Venkatstatistics

# -*- coding: utf-8 -*-

from gensim.models.word2vec import Word2Vec
import gensim.downloader as api

#corpus = api.load('word2vec-google-news-300')
#corpus = api.load('glove-wiki-gigaword-100')
#model = api.load('glove-wiki-gigaword-100')
corpus = api.load('text8')  # download the corpus and return it opened as an iterable
model = Word2Vec(corpus)  # train a model from the corpus

Venkatstatistics

# -*- coding: utf-8 -*-

#lowercasing
texts=["JOHN","keLLY","ArJUN","SITA"]
lower_words=[word.lower() for word in texts]
lower_words

#Stemming
import nltk
import pandas as pd

Venkatstatistics

import spacy
from spacy.lang.en import English
nlpsm = English()
sbd = nlpsm.create_pipe('sentencizer')
nlpsm.add_pipe(sbd)
import en_vectors_web_lg
nlplg = en_vectors_web_lg.load()
nlplg.add_pipe(sbd)

Venkatstatistics

###Spacy Tutorials###

## References: https://course.spacy.io/chapter1 ##

## References: https://spacy.io/usage/spacy-101 ##

### Learning to work with NLP object ###

from spacy.lang.en import English
nlp = English ()