abhishek-shrm

# Removing extra spaces
df['cleaned']=df['cleaned'].apply(lambda x: re.sub(' +',' ',x))

abhishek-shrm

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

abhishek-shrm

# Importing spacy
import spacy

# Loading model
nlp = spacy.load('en_core_web_sm',disable=['parser', 'ner'])

# Lemmatization with stopwords removal
df['lemmatized']=df['cleaned'].apply(lambda x: ' '.join([token.lemma_ for token in list(nlp(x)) if (token.is_stop==False)]))

abhishek-shrm

df_grouped=df[['name','lemmatized']].groupby(by='name').agg(lambda x:' '.join(x))
df_grouped.head()

abhishek-shrm

# Importing wordcloud for plotting word clouds and textwrap for wrapping longer text
from wordcloud import WordCloud
from textwrap import wrap

# Function for generating word clouds
def generate_wordcloud(data,title):
  wc = WordCloud(width=400, height=330, max_words=150,colormap="Dark2").generate_from_frequencies(data)
  plt.figure(figsize=(10,8))
  plt.imshow(wc, interpolation='bilinear')
  plt.axis("off")

abhishek-shrm

from textblob import TextBlob
df['polarity']=df['lemmatized'].apply(lambda x:TextBlob(x).sentiment.polarity)

abhishek-shrm

print("3 Random Reviews with Highest Polarity:")
for index,review in enumerate(df.iloc[df['polarity'].sort_values(ascending=False)[:3].index]['reviews.text']):
  print('Review {}:\n'.format(index+1),review)

abhishek-shrm

print("3 Random Reviews with Lowest Polarity:")
for index,review in enumerate(df.iloc[df['polarity'].sort_values(ascending=True)[:3].index]['reviews.text']):
  print('Review {}:\n'.format(index+1),review)

abhishek-shrm

import textstat
df['dale_chall_score']=df['reviews.text'].apply(lambda x: textstat.dale_chall_readability_score(x))
df['flesh_reading_ease']=df['reviews.text'].apply(lambda x: textstat.flesch_reading_ease(x))
df['gunning_fog']=df['reviews.text'].apply(lambda x: textstat.gunning_fog(x))

print('Dale Chall Score of upvoted reviews=>',df[df['reviews.numHelpful']>1]['dale_chall_score'].mean())
print('Dale Chall Score of not upvoted reviews=>',df[df['reviews.numHelpful']<=1]['dale_chall_score'].mean())

print('Flesch Reading Score of upvoted reviews=>',df[df['reviews.numHelpful']>1]['flesh_reading_ease'].mean())
print('Flesch Reading Score of not upvoted reviews=>',df[df['reviews.numHelpful']<=1]['flesh_reading_ease'].mean())

abhishek-shrm

df['text_standard']=df['reviews.text'].apply(lambda x: textstat.text_standard(x))

print('Text Standard of upvoted reviews=>',df[df['reviews.numHelpful']>1]['text_standard'].mode())
print('Text Standard of not upvoted reviews=>',df[df['reviews.numHelpful']<=1]['text_standard'].mode())