diff --git a/scikits/crab/datasets/book_crossing.py b/scikits/crab/datasets/book_crossing.py
@@ -0,0 +1,167 @@
+"""Caching loader for the Book-Crossing Dataset
+
+The description of the dataset is available on the official website at:
+
+    http://www.informatik.uni-freiburg.de/~cziegler/BX/
+
+Quoting the introduction:
+
+    Collected by Cai-Nicolas Ziegler in a 4-week crawl
+    (August / September 2004) from the Book-Crossing community
+    with kind permission from Ron Hornbaker, CTO of Humankind
+    Systems. Contains 278,858 users (anonymized but with
+    demographic information) providing 1,149,780 ratings
+    (explicit / implicit) about 271,379 books.
+
+
+This dataset loader will download the dataset,
+which its size is around 22 Mb compressed. Once
+uncompressed the train set is around 130 MB.
+
+The data is downloaded, extracted and cached in the '~/scikit_crab_data'
+folder.
+
+References
+----------
+Improving Recommendation Lists Through Topic Diversification,
+Cai-Nicolas Ziegler, Sean M. McNee, Joseph A. Konstan, Georg Lausen;
+Proceedings of the 14th International World Wide Web Conference (WWW '05),
+May 10-14, 2005, Chiba, Japan.
+
+
+"""
+# Copyright (c) 2011 Marcel Caraciolo <marcel@muricoca.com>
+# License: Simplified BSD
+
+import os
+import urllib
+import logging
+import zipfile
+from os.path import dirname
+from os.path import join
+import numpy as np
+from base import Bunch
+import csv
+
+logger = logging.getLogger(__name__)
+
+URL = "http://www.informatik.uni-freiburg.de/~cziegler/BX/BX-CSV-Dump.zip"
+ARCHIVE_NAME = "BX-CSV-Dump.zip"
+
+
+def download_book_crossings(target_dir):
+    """ Download the book-crossing data and unzip it """
+    archive_path = os.path.join(target_dir, ARCHIVE_NAME)
+
+    if not os.path.exists(target_dir):
+        os.makedirs(target_dir)
+
+    if not os.path.exists(archive_path):
+        logger.warn("Downloading dataset from %s (77 MB)", URL)
+        opener = urllib.urlopen(URL)
+        open(archive_path, 'wb').write(opener.read())
+
+    logger.info("Decompressing %s", archive_path)
+
+    source_zip = zipfile.ZipFile(archive_path, 'r')
+    archives = []
+    for name in source_zip.namelist():
+        if name.find('.csv') != -1:
+            source_zip.extract(name, target_dir)
+            archives.append(name)
+    source_zip.close()
+    os.remove(archive_path)
+
+    return archives
+
+
+def load_bookcrossings(data_home=None, download_if_missing=True,
+                     implicit=False):
+    """
+    Load the filenames of the Book Crossings dataset
+
+    data_home: optional, default: None
+        Specify the storage folder for the datasets. If None,
+        all files is stored in '~/data subfolders.
+
+    download_if_missing: optional, True by default
+        If False, raise an IOError if the data is not locally available
+        instead of trying to download the data from the source site.
+
+    implicit: optional, False by default
+        If True, it will load the implicit ratings expressed by rating 0,
+        otherwise it will load the explicit ratings expressed by rating 1-10.
+
+    Examples
+    --------
+    >>> from os.path import join
+    >>> from os.path import dirname
+    >>> from scikits.crab.datasets.book_crossing import load_bookcrossings
+    >>> data_home = join(dirname(__file__), 'scikits/crab/datasets/tests/data/')
+    >>> books = load_bookcrossings(data_home)
+    >>> len(books.data)
+    26
+    >>> len(books.item_ids)
+    100
+
+    """
+
+    if data_home:
+        if not os.path.exists(data_home):
+            os.makedirs(data_home)
+    else:
+        data_home = join(dirname(__file__), 'data/')
+
+    try:
+        if not os.path.exists(os.path.join(data_home, 'BX-Book-Ratings.csv')) \
+            and not open(os.path.join(data_home, 'BX-Books.csv')):
+            raise IOError
+    except Exception, e:
+        print 80 * '_'
+        print 'Loading files failed'
+        print 80 * '_'
+        print e
+
+        if download_if_missing:
+            print 'downloading the dataset...'
+            try:
+                download_book_crossings(data_home)
+            except:
+                raise Exception('FAIL: Problems during the download.')
+            print 'dataset downloaded.'
