#多变量分析，保留相关性低于阈值0.6的变量
#对产生的相关系数矩阵进行比较，并删除IV比较小的变量
per_col = step02_modle_plot.fillter_pearson(pearson_coef, threshold=0.60)
print('保留了变量有:', len(per_col))
print(per_col) #136个变量,保留37个
lf5 = new_data[[
'var8', 'var94', 'var17', 'var7', 'var13', 'var139', 'var78', 'var53',
'var121', 'var97', 'var147', 'var113', 'var59', 'var57', 'var27', 'var114',
'var26', 'var144', 'var154', 'var2', 'var141', 'var136', 'var65', 'var135',
'var123', 'var107', 'var108', 'var122', 'var40', 'var118', 'var133',
'var89', 'var19', 'var14', 'var134', 'var145', 'var156', 'y'
]]
pearson_coef = step02_modle_plot.plot_pearson(lf5) #再次观察共线情况
lf5.to_csv(r"C:\Users\Administrator\Desktop\data.csv")
data, iv_value = step01_feature_engine.filter_iv(lf5, group=5)
iv_value.to_excel(
r"F:\TS\external_data_test\电话邦\通善_测试结果\output\iv_value_2.xls")
X, y = step01_feature_engine.x_y_data(data)
vif_data = step01_feature_engine.judge_vif(X) #两个变量VIF>10,共线
X, y = step01_feature_engine.smote_data(X, y)
model = step03_built_modle.baseline_model(X, y)
# pvals = pvals.to_dict()
#
#==============================================================================
#==============================================================================
# from sklearn.preprocessing import StandardScaler # 导入模块
# sc = StandardScaler()
# X[Col] = sc.fit_transform(X[Col])
#==============================================================================
##处理样本不平衡；当样本过少的时候建议采用这个方法
X, y = step01_feature_engine.smote_data(X, y)
model = step03_built_modle.baseline_model(X, y)
'''
confusion_matrix
[[1531 861]
[ 764 1628]]
accuracy_score 0.668147373922
precision_score 0.663346613546
recall_score 0.691588785047
ROC_AUC is 0.728932086353
K-S score 0.354737526648'''
'''or: '''
model = log_model_test(X,y)