Python 3 compatibility

.travis.yml

@@ -2,6 +2,7 @@ language: python
 
 python:
   - "2.7"
+  - "3.4"
 
 sudo: false
 
@@ -24,6 +25,8 @@ before_install:
   - pip install cython
   - pip install numpy
   - travis_wait pip install scipy
+  # setup.py import mrec and install
+  - pip install six>=1.9
 
 # This is a library, not an application.
 # So we do not have a requirements.txt

doc/conf.py

@@ -11,6 +11,8 @@
 # All configuration values have a default; values that are commented out
 # serve to show the default.
 
+from __future__ import print_function
+
 import sys, os
 
 # If extensions (or modules to document with autodoc) are in another directory,
@@ -51,10 +53,10 @@
 try:
     release = pkg_resources.get_distribution('mrec').version
 except pkg_resources.DistributionNotFound:
-    print 'To build the documentation, The distribution information of mrec'
-    print 'has to be available.  Either install the package into your'
-    print 'development environment or run "python setup.py develop" to setup'
-    print 'the metadata.'
+    print('To build the documentation, The distribution information of mrec')
+    print('has to be available.  Either install the package into your')
+    print('development environment or run "python setup.py develop" to setup')
+    print('the metadata.')
     sys.exit(1)
 del pkg_resources
 version = '.'.join(release.split('.')[:2])

doc/hybrid.rst

@@ -39,7 +39,7 @@ The resulting features are simply `tf-idf counts <http://en.wikipedia.org/wiki/T
 
 and inspect the top few word counts for the first few items::
 
-    >>> for i in xrange(3):
+    >>> for i in range(3):
     ...     for tfidf,word in sorted(zip(features[i].data,features[i].indices),reverse=True)[:3]:
     ...         print '{0}\t{1}\t{2:.3f}'.format(i,word,tfidf)
     ...

mrec/__init__.py

@@ -1,4 +1,8 @@
-from itertools import izip
+from __future__ import absolute_import, print_function
+try:
+    from itertools import izip as zip
+except ImportError:
+    pass
 import numpy as np
 from scipy.sparse import coo_matrix, csr_matrix
 from scipy.io import mmread, mmwrite
@@ -7,8 +11,8 @@
 except ImportError:
     import pickle
 
-from sparse import fast_sparse_matrix, loadtxt, loadz, savez
-from base_recommender import BaseRecommender
+from .sparse import fast_sparse_matrix, loadtxt, loadz, savez
+from .base_recommender import BaseRecommender
 
 __version__ = '0.3.1'
 
@@ -89,13 +93,13 @@ def save_sparse_matrix(data,fmt,filepath):
     if fmt == 'tsv':
         m = data.tocoo()
         with open(filepath,'w') as out:
-            for u,i,v in izip(m.row,m.col,m.data):
-                print >>out,'{0}\t{1}\t{2}'.format(u+1,i+1,v)
+            for u,i,v in zip(m.row,m.col,m.data):
+                print('{0}\t{1}\t{2}'.format(u+1,i+1,v), file=out)
     elif fmt == 'csv':
         m = data.tocoo()
         with open(filepath,'w') as out:
-            for u,i,v in izip(m.row,m.col,m.data):
-                print >>out,'{0},{1},{2}'.format(u+1,i+1,v)
+            for u,i,v in zip(m.row,m.col,m.data):
+                print('{0},{1},{2}'.format(u+1,i+1,v), file=out)
     elif fmt == 'mm':
         mmwrite(filepath,data)
     elif fmt == 'npz':

mrec/base_recommender.py

@@ -1,7 +1,9 @@
+from __future__ import print_function
 try:
     import cPickle as pickle
 except ImportError:
     import pickle
+from six.moves import xrange
 import numpy as np
 from scipy.sparse import csr_matrix
 
@@ -86,7 +88,7 @@ def save(self,filepath):
         if archive:
             np.savez(filepath,**archive)
         else:
-            pickle.dump(self,open(filepath,'w'))
+            pickle.dump(self,open(filepath,'wb'))
 
     def _create_archive(self):
         """
@@ -117,7 +119,7 @@ def load(filepath):
         if isinstance(r,BaseRecommender):
             model = r
         else:
-            model = np.loads(str(r['model']))
+            model = np.loads(r['model'])
             model._load_archive(r)  # restore any fields serialized separately
         return model
 
