explore

import logging
import pandas as pd
import numpy as np
from numpy import random
import gensim
import nltk
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer
from sklearn.metrics import accuracy_score, confusion_matrix
import matplotlib.pyplot as plt
from nltk.corpus import stopwords
import re
from bs4 import BeautifulSoup
%matplotlib inline

df = pd.read_csv('stack-overflow-data.csv')
df = df[pd.notnull(df['tags'])]
print(df.head(10))
print(df['post'].apply(lambda x: len(x.split(' '))).sum())