bug修正

graph/matplot.py

@@ -26,7 +26,7 @@ def topN_feature_importance(model, clf, title="untitled", save_path='./mvp/plots
     model.plot_importance(clf, max_num_features=topN)
     plt.title("Feature Importances")
 
-    path = save_path + title + " featureImportance.png"
+    path = save_path + title + "_featureImportance.png"
     plt.savefig(path)
     plt.show()
     return path
@@ -67,13 +67,14 @@ def plot_table_list(datalist, auc, datalist_description=None, title='untitled',
         tab_df = []
         if tab_df_list is None:
             for data in datalist:
+                data = data.fillna(-1)
                 tab_df.append(
                     pd.Series(data.index).astype(str).map(lambda x: x.replace(' ', '').replace('0.', '.')).tolist())
                 tab_df.append(
                     pd.Series(data.values).astype(str).map(lambda x: x.replace(' ', '').replace('0.', '.')).tolist())
                 # validate tab_rows
                 if tab_rows is None:
-                    table_rows.append('index');
+                    table_rows.append('index')
                     table_rows.append('values')
                 else:
                     # tab_rows was given by
@@ -113,12 +114,11 @@ def plot_table_list(datalist, auc, datalist_description=None, title='untitled',
     if saved_path is not None:
         plt.savefig(saved_path + title + ".png")
     plt.show()
-    return 1
+    return saved_path + title + ".png"
 
 
-def plot_table_df(dataset, auc, title='untitled', X_label=None, y_label=None,
+def plot_table_df(dataset, auc=None, title='untitled', X_label=None, y_label=None,
                   tab_df=None, plot_tab=True, saved_path=None):
-    print(tab_df)
     '''
     instructions : visualization of pivot with single dataframe
     Params :
@@ -132,7 +132,24 @@ def plot_table_df(dataset, auc, title='untitled', X_label=None, y_label=None,
     '''
     fig, axs = plt.subplots(1, 1, figsize=(13, 9), linewidth=0.1)
 
+
+    if isinstance(dataset, pd.DataFrame):
         table_rows = dataset.columns
+    else:
+        axs.plot(range(len(dataset.index)), dataset.values)
+        fig.subplots_adjust(bottom=0.2)
+        plt.grid()
+        if y_label is not None:
+            plt.ylabel(y_label)
+        if X_label is not None:
+            plt.xlabel(X_label)
+        # plt.vlines(xrange(len(cols))0],y,color='lightgrey',linestyle='--')
+        plt.title(title)
+        if saved_path is not None:
+            plt.savefig(saved_path + title + ".png")
+        plt.show()
+        return saved_path + title + ".png"
+
     table_cols = pd.Series(dataset.index).astype(str).map(lambda x: x.replace(' ', '')).map(
         lambda x : x.replace('0.', '.'))
 
@@ -140,7 +157,10 @@ def plot_table_df(dataset, auc, title='untitled', X_label=None, y_label=None,
     for i in range(len(table_rows)):
         x = range(len(table_cols))
         y = dataset.iloc[:, i]
+        if auc != None:
             axs.plot(x, y, label=str(table_rows[i]) + ' AUC: ' + str(auc[i]))
+        else:
+            axs.plot(x, y, label=str(table_rows[i]))
     # if table should be plot
     if plot_tab:
         if tab_df is None:
@@ -158,7 +178,7 @@ def plot_table_df(dataset, auc, title='untitled', X_label=None, y_label=None,
         plt.xticks([])
     # otherwise, nothing to do here
         the_table.auto_set_font_size(False)
-    the_table.set_fontsize(9)
+        the_table.set_fontsize(8)
     fig.subplots_adjust(bottom=0.2)
     plt.grid()
     if y_label is not None:
@@ -171,7 +191,7 @@ def plot_table_df(dataset, auc, title='untitled', X_label=None, y_label=None,
     if saved_path is not None:
         plt.savefig(saved_path + title + ".png")
     plt.show()
-    return 1
+    return saved_path + title + ".png"
 
 
 

mvp/refit.py

@@ -22,8 +22,6 @@ score = 'score'
 prediction = 'predict'
 
 ############################
-
-
 # 备份df_sample
 #df_sample.to_csv(str(datetime.date.today())+"dhb_samples.xlsx")
 
@@ -61,15 +59,24 @@ predictions ,test_auc = lightgbm.predict(lgbm,df_test,dhb.features,target)
 # 把新的预测结果加入test
 df_test[prediction] = predictions
 