@@ -148,7 +150,7 @@ def read_recommender_description(filepath):
         if isinstance(r,BaseRecommender):
             model = r
         else:
-            model = np.loads(str(r['model']))
+            model = np.loads(r['model'])
         return str(model)
 
     def __str__(self):
@@ -192,10 +194,10 @@ def batch_recommend_items(self,
         recs = []
         for u in xrange(self.num_users):
             if show_progress and u%1000 == 0:
-               print u,'..',
+               print(u, '..',)
             recs.append(self.recommend_items(dataset,u,max_items,return_scores))
         if show_progress:
-            print
+            print()
         return recs
 
     def range_recommend_items(self,

mrec/evaluation/metrics.py

@@ -3,7 +3,8 @@
 * with hit rate, following e.g. Karypis lab SLIM and FISM papers
 * with prec@k and MRR
 """
-
+from __future__ import print_function
+from six.moves import xrange
 import numpy as np
 from scipy import stats
 from collections import defaultdict
@@ -62,8 +63,8 @@ def run_evaluation(models,retrain,get_split,num_runs,evaluation_func):
         for i,model in enumerate(models):
             retrain(model,train)
             run_metrics = evaluation_func(model,train,users,test)
-            for m,val in run_metrics.iteritems():
-                print m,val
+            for m,val in run_metrics.items():
+                print(m, val)
                 metrics[i][m].append(val)
     return metrics
 
@@ -83,10 +84,10 @@ def sort_metrics_by_name(names):
             prefix2val[name].append(val)
         else:
             prefix2val[name] = []
-    for name,vals in prefix2val.iteritems():
+    for name,vals in prefix2val.items():
         prefix2val[name] = sorted(vals)
     ret = []
-    for name,vals in sorted(prefix2val.iteritems()):
+    for name,vals in sorted(prefix2val.items()):
         if vals:
             for val in vals:
                 ret.append('{0}@{1}'.format(name,val))
@@ -99,15 +100,15 @@ def print_report(models,metrics):
     Call this to print out the metrics returned by run_evaluation().
     """
     for model,results in zip(models,metrics):
-        print model
+        print(model)
         if hasattr(model,'similarity_matrix'):
             nnz = model.similarity_matrix.nnz
             num_items = model.similarity_matrix.shape[0]
             density = float(model.similarity_matrix.nnz)/num_items**2
-            print 'similarity matrix nnz = {0} (density {1:.3f})'.format(nnz,density)
+            print('similarity matrix nnz = {0} (density {1:.3f})'.format(nnz,density))
         for m in sort_metrics_by_name(results.keys()):
             vals = results[m]
-            print '{0}{1:.4f} +/- {2:.4f}'.format(m.ljust(15),np.mean(vals),stats.sem(vals,ddof=0))
+            print('{0}{1:.4f} +/- {2:.4f}'.format(m.ljust(15),np.mean(vals),stats.sem(vals,ddof=0)))
 
 def evaluate(model,train,users,get_known_items,compute_metrics):
     avg_metrics = defaultdict(float)
@@ -116,7 +117,7 @@ def evaluate(model,train,users,get_known_items,compute_metrics):
         recommended = [r for r,_ in model.recommend_items(train,u,max_items=20)]
         metrics = compute_metrics(recommended,get_known_items(u))
         if metrics:
-            for m,val in metrics.iteritems():
+            for m,val in metrics.items():
                 avg_metrics[m] += val
             count += 1
     for m in avg_metrics:

mrec/evaluation/tests/test_metrics.py

@@ -1,3 +1,4 @@
+from six.moves import xrange
 from sklearn.utils.testing import assert_equal
 from sklearn.utils.testing import assert_raises
 

mrec/examples/convert.py

@@ -1,6 +1,7 @@
 """
 Convert sparse matrix from one file format to another.
 """
+from __future__ import print_function
 
 import os
 import subprocess
@@ -18,8 +19,8 @@ def tsv2mtx(infile,outfile):
         nnz += 1
     headerfile = outfile+'.header'
     with open(headerfile,'w') as header:
-        print >>header,'%%MatrixMarket matrix coordinate real general'
-        print >>header,'{0} {1} {2}'.format(num_users,num_items,nnz)
+        print('%%MatrixMarket matrix coordinate real general', file=header)
+        print('{0} {1} {2}'.format(num_users,num_items,nnz), file=header)
     subprocess.check_call(['cat',headerfile,infile],stdout=open(outfile,'w'))
     subprocess.check_call(['rm',headerfile])
 

mrec/examples/predict.py

@@ -19,6 +19,7 @@
 from shutil import rmtree
 import logging
 from collections import defaultdict
+from six.moves import xrange
 
 from mrec import load_sparse_matrix, read_recommender_description, load_recommender
 from mrec.parallel import predict
@@ -82,7 +83,7 @@ def process(view,opts,modelfile,trainfile,testfile,featurefile,outdir,evaluator)
         tot_count = 0
         for results in processed:
             for cum_metrics,count in results:
-                for m,val in cum_metrics.iteritems():
+                for m,val in cum_metrics.items():
                     avg_metrics[m] += val
                 tot_count += count
         for m in avg_metrics:

mrec/examples/prepare.py

@@ -1,3 +1,6 @@
+from __future__ import print_function
+from six.moves import xrange
+
 class Processor(object):
 
     def __init__(self,splitter,parser,min_items_per_user,preprocess=None):
@@ -8,7 +11,7 @@ def __init__(self,splitter,parser,min_items_per_user,preprocess=None):
 
     def output(self,user,vals,outfile):
         for v,c in vals:
-            print >>outfile,'{0}\t{1}\t{2}'.format(user,v,c)
+            print('{0}\t{1}\t{2}'.format(user,v,c), file=outfile)
 
     def handle(self,user,vals):
         if len(vals) >= self.min_items_per_user:

mrec/examples/tune_slim.py

@@ -2,7 +2,9 @@
 Try to find a sensible range for regularization
 constants for SLIM by looking at model sparsity.
 """
+from __future__ import print_function
 
