Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
| import numpy as np | |
| from scipy.sparse import csr_matrix | |
| """ | |
| Function to calculate the multi project matching results | |
| The Multi-Project Matching Feature uncovers synergy opportunities among various development banks and organizations by facilitating the search for similar projects | |
| within a selected filter setting (filtered_df) and all projects (project_df). | |
| """ | |
| def calc_multi_matches(filtered_df, project_df, similarity_matrix, top_x, identical_country=False): | |
| """ | |
| filtered_df: df with applied filters | |
| project_df: df with all projects | |
| similarity_matrix: np sparse matrix with all similarities between projects | |
| top_x: top x project which should be displayed | |
| identical_country: boolean flag to filter matches where country is identical | |
| """ | |
| # convert npz sparse matrix into csr matrix | |
| if not isinstance(similarity_matrix, csr_matrix): | |
| similarity_matrix = csr_matrix(similarity_matrix) | |
| # extract indices of the projects | |
| filtered_indices = filtered_df.index.to_list() | |
| project_indices = project_df.index.to_list() | |
| # size down the matrix to only projects within the filter and convert to dense matrix and flatten it | |
| match_matrix = similarity_matrix[project_indices, :][:, filtered_indices] # row / column | |
| dense_match_matrix = match_matrix.toarray() | |
| flat_matrix = dense_match_matrix.flatten() | |
| # get the indices of the top X values in the flattened matrix | |
| top_indices = np.argsort(flat_matrix)[-top_x:] | |
| # Convert flat indices back to 2D indices | |
| top_2d_indices = np.unravel_index(top_indices, dense_match_matrix.shape) | |
| # Extract the corresponding values | |
| top_values = flat_matrix[top_indices] | |
| # Prepare the result with row and column indices from original dataframes | |
| org_rows = [] | |
| org_cols = [] | |
| for value, row, col in zip(top_values, top_2d_indices[0], top_2d_indices[1]): | |
| original_row_index = project_indices[row] | |
| original_col_index = filtered_indices[col] | |
| org_rows.append(original_row_index) | |
| org_cols.append(original_col_index) | |
| # create two result dataframes | |
| """ | |
| p1_df: first results of match | |
| p2_df: matching result | |
| matches are displayed through the indices of p1 and p2 dfs | |
| match1 p1_df.iloc[0] & p2_df.iloc[0] | |
| match2 p1_df.iloc[1] & p2_df.iloc[1] | |
| """ | |
| p1_df = filtered_df.loc[org_cols].copy() | |
| p1_df['similarity'] = top_values | |
| # filter out rows with similarity score less than 50 | |
| p1_df = p1_df[p1_df['similarity'] > 0.50] | |
| p2_df = project_df.loc[org_rows].copy() | |
| p2_df['similarity'] = top_values | |
| p2_df = p2_df[p2_df['similarity'] > 0.50] | |
| if identical_country: | |
| # Reset indices before comparison | |
| p1_df = p1_df.reset_index(drop=True) | |
| p2_df = p2_df.reset_index(drop=True) | |
| # Filter to only include matches with identical countries | |
| identical_country_mask = p1_df['country'] == p2_df['country'] | |
| p1_df = p1_df[identical_country_mask] | |
| p2_df = p2_df[identical_country_mask] | |
| # return both results df with matching projects | |
| return p1_df, p2_df | |