python金融风控评分卡模型和数据分析(加强版)_2025年版

import pandas as pdimport numpy as npimport matplotlib.pyplot as pltfrom sklearn.ensemble import RandomForestClassifierfrom sklearn.model_selection import train_test_splittrees=1000#读取文件readFileName="German_credit.xlsx"#读取exceldf=pd.read_excel(readFileName)list_columns=list(df.columns[:-1])X=df.ix[:,:-1]y=df.ix[:,-1]names=X.columnsx_train,x_test,y_train,y_test=train_test_split(X,y,random_state=0)#n_estimators表示树的个数，测试中100颗树足够forest=RandomForestClassifier(n_estimators=trees,random_state=0)forest.fit(x_train,y_train)print("random forest with %d trees:"%trees) print("accuracy on the training subset:{:.3f}".format(forest.score(x_train,y_train)))print("accuracy on the test subset:{:.3f}".format(forest.score(x_test,y_test)))print('Feature importances:{}'.format(forest.feature_importances_))n_features=X.shape[1]plt.barh(range(n_features),forest.feature_importances_,align='center')plt.yticks(np.arange(n_features),names)plt.title("random forest with %d trees:"%trees)plt.xlabel('Feature Importance')plt.ylabel('Feature')plt.show()

from sklearn import preprocessingfrom sklearn.svm import SVCfrom sklearn.model_selection import train_test_splitimport matplotlib.pyplot as pltimport pandas as pd#读取文件readFileName="German_credit.xlsx"#读取exceldf=pd.read_excel(readFileName)list_columns=list(df.columns[:-1])x=df.ix[:,:-1]y=df.ix[:,-1]names=x.columns#random_state 相当于随机数种子X_train,x_test,y_train,y_test=train_test_split(x,y,stratify=y,random_state=42)svm=SVC()svm.fit(X_train,y_train)print("accuracy on the training subset:{:.3f}".format(svm.score(X_train,y_train)))print("accuracy on the test subset:{:.3f}".format(svm.score(x_test,y_test)))'''accuracy on the training subset:1.000accuracy on the test subset:0.700'''#观察数据是否标准化plt.plot(X_train.min(axis=0),'o',label='Min')plt.plot(X_train.max(axis=0),'v',label='Max')plt.xlabel('Feature Index')plt.ylabel('Feature magnitude in log scale')plt.yscale('log')plt.legend(loc='upper right')#标准化数据X_train_scaled = preprocessing.scale(X_train)x_test_scaled = preprocessing.scale(x_test)svm1=SVC()svm1.fit(X_train_scaled,y_train)print("accuracy on the scaled training subset:{:.3f}".format(svm1.score(X_train_scaled,y_train)))print("accuracy on the scaled test subset:{:.3f}".format(svm1.score(x_test_scaled,y_test)))'''accuracy on the scaled training subset:0.867accuracy on the scaled test subset:0.800'''#改变C参数，调优,kernel表示核函数，用于平面转换，probability表示是否需要计算概率svm2=SVC(C=10,gamma="auto",kernel='rbf',probability=True)svm2.fit(X_train_scaled,y_train)print("after c parameter=10,accuracy on the scaled training subset:{:.3f}".format(svm2.score(X_train_scaled,y_train)))print("after c parameter=10,accuracy on the scaled test subset:{:.3f}".format(svm2.score(x_test_scaled,y_test)))