from nltk.corpus import indian
from nltk.tokenize import sent_tokenize
sample_text = indian.raw("marathi.pos")
marathi_text = sent_tokenize(sample_text)
print("Below is marathi text: (this is not proper way of reading text)")
print(marathi_text[0:5])
# -*- coding: utf-8 -*-
"""
Created on Mon Oct 12 11:11:06 2015
@author: suppu
"""
from nltk.corpus import indian
'''
Let us generate a file having sentences in indian languages. The file is generated from the indian languages scorpus available
'''
print "Number of charachetrs is:"
for f in indian.fileids():
print f
print len(indian.raw(f))
print "No of words in each language are:"
for f in indian.fileids():
print f
print len(indian.words(f))
print "Number of sentences in each language:"
for f in indian.fileids():
print f
print len(indian.sents(f))
'''POS for hindi
'''
hindi_sent = indian.sents("hindi.pos")
hsent = file("hws.txt", 'w')
for i in hindi_sent:
hsent.write(" ".join(i))
hpos = indian.tagged_sents("hindi.pos")
hpossent = open("hpossent.txt", 'w')
hpossent.seek(0)
#This is for my corpus (indian)
import nltk
from nltk.corpus import indian
import matplotlib as cdf
print(indian.raw())
print(indian.fileids())
print(indian.sents())
import matplotlib
word1 = 'country'
word2 = 'city'
cfd = nltk.ConditionalFreqDist((target, fileid[:4])
for fileid in indian.fileids()
for w in indian.words(fileid)
for target in [word1, word2]
if w.lower().startswith(target))
cfd.plot()
#nltk.download()
from nltk.corpus import indian
print("Files of Indian languages:-")
# check files for each languare in NLTK
print(indian.fileids())
print()
print("Language details :-")
# find no. of characters in each language
for f in indian.fileids():
print("Language :-", f)
print(
" No of Characters",
len(indian.raw(f)),
)
print(" No of words :-", len(indian.words(f)))
print(" No of Sentences :-", len(indian.sents(f)))
print()
print("Checking raw sentences of languages:-")
# print(indian.raw(indian.raw('bangla.pos'))
# print(indian.raw(indian.raw('hindi.pos'))
# print(indian.raw(indian.raw('marathi.pos'))
# print(indian.raw(indian.raw('telugu.pos'))
print("Printing & writing the sentences to a file, from Marathi language")
sentencesMarathi = open("marathiSentences.txt", "w")
# This will print sentence as a list of words
for sentence in indian.sents('marathi.pos'):
from nltk.stem import WordNetLemmatizer
lemmatizer = WordNetLemmatizer()
print(lemmatizer.lemmatize("better", pos="a"))
# In[18]:
import nltk
print(nltk.__file__)
# In[19]:
import cv2
print(cv2.__file__)
# In[24]:
from nltk.corpus import indian
from nltk.tokenize import sent_tokenize
sample = indian.raw("hindi.pos")
t = sent_tokenize(sample)
print(t[:4])
# In[26]:
from nltk.corpus import wordnet
syns = wordnet.synsets("program")
print(syns)
# In[ ]: