megha444

pip install glove_python
import nltk 
nltk.download('stopwords')
nltk.download ('punkt')
nltk.download('wordnet')

megha444

lines=  ["Hello this is a tutorial to convert word to integer" , "It is a beautiful day" , "Jack is going to office"]

megha444

from nltk.tokenize import sent_tokenize, word_tokenize
word_tokens=[]
i=0
for line in lines:
 words = word_tokenize(line)
 word_tokens.insert(i,words)
 i=i+1
print (word_tokens)

megha444

from nltk.corpus import stopwords 
stop_words=stopwords.words('english') 
lines_without_stopwords=[] 
for line in lines: 
  stop_removed=[] 
for line in word_tokens:
  for word in line: 
    if word not in stop_words: 
      stop_removed.append(word) 
print (stop_removed)

megha444

from nltk import WordNetLemmatizer  
from nltk.stem import WordNetLemmatizer
wordnet_lemmatizer = WordNetLemmatizer() 
lines_with_lemmas=[] #stop words contain the set of stop words 
for line in lines: 
  lem_line=[] 
for word in stop_removed: 
  lem_line.append(wordnet_lemmatizer.lemmatize(word)) 
string='' 
new_lines=','.join([str(i) for i in lem_line])

megha444

#importing the glove library
from glove import Corpus, Glove
# creating a corpus object
corpus = Corpus() 
#training the corpus to generate the co occurence matrix which is used in GloVe
corpus.fit(new_lines, window=10)
#creating a Glove object which will use the matrix created in the above lines to create embeddings
#We can set the learning rate as it uses Gradient Descent and number of components
glove = Glove(no_components=5, learning_rate=0.05)
 

megha444

glove.add_dictionary(corpus.dictionary)

megha444

print glove.word_vectors[glove.dictionary['samsung']]

megha444

with open(‘data/reviews.txt’, ‘r’) as f:
 reviews = f.read()
with open(‘data/labels.txt’, ‘r’) as f:
 labels = f.read()
print(reviews[:50])
print()
print(labels[:26])

megha444

with open(‘data/reviews.txt’, ‘r’) as f:
 reviews = f.read()
with open(‘data/labels.txt’, ‘r’) as f:
 labels = f.read()