+        else:
+            raise IOError('Book-Crossing dataset not found')
+
+    #TO FIX: it is not working for np.loadtxt
+    #ratings_m = np.loadtxt(os.path.join(data_home, 'BX-Book-Ratings.csv'),
+    #            delimiter=';', skiprows=1)
+
+    ratings_m = csv.reader(open(os.path.join(data_home,
+                'BX-Book-Ratings.csv')), delimiter=';')
+    ratings_m.next()
+    data_books = {}
+    if implicit:
+        for user_id, item_id, rating in ratings_m:
+            if rating == "0":
+                data_books.setdefault(user_id, {})
+                data_books[user_id][item_id] = True
+    else:
+        for user_id, item_id, rating in ratings_m:
+            rating = int(rating)
+            if rating != "0":
+                data_books.setdefault(user_id, {})
+                data_books[user_id][item_id] = int(rating)
+
+    #Read the titles
+    data_titles = np.loadtxt(os.path.join(data_home, 'BX-Books.csv'),
+             delimiter=';', usecols=(0, 1), dtype=str)
+
+    data_t = []
+    for item_id, label in data_titles:
+        data_t.append((item_id, label))
+    data_titles = dict(data_t)
+
+    fdescr = open(dirname(__file__) + '/descr/book-crossing.rst')
+
+    return Bunch(data=data_books, item_ids=data_titles,
+                 user_ids=None, DESCR=fdescr.read())
diff --git a/scikits/crab/datasets/data/movielens100k.csv b/scikits/crab/datasets/data/movielens100k.csv
diff --git a/scikits/crab/datasets/data/movielens100k.data b/scikits/crab/datasets/data/movielens100k.data
diff --git a/scikits/crab/datasets/data/movielens100k.item b/scikits/crab/datasets/data/movielens100k.item
diff --git a/scikits/crab/datasets/data/sample_movies.csv b/scikits/crab/datasets/data/sample_movies.csv
@@ -0,0 +1,35 @@
+Jack Matthews;Lady in the Water;3.0
+Jack Matthews;Snakes on a Planet;4.0
+Jack Matthews;You, Me and Dupree;3.5
+Jack Matthews;Superman Returns;5.0
+Jack Matthews;The Night Listener;3.0
+Mick LaSalle;Lady in the Water;3.0
+Mick LaSalle;Snakes on a Planet;4.0
+Mick LaSalle;Just My Luck;2.0
+Mick LaSalle;Superman Returns;3.0
+Mick LaSalle;You, Me and Dupree;2.0
+Mick LaSalle;The Night Listener;3.0
+Claudia Puig;Snakes on a Planet;3.5
+Claudia Puig;Just My Luck;3.0
+Claudia Puig;You, Me and Dupree;2.5
+Claudia Puig;Superman Returns;4.0
+Claudia Puig;The Night Listener;4.5
+Lisa Rose;Lady in the Water;2.5
+Lisa Rose;Snakes on a Planet;3.5
+Lisa Rose;Just My Luck;3.0
+Lisa Rose;Superman Returns;3.5
+Lisa Rose;The Night Listener;3.0
+Lisa Rose;You, Me and Dupree;2.5
+Toby;Snakes on a Planet;4.5
+Toby;Superman Returns;4.0
+Toby;You, Me and Dupree;1.0
+Gene Seymour;Lady in the Water;3.0
+Gene Seymour;Snakes on a Planet;3.5
+Gene Seymour;Just My Luck;1.5
+Gene Seymour;Superman Returns;5.0
+Gene Seymour;You, Me and Dupree;3.5
+Gene Seymour;The Night Listener;3.0
+Michael Phillips;Lady in the Water;2.5
+Michael Phillips;Snakes on a Planet;3.0
+Michael Phillips;Superman Returns;3.5
+Michael Phillips;The Night Listener;4.0
diff --git a/scikits/crab/datasets/data/sample_songs.csv b/scikits/crab/datasets/data/sample_songs.csv
@@ -0,0 +1,49 @@
+Angelica,The Strokes,2.5
+Angelica,Blues Traveler,3.5
+Angelica,Phoenix,5
+Angelica,Broken Bells,2
+Angelica,Norah Jones,4.5
+Angelica,Slightly Stoopid,1.5
+Angelica,Vampire Weekend,2
+Veronica,The Strokes,3
+Veronica,Slightly Stoopid,2.5
+Veronica,Norah Jones,5
+Veronica,Phoenix,4
+Veronica,Blues Traveler,3
+Sam,The Strokes,5
+Sam,Blues Traveler,5
+Sam,Phoenix,5
+Sam,Broken Bells,2
+Sam,Norah Jones,3
+Sam,Slightly Stoopid,4
+Jordyn,The Strokes,4
+Jordyn,Phoenix,5
+Jordyn,Broken Bells,4.5
+Jordyn,Deadmau5,4
