experiment

functions/calc_matches.py

@@ -43,18 +43,14 @@ def calc_matches(filtered_df, project_df, similarity_matrix, top_x):
     st.write(similarity_matrix.shape)
 
     # Ensure the matrix is in a suitable format for manipulation
-    #if not isinstance(similarity_matrix, csr_matrix):
-        #similarity_matrix = csr_matrix(similarity_matrix)
+    if not isinstance(similarity_matrix, csr_matrix):
+        similarity_matrix = csr_matrix(similarity_matrix)
 
     # Get indices from dataframes
     filtered_df_indices = filtered_df.index.to_list()
     project_df_indices = project_df.index.to_list()
 
-    # Efficiently zero out diagonal elements if necessary
-    if np.array_equal(filtered_df_indices, project_df_indices):
-        similarity_matrix = lil_matrix(similarity_matrix)
-        similarity_matrix.setdiag(0)
-        similarity_matrix = csr_matrix(similarity_matrix)
+    similarity_matrix.setdiag(0)
 
     # Select submatrix based on indices from both dataframes
     match_matrix = similarity_matrix[filtered_df_indices, :][:, project_df_indices]