functions/calc_matches.py

import pandas as pd
import numpy as np

def calc_matches(filtered_df, project_df, similarity_matrix, top_x):
    # matching project2 can be nay project
    # indecies (rows) = project1
    # columns = project2
    # -> find matches

    # filter out all row considering the filter
    filtered_df_indecies_list = filtered_df.index
    project_df_indecies_list = project_df.index

    np.fill_diagonal(similarity_matrix, 0)
    match_matrix = similarity_matrix[filtered_df_indecies_list, :][:, project_df_indecies_list]

    best_matches_list = np.argsort(match_matrix, axis=None)

    if len(best_matches_list) < top_x:
        top_x = len(best_matches_list)

    # get row (project1) and column (project2) with highest similarity in filtered df
    top_indices = np.unravel_index(best_matches_list[-top_x:], match_matrix.shape)

    # get the corresponding similarity values
    top_values = match_matrix[top_indices]

    p1_df = filtered_df.iloc[top_indices[0]]
    p1_df["similarity"] = top_values
    p2_df = project_df.iloc[top_indices[1]]
    p2_df["similarity"] = top_values

    return p1_df, p2_df