show

functions/filter_single.py

@@ -5,5 +5,18 @@ def contains_code(crs_codes, code_list):
     codes = str(crs_codes).split(';')
     return any(code in code_list for code in codes)
 
-def filter_projects(df, crs3_list, crs5_list, sdg_str, country_code_list, orga_code_list, query, model, embeddings, TOP_X_PROJECTS=30):
-    # Check if filters where not all should be selected are empty
+def filter_projects(df, country_code_list, orga_code_list):
+    # FILTER COUNTRY
+    if country_code_list != []:
+        country_filtered_df = pd.DataFrame()
+        for c in country_code_list:
+            c_df = df[df["country"].str.contains(c, na=False)]
+            country_filtered_df = pd.concat([country_filtered_df, c_df], ignore_index=False)
+        
+        df = country_filtered_df
+    
+    # FILTER ORGANIZATION
+    if orga_code_list != []:
+        df = df[df['orga_abbreviation'].isin(orga_code_list)]
+    
+    return df

similarity_page.py

@@ -13,6 +13,7 @@ from sentence_transformers import SentenceTransformer
 from modules.multimatch_result_table import show_multi_table
 from modules.singlematch_result_table import show_single_table
 from functions.filter_projects import filter_projects
+from functions.filter_single import filter_single
 from functions.calc_matches import calc_matches
 from functions.same_country_filter import same_country_filter
 from functions.single_similar import find_similar
@@ -239,7 +240,6 @@ def show_multi_matching_page():
     orga_code_list = [option.split("(")[1][:-1].lower() for option in orga_option]
 
     # FILTER DF WITH SELECTED FILTER OPTIONS
-    
     TOP_X_PROJECTS = 30
     filtered_df = filter_projects(projects_df, crs3_list, crs5_list, sdg_str, country_code_list, orga_code_list, query, model, embeddings, TOP_X_PROJECTS)
     if isinstance(filtered_df, pd.DataFrame) and len(filtered_df) != 0:
@@ -338,6 +338,19 @@ def show_single_matching_page():
         selected_index = search_list.index(project_option)
         st.dataframe(projects_df.iloc[selected_index])
 
-        top_projects_df = find_similar(selected_index, sim_matrix, projects_df, 10)
-        show_single_table(top_projects_df)
+        # COUNTRY CODES LIST
+        country_code_list = [option[-3:-1] for option in country_option_s]
+
+        # ORGANIZATION CODES LIST
+        orga_code_list = [option.split("(")[1][:-1].lower() for option in orga_option_s]
+
+        TOP_X_PROJECTS = 10
+        filtered_df_s = filter_single(projects_df, country_code_list, orga_code_list)
+        st.dataframe(filtered_df_s)
+
+        #if isinstance(filtered_df_s, pd.DataFrame) and len(filtered_df_s) != 0:
+
+
+        #top_projects_df = find_similar(selected_index, sim_matrix, projects_df, 10)
+        #show_single_table(top_projects_df)