Python基于数据挖掘的银行风控模型的建立

1.BP神经网络

数据可视化

import pandas as pd
from keras.models import Sequential
from keras.layers.core import Dense, Activation
import numpy as np
# 参数初始化
inputfile = 'E:/Python/bankloan.xls'
data = pd.read_excel(inputfile)
x_test = data.iloc[:,:8].values
y_test = data.iloc[:,8].values

import pandas as pd
from keras.models import Sequential
from keras.layers.core import Dense, Activation
import numpy as np
# 参数初始化
inputfile = 'E:/Python/bankloan.xls'
data = pd.read_excel(inputfile)
x_test = data.iloc[:,:8].values
y_test = data.iloc[:,8].values

inputfile = 'E:/Python/bankloan.xls'
data = pd.read_excel(inputfile)
x_test = data.iloc[:,:8].values
y_test = data.iloc[:,8].values

model = Sequential()  # 建立模型
model.add(Dense(input_dim = 8, units = 8))
model.add(Activation('relu'))  # 用relu函数作为激活函数，能够大幅提供准确度
model.add(Dense(input_dim = 8, units = 1))
model.add(Activation('sigmoid'))  # 由于是0-1输出，用sigmoid函数作为激活函数
model.compile(loss = 'mean_squared_error', optimizer = 'adam')
# 编译模型。由于我们做的是二元分类，所以我们指定损失函数为binary_crossentropy，以及模式为binary
# 另外常见的损失函数还有mean_squared_error、categorical_crossentropy等，请阅读帮助文件。
# 求解方法我们指定用adam，还有sgd、rmsprop等可选
model.fit(x_test, y_test, epochs = 1000, batch_size = 10)
predict_x=model.predict(x_test)
classes_x=np.argmax(predict_x,axis=1)
yp = classes_x.reshape(len(y_test))

def cm_plot(y, yp):
  from sklearn.metrics import confusion_matrix
  cm = confusion_matrix(y, yp)
  import matplotlib.pyplot as plt
  plt.matshow(cm, cmap=plt.cm.Greens)
  plt.colorbar()
  for x in range(len(cm)):
    for y in range(len(cm)):
      plt.annotate(cm[x,y], xy=(x, y), horizontalalignment='center', verticalalignment='center')
  plt.ylabel('True label')
  plt.xlabel('Predicted label')
  return plt
cm_plot(y_test,yp).show()# 显示混淆矩阵可视化结果

2.SVM支持向量机

import pandas as pd
import numpy as np
# 参数初始化

from sklearn import svm
from sklearn.metrics import accuracy_score
from sklearn.metrics import confusion_matrix
from matplotlib import pyplot as plt
import seaborn as sns
from sklearn.model_selection import train_test_split

data_load = "E:/Python/bankloan.xls"
data = pd.read_excel(data_load)
data.describe()
data.columns
data.index
## 转为np 数据切割
X = np.array(data.iloc[:,0:-1])
y = np.array(data.iloc[:,-1])
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=1, train_size=0.8, test_size=0.2, shuffle=True)
svm = svm.SVC()
svm.fit(X_test,y_test)
y_pred = svm.predict(X_test)
accuracy_score(y_test, y_pred)
print(accuracy_score(y_test, y_pred))
cm = confusion_matrix(y_test, y_pred)
heatmap = sns.heatmap(cm, annot=True, fmt='d')
heatmap.yaxis.set_ticklabels(heatmap.yaxis.get_ticklabels(), rotation=0, ha='right')
heatmap.xaxis.set_ticklabels(heatmap.xaxis.get_ticklabels(), rotation=45, ha='right')
plt.ylabel("true label")
plt.xlabel("predict label")
plt.show()

3.决策树

import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier as DTC
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
import time
start_time = time.time()

filePath = 'E:/Python/bankloan.xls'
data = pd.read_excel(filePath)
x = data.iloc[:,:8]
y = data.iloc[:,8]
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=100)
#模型
dtc_clf = DTC(criterion='entropy')#决策树
#训练
dtc_clf.fit(x_train,y_train)
#模型评价
dtc_yp = dtc_clf.predict(x)
dtc_score = accuracy_score(y, dtc_yp)
score = {"决策树得分":dtc_score}

score = sorted(score.items(),key = lambda score:score[0],reverse=True)
print(pd.DataFrame(score)) 
#中文标签、负号正常显示
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False 
#绘制混淆矩阵
figure = plt.subplots(figsize=(12,10))
plt.title('决策树')
dtc_cm = confusion_matrix(y, dtc_yp)
heatmap = sns.heatmap(dtc_cm, annot=True, fmt='d')
heatmap.yaxis.set_ticklabels(heatmap.yaxis.get_ticklabels(), rotation=0, ha='right')
heatmap.xaxis.set_ticklabels(heatmap.xaxis.get_ticklabels(), rotation=45, ha='right')
plt.ylabel("true label")
plt.xlabel("predict label")
plt.show()
end_time = time.time()
run_time = end_time-start_time#运行时间
print('模型运行时间：{}'.format(run_time))
print('模型损失值：{}'.format(loss))
print('模型精度：{}'.format(binary_accuracy))

运行结果