+Jordyn,Norah Jones,5
+Jordyn,Slightly Stoopid,4.5
+Jordyn,Vampire Weekend,4
+Dan,The Strokes,4
+Dan,Blues Traveler,3
+Dan,Phoenix,3
+Dan,Broken Bells,4
+Dan,Deadmau5,4.5
+Dan,Slightly Stoopid,4.5
+Dan,Vampire Weekend,2
+Bill,Blues Traveler,2
+Bill,Phoenix,2
+Bill,Broken Bells,3.5
+Bill,Deadmau5,4
+Bill,Slightly Stoopid,3.5
+Bill,Vampire Weekend,3
+Chan,Blues Traveler,5
+Chan,Phoenix,5
+Chan,Broken Bells,1
+Chan,Deadmau5,1
+Chan,Norah Jones,3
+Chan,Slightly Stoopid,1
+Hailey,Broken Bells,4
+Hailey,Deadmau5,1
+Hailey,Norah Jones,4
+Hailey,Vampire Weekend,1
+Hailey,The Strokes,4
diff --git a/scikits/crab/datasets/descr/book-crossing.rst b/scikits/crab/datasets/descr/book-crossing.rst
@@ -0,0 +1,27 @@
+Book-Crossing Dataset ... mined by Cai-Nicolas Ziegler, DBIS Freiburg
+http://www.informatik.uni-freiburg.de/~cziegler/BX/
+
+Notes
+-----
+Collected by Cai-Nicolas Ziegler in a 4-week crawl (August / September 2004) from the Book-Crossing community with kind permission from Ron Hornbaker, CTO of Humankind Systems. Contains 278,858 users (anonymized but with demographic information) providing 1,149,780 ratings (explicit / implicit) about 271,379 books.
+
+[Freely available for research use when acknowledged with the following reference (further details on the dataset are given in this publication):
+Improving Recommendation Lists Through Topic Diversification,
+Cai-Nicolas Ziegler, Sean M. McNee, Joseph A. Konstan, Georg Lausen; Proceedings of the 14th International World Wide Web Conference (WWW '05), May 10-14, 2005, Chiba, Japan. To appear.
+
+
+This data set consists of
+	* 1,149,780 ratings (explicit / implicit) with (0-10) from 278,858 users to  271,379 books.
+
+Format
+------
+
+The Book-Crossing dataset comprises 3 tables.
+	*BX-Users
+	Contains the users. Note that user IDs (`User-ID`) have been anonymized and map to integers. Demographic data is provided (`Location`, `Age`) if available. Otherwise, these fields contain NULL-values.
+
+	*BX-Books
+	Books are identified by their respective ISBN. Invalid ISBNs have already been removed from the dataset. Moreover, some content-based information is given (`Book-Title`, `Book-Author`, `Year-Of-Publication`, `Publisher`), obtained from Amazon Web Services. Note that in case of several authors, only the first is provided. URLs linking to cover images are also given, appearing in three different flavours (`Image-URL-S`, `Image-URL-M`, `Image-URL-L`), i.e., small, medium, large. These URLs point to the Amazon web site.
+
+	*BX-Book-Ratings
+	Contains the book rating information. Ratings (`Book-Rating`) are either explicit, expressed on a scale from 1-10 (higher values denoting higher appreciation), or implicit, expressed by 0.
diff --git a/scikits/crab/datasets/descr/movielens100k.rst b/scikits/crab/datasets/descr/movielens100k.rst
@@ -0,0 +1,145 @@
+SUMMARY & USAGE LICENSE
+=============================================
+
+MovieLens data sets were collected by the GroupLens Research Project
+at the University of Minnesota.
+
+This data set consists of:
+	* 100,000 ratings (1-5) from 943 users on 1682 movies. 
+	* Each user has rated at least 20 movies. 
+        * Simple demographic info for the users (age, gender, occupation, zip)
+
+The data was collected through the MovieLens web site
+(movielens.umn.edu) during the seven-month period from September 19th, 
+1997 through April 22nd, 1998. This data has been cleaned up - users
+who had less than 20 ratings or did not have complete demographic
+information were removed from this data set. Detailed descriptions of
+the data file can be found at the end of this file.
