import sys
# !{sys.executable} -m spacy download en
import re, numpy as np, pandas as pd
from pprint import pprint

# Gensim
import gensim, spacy, logging, warnings
import gensim.corpora as corpora
from gensim.utils import lemmatize, simple_preprocess
from gensim.models import CoherenceModel
import matplotlib.pyplot as plt

# NLTK Stop words
from nltk.corpus import stopwords
stop_words = stopwords.words('english')
stop_words.extend(['from', 'subject', 're', 'edu', 'use', 'not', 'would', 'say', 'could', '_', 'be', 'know', 'good', 'go', 'get', 'do', 'done', 'try', 'many', 'some', 'nice', 'thank', 'think', 'see', 'rather', 'easy', 'easily', 'lot', 'lack', 'make', 'want', 'seem', 'run', 'need', 'even', 'right', 'line', 'even', 'also', 'may', 'take', 'come'])

%matplotlib inline
warnings.filterwarnings("ignore",category=DeprecationWarning)
logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.ERROR)