experiment

functions/calc_matches.py

@@ -5,10 +5,6 @@ import streamlit as st
 
 # multi_project_matching
 def calc_matches(filtered_df, project_df, similarity_matrix, top_x):
-    st.write(filtered_df.shape)
-    st.write(project_df.shape)
-    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)
@@ -16,12 +12,33 @@ def calc_matches(filtered_df, project_df, similarity_matrix, top_x):
     filtered_indices = filtered_df.index.to_list()
     project_indices = project_df.index.to_list()
 
-    match_matrix = similarity_matrix[project_indices, :][:, filtered_indices]
+    match_matrix = similarity_matrix[project_indices, :][:, filtered_indices] # row / column
 
     dense_match_matrix = match_matrix.toarray()
     
     st.write(dense_match_matrix.shape)
 
+    flat_matrix = dense_match_matrix.flatten()
+    
+    # Get the indices of the top 15 values in the flattened matrix
+    top_15_indices = np.argsort(flat_matrix)[-top_x:][::-1]
+
+    # Convert flat indices back to 2D indices
+    top_15_2d_indices = np.unravel_index(top_15_indices, dense_match_matrix.shape)
+    
+    # Extract the corresponding values
+    top_15_values = flat_matrix[top_15_indices]
+
+    # Prepare the result with row and column indices from original dataframes
+    top_15_matches = []
+    for value, row, col in zip(top_15_values, top_15_2d_indices[0], top_15_2d_indices[1]):
+        original_row_index = project_indices[row]
+        original_col_index = filtered_indices[col]
+        top_15_matches.append((value, original_row_index, original_col_index))
+    
+    st.write(top_15_matches)
+
+
     """
     p1_df = filtered_df.loc[top_col_indices].copy()
     p1_df['similarity'] = top_values