Add top count option for Plot_Feature_importances

minjk-bl · minjk-bl · commit 6d4492d50a81 · 2022-06-21T10:36:36.000+09:00
diff --git a/js/m_ml/ModelInfo.js b/js/m_ml/ModelInfo.js
@@ -425,11 +425,12 @@ define([
                 'plot_feature_importances': {
                     name: 'plot_feature_importances',
                     label: 'Plot feature importances',
-                    code: "vp_plot_feature_importances(${model}, ${fi_featureData}${sort})",
+                    code: "vp_plot_feature_importances(${model}, ${fi_featureData}${sort}${top_count})",
                     description: 'Draw feature_importances_',
                     options: [
                         { name: 'fi_featureData', label: 'Feature Data', component: ['data_select'], var_type: ['DataFrame', 'Series', 'ndarray', 'list', 'dict'], value: 'X_train' },
-                        { name: 'sort', label: 'Sort data', component: ['bool_checkbox'], value: true, usePair: true }
+                        { name: 'sort', label: 'Sort data', component: ['bool_checkbox'], value: true, usePair: true },
+                        { name: 'top_count', label: 'Top count', component: ['input_number'], min: 0, max: 5, usePair: true },
                     ]
                 }
             }
diff --git a/python/userCommand.py b/python/userCommand.py
@@ -81,11 +81,16 @@ def vp_create_feature_importances(model, X_train=None, sort=False):
 ######
 # Visual Python: Machine Learning > Model Info
 ######
-def vp_plot_feature_importances(model, X_train=None, sort=False):
+def vp_plot_feature_importances(model, X_train=None, sort=False, top_count=0):
     df_i = vp_create_feature_importances(model, X_train, sort)
                         
-    if sort: df_i['Percentage'].sort_values().plot(kind='barh')
-    else: df_i['Percentage'].plot(kind='barh')
+    if sort: 
+        if top_count > 0:
+            df_i['Percentage'].sort_values().tail(top_count).plot(kind='barh')
+        else:
+            df_i['Percentage'].sort_values().plot(kind='barh')
+    else: 
+        df_i['Percentage'].plot(kind='barh')
     _vp_plt.xlabel('Feature importance Percentage')
     _vp_plt.ylabel('Features')
                         

Original file line number	Diff line number	Diff line change
`@@ -425,11 +425,12 @@ define([`
`425`	`425`	`'plot_feature_importances': {`
`426`	`426`	`name: 'plot_feature_importances',`
`427`	`427`	`label: 'Plot feature importances',`
`428`		`- code: "vp_plot_feature_importances(${model}, ${fi_featureData}${sort})",`
	`428`	`+ code: "vp_plot_feature_importances(${model}, ${fi_featureData}${sort}${top_count})",`
`429`	`429`	`description: 'Draw feature_importances_',`
`430`	`430`	`options: [`
`431`	`431`	`{ name: 'fi_featureData', label: 'Feature Data', component: ['data_select'], var_type: ['DataFrame', 'Series', 'ndarray', 'list', 'dict'], value: 'X_train' },`
`432`		`- { name: 'sort', label: 'Sort data', component: ['bool_checkbox'], value: true, usePair: true }`
	`432`	`+ { name: 'sort', label: 'Sort data', component: ['bool_checkbox'], value: true, usePair: true },`
	`433`	`+ { name: 'top_count', label: 'Top count', component: ['input_number'], min: 0, max: 5, usePair: true },`
`433`	`434`	`]`
`434`	`435`	`}`
`435`	`436`	`}`