Mercurial > repos > bgruening > sklearn_train_test_eval
comparison label_encoder.py @ 11:caf7d2b71a48 draft
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit ea12f973df4b97a2691d9e4ce6bf6fae59d57717"
author | bgruening |
---|---|
date | Sat, 01 May 2021 01:47:26 +0000 |
parents | |
children | 2eb5c017958d |
comparison
equal
deleted
inserted
replaced
10:a9e0b963b7bb | 11:caf7d2b71a48 |
---|---|
1 import argparse | |
2 import json | |
3 import warnings | |
4 | |
5 import numpy as np | |
6 import pandas as pd | |
7 from sklearn.preprocessing import LabelEncoder | |
8 | |
9 | |
10 def main(inputs, infile, outfile): | |
11 """ | |
12 Parameter | |
13 --------- | |
14 input : str | |
15 File path to galaxy tool parameter | |
16 | |
17 infile : str | |
18 File paths of input vector | |
19 | |
20 outfile : str | |
21 File path to output vector | |
22 | |
23 """ | |
24 warnings.simplefilter('ignore') | |
25 | |
26 with open(inputs, 'r') as param_handler: | |
27 params = json.load(param_handler) | |
28 | |
29 input_header = params['header0'] | |
30 header = 'infer' if input_header else None | |
31 | |
32 input_vector = pd.read_csv(infile, sep='\t', header=header) | |
33 | |
34 le = LabelEncoder() | |
35 | |
36 output_vector = le.fit_transform(input_vector) | |
37 | |
38 np.savetxt(outfile, output_vector, fmt="%d", delimiter='\t') | |
39 | |
40 | |
41 if __name__ == '__main__': | |
42 aparser = argparse.ArgumentParser() | |
43 aparser.add_argument("-i", "--inputs", dest="inputs", required=True) | |
44 aparser.add_argument("-y", "--infile", dest="infile") | |
45 aparser.add_argument("-o", "--outfile", dest="outfile") | |
46 args = aparser.parse_args() | |
47 | |
48 main(args.inputs, args.infile, args.outfile) |