Mercurial > repos > bgruening > flexynesis_utils

comparison index_to_name.py @ 3:f413f828ef30 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/flexynesis commit 6b520305ec30e6dc37eba92c67a5368cea0fc5ad
author bgruening
date Wed, 23 Jul 2025 07:50:03 +0000
parents e5ecfffcfe45
children
comparison
equal deleted inserted replaced
2:e5ecfffcfe45 3:f413f828ef30
1 #!/usr/bin/env python 1 #!/usr/bin/env python
2 2
3 import sys 3 import sys
4 from pathlib import Path
4 5
5 import pandas as pd 6 import pandas as pd
6 7
7 8
8 def get_column_name(file_path, index): 9 def get_column_names(file_path, indices):
9 """ 10 """
10 Get the column name based on an index from a tabular file. 11 Get column names based on multiple indices from a tabular file.
11 """ 12 """
12 data = pd.read_csv(file_path, sep=",") 13 try:
13 index = index - 1 # Convert to zero-based index 14 file_ext = Path(file_path).suffix.lower()
14 if index < 0 or index >= len(data.columns): 15 sep = ',' if file_ext == '.csv' else '\t'
15 print(f"Error: Index {index+1} is out of range. File has {len(data.columns)} columns (1-{len(data.columns)}).") 16
16 return None 17 if file_ext in ['.csv', '.tsv', '.txt', '.tab', '.tabular']:
17 return data.columns[index].strip() 18 data = pd.read_csv(file_path, sep=sep)
19 else:
20 raise ValueError(f"Unsupported file extension: {file_ext}")
21
22 except Exception as e:
23 raise ValueError(f"Error loading data from {file_path}: {e}") from e
24
25 column_names = []
26
27 for index in indices:
28 zero_based_index = index - 1 # Convert to zero-based index
29 if zero_based_index < 0 or zero_based_index >= len(data.columns):
30 print(f"Error: Index {index} is out of range. File has {len(data.columns)} columns (1-{len(data.columns)}).")
31 return None
32 column_names.append(data.columns[zero_based_index].strip())
33
34 return column_names
18 35
19 36
20 if __name__ == "__main__": 37 if __name__ == "__main__":
21 38
22 file_path = sys.argv[1] 39 file_path = sys.argv[1]
23 index = int(sys.argv[2]) 40 indices_str = sys.argv[2]
24 41
25 print(get_column_name(file_path, index)) 42 # Parse comma-separated indices
43 try:
44 indices = [int(i.strip()) for i in indices_str.split(',')]
45 except ValueError:
46 print("Error: All indices must be integers.")
47 sys.exit(1)
48
49 result = get_column_names(file_path, indices)
50 if result is not None:
51 print(','.join(result))