优化plot

data/graph/drawplot.py

@@ -27,21 +27,30 @@ def liftchart(df,x,y,classes='',bin=10,title='',xlabel='',ylabel=''):
     '''
 
     # #== 单个TODO 待输出
-    # df_fig1=pd.pivot_table(df_out, index=classes, columns=['lbl', 'grid'],
-    #                values=['count'], aggfunc=['mean'])
-    plt.cla()
+    plt.close('all')
     if classes !='':
         df_out = datacal.cal_accume(df, x, y, bin, classes=[classes])
+        #== 显示样本数量
+        df_fig = pd.pivot_table(df_out, index=classes, columns=['lbl', 'grid'],
+                                 values=['count'], aggfunc=['mean'])
+        df_fig=df_fig['mean']['count']
+        #== 行数
+        rows=df_fig.index.tolist()
+        n_rows=len(rows)
+        # 列数
+        cols=df_fig.columns.levels[0].categories.to_tuples().tolist()
+        n_cols=len(cols)
+        cell_text=df_fig.values.tolist()
         plt.subplot(2, 1,1)
         draw_lineplot(df_out,'grid','mean',hue=classes,title=title,xlabel=xlabel,ylabel=ylabel)
         plt.subplot(2, 1, 2)
-        draw_lineplot(df_out,'grid','acmMean',hue=classes,title=title,xlabel=xlabel,ylabel=ylabel)
+        draw_lineplot(df_out,'grid','acmMean',hue=classes,title=title+'累计',xlabel=xlabel,ylabel=ylabel)
     else :
         df_out = datacal.cal_accume(df, x, y, bin)
         plt.subplot(2, 1, 1)
         draw_lineplot(df_out, 'grid','mean', title=title, xlabel=xlabel, ylabel=ylabel)
         plt.subplot(2, 1, 2)
-        draw_lineplot(df_out, 'grid','acmMean', title=title, xlabel=xlabel, ylabel=ylabel)
+        draw_lineplot(df_out, 'grid','acmMean', title=title+'累计', xlabel=xlabel, ylabel=ylabel)
     plt.tight_layout()
     # plt.show()
     return plt
@@ -54,7 +63,7 @@ def univarchart(df,x,y,bin=10,classes='',title='',xlabel='',ylabel=''):
     :param df:
     :return:
     '''
-    plt.cla()
+    plt.close('all')
     plt.subplot(1, 1, 1)
     if classes !='':
         df_out = datacal.cal_univar(df, x, y, bin, classes=[classes])
@@ -71,7 +80,7 @@ def pdpchart(df,x,y,bin=10,classes='',title='',xlabel='模型分',ylabel='逾期
     :param df:
     :return:
     '''
-    plt.cla()
+    plt.close('all')
     plt.subplot(1, 1, 1)
 
     if classes !='':
@@ -83,21 +92,6 @@ def pdpchart(df,x,y,bin=10,classes='',title='',xlabel='模型分',ylabel='逾期
     # plt.show()
     return plt
 
-'''
-双坐标轴
-'''
-def draw_lineplot_doubleaxes(df,x,y1,y2,y1_hue='',y2_hue='',title=''):
-    '''
-    :param df:
-    :param x:
-    :param y1:
-    :param y2:
-    :param y1_hue:y1 轴分类
-    :param y2_hue:y2 轴分类
-    :param title:
-    :return:
-    '''
-
 
 def draw_barplot(df,x,y,hue='',title=''):
     '''
@@ -111,9 +105,7 @@ def draw_barplot(df,x,y,hue='',title=''):
     pltz = PyplotZ()
     pltz.enable_chinese()
     fig = plt.figure()
-    # ax = fig.add_subplot(1, 1, 1)
-    plt.cla()
-
+    plt.close('all')
     sns.set(style="whitegrid")
     fig = plt.figure(figsize=(6, 4))
     ax = fig.add_subplot(1, 1, 1)

mvp/xgbreport.py

@@ -26,10 +26,10 @@ 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)
+    # 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)]
@@ -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)