topic_model_utils.py

# -*- coding: utf-8 -*-
"""
Created on Tue Aug  8 20:54:15 2017

@author: DIP
"""

import numpy as np


# prints components of all the topics 
# obtained from topic modeling
def print_topics_udf(topics, total_topics=1,
                     weight_threshold=0.0001,
                     display_weights=False,
                     num_terms=None):
    
    for index in range(total_topics):
        topic = topics[index]
        topic = [(term, float(wt))
                 for term, wt in topic]
        topic = [(word, round(wt,2)) 
                 for word, wt in topic 
                 if abs(wt) >= weight_threshold]
                     
        if display_weights:
            print('Topic #'+str(index+1)+' with weights')
            print(topic[:num_terms]) if num_terms else topic
        else:
            print('Topic #'+str(index+1)+' without weights')
            tw = [term for term, wt in topic]
            print(tw[:num_terms]) if num_terms else tw
        print()
        

# extracts topics with their terms and weights
# format is Topic N: [(term1, weight1), ..., (termn, weightn)]        
def get_topics_terms_weights(weights, feature_names):
    feature_names = np.array(feature_names)
    sorted_indices = np.array([list(row[::-1]) 
                           for row 
                           in np.argsort(np.abs(weights))])
    sorted_weights = np.array([list(wt[index]) 
                               for wt, index 
                               in zip(weights,sorted_indices)])
    sorted_terms = np.array([list(feature_names[row]) 
                             for row 
                             in sorted_indices])
    
    topics = [np.vstack((terms.T, 
                     term_weights.T)).T 
              for terms, term_weights 
              in zip(sorted_terms, sorted_weights)]     
    
    return topics