Python add_to_dict Examples

Example #1

File: stemming.py Project: spolnik/NaturalLanguageProcessing_Python_vs_CSharp

    def stemm(self, word):
        u"""Dokonuje stemmingu na slowie podanym w metodzie.
        Zwraca liste entity."""
        self.__entities = []
        if (word[len(word) - 1] == 'x'):
            utility.add_to_dict(self.__onlybase, word)
            return None

        similar_forms = self.__findSimilarForms(word)
        if similar_forms != None:
            self.__createEntities(word, similar_forms)
        else:
            utility.add_to_dict(self.__onlybase, word)
            return None

        return self.__entities

Example #2

File: text_checker.py Project: spolnik/NaturalLanguageProcessing_Python_vs_CSharp

def __processWord(word):
    u"""Przetwarzanie slowa, sprawdzenie jego typu i dodanie go do odpowiedniej listy."""
    if len(word) == 3 or word.isupper():
        if __isRome(word):
            utility.add_to_dict(__rome, word)
        else:
            utility.add_to_dict(__shortcuts, word)
    else:
        utility.add_to_dict(__results, word)

Example #3

File: checker.py Project: spolnik/NaturalLanguageProcessing_Python_vs_CSharp

#!/usr/bin/python
#-*- coding: utf-8 -*-
from plp import *
import sys
import re
import operator
import utility

list = {}
plp_init()
should_be_utf = False

if (sys.argv[2] == 'u'):
    should_be_utf = True

for line in open(sys.argv[1], "r"):
    for word in re.split("\[|\]|\\d+|\\s+|[-=`;!.:?,\")(\'\\_/]", line.decode('iso-8859-2').lower()):
        if len(word) == 0:
            continue

        word = word.encode('iso-8859-2')
        if not plp_rec(word):
            if should_be_utf:
                utility.add_to_dict(list, word.decode('iso-8859-2'))
            else:
                utility.add_to_dict(list, word)

for key, value in sorted(list.iteritems(), key = operator.itemgetter(1), reverse = True):
    print(key + ' : ' + str(value))