特征图

mvp/xgbreport.py

@@ -26,30 +26,30 @@ def report(dftrain,dftest,features,label,path,filename):
     document.add_paragraph('模型训练集{}'.format(xgboost.auc(clf,dftrain,features,label)))
     document.add_paragraph('模型测试集{}'.format(xgboost.auc(clf, dftest, features, label)))
 
-    # document.add_heading('调整参数')
-    # max_depth=[2,3]
-    # min_child_weight=range(1,4,1)
-    # document, clf = tun_params(document, clf, dftrain, dftest, {'max_depth': max_depth,'min_child_weight':min_child_weight}, features, label)
-
-    # # gamma
-    # gamma=[i/10 for i in range(0,5)]
-    # document,clf=tun_params(document,clf,dftrain,dftest,{'gamma':gamma},features,label)
-    #
-    # # subsample colsample_bytree
-    # subsample=[0.8,0.9,1]
-    # colsample_bytree=[0.8,0.9,1]
-    # document, clf = tun_params(document, clf, dftrain, dftest,
-    #                            {'subsample': subsample, 'colsample_bytree': colsample_bytree}, features, label)
-    #
-    # # reg_alpha
-    # reg_alpha=[0.001,0.01,0.1,1,10]
-    # document, clf = tun_params(document, clf, dftrain, dftest,
-    #                            {'reg_alpha': reg_alpha}, features, label)
-    #
-    # # reg_lambda
-    # reg_lambda = [0.001, 0.01, 0.1, 1, 10]
-    # document, clf = tun_params(document, clf, dftrain, dftest,
-    #                            {'reg_lambda': reg_lambda}, features, label)
+    document.add_heading('调整参数')
+    max_depth=[2,3]
+    min_child_weight=range(1,4,1)
+    document, clf = tun_params(document, clf, dftrain, dftest, {'max_depth': max_depth,'min_child_weight':min_child_weight}, features, label)
+
+    # gamma
+    gamma=[i/10 for i in range(0,5)]
+    document,clf=tun_params(document,clf,dftrain,dftest,{'gamma':gamma},features,label)
+
+    # subsample colsample_bytree
+    subsample=[0.8,0.9,1]
+    colsample_bytree=[0.8,0.9,1]
+    document, clf = tun_params(document, clf, dftrain, dftest,
+                               {'subsample': subsample, 'colsample_bytree': colsample_bytree}, features, label)
+
+    # reg_alpha
+    reg_alpha=[0.001,0.01,0.1,1,10]
+    document, clf = tun_params(document, clf, dftrain, dftest,
+                               {'reg_alpha': reg_alpha}, features, label)
+
+    # reg_lambda
+    reg_lambda = [0.001, 0.01, 0.1, 1, 10]
+    document, clf = tun_params(document, clf, dftrain, dftest,
+                               {'reg_lambda': reg_lambda}, features, label)
 
     #==生成模型最后的报告，各个特征的单变量图，PDP，liftchart
     dftrain=xgboost.predict(clf,dftrain,features)
@@ -87,17 +87,17 @@ def report(dftrain,dftest,features,label,path,filename):
     document.add_paragraph('测试集分渠道--liftchart')
     document.add_picture('tmp.png')
 
-    # #== 各个特征的 单变量图 和 pdp 图
-    # for i in featureimp.feature.tolist():
-    #     drawplot.univarchart(dftest, i, label, bin=10, title='单变量%s' % i,
-    #                         ylabel='逾期率').savefig('tmp.png')
-    #     document.add_paragraph('单变量%s' % i)
-    #     document.add_picture('tmp.png')
-    #     #= pdp
-    #     drawplot.pdpchart(dftest, i, 'predict_proba', bin=10, title='pdp %s' % i,
-    #                          ylabel='模型分').savefig('tmp.png')
-    #     document.add_paragraph('pdp %s' % i)
-    #     document.add_picture('tmp.png')
+    #== 各个特征的 单变量图 和 pdp 图
+    for i in featureimp.feature.tolist():
+        drawplot.univarchart(dftest, i, label, bin=10, title='单变量%s' % i,
+                            ylabel='逾期率').savefig('tmp.png')
+        document.add_paragraph('单变量%s' % i)
+        document.add_picture('tmp.png')
+        #= pdp
+        drawplot.pdpchart(dftest, i, 'predict_proba', bin=10, title='pdp %s' % i,
+                             ylabel='模型分').savefig('tmp.png')
+        document.add_paragraph('pdp %s' % i)
+        document.add_picture('tmp.png')
 
     filetool.saveDocument(document, path, filename)