Update app.py

app.py

@@ -46,22 +46,28 @@ def get_chunks():
 
     projects_df.drop(columns= ['orga_abbreviation', 'client',
        'orga_full_name', 'country', 
-       'country_flag', 'crs_5_code', 'crs_3_code',
-       'sgd_pred_code'], inplace=True)
+       'country_flag', 'crs_5_code', 'crs_3_code','country_code_list',
+       'sgd_pred_code','crs_5_name', 'crs_3_name', 'sgd_pred_str'], 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)
+    projects_df['source'] = 'IATI'
+    projects_df.rename(columns = {'iati_id':'id','iati_orga_id':'org'}, inplace=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['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.drop(columns = ['filename', 'url', 'name', 'mail', 
+                           'language', 'start_year', 'end_year','poli_trager'], inplace=True)
+    giz_df.rename(columns = {'project_name':'title_main','countries':'country_name',
+                            'client':'org','project_description':'description_main'}, inplace=True)
+    df = pd.concat([projects_df,giz_df],ignore_index=True)
+    print(df.columns)