added bautifications

modules/result_table.py

@@ -1,4 +1,5 @@
 import streamlit as st
+from st_aggrid import AgGrid, GridOptionsBuilder
 import pandas as pd
 
 def show_table(p1_df, p2_df):
@@ -7,24 +8,44 @@ def show_table(p1_df, p2_df):
         p1_df = p1_df.reset_index(drop=True)
         p2_df = p2_df.reset_index(drop=True)
 
-        for i in range(len(p1_df) - 1, -1, -2):
+        actual_ind = 0
+        for i in range(len(p1_df) - 1, -1, -2): # stepsize because project matchs in both ways and it should only display a match one time
+            actual_ind += 1
             match_df = pd.DataFrame()
             row_from_p1 = p1_df.iloc[[i]]
             row_from_p2 = p2_df.iloc[[i]]
 
+            # transform strings to list
+            row_from_p1["crs_3_code_list"] = [row_from_p1['crs_3_code'].item().split(";")[:-1]]
+            row_from_p2["crs_3_code_list"] = [row_from_p2['crs_3_code'].item().split(";")[:-1]]
+
+            row_from_p1["crs_5_code_list"] = [row_from_p1['crs_3_code'].item().split(";")[:-1]]
+            row_from_p2["crs_5_code_list"] = [row_from_p2['crs_3_code'].item().split(";")[:-1]]
+
+            row_from_p1["sdg_list"] = [row_from_p1['sgd_pred_code'].item()]
+            row_from_p2["sdg_list"] = [row_from_p2['sgd_pred_code'].item()]
+
             # Correctly append rows to match_df
+            st.subheader(f"#{actual_ind}")
+            st.caption(f"Similarity: {round(row_from_p1['similarity'].item(), 4) * 100}%")
             match_df = pd.concat([row_from_p1, row_from_p2], ignore_index=True)
 
+
+
+            #AgGrid(match_df)
+
             st.dataframe(
-                match_df[["similarity", "iati_id", "title_main", "orga_abbreviation", "client", "description_main", "country", "sgd_pred_code", "crs_3_code", "crs_5_code"]],
+                match_df[["iati_id", "title_main", "orga_abbreviation", "client", "description_main", "country", "sdg_list", "crs_3_code_list", "crs_5_code_list"]],
                 use_container_width = True,
                 height = 35 + 35 * len(match_df),
                 column_config={
+                    """
                     "similarity": st.column_config.TextColumn(
                         "Similarity",
                         help="simialrity",
                         disabled=True
                     ),
+                    """
                     "iati_id": st.column_config.TextColumn(
                         "IATI ID",
                         help="IATI Project ID",
@@ -55,20 +76,17 @@ def show_table(p1_df, p2_df):
                         help="Country of project",
                         disabled=True
                     ),
-                    "sgd_pred_code": st.column_config.TextColumn(
+                    "sdg_list": st.column_config.ListColumn(
                         "SDG Prediction",
                         help="Prediction of SDG's",
-                        disabled=True
                     ),
-                    "crs_3_code": st.column_config.TextColumn(
+                    "crs_3_code_list": st.column_config.ListColumn(
                         "CRS 3",
                         help="CRS 3 code given by organization",
-                        disabled=True
                     ),
-                    "crs_5_code": st.column_config.TextColumn(
+                    "crs_5_code_list": st.column_config.ListColumn(
                         "CRS 5",
-                        help="CRS 5 code given by organization",
-                        disabled=True
+                        help="CRS 5 code given by organization"
                     ),
                 },
                 hide_index=True,

requirements.txt

@@ -5,4 +5,5 @@ streamlit-option-menu==0.3.12
 scipy==1.12.0
 faiss-cpu==1.8.0
 faiss-gpu==1.7.2
-sentence-transformers==2.5.1
+sentence-transformers==2.5.1
+streamlit-aggrid==0.3.4.

similarity_page.py

@@ -9,7 +9,6 @@ import streamlit as st
 import pandas as pd
 from scipy.sparse import load_npz
 import pickle
-import faiss
 from sentence_transformers import SentenceTransformer
 from modules.result_table import show_table
 from functions.filter_projects import filter_projects
@@ -129,7 +128,6 @@ COUNTRY_OPTION_LIST = getCountry()
 # LOAD MODEL FROM CACHE FO SEMANTIC SEARCH
 model = load_model()
 embeddings = load_embeddings_and_index()
-#embeddings = []
 
 def show_page():
     st.write(f"Current RAM usage of this app: {get_process_memory():.2f} MB")