银行风控模型的建立

代码1

import pandas as pd
from sklearn.model_selection import train_test_split
from keras.models import Sequential
from keras.layers.core import Dense, Activation
from keras.layers import Activation,Dense,Dropout
import numpy as np

inputfile = './bankloan.xls'
data = pd.read_excel(inputfile)

X = data.drop(columns='违约')
y = data['违约']


X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=1)

model = Sequential()
model.add(Dense(64,input_dim=8,activation='relu'))
# Drop防止过拟合的数据处理方式
model.add(Dropout(0.5))
model.add(Dense(64,activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(1,activation='sigmoid'))
# 编译模型，定义损失函数，优化函数，绩效评估函数
model.compile(loss='binary_crossentropy',
    optimizer='rmsprop',
    metrics=['accuracy'])
# 导入数据进行训练
model.fit(X_train,y_train,epochs=200,batch_size=128)
# 模型评估
score = model.evaluate(X_test,y_test,batch_size=128)
print(score)

predict_x=model.predict(X_test) 
yp=np.argmax(predict_x,axis=1)


def cm_plot(y, y_pred):
    from sklearn.metrics import confusion_matrix #导入混淆矩阵函数
    cm = confusion_matrix(y, y_pred) #混淆矩阵
    import matplotlib.pyplot as plt #导入作图库
    plt.matshow(cm, cmap=plt.cm.Greens) #画混淆矩阵图，配色风格使用cm.Greens，更多风格请参考官网。
    plt.colorbar() #颜色标签
    for x in range(len(cm)): #数据标签
        for y in range(len(cm)):
            plt.annotate(cm[x,y], xy=(x, y), horizontalalignment='center', verticalalignment='center')
    plt.ylabel('True label') #坐标轴标签
    plt.xlabel('Predicted label') #坐标轴标签
    plt.show()
    return plt

cm_plot(y_test, yp)

代码2

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score

inputfile = './bankloan.xls'
data = pd.read_excel(inputfile)

X = data.drop(columns='违约')
y = data['违约']


X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=1)

model = LogisticRegression()
model.fit(X_train, y_train)
y_pred = model.predict(X_test)

score = accuracy_score(y_pred, y_test)
print(score)

def cm_plot(y, y_pred):
    from sklearn.metrics import confusion_matrix #导入混淆矩阵函数
    cm = confusion_matrix(y, y_pred) #混淆矩阵
    import matplotlib.pyplot as plt #导入作图库
    plt.matshow(cm, cmap=plt.cm.Greens) #画混淆矩阵图，配色风格使用cm.Greens，更多风格请参考官网。
    plt.colorbar() #颜色标签
    for x in range(len(cm)): #数据标签
        for y in range(len(cm)):
            plt.annotate(cm[x,y], xy=(x, y), horizontalalignment='center', verticalalignment='center')
    plt.ylabel('True label') #坐标轴标签
    plt.xlabel('Predicted label') #坐标轴标签
    plt.show()
    return plt

cm_plot(y_test, y_pred)

结果1：

 

 [0.3884179890155792, 0.800000011920929]

结果2：

 

 0.8285714285714286

标签：plt,cm,模型,银行,风控,train,test,import,model
来源： https://www.cnblogs.com/yanjiahao/p/16076488.html