EDA

EDA.py

#first we need to import required libraries
#basic libraries
import pandas as pd 
import numpy as np

#misc
import gc
import time
import warnings

#statistics
from scipy.misc import imread
from scipy import sparse
import scipy.stats as ss

#visualization
import matplotlib.pyplot as plt
import matplotlib.gridspec as gridspec 
import seaborn as sns
from wordcloud import WordCloud ,STOPWORDS
from PIL import Image
import matplotlib_venn as venn

#natural language processing
import string
import re    #for regex
import nltk
from nltk.corpus import stopwords
import spacy
from nltk import pos_tag
from nltk.stem.wordnet import WordNetLemmatizer 
from nltk.tokenize import word_tokenize
# Tweet tokenizer does not split at apostophes which is what we want
from nltk.tokenize import TweetTokenizer   


#FeatureEngineering
from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer, HashingVectorizer
from sklearn.decomposition import TruncatedSVD
from sklearn.base import BaseEstimator, ClassifierMixin
from sklearn.utils.validation import check_X_y, check_is_fitted
from sklearn.linear_model import LogisticRegression
from sklearn import metrics
from sklearn.metrics import log_loss
from sklearn.model_selection import StratifiedKFold
from sklearn.model_selection import train_test_split