Mercurial > repos > recetox > aplcms_to_ramclustr_converter
comparison aplcms_to_ramclustr_converter.py @ 0:c6c0f6027e34 draft default tip
"planemo upload for repository https://github.com/RECETOX/galaxytools/tools/aplcms_to_ramclustr_converter/ commit 4d2ac914c951166e386a94d8ebb8cb1becfac122"
| author | recetox |
|---|---|
| date | Tue, 22 Mar 2022 16:06:28 +0000 |
| parents | |
| children |
comparison
equal
deleted
inserted
replaced
| -1:000000000000 | 0:c6c0f6027e34 |
|---|---|
| 1 #!/usr/bin/env python | |
| 2 | |
| 3 import argparse | |
| 4 import sys | |
| 5 | |
| 6 import pandas as pd | |
| 7 | |
| 8 | |
| 9 parser = argparse.ArgumentParser() | |
| 10 parser.add_argument("--dataframe", help="Parquet dataframe") | |
| 11 parser.add_argument('output') | |
| 12 args = parser.parse_args() | |
| 13 | |
| 14 | |
| 15 def main(): | |
| 16 featureTable = pd.read_parquet(args.dataframe) | |
| 17 | |
| 18 # Concatenate "mz" and "rt" columns; select relevant columns; pivot the table | |
| 19 featureTable["mz_rt"] = featureTable["mz"].astype(str) + "_" + featureTable["rt"].astype(str) | |
| 20 featureTable = featureTable[["sample", "mz_rt", "sample_intensity"]] | |
| 21 featureTable = pd.pivot_table(featureTable, columns="mz_rt", index="sample", values="sample_intensity") | |
| 22 | |
| 23 try: | |
| 24 featureTable.to_csv(args.output, sep=',') | |
| 25 msg = f"Dataset of {len(featureTable)} samples is converted to a feature-by-sample table" | |
| 26 print(msg, file=sys.stdout) | |
| 27 return 0 | |
| 28 except Exception: | |
| 29 print("Could not write the data", file=sys.stdout) | |
| 30 return 1 | |
| 31 | |
| 32 | |
| 33 if __name__ == "__main__": | |
| 34 main() |