Created
February 8, 2017 01:26
-
-
Save sureshgorakala/47bf062020eebf71fea9a653d71e2081 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import nltk | |
#reading text into python | |
path = "~/textCourpus.txt" | |
f = open(path,'r') | |
lines = [line.replace('\n','') for line in f.readlines()] | |
#lines2 = [line.replace('\n','') for line in f.readlines()] | |
type(lines) | |
len(lines) | |
#sentence tokenizing | |
from nltk.tokenize import sent_tokenize | |
lines[4] | |
sent_tokenize(lines[4]) | |
len(sent_tokenize(lines[4])) | |
#download required resources for tokenizer - english.pickle | |
nltk.download() | |
#nltk.download('punkt') | |
sent_tokenize(lines[4]) | |
sent_tokenize(lines[4])[0] | |
sent_tokenize(lines[4])[1] | |
#tokenising sentences to words | |
from nltk.tokenize import word_tokenize | |
sent = sent_tokenize(lines[4])[1] | |
word_tokenize(sent) | |
type(word_tokenize(sent)) | |
# (OR) | |
from nltk.tokenize import TreebankWordTokenizer | |
tokenizer = TreebankWordTokenizer() | |
tokenizer.tokenize(sent) | |
#frequency distributions: | |
from nltk.probability import FreqDist | |
fdist = FreqDist(word.lower() for word in word_tokenize(sent)) | |
#length of each word | |
[len(word) for word in word_tokenize(sent)] | |
#collocations, wordsense disambiguation, co-reference | |
#stopwords | |
from nltk.corpus import stopwords | |
english_stops = set(stopwords.words('english')) | |
[word for word in word_tokenize(sent) if word not in english_stops] | |
english_stops | |
stopwords.fileids() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment