Update app.py

app.py

@@ -42,26 +42,29 @@ def get_chunks():
     projects_df = pd.merge(projects_df, sector_df, on='iati_id', how='inner')
     projects_df = pd.merge(projects_df, status_df, on='iati_id', how='inner')
     projects_df = pd.merge(projects_df, texts_df, on='iati_id', how='inner')
-    giz_df = projects_df[projects_df.client.str.contains('bmz')].reset_index(drop=True)
+    projects_df = projects_df[projects_df.client.str.contains('bmz')].reset_index(drop=True)
 
-    giz_df.drop(columns= ['orga_abbreviation', 'client',
+    projects_df.drop(columns= ['orga_abbreviation', 'client',
        'orga_full_name', 'country', 
        'country_flag', 'crs_5_code', 'crs_3_code',
        'sgd_pred_code'], inplace=True)
+    print(projects_df.columns)
+    projects_df['text_size'] = projects_df.apply(lambda x: len((x['title_main'] + x['description_main']).split()), axis=1)
+    projects_df['chunks'] = projects_df.apply(lambda x:create_chunks(x['title_main'] + x['description_main']),axis=1)
+    projects_df = projects_df.explode(column=['chunks'], ignore_index=True)
 
     #### code for eading the giz_worldwide data
-    #giz_df = pd.read_json('iati_files/data_giz_website.json')
-    #giz_df = giz_df.rename(columns={'content':'project_description'})
+    giz_df = pd.read_json('iati_files/data_giz_website.json')
+    giz_df = giz_df.rename(columns={'content':'project_description'})
     
 
-    #giz_df['text_size'] = giz_df.apply(lambda x: len((x['project_name'] + x['project_description']).split()), axis=1)
-    #giz_df['chunks'] = giz_df.apply(lambda x:create_chunks(x['project_name'] + x['project_description']),axis=1)
-    #giz_df = giz_df.explode(column=['chunks'], ignore_index=True)
+    giz_df['text_size'] = giz_df.apply(lambda x: len((x['project_name'] + x['project_description']).split()), axis=1)
+    giz_df['chunks'] = giz_df.apply(lambda x:create_chunks(x['project_name'] + x['project_description']),axis=1)
+    giz_df = giz_df.explode(column=['chunks'], ignore_index=True)
+    print(giz_df.columns)
 
 
-    giz_df['text_size'] = giz_df.apply(lambda x: len((x['title_main'] + x['description_main']).split()), axis=1)
-    giz_df['chunks'] = giz_df.apply(lambda x:create_chunks(x['title_main'] + x['description_main']),axis=1)
-    giz_df = giz_df.explode(column=['chunks'], ignore_index=True)
+    
 
     placeholder= []
     for i in range(len(giz_df)):