银行客户流失预测

from sklearn.metrics import accuracy_score,precision_score,recall_score,f1_score

X_train,X_test,y_train,y_test=train_test_split(StS,y,test_size=0.4,random_state=0)
clf = tree.DecisionTreeClassifier()
clf = clf.fit(X_train, y_train)
pre_labels = clf.predict(X_test)
print(‘accuracy score:‘,accuracy_score(y_test,pre_labels,normalize=True))
print(‘recall score:‘,recall_score(y_test,pre_labels))
print(‘precision score:‘,precision_score(y_test,pre_labels))
print(‘f1  score:‘,f1_score(y_test,pre_labels))

import xgboost as xgb
from sklearn.preprocessing import StandardScaler
#记录程序运行时间
import time
start_time = time.time()
from xgboost.sklearn import XGBClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score,precision_score,recall_score,f1_score,classification_report,roc_auc_score
bankChurn = pd.read_csv(‘D:/work/lost data and dictionary/test/bankChurn.csv‘)#原始数据
bankChurn_data = pd.read_csv(‘D:/work/lost data and dictionary/test/bankChurn_data.csv‘)#预处理数据
Y_train=bankChurn[‘CHUR0_CUST_I0D‘]#标签
StS=StandardScaler().fit_transform(bankChurn_data)
X_train,X_test,y_train,y_test=train_test_split(StS,Y_train,test_size=0.4,random_state=None)
print(X_train.shape, X_test.shape)
#模型参数设置
xlf = xgb.XGBClassifier(max_depth=10,
                        learning_rate=0.1,
                        n_estimators=10,
                        silent=True,
                        objective=‘binary:logistic‘,
                        nthread=-1,
                        gamma=0,
                        min_child_weight=1,
                        max_delta_step=0,
                        subsample=0.85,
                        colsample_bytree=0.7,
                        colsample_bylevel=1,
                        reg_alpha=0,
                        reg_lambda=1,
                        scale_pos_weight=1,#这个值是因为类别十分不平衡。
                        seed=1440)

xlf.fit(X_train, y_train, eval_metric=‘error‘, verbose = True, eval_set = [(X_test, y_test)],early_stopping_rounds=100)
# 计算 auc 分数、预测
preds = xlf.predict(X_test)
pre_pro = xlf.predict_proba(X_test)[:,1]
print(‘accuracy score:‘,accuracy_score(y_test,preds ,normalize=True))
print(‘classification report:‘,classification_report(y_test,preds ))
print(‘precision score:‘,precision_score(y_test,preds ))
print(‘roc_auc_score:%f‘ % roc_auc_score(y_test,pre_pro))
#输出运行时长
cost_time = time.time()-start_time
print("xgboost success!",‘\n‘,"cost time:",cost_time,"(s)......")

import os
os.chdir(‘C:\libsvm-2.81\python‘)
from svmutil import *
from sklearn.metrics import accuracy_score,classification_report
y,x=svm_read_problem(‘bankchurnLibsvm.txt‘)#转换成libsvm格式
# print(type(x))
x=np.array(x)
y=np.array(y)
stratified_folder=StratifiedKFold(n_splits=4,random_state=0,shuffle=True)
for train_index,test_index in stratified_folder.split(x,y):
    print(‘shuffled train index:‘,train_index)
    print(‘shuffled test index:‘, test_index)
    print(‘shuffled x_train:‘, x[train_index])
    print(‘shuffled x_test:‘, x[test_index])
    print(‘shuffled y_train:‘, y[train_index])
    print(‘shuffled y_test:‘, y[test_index])
    print(‘.......‘)
y_train=list(y[train_index])
y_test=list(y[test_index])
x_train=list(x[train_index])
x_test=list(x[test_index])
m=svm_train( y_train,x_train,‘-c 4  -g 2‘)
p_label,p_acc,p_val=svm_predict(y_test,x_test,m)
print(‘accuracy score:‘,accuracy_score(y_test,p_label ,normalize=True))
print(‘classification report:‘,classification_report(y_test,p_label ))