def main():
""" Read user input, analyze, output results. """
analyzer = pyaramorph.Analyzer()
print("Unicode Arabic Morphological Analyzer (press ctrl-d to exit)")
while True:
try:
s = input("$ ")
results = analyzer.analyze_text(s)
except EOFError:
print("Goodbye!")
break
for analyses in results:
for solution in analyses:
print(solution)
def __init__(self, raw_data=None):
self.analyzer = pyaramorph.Analyzer()
self.stemmer = nltk.ISRIStemmer()
self.lemmatizer = nltk.WordNetLemmatizer()
self.segmenter = nltk.data.load("tokenizers/punkt/english.pickle")
if raw_data is not None:
self.raw_data = raw_data
self.org_data = raw_data
self.analyze_text()
self.ambig()
self.load_corpus('Tashkeela')
self.select_cand()
self.print_result()
# -*- coding: utf-8 -*-
"""
@author: Asma Baccouche
"""
import re
import pandas as pd
import Lexicons
import Util
import pyaramorph
analyzer = pyaramorph.Analyzer()
file = open('Util_Files/Arabic_Pos_Bigrams.txt', 'r', encoding='utf8')
Pos_ar = [line[:-1].split(' ') for line in file.readlines()]
file = open('Util_Files/Arabic_Neg_Bigrams.txt', 'r', encoding='utf8')
Neg_ar = [line[:-1].split(' ') for line in file.readlines()]
def find_bigrams(input_list):
bigram_list = []
for i in range(len(input_list) - 1):
bigram_list.append((input_list[i], input_list[i + 1]))
return bigram_list
P, N = Lexicons.lexicons('English')
def arabic_labeling(New, lang):
Positive, Negative = Lexicons.lexicons(lang)
def analysText(self, text):
print(text)
p = pyaramorph.Analyzer()
text = text.split()
for w in text:
self.printResult(self, p.analyze_text(w))
def __init__(self):
self.analyzer = pyaramorph.Analyzer()
self.stemmer = nltk.ISRIStemmer()
self.lemmatizer = nltk.WordNetLemmatizer()
self.segmenter = nltk.data.load("tokenizers/punkt/english.pickle")
def _GetGloss(_word):
analizer = par.Analyzer()
analized = analizer.analyze_text(_word)
return analized