comparison g_pos.py @ 2:a47980ef2b96 draft

planemo upload for repository https://github.com/Alveo/alveo-galaxy-tools commit b5b26e9118f2ad8af109d606746b39a5588f0511-dirty

1:fb617586f4b2

import nltk
import argparse
import json

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


def postag(in_file, out_file):
    """Input: a text file with one token per line
    Output: a version of the text with Part of Speech tags written as word/TAG
    """
    with open(in_file, 'r') as fd:
        text = fd.read()

    sentences = nltk.sent_tokenize(text)
    
    with open(out_file, 'w') as output:
        for sentence in sentences:
            tokens = nltk.word_tokenize(sentence)
            postags = nltk.pos_tag(tokens)
            for postag in postags:

2:a47980ef2b96

import nltk
import argparse

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")
    return parser.parse_args()


def postag(in_file, out_file):
    """Input: a text file with one token per line
    Output: a version of the text with Part of Speech tags written as word/TAG
    """
    with open(in_file, 'r') as fd:
        text = fd.read()

    sentences = nltk.sent_tokenize(text)

    with open(out_file, 'w') as output:
        for sentence in sentences:
            tokens = nltk.word_tokenize(sentence)
            postags = nltk.pos_tag(tokens)
            for postag in postags: