逻辑回归

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)
print(y_pred)

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) #画混淆矩阵

 

运行结果：