+from six.moves import xrange
 import random
 from math import log10
 import logging
@@ -91,12 +93,12 @@ def main():
     if candidates:
         best = min(candidates,key=itemgetter(1))
 
-        print 'best parameter setting: {0}'.format(best[0])
-        print 'mean # positive similarity weights per item = {0:.3}'.format(best[1])
-        print 'proportion of items with fewer than {0} positive similarity weights = {1:.3}'.format(opts.min_sims,best[2])
-        print 'mean # negative similarity weights per item = {0:.3}'.format(best[3])
+        print('best parameter setting: {0}'.format(best[0]))
+        print('mean # positive similarity weights per item = {0:.3}'.format(best[1]))
+        print('proportion of items with fewer than {0} positive similarity weights = {1:.3}'.format(opts.min_sims,best[2]))
+        print('mean # negative similarity weights per item = {0:.3}'.format(best[3]))
     else:
-        print 'no parameter settings satisfied the conditions, try increasing --min_sims, --max_sims or --max_sparse'
+        print('no parameter settings satisfied the conditions, try increasing --min_sims, --max_sims or --max_sparse')
 
 if __name__ == '__main__':
     main()

mrec/item_similarity/knn.py

@@ -2,10 +2,12 @@
 Brute-force k-nearest neighbour recommenders
 intended to provide evaluation baselines.
 """
+from __future__ import absolute_import, print_function
 
+from six.moves import xrange
 import numpy as np
 from sklearn.metrics.pairwise import cosine_similarity
-from recommender import ItemSimilarityRecommender
+from mrec.item_similarity.recommender import ItemSimilarityRecommender
 
 class KNNRecommender(ItemSimilarityRecommender):
     """
@@ -79,12 +81,12 @@ def __str__(self):
     # use knn models like this:
 
     import random
-    import StringIO
+    from io import BytesIO
     from mrec import load_fast_sparse_matrix
 
     random.seed(0)
 
-    print 'loading test data...'
+    print('loading test data...')
     data = """\
 %%MatrixMarket matrix coordinate real general
 3 5 9
@@ -98,8 +100,8 @@ def __str__(self):
 3	3	1
 3	4	1
 """
-    print data
-    dataset = load_fast_sparse_matrix('mm',StringIO.StringIO(data))
+    print(data)
+    dataset = load_fast_sparse_matrix('mm', BytesIO(data.encode('ascii')))
     num_users,num_items = dataset.shape
 
     model = CosineKNNRecommender(k=2)
@@ -108,32 +110,32 @@ def __str__(self):
 
     def output(i,j,val):
         # convert back to 1-indexed
-        print '{0}\t{1}\t{2:.3f}'.format(i+1,j+1,val)
+        print('{0}\t{1}\t{2:.3f}'.format(i+1,j+1,val))
 
-    print 'computing some item similarities...'
-    print 'item\tsim\tweight'
+    print('computing some item similarities...')
+    print('item\tsim\tweight')
     # if we want we can compute these individually without calling fit()
     for i in random.sample(xrange(num_items),num_samples):
         for j,weight in model.get_similar_items(i,max_similar_items=2,dataset=dataset):
             output(i,j,weight)
 
-    print 'learning entire similarity matrix...'
+    print('learning entire similarity matrix...')
     # more usually we just call train() on the entire dataset
     model = CosineKNNRecommender(k=2)
     model.fit(dataset)
-    print 'making some recommendations...'
-    print 'user\trec\tscore'
+    print('making some recommendations...')
+    print('user\trec\tscore')
     for u in random.sample(xrange(num_users),num_samples):
         for i,score in model.recommend_items(dataset.X,u,max_items=10):
             output(u,i,score)
 
-    print 'making batch recommendations...'
+    print('making batch recommendations...')
     recs = model.batch_recommend_items(dataset.X)
     for u in xrange(num_users):
         for i,score in recs[u]:
             output(u,i,score)
 
-    print 'making range recommendations...'
+    print('making range recommendations...')
     for start,end in [(0,2),(2,3)]:
         recs = model.range_recommend_items(dataset.X,start,end)
         for u in xrange(start,end):

mrec/item_similarity/precomputed.py

@@ -1,8 +1,8 @@
 """
 Make recommendations from a precomputed item similarity matrix.
 """
-
-from recommender import ItemSimilarityRecommender
+from __future__ import absolute_import
+from .recommender import ItemSimilarityRecommender
 
 class PrecomputedItemSimilarityRecommender(ItemSimilarityRecommender):
     """