Created
December 20, 2020 04:33
-
-
Save alinazhanguwo/3b6c11cabbbd74c365d2f23efede2ec2 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| def get_matches_df(sparse_matrix, name_vector, top=100): | |
| non_zeros = sparse_matrix.nonzero() | |
| sparserows = non_zeros[0] | |
| sparsecols = non_zeros[1] | |
| if top: | |
| nr_matches = top | |
| else: | |
| nr_matches = sparsecols.size | |
| left_side = np.empty([nr_matches], dtype=object) | |
| right_side = np.empty([nr_matches], dtype=object) | |
| similairity = np.zeros(nr_matches) | |
| for index in range(0, nr_matches): | |
| left_side[index] = name_vector[sparserows[index]] | |
| right_side[index] = name_vector[sparsecols[index]] | |
| similairity[index] = sparse_matrix.data[index] | |
| return pd.DataFrame({'TITLE': left_side, | |
| 'SIMILAR_TITLE': right_side, | |
| 'similairity_score': similairity}) | |
| matches_df = pd.DataFrame() | |
| matches_df = get_matches_df(matches, df['TITLE'], top=10000) | |
| # Remove all exact matches | |
| matches_df = matches_df[matches_df['similairity_score'] < 0.99999] | |
| matches_df.sample(10) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
matches_df = get_matches_df(matches, df['TITLE'], top=10000) - what does top=10000 mean in this?