+
+Neither the University of Minnesota nor any of the researchers
+involved can guarantee the correctness of the data, its suitability
+for any particular purpose, or the validity of results based on the
+use of the data set.  The data set may be used for any research
+purposes under the following conditions:
+
+     * The user may not state or imply any endorsement from the
+       University of Minnesota or the GroupLens Research Group.
+
+     * The user must acknowledge the use of the data set in
+       publications resulting from the use of the data set, and must
+       send us an electronic or paper copy of those publications.
+
+     * The user may not redistribute the data without separate
+       permission.
+
+     * The user may not use this information for any commercial or
+       revenue-bearing purposes without first obtaining permission
+       from a faculty member of the GroupLens Research Project at the
+       University of Minnesota.
+
+If you have any further questions or comments, please contact Jon Herlocker
+<herlocke@cs.umn.edu>. 
+
+ACKNOWLEDGEMENTS
+==============================================
+
+Thanks to Al Borchers for cleaning up this data and writing the
+accompanying scripts.
+
+PUBLISHED WORK THAT HAS USED THIS DATASET
+==============================================
+
+Herlocker, J., Konstan, J., Borchers, A., Riedl, J.. An Algorithmic
+Framework for Performing Collaborative Filtering. Proceedings of the
+1999 Conference on Research and Development in Information
+Retrieval. Aug. 1999.
+
+FURTHER INFORMATION ABOUT THE GROUPLENS RESEARCH PROJECT
+==============================================
+
+The GroupLens Research Project is a research group in the Department
+of Computer Science and Engineering at the University of Minnesota.
+Members of the GroupLens Research Project are involved in many
+research projects related to the fields of information filtering,
+collaborative filtering, and recommender systems. The project is lead
+by professors John Riedl and Joseph Konstan. The project began to
+explore automated collaborative filtering in 1992, but is most well
+known for its world wide trial of an automated collaborative filtering
+system for Usenet news in 1996.  The technology developed in the
+Usenet trial formed the base for the formation of Net Perceptions,
+Inc., which was founded by members of GroupLens Research. Since then
+the project has expanded its scope to research overall information
+filtering solutions, integrating in content-based methods as well as
+improving current collaborative filtering technology.
+
+Further information on the GroupLens Research project, including
+research publications, can be found at the following web site:
+
+        http://www.grouplens.org/
+
+GroupLens Research currently operates a movie recommender based on
+collaborative filtering:
+
+        http://www.movielens.org/
+
+DETAILED DESCRIPTIONS OF DATA FILES
+==============================================
+
+Here are brief descriptions of the data.
+
+ml-data.tar.gz   -- Compressed tar file.  To rebuild the u data files do this:
+                gunzip ml-data.tar.gz
+                tar xvf ml-data.tar
+                mku.sh
+
+u.data     -- The full u data set, 100000 ratings by 943 users on 1682 items.
+              Each user has rated at least 20 movies.  Users and items are
+              numbered consecutively from 1.  The data is randomly
+              ordered. This is a tab separated list of 
+	         user id | item id | rating | timestamp. 
+              The time stamps are unix seconds since 1/1/1970 UTC   
+
+u.info     -- The number of users, items, and ratings in the u data set.
+
+u.item     -- Information about the items (movies); this is a tab separated
+              list of
+              movie id | movie title | release date | video release date |
+              IMDb URL | unknown | Action | Adventure | Animation |
+              Children's | Comedy | Crime | Documentary | Drama | Fantasy |
+              Film-Noir | Horror | Musical | Mystery | Romance | Sci-Fi |
+              Thriller | War | Western |
+              The last 19 fields are the genres, a 1 indicates the movie
+              is of that genre, a 0 indicates it is not; movies can be in
+              several genres at once.
+              The movie ids are the ones used in the u.data data set.
+
+u.genre    -- A list of the genres.
+
+u.user     -- Demographic information about the users; this is a tab
+              separated list of
+              user id | age | gender | occupation | zip code
+              The user ids are the ones used in the u.data data set.
+
+u.occupation -- A list of the occupations.
+
+u1.base    -- The data sets u1.base and u1.test through u5.base and u5.test
+u1.test       are 80%/20% splits of the u data into training and test data.
+u2.base       Each of u1, ..., u5 have disjoint test sets; this if for
+u2.test       5 fold cross validation (where you repeat your experiment
+u3.base       with each training and test set and average the results).
