Mercurial > repos > stevecassidy > nltktools
diff g_pos.py @ 2:a47980ef2b96 draft
planemo upload for repository https://github.com/Alveo/alveo-galaxy-tools commit b5b26e9118f2ad8af109d606746b39a5588f0511-dirty
author | stevecassidy |
---|---|
date | Wed, 01 Nov 2017 01:19:55 -0400 |
parents | fb617586f4b2 |
children | 0df72a8ab095 |
line wrap: on
line diff
--- a/g_pos.py Mon Dec 05 05:22:05 2016 -0500 +++ b/g_pos.py Wed Nov 01 01:19:55 2017 -0400 @@ -1,13 +1,14 @@ import nltk import argparse -import json + +nltk.download('averaged_perceptron_tagger', quiet=True) + def arguments(): parser = argparse.ArgumentParser(description="tokenize a text") parser.add_argument('--input', required=True, action="store", type=str, help="input text file") - parser.add_argument('--output', required=True, action="store", type=str, help="output file path") - args = parser.parse_args() - return args + parser.add_argument('--output', required=True, action="store", type=str, help="output file path") + return parser.parse_args() def postag(in_file, out_file): @@ -18,7 +19,7 @@ text = fd.read() sentences = nltk.sent_tokenize(text) - + with open(out_file, 'w') as output: for sentence in sentences: tokens = nltk.word_tokenize(sentence)