word_cloud.py

from wordcloud import WordCloud
import matplotlib.pyplot as plt 
from sklearn.feature_extraction.text import CountVectorizer    
    
# Analyzing top frquent bi-gram words in the interview questions of type Methodology with CountVectorizer
def counter(Q_A, category, data, n_gram_min, n_gram_max): 
    data = data[data[category]==1]
    word_vectorizer = CountVectorizer(ngram_range=(n_gram_min,n_gram_max), analyzer='word')
    sparse_matrix = word_vectorizer.fit_transform(data[Q_A])
    frequencies = sum(sparse_matrix).toarray()[0]
    return pd.DataFrame(frequencies, index=word_vectorizer.get_feature_names(), columns=['frequency']).sort_values('frequency', ascending=False)

# Data visualization with bi-gram word clouds 
for column in list(category.columns):
    cluster = data[data[column]==1]
    d = counter('Questions', column, cluster, 2, 2) # n-gram words within range (2,2) for example 
    frequency = d.T.to_dict('records')[0]
    wordcloud = WordCloud(background_color='black',width=3000, height=2000, max_words=100, 
 random_state=1, colormap='Set2', collocations=False)
    wordcloud.generate_from_frequencies(frequencies=frequency)
    print('Cluster: {}'.format(column))
    plt.figure(figsize=(20,10), facecolor='k')
    plt.imshow(wordcloud)
    plt.axis("off")
    plt.tight_layout(pad=0)
    plt.show()