Merge pull request #85 from knaveofdiamonds/documentation_typo_fixes

Fix documentation typos.

Author: maciejkula

doc/examples/warp_loss.rst

@@ -17,7 +17,7 @@ the form of the k-OS WARP loss, also implemented in LightFM.
 
 Like the BPR model, WARP deals with (user, positive item, negative item)
 triplets. Unlike BPR, the negative items in the triplet are not chosen
-by random sampling: they are chosen from among those negatie items which
+by random sampling: they are chosen from among those negative items which
 would violate the desired item ranking given the state of the model.
 This approximates a form of active learning where the model selects
 those triplets that it cannot currently rank correctly.

doc/home.rst

@@ -3,7 +3,7 @@ Welcome to LightFM's documentation!
 
 LightFM is a Python implementation of a number of popular recommendation algorithms for both implicit and explicit feedback.
 
-It also makes it possible to incorporate both item and user metadata into the traditional matrix factorization algorithms It represents each user and item as the sum of the latent representations of their features, thus allowing recommendations to generalise to new items (via item features) and to new users (via user features).
+It also makes it possible to incorporate both item and user metadata into the traditional matrix factorization algorithms. It represents each user and item as the sum of the latent representations of their features, thus allowing recommendations to generalise to new items (via item features) and to new users (via user features).
 
 The details of the approach are described in the LightFM paper, available on `arXiv <http://arxiv.org/abs/1507.08439>`_.