+
+
 ####### allocator cache ############
 applied_from = {'1,214,217,198': '内部', '333': '融360', '159537': '360金融'}
 applied_type = {'1,2':'首贷','1,2,3':'全量客群','1':'首申','2':'复申','3':'复贷'}
 ####################################
 
 ### report
+import os
+os.chdir("E:/bla/model_mvp/")
 
 # plot feature importance
-topnfeat_path = matplot.topN_feature_importance(lgb, lgbm, title="untitled", save_path='./mvp/plots/', topN=20)
+topnfeat_path = matplot.topN_feature_importance(lgb, lgbm, title="untitled", save_path='./mvp/plots/cache/', topN=20)
+
+importanct_feat = pd.DataFrame({
+        'column': dhb.features,
+        'importance': lgbm.feature_importance(),
+    }).sort_values(by='importance',ascending=False).column.tolist()[:3]
 
 # report file
 report_path = "E:/bla/model_mvp/"
@@ -91,21 +98,23 @@ document.add_picture(topnfeat_path)
 document.add_paragraph('univar_chart')
 
 # 遍历目标features画出univarchart
-for i in dhb.features[:3]:
+for i in importanct_feat:
     univar_train = datacal.cal_univar(df_train, i, target, qcut=10)
     univar_val = datacal.cal_univar(df_val, i, target, qcut=10)
     univar_test = datacal.cal_univar(df_test, i, target, qcut=10)
+    tab_df_list = [univar_train,univar_val,univar_test]
     univarChart = matplot.plot_table_list([univar_train,univar_val,univar_test], [1,2,3], datalist_description=None, title= i +' univar Chart', X_label=None, y_label=None,
-                    tab_df_list=None, plot_tab=True,
+                    tab_df_list=tab_df_list, plot_tab=False,
                     saved_path='./mvp/plots/cache/')
-    document.add_picture('./mvp/plots/cache/' + i +' univar Chart' + ".png")
+    document.add_picture(univarChart)
 
 document.add_paragraph('PDP_chart')
 # 遍历目标features 画出对应PDP
-for i in dhb.features[:3]:
+for i in importanct_feat:
     pdp = datacal.cal_pdp(df=df_test, score=prediction, feature=i, qcut=10)
-    pdpChart = matplot.plot_table(pdp,title= i +' PDP Chart',saved_path='./mvp/plots/cache/')
-    document.add_picture('./mvp/plots/cache/' + i +' PDP Chart' + ".png")
+    pdpChart = matplot.plot_table_df(pdp, ['1'], title=i + ' PDP Chart', X_label=None, y_label=None,
+                  tab_df=None, plot_tab=True, saved_path='./mvp/plots/cache/')
+    document.add_picture(pdpChart)
 
 
 
@@ -113,13 +122,20 @@ filetool.saveDocument(document, report_path, report_name)
 
 document.add_paragraph('lift_chart')
 # 遍历给定渠道 & 客群 默认等频画出liftchart
-for channel in applied_from:
-    for type in applied_type:
+try:
+    for channel in ['333','159537','1,214,217,198']:
+        for type in ['1','2','3']:
             df_sliced = df_test[df_test.applied_type.map(lambda x : True if str(x) in type.split(',') else False) & df_test.applied_from.map(lambda x : True if str(x) in channel.split(',') else False)]
-        lift = datacal.cal_liftchart(df_sliced,score=prediction)
-        liftChart = matplot.plot_table(lift, title=i +' lift Chart',saved_path='./mvp/plots/cache')
-        document.add_picture("./mvp/plots/cache" + i + ' lift Chart.png')
-
+            lift_pred = datacal.cal_lift(df_sliced,score=prediction)
+            lift_online = datacal.cal_lift(df_sliced,score=score)
+            #liftChart = matplot.plot_table(lift, title=i +' lift Chart',saved_path='./mvp/plots/cache/')
+            liftChart = matplot.plot_table_list([lift_pred, lift_online], [roc_auc_score(df_test[target],df_test[prediction]),roc_auc_score(df_test[target],df_test[score])], datalist_description=None,
+                                    title= applied_from[channel]+applied_type[type]+ ' lift Chart', X_label=None, y_label=None,
+                                    tab_df_list=tab_df_list, plot_tab=False,
+                                    saved_path='./mvp/plots/cache/')
+            document.add_picture(liftChart)
+except:
+    pass
 
 filetool.saveDocument(document, report_path, report_name)