updated doc

doc/source/getting_started.rst

@@ -28,6 +28,8 @@ splits the dataset into 3 folds and the :func:`evaluate()
 compute some :mod:`accuracy <recsys.accuracy>` measures.
 
 
+.. _load_custom:
+
 Load a custom dataset
 ---------------------
 

doc/source/index.rst

@@ -3,18 +3,33 @@
    You can adapt this file completely to your liking, but it should at least
    contain the root `toctree` directive.
 
-Welcome to RecSys's documentation!
-==================================
+.. _index:
+
+Welcome to RecSys' documentation!
+=================================
 
 RecSys is an open source Python package that provides with tools to build and
 evaluate the performance of many recommender system prediction algorithms. Its
 goal is to make life easy(-ier) for reseachers and students who want to play
 around with new recommender algorithm ideas.
 
-A strong emphasis is laid on documentation, which we have tried to make as
-clear and precise as possible by pointing out every details of the algorithms,
-in order for the practitioner to have perfect control over his experiments.
-
+RecSys was designed with the following purposes in mind:
+
+- Give the user perfect control over his experiments. To this end, a strong
+  emphasis is laid on :ref:`documentation <index>`, which we
+  have tried to make as clear and precise as possible by pointing out every
+  details of the algorithms.
+- Alleviate the pain of :ref:`dataset handling <load_custom>`. Users can use
+  both *built-in* datasets
+  (`Movielens <http://grouplens.org/datasets/movielens/>`_,
+  `Jester <http://eigentaste.berkeley.edu/dataset/>`_), and their own *custom*
+  datasets.
+- Provide with various ready-to-use :ref:`prediction
+  algorithms <prediction_algorithms_package>`.
+- Make it easy to implement :ref:`new algorithm
+  ideas <building_custom_algo>`.
+- Provide with tools to :func:`evaluate <recsys.evaluate.evaluate>`,
+  `analyse <http://nbviewer.jupyter.org/github/Niourf/RecSys/tree/master/examples/notebooks/KNNBasic_analysis.ipynb/>`_ and `compare <http://nbviewer.jupyter.org/github/Niourf/RecSys/tree/master/examples/notebooks/Compare.ipynb/>`_ the algorithms performance. Cross-validation procedures can be run very easily.
 
 .. toctree::
    :caption: User Guide

examples/basic_usage.py

@@ -11,8 +11,8 @@
 from recsys import evaluate
 
 
-# Load the movielens-100k dataset and split it into 3 folds for
-# cross-validation.
+# Load the movielens-100k dataset (it will be downloaded if needed) and split
+# it into 3 folds for cross-validation.
 data = Dataset.load_builtin('ml-100k')
 data.split(n_folds=3)