Mercurial > repos > recetox > matchms_filtering
changeset 19:c5076cc15e8c draft
planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit c626c8db7ba4dd30f85f7086e16e1e2413e36bd8
author | recetox |
---|---|
date | Mon, 22 Apr 2024 08:39:32 +0000 |
parents | 7466cd7204ac |
children | 86d265d2a334 |
files | formatter.py |
diffstat | 1 files changed, 0 insertions(+), 51 deletions(-) [+] |
line wrap: on
line diff
--- a/formatter.py Tue Apr 16 11:24:10 2024 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,51 +0,0 @@ -import click -from matchms.importing import scores_from_json -from pandas import DataFrame - - -def scores_to_dataframe(scores): - """Unpack scores from matchms.scores into two dataframes of scores and matches. - - Args: - scores (matchms.scores): matchms.scores object. - - Returns: - DataFrame: Scores - DataFrame: Matches - """ - data = [] - - for i, (row, col) in enumerate(zip(scores.scores.row, scores.scores.col)): - data.append([scores.queries[col].metadata['compound_name'], scores.references[row].metadata['compound_name'], *scores.scores.data[i]]) - - dataframe = DataFrame(data, columns=['query', 'reference', *scores.scores.score_names]) - - return dataframe - - -def load_data(scores_filename: str) -> DataFrame: - """Load data from filenames and join on compound id. - - Args: - scores_filename (str): Path to json file with serialized scores. - - Returns: - DataFrame: Joined dataframe on compounds containing scores and matches in long format. - """ - scores = scores_from_json(scores_filename) - scores = scores_to_dataframe(scores) - - return scores - - -@click.group(invoke_without_command=True) -@click.option('--sf', 'scores_filename', type=click.Path(exists=True), required=True) -@click.option('--o', 'output_filename', type=click.Path(writable=True), required=True) -def cli(scores_filename, output_filename): - result = load_data(scores_filename) - result.to_csv(output_filename, sep="\t", index=False) - pass - - -if __name__ == '__main__': - cli()