diff label_encoder.py @ 37:0f460421b212 draft

"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit ea12f973df4b97a2691d9e4ce6bf6fae59d57717"
author bgruening
date Sat, 01 May 2021 01:34:53 +0000
parents
children 7f8fa89929e0
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/label_encoder.py	Sat May 01 01:34:53 2021 +0000
@@ -0,0 +1,48 @@
+import argparse
+import json
+import warnings
+
+import numpy as np
+import pandas as pd
+from sklearn.preprocessing import LabelEncoder
+
+
+def main(inputs, infile, outfile):
+    """
+    Parameter
+    ---------
+    input : str
+        File path to galaxy tool parameter
+
+    infile : str
+        File paths of input vector
+
+    outfile : str
+        File path to output vector
+
+    """
+    warnings.simplefilter('ignore')
+
+    with open(inputs, 'r') as param_handler:
+        params = json.load(param_handler)
+
+    input_header = params['header0']
+    header = 'infer' if input_header else None
+
+    input_vector = pd.read_csv(infile, sep='\t', header=header)
+
+    le = LabelEncoder()
+
+    output_vector = le.fit_transform(input_vector)
+
+    np.savetxt(outfile, output_vector, fmt="%d", delimiter='\t')
+
+
+if __name__ == '__main__':
+    aparser = argparse.ArgumentParser()
+    aparser.add_argument("-i", "--inputs", dest="inputs", required=True)
+    aparser.add_argument("-y", "--infile", dest="infile")
+    aparser.add_argument("-o", "--outfile", dest="outfile")
+    args = aparser.parse_args()
+
+    main(args.inputs, args.infile, args.outfile)