experiment

functions/calc_matches.py

@@ -45,25 +45,29 @@ def calc_matches(filtered_df, project_df, similarity_matrix, top_x):
 
     # Take the first k indices to get the top k maximum values
     top_indices = sorted_indices[:top_x]
-
+    st.write(top_indices)
     # Convert flat indices to 2D row and column indices
-    row_indices, col_indices = match_matrix.nonzero()
-    row_indices = row_indices[top_indices]
-    col_indices = col_indices[top_indices]
+    #row_indices, col_indices = match_matrix.nonzero()
+    #row_indices = row_indices[top_indices]
+    #col_indices = col_indices[top_indices]
 
     # Get the values corresponding to the top k indices
     top_values = flat_data[top_indices]
 
-    #top_filtered_df_indices = [filtered_df_index_map[i] for i in col_indices]
-    #top_project_df_indices = [project_df_index_map[i] for i in row_indices]
 
-    st.write(row_indices)
+    # Get the values corresponding to the top k indices
+    top_values = match_matrix[row_indices, col_indices]
+
+    top_filtered_df_indices = [filtered_df_index_map[i] for i in col_indices]
+    top_project_df_indices = [project_df_index_map[i] for i in row_indices]
+
+    st.write(top_filtered_df_indices)
 
     # Create resulting dataframes with top matches and their similarity scores
-    p1_df = filtered_df.loc[row_indices].copy()
+    p1_df = filtered_df.loc[top_filtered_df_indices].copy()
     p1_df['similarity'] = top_values
 
-    p2_df = project_df.loc[col_indices].copy()
+    p2_df = project_df.loc[top_project_df_indices].copy()
     p2_df['similarity'] = top_values
     print("finished calc matches")