Model_Bank

银行家完整代码

import pandas as pd
import numpy as np
#导入划分数据集函数
from sklearn.model_selection import train_test_split
#读取数据
datafile = r'F:\python\Python Scripts\data\bankloan.xls'#文件路径
data = pd.read_excel(datafile)
x = data.iloc[:,:8]
y = data.iloc[:,8]
#划分数据集
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=100)
#导入模型和函数
from keras.models import Sequential
from keras.layers import Dense,Dropout
#导入指标
from keras.metrics import BinaryAccuracy
#导入时间库计时
import time
start_time = time.time()
#-------------------------------------------------------#
model = Sequential()
model.add(Dense(input_dim=8,units=800,activation='relu'))#激活函数relu
model.add(Dropout(0.5))#防止过拟合的掉落函数
model.add(Dense(input_dim=800,units=400,activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(input_dim=400,units=1,activation='sigmoid'))

model.compile(loss='binary_crossentropy', optimizer='adam',metrics=[BinaryAccuracy()])
model.fit(x_train,y_train,epochs=100,batch_size=128)
loss,binary_accuracy = model.evaluate(x,y,batch_size=128)
#--------------------------------------------------------#
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))

yp = model.predict(x).reshape(len(y))
yp = np.around(yp,0).astype(int) #转换为整型
from cm_plot import *  # 导入自行编写的混淆矩阵可视化函数

cm_plot(y,yp).show()  # 显示混淆矩阵可视化结果

cm_plot函数：

def cm_plot(y, yp):
  
  from sklearn.metrics import confusion_matrix #导入混淆矩阵函数

  cm = confusion_matrix(y, yp) #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
  return plt

 

 决策树

import pandas as pd
# 参数初始化
filename = r'F:/python/Python Scripts/data/bankloan.xls'
data = pd.read_excel(filename) # 导入数据

# 数据是类别标签，要将它转换为数据
# 用1来表示“好”“是”“高”这三个属性，用-1来表示“坏”“否”“低”

x = data.iloc[:,:8].astype(int)
y = data.iloc[:,8].astype(int)

from sklearn.tree import DecisionTreeClassifier as DTC
dtc = DTC(criterion='entropy') # 建立决策树模型，基于信息熵
dtc.fit(x, y) # 训练模型

# 导入相关函数，可视化决策树。
# 导出的结果是一个dot文件，需要安装Graphviz才能将它转换为pdf或png等格式。
from sklearn.tree import export_graphviz
x = pd.DataFrame(x)

"""
string1 = '''
edge [fontname="NSimSun"];
node [ fontname="NSimSun" size="15,15"];
{
'''
string2 = '}'
"""

with open("F:/python/Python Scripts/data/tree.dot", 'w') as f:
export_graphviz(dtc, feature_names = x.columns, out_file = f)
f.close()

from IPython.display import Image
from sklearn import tree
import pydotplus

dot_data = tree.export_graphviz(dtc, out_file=None, #regr_1 是对应分类器
feature_names=data.columns[:8], #对应特征的名字
class_names=data.columns[8], #对应类别的名字
filled=True, rounded=True,
special_characters=True)

graph = pydotplus.graph_from_dot_data(dot_data)
graph.write_png('F:/python/Python Scripts/data/example.png') #保存图像
Image(graph.create_png())