Migrate to Python3

.travis.yml

@@ -1,7 +1,7 @@
 language: python
 
 python:
-  - "2.7"
+  - "3.6"
 
 sudo: false
 

README.rst

@@ -9,6 +9,7 @@ mrec recommender systems library
 
 Introduction
 ------------
+This fork is Python 3 only.
 `mrec` is a Python package developed at `Mendeley <http://www.mendeley.com>`_ to support recommender systems development and evaluation.  The package currently focuses on item similarity and other methods that work well on implicit feedback, and on experimental evaluation.
 
 Why another package when there are already some really good software projects implementing recommender systems?

doc/conf.py

@@ -51,10 +51,10 @@
 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])

mrec/__init__.py

@@ -1,18 +1,12 @@
-from itertools import izip
-import numpy as np
-from scipy.sparse import coo_matrix, csr_matrix
 from scipy.io import mmread, mmwrite
-try:
-    import cPickle as pickle
-except ImportError:
-    import pickle
 
-from sparse import fast_sparse_matrix, loadtxt, loadz, savez
-from base_recommender import BaseRecommender
+from mrec.base_recommender import BaseRecommender
+from mrec.sparse import fast_sparse_matrix, loadtxt, loadz, savez
 
 __version__ = '0.3.1'
 
-def load_fast_sparse_matrix(input_format,filepath):
+
+def load_fast_sparse_matrix(input_format, filepath):
     """
     Load a fast_sparse_matrix from an input file of the specified format,
     by delegating to the appropriate static method.
@@ -31,14 +25,15 @@ def load_fast_sparse_matrix(input_format,filepath):
     if input_format == 'tsv':
         return fast_sparse_matrix.loadtxt(filepath)
     elif input_format == 'csv':
-        return fast_sparse_matrix.loadtxt(filepath,delimiter=',')
+        return fast_sparse_matrix.loadtxt(filepath, delimiter=',')
     elif input_format == 'mm':
         return fast_sparse_matrix.loadmm(filepath)
     elif input_format == 'fsm':
         return fast_sparse_matrix.load(filepath)
     raise ValueError('unknown input format: {0}'.format(input_format))
 
-def load_sparse_matrix(input_format,filepath):
+
+def load_sparse_matrix(input_format, filepath):
     """
     Load a scipy.sparse.csr_matrix from an input file of the specified format.
 
@@ -57,7 +52,7 @@ def load_sparse_matrix(input_format,filepath):
     if input_format == 'tsv':
         return loadtxt(filepath)
     elif input_format == 'csv':
-        return loadtxt(filepath,delimiter=',')
+        return loadtxt(filepath, delimiter=',')
     elif input_format == 'mm':
         return mmread(filepath).tocsr()
     elif input_format == 'npz':
@@ -66,7 +61,8 @@ def load_sparse_matrix(input_format,filepath):
         return fast_sparse_matrix.load(filepath).X
     raise ValueError('unknown input format: {0}'.format(input_format))
 
-def save_sparse_matrix(data,fmt,filepath):
+
+def save_sparse_matrix(data, fmt, filepath):
     """
     Save a scipy sparse matrix in the specified format. Row and column
     indices will be converted to 1-indexed if you specify a plain text
@@ -88,24 +84,25 @@ 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)
+        with open(filepath, 'w') as out:
+            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)
+        with open(filepath, 'w') as out:
+            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)
+        mmwrite(filepath, data)
     elif fmt == 'npz':
-        savez(data.tocoo(),filepath)
+        savez(data.tocoo(), filepath)
     elif fmt == 'fsm':
         fast_sparse_matrix(data).save(filepath)
     else:
         raise ValueError('unknown output format: {0}'.format(fmt))
 
-def save_recommender(model,filepath):
+
+def save_recommender(model, filepath):
     """
     Save a recommender model to file.
 
@@ -118,6 +115,7 @@ def save_recommender(model,filepath):
     """
     model.save(filepath)
 
+
 def load_recommender(filepath):
     """
     Load a recommender model from file after it has been saved by
@@ -130,6 +128,7 @@ def load_recommender(filepath):
     """
     return BaseRecommender.load(filepath)
 
+
 def read_recommender_description(filepath):
     """
     Read a recommender model description from file after it has

mrec/base_recommender.py

@@ -1,10 +1,9 @@
-try:
-    import cPickle as pickle
-except ImportError:
-    import pickle
+import pickle
+
 import numpy as np
 from scipy.sparse import csr_matrix
 
+
 class BaseRecommender(object):
     """
     Minimal interface to be implemented by recommenders, along with
@@ -23,7 +22,7 @@ class BaseRecommender(object):
     and the batch methods to recommend items.
     """
 
-    def recommend_items(self,dataset,u,max_items=10,return_scores=True,item_features=None):
+    def recommend_items(self, dataset, u, max_items=10, return_scores=True, item_features=None):
         """
         Recommend new items for a user.
 
@@ -48,7 +47,7 @@ def recommend_items(self,dataset,u,max_items=10,return_scores=True,item_features
         """
         raise NotImplementedError('you must implement recommend_items()')
 
-    def fit(self,train,item_features=None):
+    def fit(self, train, item_features=None):
         """
         Train on supplied data. In general you will want to
         implement this rather than computing recommendations on
@@ -63,7 +62,7 @@ def fit(self,train,item_features=None):
         """
         raise NotImplementedError('you should implement fit()')
 
-    def save(self,filepath):
+    def save(self, filepath):
         """
         Serialize model to file.
 
