pred_keras)   
    roc_auc = auc(fpr,tpr)
    plt.plot(fpr, tpr, 'b', label='Keras AUC = %0.2f' % roc_auc)
    plt.legend(loc='lower right')
    plt.plot([0, 1], [0, 1], 'r--')
    plt.xlabel('False Positive Rate')
    plt.ylabel('True Positive Rate')
    plt.show()

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3hpYW9jeHljemg_size_16_color_FFFFFF_t_70 1][]

[http_archive.ics.uci.edu_ml_datasets_Bank_Marketing]: http://archive.ics.uci.edu/ml/datasets/Bank+Marketing
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3hpYW9jeHljemg_size_16_color_FFFFFF_t_70]: /images/20220403/bc1a5e99c1274c6b957682d0d6182359.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3hpYW9jeHljemg_size_16_color_FFFFFF_t_70 1]: /images/20220403/a2942c51914b46b9a272d17d7896c5fe.png