experiment

functions/calc_matches.py

@@ -13,89 +13,13 @@ def calc_matches(filtered_df, project_df, similarity_matrix, top_x):
     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()
+    filtered_indices = filtered_df.index.to_list()
+    project_indices = project_df.index.to_list()
 
-    # Create mapping dictionaries
-    filtered_df_index_map = {i: index for i, index in enumerate(filtered_df_indices)}
-    project_df_index_map = {i: index for i, index in enumerate(project_df_indices)}
+    st.write(filtered_indices[:100])
+    st.write(project_indices[:100])
 
-    # Select submatrix based on indices from both dataframes
-    match_matrix = similarity_matrix[filtered_df_indices, :][:, project_df_indices]
-
-    coo = match_matrix.tocoo()
-
-    data = coo.data
-    row_indices = coo.row
-    col_indices = coo.col
-
-    top_n = 15
-    if len(data) < top_n:
-        top_n = len(data) 
-    top_n_indices = np.argsort(data)[-top_n:][::-1]
-
-    top_n_percentages = data[top_n_indices]
-    top_n_row_indices = row_indices[top_n_indices]
-    top_n_col_indices = col_indices[top_n_indices]
-
-    st.write("row")
-    st.write(filtered_df_index_map)
-    st.write(top_n_row_indices)
-    original_row_indices = [project_df_index_map[i].value for i in top_n_row_indices]
-    st.write(original_row_indices)
-
-    st.write("col")
-    st.write(top_n_col_indices)
-    original_col_indices = [filtered_df_index_map[i] for i in top_n_col_indices]
-    st.write(original_col_indices)
-
-    # Get the linear indices of the top 'top_x' values
-    # (flattened index to handle the sparse matrix more effectively)
-    #linear_indices = np.argsort(match_matrix.data)[-top_x:]
-    #if len(linear_indices) < top_x:
-    #    top_x = len(linear_indices)
-
-    # Convert flat indices to 2D indices using the shape of the submatrix
-    #top_indices = np.unravel_index(linear_indices, match_matrix.shape)
-
-    # Get the corresponding similarity values
-    #top_values = match_matrix.data[linear_indices]
-
-    #flat_data = match_matrix.data
-
-    # Get the indices that would sort the data array in descending order
-    #sorted_indices = np.argsort(flat_data)[::-1]
-
-    # Take the first k indices to get the top k maximum values
-    #top_indices = sorted_indices[:top_x]
-    #top_row_indices = []
-    #top_col_indices = []
-
-    #for idx in top_indices:
-    #    row, col = np.unravel_index(idx, match_matrix.shape)
-    #    top_row_indices.append(row)
-    #    top_col_indices.append(col)
-
-    #st.write(top_col_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]
-
-    # Get the values corresponding to the top k indices
-    #top_values = flat_data[top_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 top_col_indices]
-    #top_project_df_indices = [project_df_index_map[i] for i in top_row_indices]
-
-    #st.write(top_filtered_df_indices)
-
-    # Create resulting dataframes with top matches and their similarity scores
+    """
     p1_df = filtered_df.loc[top_col_indices].copy()
     p1_df['similarity'] = top_values
 
@@ -104,4 +28,4 @@ def calc_matches(filtered_df, project_df, similarity_matrix, top_x):
     print("finished calc matches")
 
     return p1_df, p2_df
-
+    """