abhishek-shrm

import numpy as np
import pandas as pd
# For visualizations
import matplotlib.pyplot as plt
# For regular expressions
import re
# For handling string
import string
# For performing mathematical operations
import math

abhishek-shrm

df=df[['name','reviews.text','reviews.doRecommend','reviews.numHelpful']]
print("Shape of data=>",df.shape)
df.head(5)

abhishek-shrm

df.isnull().sum()

abhishek-shrm

df.dropna(inplace=True)
df.isnull().sum()

abhishek-shrm

df=df.groupby('name').filter(lambda x:len(x)>500).reset_index(drop=True)
print('Number of products=>',len(df['name'].unique()))

abhishek-shrm

df['reviews.doRecommend']=df['reviews.doRecommend'].astype(int)
df['reviews.numHelpful']=df['reviews.numHelpful'].astype(int)

abhishek-shrm

df['name'].unique()

abhishek-shrm

df['name']=df['name'].apply(lambda x: x.split(',,,')[0])

abhishek-shrm

for index,text in enumerate(df['reviews.text'][35:40]):
  print('Review %d:\n'%(index+1),text)

abhishek-shrm

# Dictionary of English Contractions
contractions_dict = { "ain't": "are not","'s":" is","aren't": "are not",
                     "can't": "cannot","can't've": "cannot have",
                     "'cause": "because","could've": "could have","couldn't": "could not",
                     "couldn't've": "could not have", "didn't": "did not","doesn't": "does not",
                     "don't": "do not","hadn't": "had not","hadn't've": "had not have",
                     "hasn't": "has not","haven't": "have not","he'd": "he would",
                     "he'd've": "he would have","he'll": "he will", "he'll've": "he will have",
                     "how'd": "how did","how'd'y": "how do you","how'll": "how will",
                     "I'd": "I would", "I'd've": "I would have","I'll": "I will",