generate_book_batch.py

import numpy as np
import random
random.seed(100)

def generate_batch(pairs, n_positive = 50, negative_ratio = 1.0):
    """Generate batches of samples for training. 
       Random select positive samples
       from pairs and randomly select negatives."""
    
    # Create empty array to hold batch
    batch_size = n_positive * (1 + negative_ratio)
    batch = np.zeros((batch_size, 3))
    
    # Continue to yield samples
    while True:
        # Randomly choose positive examples
        for idx, (book_id, link_id) in enumerate(random.sample(pairs, n_positive)):
            batch[idx, :] = (book_id, link_id, 1)
        idx += 1
        
        # Add negative examples until reach batch size
        while idx < batch_size:
            
            # Random selection
            random_book = random.randrange(len(books))
            random_link = random.randrange(len(links))
            
            # Check to make sure this is not a positive example
            if (random_book, random_link) not in pairs_set:
                
                # Add to batch and increment index
                batch[idx, :] = (random_book, random_link, neg_label)
                idx += 1
                
        # Make sure to shuffle order
        np.random.shuffle(batch)
        yield {'book': batch[:, 0], 'link': batch[:, 1]}, batch[:, 2]