some more doc, added tests for SlopeOne

README.md

@@ -47,26 +47,27 @@ following purposes in mind**:
 At the moment, the available prediction algorithms are:
 
 - [NormalPredictor](http://surprise.readthedocs.io/en/latest/basic_algorithms.html#surprise.prediction_algorithms.random_pred.NormalPredictor):
-  An algorithm predicting a random rating based on the distribution of the
+  an algorithm predicting a random rating based on the distribution of the
   training set, which is assumed to be normal.
 - [BaselineOnly](http://surprise.readthedocs.io/en/latest/basic_algorithms.html#surprise.prediction_algorithms.baseline_only.BaselineOnly):
-  An agorithm predicting the baseline estimate for given user and item.
+  an agorithm predicting the baseline estimate for given user and item.
 - [KNNBasic](http://surprise.readthedocs.io/en/latest/knn_inspired.html#surprise.prediction_algorithms.knns.KNNBasic):
-  A basic collaborative filtering algorithm.
+  a basic collaborative filtering algorithm.
 - [KNNWithMeans](http://surprise.readthedocs.io/en/latest/knn_inspired.html#surprise.prediction_algorithms.knns.KNNWithMeans):
-  A basic collaborative filtering algorithm, taking into account the mean
+  a basic collaborative filtering algorithm, taking into account the mean
   ratings of each user.
 - [KNNBaseline](http://surprise.readthedocs.io/en/latest/knn_inspired.html#surprise.prediction_algorithms.knns.KNNBaseline):
-  A basic collaborative filtering algorithm taking into account a baseline
+  a basic collaborative filtering algorithm taking into account a baseline
   rating.
 - [SVD](http://surprise.readthedocs.io/en/latest/matrix_factorization.html#surprise.prediction_algorithms.matrix_factorization.SVD)
   and
   [PMF](http://surprise.readthedocs.io/en/latest/matrix_factorization.html#unbiased-note):
-  The famous SVD algorithm, as popularized by Simon Funk during the Netflix
+  the famous SVD algorithm, as popularized by Simon Funk during the Netflix
   Prize. The unbiased version is equivalent to Probabilistic Matrix
   Factorization.
 - [SVD++](http://surprise.readthedocs.io/en/latest/matrix_factorization.html#surprise.prediction_algorithms.matrix_factorization.SVDpp):
-  An extension of SVD taking into account implicite ratings.
+  an extension of SVD taking into account implicite ratings.
+- [Slope One](http://surprise.readthedocs.io/en/latest/slope_one.html#surprise.prediction_algorithms.slope_one.SlopeOne): a simple yet accurate collaborative filtering algorithm.
 
 
 The name *SurPRISE* (roughly :) ) stands for Simple Python RecommendatIon

surprise/prediction_algorithms/slope_one.pyx

@@ -26,12 +26,12 @@ class SlopeOne(AlgoBase):
     .. math::
         \hat{r}_{ui} = \\mu_u + \\frac{1}{
         |R_i(u)|}
-        \\sum\\limits_{j \in R_i(u)} \\text{dev}(i, j).
+        \\sum\\limits_{j \in R_i(u)} \\text{dev}(i, j),
 
     where :math:`R_i(u)` is the set of relevents items, i.e. the set of items
     :math:`j` rated by :math:`u` that also have at least one common user with
     :math:`i`. :math:`\\text{dev}_(i, j)` is defined as the average difference
-    between the ratings of :math:`i` and :math`j`:
+    between the ratings of :math:`i` and those of :math:`j`:
 
     .. math::
         \\text{dev}(i, j) = \\frac{1}{

tests/test_algorithms.py

@@ -13,6 +13,7 @@
 from surprise.prediction_algorithms import KNNBaseline
 from surprise.prediction_algorithms import SVD
 from surprise.prediction_algorithms import SVDpp
+from surprise.prediction_algorithms import SlopeOne
 from surprise.dataset import Dataset
 from surprise.dataset import Reader
 
@@ -33,7 +34,7 @@ def test_unknown_user_or_item():
         pass  # just need trainset and testset to be set
 
     klasses = (NormalPredictor, BaselineOnly, KNNBasic, KNNWithMeans,
-               KNNBaseline, SVD, SVDpp)
+               KNNBaseline, SVD, SVDpp, SlopeOne)
     for klass in klasses:
         algo = klass()
         algo.train(trainset)