+u3.test       These data sets can be generated from u.data by mku.sh.
+u4.base
+u4.test
+u5.base
+u5.test
+
+ua.base    -- The data sets ua.base, ua.test, ub.base, and ub.test
+ua.test       split the u data into a training set and a test set with
+ub.base       exactly 10 ratings per user in the test set.  The sets
+ub.test       ua.test and ub.test are disjoint.  These data sets can
+              be generated from u.data by mku.sh.
+
+allbut.pl  -- The script that generates training and test sets where
+              all but n of a users ratings are in the training data.
+
+mku.sh     -- A shell script to generate all the u data sets from u.data.
diff --git a/scikits/crab/datasets/descr/sample_movies.rst b/scikits/crab/datasets/descr/sample_movies.rst
@@ -0,0 +1,7 @@
+sample_movies data set was collected by the book called 
+Programming the Collective Intelligence by Toby Segaran 
+
+Notes
+-----
+This data set consists of
+	* n ratings with (1-5) from n users to n movies.
diff --git a/scikits/crab/datasets/descr/sample_songs.rst b/scikits/crab/datasets/descr/sample_songs.rst
@@ -0,0 +1,7 @@
+Sample_song data set was collected by the e-book called 
+A Programmer's Guide to Data Mining - http://guidetodatamining.com
+
+Notes
+-----
+This data set consists of
+	* 49 ratings with (1-5) from 8 users to 8 movies.
diff --git a/scikits/crab/datasets/tests/__init__.py b/scikits/crab/datasets/tests/__init__.py
diff --git a/scikits/crab/datasets/tests/data/BX-Book-Ratings.csv b/scikits/crab/datasets/tests/data/BX-Book-Ratings.csv
@@ -0,0 +1,100 @@
+"User-ID";"ISBN";"Book-Rating"
+"276725";"034545104X";"0"
+"276726";"0155061224";"5"
+"276727";"0446520802";"0"
+"276729";"052165615X";"3"
+"276729";"0521795028";"6"
+"276733";"2080674722";"0"
+"276736";"3257224281";"8"
+"276737";"0600570967";"6"
+"276744";"038550120X";"7"
+"276745";"342310538";"10"
+"276746";"0425115801";"0"
+"276746";"0449006522";"0"
+"276746";"0553561618";"0"
+"276746";"055356451X";"0"
+"276746";"0786013990";"0"
+"276746";"0786014512";"0"
+"276747";"0060517794";"9"
+"276747";"0451192001";"0"
+"276747";"0609801279";"0"
+"276747";"0671537458";"9"
+"276747";"0679776818";"8"
+"276747";"0943066433";"7"
+"276747";"1570231028";"0"
+"276747";"1885408226";"7"
+"276748";"0747558167";"6"
+"276748";"3442437407";"0"
+"276751";"033390804X";"0"
+"276751";"3596218098";"8"
+"276754";"0684867621";"8"
+"276755";"0451166892";"5"
+"276760";"8440682697";"10"
+"276762";"034544003X";"0"
+"276762";"0380000059";"0"
+"276762";"0380711524";"5"
+"276762";"0451167317";"0"
+"276762";"0451454952";"0"
+"276762";"0843920262";"0"
+"276762";"3404122879";"0"
+"276762";"3404182928";"0"
+"276762";"3404611306";"0"
+"276762";"342662429";"0"
+"276762";"3426690179";"0"
+"276762";"3442424216";"0"
+"276762";"3442425573";"0"
+"276762";"3453092007";"8"
+"276762";"3453157745";"0"
+"276762";"3453176944";"0"
+"276762";"3453185137";"0"
+"276762";"3453185323";"0"
+"276762";"3453213025";"3"
+"276762";"3453877241";"0"
+"276762";"3492226604";"0"
+"276762";"3517017442";"0"
+"276762";"3596125006";"0"
+"276762";"B0000BLD7X";"0"
+"276762";"N3453124715";"4"
+"276765";"9029716894";"0"
+"276768";"9057868059";"4"
+"276772";"0140279091";"0"
+"276772";"0553572369";"7"
+"276772";"0571058086";"0"
+"276772";"3499230933";"10"
+"276772";"3596151465";"10"
+"276774";"0099543818";"0"
+"276774";"3404147723";"0"
+"276774";"3423111321";"0"
+"276774";"3442136644";"9"
+"276774";"3492232000";"0"
+"276780";"8434811634";"0"
+"276780";"8484330478";"7"
+"276780";"8484332039";"7"
+"276786";"2864322102";"6"
+"276786";"8402065945";"0"
+"276786";"8423314901";"0"
