errors in summary plot fixed

explainX · Jun 24, 2020 · d2dcaf9 · d2dcaf9
1 parent 07887a2
commit d2dcaf9
Show file tree

Hide file tree

Showing 4 changed files with 32 additions and 17 deletions.
diff --git a/lib/__pycache__/calculate_shap.cpython-37.pyc b/lib/__pycache__/calculate_shap.cpython-37.pyc
diff --git a/lib/plotly_graphs.py b/lib/plotly_graphs.py
@@ -4,16 +4,17 @@
 from shap_pdp import *
 from summary_plot import *
 from data_for_shap_graphs import *
+import plotly.graph_objects as go
+
 
 class plotly_graphs():
     def __init__(self):
         super(plotly_graphs, self).__init__()
-        self.data= data_for_shap_graphs()
+        self.data = data_for_shap_graphs()
 
         # save all important variables here.
 
-
-    def feature_importance(self,  df):
+    def feature_importance(self, df):
         df2 = self.data.feature_importance(df)
 
         names = list(df2["VariableName"])
@@ -24,7 +25,8 @@ def feature_importance(self,  df):
 
         df2["VariableName"] = new_names
 
-        feature_importance = px.bar(df2, x='Impact_Value', y="VariableName", orientation='h', title='Feature Importance',)
+        feature_importance = px.bar(df2, x='Impact_Value', y="VariableName", orientation='h',
+                                    title='Feature Importance', )
         return feature_importance, df2
 
     def feature_impact(self, df):
@@ -45,21 +47,31 @@ def feature_impact(self, df):
 
     def summary_plot(self, df):
         df2 = self.data.summary_plot(df)
+        # summary_plot = go.Figure()
+
 
+        # summary_plot.add_trace(go.Scattergl(x=df2['xaxis'], y=df2['yaxis'],
+        #                                     mode='markers',hovertext=df2['hover'],
+        #                                     marker=dict(color=list(df2['color']),showscale=True,autocolorscale=False,
+        #                                                 cauto=False)))
         summary_plot = px.scatter(df2, x="xaxis", y="yaxis", color="color", hover_data=["hover"])
 
         return summary_plot, df2
 
     def partial_dependence_plot(self, df, v1, v2, v3):
         pdp = shap_pdp()
         df = pdp.find(df)
-        g= px.scatter(df, x=v1, y=v2, color=v3)
+        g = go.Figure()
+        print("new")
+        # g.add_trace(go.Scattergl(x=df[v1], y=df[v2], mode='markers',showlegend=True,
+        #                                     marker=dict(color=list(df[v3]),
+        #                                                 autocolorscale=False,
+        #                                                 cauto=False
+        #                                                 )))
+
+        g = px.scatter(df, x=v1, y=v2, color=v3)
         return g, df
 
-
     def distributions(self, df, variable_name):
-        graph= px.histogram(df, x=variable_name, marginal="box")
+        graph = px.histogram(df, x=variable_name, marginal="box")
         return graph
-
-
-
diff --git a/lib/rescale_numeric_feature.py b/lib/rescale_numeric_feature.py
@@ -99,9 +99,10 @@ def add_col_rescaled(self, df):
 
         for nc in numeric_columns:
             # get min and max
-            mini, maxi = self.get_min_max(df_describe, nc)
+            if nc in df_describe:
+                mini, maxi = self.get_min_max(df_describe, nc)
 
-            df[nc + "_rescaled"] = (df[nc] - mini) / (maxi - mini) * 10
+                df[nc + "_rescaled"] = (df[nc] - mini) / (maxi - mini) * 10
 
         for cc in categorical_columns:
             df[cc + "_rescaled"] = 0

diff --git a/lib/summary_plot.py b/lib/summary_plot.py
@@ -33,11 +33,13 @@ def rearrange_dataframe(self, df_re ):
         df_final = pd.DataFrame()
 
         for v in self.original_columns:
-            df_single = df_re[[v, v + '_rescaled', v + '_impact']]
-            df_single["variable_name"] = v
-            df_single.columns = ['hover', 'color', 'xaxis', 'yaxis']
-            df_final = pd.concat([df_final, df_single])
-
+            try:
+                df_single = df_re[[v, v + '_rescaled', v + '_impact']]
+                df_single["variable_name"] = v
+                df_single.columns = ['hover', 'color', 'xaxis', 'yaxis']
+                df_final = pd.concat([df_final, df_single])
+            except Exception as e:
+                pass
         return df_final