fix2

mpl_data_plotter.py

@@ -19,15 +19,13 @@ class MatplotlibDataPlotter:
 
     def plot_single_domains(self, num_domains, split_name):
         
-        # fig = plt.gcf()
-        #fig.set_size_inches(10, 5)
-        selected_region_ids = self.num_domains_in_region_df.loc[
-            self.num_domains_in_region_df.num_domains >= num_domains, 
-            'cds_region_id'].values
-        single_df_subset = self.single_df.loc[self.single_df.cds_region_id.isin(selected_region_ids)]
+        # selected_region_ids = self.num_domains_in_region_df.loc[
+        #     self.num_domains_in_region_df.num_domains >= num_domains, 
+        #     'cds_region_id'].values
+        # single_df_subset = self.single_df.loc[self.single_df.cds_region_id.isin(selected_region_ids)]
         
         return self.single_domains_fig
-        split_name = 'stratified'
+        # split_name = 'stratified'
         column_name = f'cosine_similarity_{split_name}'
         # single_df_subset = single_df.loc[single_df.dom_location_len >= num_domains]
         selected_keyword_index = single_df_subset.groupby('cds_region_id').agg(
@@ -66,12 +64,12 @@ class MatplotlibDataPlotter:
         return fig # plt.gcf()
 
     def plot_pair_domains(self, num_domains, split_name):
-        selected_region_ids = self.num_domains_in_region_df.loc[
-            self.num_domains_in_region_df.num_domains >= num_domains, 
-            'cds_region_id'].values
-        pair_df_subset = self.pair_df.loc[self.pair_df.cds_region_id.isin(selected_region_ids)]
+        # selected_region_ids = self.num_domains_in_region_df.loc[
+        #     self.num_domains_in_region_df.num_domains >= num_domains, 
+        #     'cds_region_id'].values
+        # pair_df_subset = self.pair_df.loc[self.pair_df.cds_region_id.isin(selected_region_ids)]
         return self.pair_domains_fig
-        split_name = 'stratified'
+        # split_name = 'stratified'
         column_name = f'cosine_similarity_{split_name}'
         # pair_df_subset = pair_df.loc[pair_df.dom_location_len >= num_domains]
         selected_keyword_index = pair_df_subset.groupby('cds_region_id').agg(