forgot to remove debugging prints

LICENSE

@@ -1,6 +1,6 @@
 BSD 2-Clause License
 
-Copyright (c) 2018, david-cortes
+Copyright (c) 2018, David Cortes
 All rights reserved.
 
 Redistribution and use in source and binary forms, with or without

README.md

@@ -2,7 +2,7 @@
 
 This is a Python package for hierarchical Poisson factorization, a form of probabilistic matrix factorization used for recommender systems with implicit count data, based on the paper _Scalable Recommendation with Hierarchical Poisson Factorization (P. Gopalan, 2015)_.
 
-Although the package was created with recommender systems in mind, it can also be used for other domains, e.g. as a faster alternative to LDA (Latent Ditichlet Allocation), where users become documents and items become words. For a similar package using also item/user side information see [ctpfrec](https://github.com/david-cortes/ctpfrec)
+Although the package was created with recommender systems in mind, it can also be used for other domains, e.g. as a faster alternative to LDA (Latent Ditichlet Allocation), where users become documents and items become words. For a similar package using also item/user side information see [ctpfrec](https://github.com/david-cortes/ctpfrec).
 
 Supports parallelization, full-batch variational inference, mini-batch stochastic variational inference (based on batches of data from subsets of users), and different stopping criteria for the coordinate-ascent procedure. The bottleneck computations are written in fast Cython code.
 

hpfrec/cython_loops.pyx

@@ -256,11 +256,8 @@ def fit_hpf(float a, float a_prime, float b_prime,
 			step_size_batch = <float> step_size(i)
 			np.random.shuffle(users_numeration)
 			for bt in range(nbatches):
-				print "bt: ", bt
 				st_batch = bt * users_per_batch
 				end_batch = min(nU, (bt + 1) * users_per_batch)
-				if st_batch>end_batch:
-					break
 				users_this_batch = users_numeration[st_batch : end_batch]
 				multiplier_batch = float(nU) / float(end_batch - st_batch)
 				nUbatch = <int> users_this_batch.shape[0]

setup.py

@@ -27,12 +27,12 @@
    'scipy',
    'cython'
 ],
-  version = '0.2.1.4',
+  version = '0.2.1.5',
   description = 'Hierarchical Poisson matrix factorization for recommender systems',
   author = 'David Cortes',
   author_email = 'david.cortes.rivera@gmail.com',
   url = 'https://github.com/david-cortes/hpfrec',
-  download_url = 'https://github.com/david-cortes/hpfrec/archive/0.2.1.4.tar.gz',
+  download_url = 'https://github.com/david-cortes/hpfrec/archive/0.2.1.5.tar.gz',
   keywords = ['poisson', 'probabilistic', 'non-negative', 'factorization', 'variational inference', 'collaborative filtering'],
   classifiers = [],