@@ -84,9 +83,9 @@ def save(self,filepath):
 
         archive = self._create_archive()
         if archive:
-            np.savez(filepath,**archive)
+            np.savez(filepath, **archive)
         else:
-            pickle.dump(self,open(filepath,'w'))
+            pickle.dump(self, open(filepath, 'wb'))
 
     def _create_archive(self):
         """
@@ -114,10 +113,10 @@ def load(filepath):
             The filepath to read from.
         """
         r = np.load(filepath)
-        if isinstance(r,BaseRecommender):
+        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
 
@@ -144,15 +143,15 @@ def read_recommender_description(filepath):
         filepath : str
             The filepath to read from.
         """
-        r = np.load(filepath,mmap_mode='r')
-        if isinstance(r,BaseRecommender):
+        r = np.load(filepath, mmap_mode='r')
+        if isinstance(r, BaseRecommender):
             model = r
         else:
-            model = np.loads(str(r['model']))
+            model = np.loads(r['model'])
         return str(model)
 
     def __str__(self):
-        if hasattr(self,'description'):
+        if hasattr(self, 'description'):
             return self.description
         return 'unspecified recommender: you should set self.description or implement __str__()'
 
@@ -190,12 +189,12 @@ def batch_recommend_items(self,
         this for most recommenders.
         """
         recs = []
-        for u in xrange(self.num_users):
-            if show_progress and u%1000 == 0:
-               print u,'..',
-            recs.append(self.recommend_items(dataset,u,max_items,return_scores))
+        for u in range(self.num_users):
+            if show_progress and u % 1000 == 0:
+                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,
@@ -234,9 +233,9 @@ def range_recommend_items(self,
         This provides a default implementation, you will be able to optimize
         this for most recommenders.
         """
-        return [self.recommend_items(dataset,u,max_items,return_scores) for u in xrange(user_start,user_end)]
+        return [self.recommend_items(dataset, u, max_items, return_scores) for u in range(user_start, user_end)]
 
-    def _zero_known_item_scores(self,r,train):
+    def _zero_known_item_scores(self, r, train):
         """
         Helper function to set predicted scores/ratings for training items
         to zero or less, to avoid recommending already known items.
@@ -255,7 +254,7 @@ def _zero_known_item_scores(self,r,train):
             in train.
         """
         col = train.indices
-        if isinstance(r,csr_matrix):
+        if isinstance(r, csr_matrix):
             max_score = r.data.max()
         else:
             max_score = r.max()
@@ -264,9 +263,8 @@ def _zero_known_item_scores(self,r,train):
         # - we can't just use row,col = train.nonzero() as this eliminates
         #   u,i for which train[u,i] has been explicitly set to zero
         row = np.zeros(col.shape)
-        for u in xrange(train.shape[0]):
-            start,end = train.indptr[u],train.indptr[u+1]
+        for u in range(train.shape[0]):
+            start, end = train.indptr[u], train.indptr[u + 1]
             if end > start:
                 row[start:end] = u
-        return r - csr_matrix((data,(row,col)),shape=r.shape)
-
+        return r - csr_matrix((data, (row, col)), shape=r.shape)

mrec/evaluation/__init__.py

@@ -11,18 +11,18 @@ class Evaluator(object):
         The number of recommendations needed to compute the evaluation function.
     """
 
-    def __init__(self,compute_metrics,max_items):
+    def __init__(self, compute_metrics, max_items):
         self.compute_metrics = compute_metrics
         self.max_items = max_items
 
-    def _add_metrics(self,predicted,actual):
-        metrics = self.compute_metrics(predicted,actual)
+    def _add_metrics(self, predicted, actual):
+        metrics = self.compute_metrics(predicted, actual)
         if metrics:
-            for m,val in metrics.iteritems():
+            for m, val in metrics.items():
                 self.cum_metrics[m] += val
             self.count += 1
 
-    def process(self,testdata,recsfile,start,end,offset=1):
+    def process(self, testdata, recsfile, start, end, offset=1):
         """
         Parameters
         ----------
@@ -54,19 +54,19 @@ def process(self,testdata,recsfile,start,end,offset=1):
         last_user = start
         recs = []
         for line in open(recsfile):
-            user,item,score = line.strip().split('\t')
-            user = int(user)-1  # convert to 0-indxed
-            item = int(item)-1
+            user, item, score = line.strip().split('\t')
+            user = int(user) - 1  # convert to 0-indxed
+            item = int(item) - 1
             if user >= end:
                 break
             if user < start:
                 continue
             if user != last_user:
-                self._add_metrics(recs,testdata[last_user,:].indices.tolist())
+                self._add_metrics(recs, testdata[last_user, :].indices.tolist())
                 last_user = user
                 recs = []
             if len(recs) < self.max_items:
                 recs.append(item)
-        self._add_metrics(recs,testdata[last_user,:].indices.tolist())
+        self._add_metrics(recs, testdata[last_user, :].indices.tolist())
 
-        return self.cum_metrics,self.count
+        return self.cum_metrics, self.count