1 import pandas as pd 
 2 from keras.models import Sequential
 3 from keras.layers.core import Dense, Activation
 4 import numpy as np
 5 # 參數初始化
 6 inputfile = 'C:/Users/76319/Desktop/bankloan.xls'
 7 data = pd.read_excel(inputfile)
 8 x_test = data.iloc[:,:8].values
 9 y_test = data.iloc[:,8].values
10 inputfile = 'C:/Users/76319/Desktop/bankloan.xls'
11 data = pd.read_excel(inputfile)
12 x_test = data.iloc[:,:8].values
13 y_test = data.iloc[:,8].values
14 
15 model = Sequential()  # 建立模型
16 model.add(Dense(input_dim = 8, units = 8))
17 model.add(Activation('relu'))  # 用relu函數作為激活函數，能夠大幅提供準確度
18 model.add(Dense(input_dim = 8, units = 1))
19 model.add(Activation('sigmoid'))  # 由於是0-1輸出，用sigmoid函數作為激活函數
20 model.compile(loss = 'mean_squared_error', optimizer = 'adam')
21 # 編譯模型。由於我們做的是二元分類，所以我們指定損失函數為binary_crossentropy，以及模式為binary
22 # 另外常見的損失函數還有mean_squared_error、categorical_crossentropy等，請閱讀幫助文件。
23 # 求解方法我們指定用adam，還有sgd、rmsprop等可選
24 model.fit(x_test, y_test, epochs = 1000, batch_size = 10)
25 predict_x=model.predict(x_test)
26 classes_x=np.argmax(predict_x,axis=1)
27 yp = classes_x.reshape(len(y_test))
28 
29 def cm_plot(y, yp):
30   from sklearn.metrics import confusion_matrix
31   cm = confusion_matrix(y, yp)
32   import matplotlib.pyplot as plt
33   plt.matshow(cm, cmap=plt.cm.Greens)
34   plt.colorbar()
35   for x in range(len(cm)):
36     for y in range(len(cm)):
37       plt.annotate(cm[x,y], xy=(x, y), horizontalalignment='center', verticalalignment='center')
38   plt.ylabel('True label')
39   plt.xlabel('Predicted label')
40   return plt
41 cm_plot(y_test,yp).show()# 顯示混淆矩陣可視化結果
42 score  = model.evaluate(x_test,y_test,batch_size=128)  # 模型評估
43 print(score)

import pandas as pd
inputfile = 'C:/Users/76319/Desktop/bankloan.xls'
data = pd.read_excel(inputfile)
print (data.head())
X = data.drop(columns='違約')
y = data['違約']
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression

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(y_pred)
from sklearn.metrics import accuracy_score
score = accuracy_score(y_pred, y_test)
print(score)
def cm_plot(y, y_pred):
  from sklearn.metrics import confusion_matrix #導入混淆矩陣函數
  cm = confusion_matrix(y, y_pred) #混淆矩陣
  import matplotlib.pyplot as plt #導入作圖庫
  plt.matshow(cm, cmap=plt.cm.Greens) #畫混淆矩陣圖，配色風格使用cm.Greens，更多風格請參考官網。
  plt.colorbar() #顏色標籤
  for x in range(len(cm)): #數據標籤
    for y in range(len(cm)):
      plt.annotate(cm[x,y], xy=(x, y), horizontalalignment='center', verticalalignment='center')
  plt.ylabel('True label') #坐標軸標籤
  plt.xlabel('Predicted label') #坐標軸標籤
  return plt
cm_plot(y_test, y_pred).show()