balachandrapai

##Text classification is always in the form of binary.
##ie, either spam or not spam

import nltk
import random
from nltk.corpus import movie_reviews
import pickle

## Create a list of tuples or features

balachandrapai

##Text classification is always in the form of binary.
##ie, either spam or not spam

import nltk
import random
from nltk.corpus import movie_reviews
import pickle

## Create a list of tuples or features

balachandrapai

from nltk.corpus import wordnet

syns = wordnet.synsets("program")
print(syns[0].name())
#plan.n.01
print(syns[0].lemmas()[0].name())
#plan
print(syns[0].definition())
#a series of steps to be carried out or goals to be accomplished
print(syns[0].examples())

balachandrapai

import nltk
from nltk.corpus import state_union
from nltk.tokenize import PunktSentenceTokenizer

train_text = state_union.raw("2005-GWBush.txt")
sample_text = state_union.raw("2006-GWBush.txt")

custom_sent_tokenizer = PunktSentenceTokenizer(train_text)

tokenized = custom_sent_tokenizer.tokenize(sample_text)

balachandrapai

##POS tagging is labeling words in a sentence as nouns, adjectives, verbs...etc
import nltk
from nltk.corpus import state_union
from nltk.tokenize import PunktSentenceTokenizer

##PunktSentenceTokenizer a new sentence tokenizer
## This tokenizer is capable of unsupervised machine learning,
##so you can actually train it on any body of text that you use

##Creating training and testing data

balachandrapai

from nltk.corpus import stopwords
from nltk.tokenize import sent_tokenize, word_tokenize

##Tokenizing - Splitting sentences and words from the body of text.
##Part of Speech tagging

##Corpus - Body of text, singular. Corpora is the plural of this.
##Example: A collection of medical journals.

##Lexicon - Words and their meanings.