diff formatter.py @ 5:a177ac3c752c draft

planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f79a5b51599254817727bc9028b9797ea994cb4e

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/formatter.py	Tue Jun 27 14:25:01 2023 +0000
@@ -0,0 +1,49 @@
+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
+    """
+    dataframe = DataFrame(columns=['query', 'reference', *scores.scores.score_names])
+
+    for i, (row, col) in enumerate(zip(scores.scores.row, scores.scores.col)):
+        dataframe.loc[i] = [scores.queries[col].metadata['compound_name'], scores.references[row].metadata['compound_name'], *scores.scores.data[i]]
+
+    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
+
+
[e-mail](invoke_without_command=True)
[e-mail]('--sf', 'scores_filename', type=click.Path(exists=True), required=True)
[e-mail]('--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()