Java教程

数据挖掘模型学习

本文主要是介绍数据挖掘模型学习,对大家解决编程问题具有一定的参考价值,需要的程序猿们随着小编来一起学习吧!

银行风险控制模型

逻辑回归模型~sklearn:

 

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 = 'E:\\pydata\\data\\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)
#print('预测值'+y_pred+'\n')

score = accuracy_score(y_pred, y_test)
#print('准确率'+score+'\n')

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)   #画混淆矩阵

 

 

BP神经网络~Keras:

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

inputfile = 'E:\\pydata\\data\\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)


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


yp = model.predict(X_test)  # 分类预测
yp[yp>0.5]=1
yp[yp<=0.5]=0
cm_plot(y_test, yp)

 

这篇关于数据挖掘模型学习的文章就介绍到这儿,希望我们推荐的文章对大家有所帮助,也希望大家多多支持为之网!