genre_words_visual

genre_words_visual.py

def freq_words(x, terms = 30): 
  all_words = ' '.join([text for text in x]) 
  all_words = all_words.split() 
  fdist = nltk.FreqDist(all_words) 
  words_df = pd.DataFrame({'word':list(fdist.keys()), 'count':list(fdist.values())}) 
  
  # selecting top 20 most frequent words 
  d = words_df.nlargest(columns="count", n = terms) 
  
  # visualize words and frequencies
  plt.figure(figsize=(12,15)) 
  ax = sns.barplot(data=d, x= "count", y = "word") 
  ax.set(ylabel = 'Word') 
  plt.show()
  
# print 100 most frequent words 
freq_words(movies_new['clean_plot'], 100)