+"276786";"842333533X";"0"
+"276786";"8427911769";"0"
+"276786";"8433914456";"0"
+"276786";"8437606322";"8"
+"276786";"8445072919";"0"
+"276786";"8466300821";"6"
+"276786";"847765011X";"0"
+"276786";"8478442588";"6"
+"276786";"8495368099";"0"
+"276788";"0345443683";"8"
+"276788";"043935806X";"7"
+"276788";"055310666X";"10"
+"276796";"0330332775";"5"
+"276796";"0330367358";"0"
+"276798";"0006379702";"5"
+"276798";"3423084049";"0"
+"276798";"3442131340";"7"
+"276798";"3442437407";"0"
+"276798";"3446202102";"0"
+"276798";"3453073398";"0"
+"276798";"3453115783";"0"
+"276798";"3499134004";"0"
+"276798";"349915398X";"0"
+"276798";"3548603203";"6"
+"276798";"3764501383";"0"
diff --git a/scikits/crab/datasets/tests/data/BX-Books.csv b/scikits/crab/datasets/tests/data/BX-Books.csv
diff --git a/scikits/crab/datasets/tests/test_base.py b/scikits/crab/datasets/tests/test_base.py
@@ -0,0 +1,65 @@
+from os.path import join
+from os.path import dirname
+from nose.tools import assert_equal, assert_raises
+from ..base import load_movielens_r100k, load_sample_songs, load_sample_movies
+from ..book_crossing import load_bookcrossings
+from ...utils.testing import assert_in
+
+
+def test_movielens_r100k():
+    #with timestamp = False
+    movies = load_movielens_r100k()
+    assert_in(movies, in_=['data', 'item_ids', 'user_ids', 'DESCR'])
+    assert_equal(len(movies.data), 943)
+    assert_equal(len(movies.item_ids), 1682)
+    assert_equal(sum([len(items) for key, items in
+             movies.data.iteritems()]), 100000)
+
+    #with timestamp = True
+    movies = load_movielens_r100k(True)
+    assert_in(movies, in_=['data', 'item_ids', 'user_ids', 'DESCR'])
+    assert_equal(len(movies.data), 943)
+    assert_equal(len(movies.item_ids), 1682)
+    assert_equal(movies.data[1][1], (874965758, 5))
+    assert_equal(sum([len(items) for key, items in
+             movies.data.iteritems()]), 100000)
+
+
+def test_sample_songs():
+    songs = load_sample_songs()
+    assert_in(songs, in_=['data', 'item_ids', 'user_ids', 'DESCR'])
+    assert_equal(len(songs.data), 8)
+    assert_equal(len(songs.item_ids), 8)
+    assert_equal(sum([len(items) for key, items in
+             songs.data.iteritems()]), 49)
+
+
+def test_sample_movies():
+    movies = load_sample_movies()
+    assert_in(movies, in_=['data', 'item_ids', 'user_ids', 'DESCR'])
+    assert_equal(len(movies.data), 7)
+    assert_equal(len(movies.item_ids), 6)
+    assert_equal(sum([len(items) for key, items in
+             movies.data.iteritems()]), 35)
+
+
+def test_load_bookcrossings():
+    data_home = join(dirname(__file__), 'data/')
+    #explicit with sample data from tests/data
+    books = load_bookcrossings(data_home)
+    assert_equal(len(books.data), 26)
+    assert_equal(len(books.item_ids), 100)
+    assert_equal(sum([len(items) for key, items in
+             books.data.iteritems()]), 99)
+
+    #implicit with sample data from tests/data
+    books = load_bookcrossings(data_home, implicit=True)
+    assert_equal(len(books.data), 15)
+    assert_equal(len(books.item_ids), 100)
+    assert_equal(sum([len(items) for key, items in
+             books.data.iteritems()]), 60)
+
+    #explicit with download denied.
+    data_home = dirname(__file__)
+    assert_raises(IOError, load_bookcrossings, data_home, implicit=False,
+                download_if_missing=False)
diff --git a/scikits/crab/models/__init__.py b/scikits/crab/models/__init__.py
@@ -1,2 +1,2 @@
-from .classes import DictPreferenceDataModel, MatrixPreferenceDataModel, \
-         MatrixBooleanPrefDataModel, DictBooleanPrefDataModel
+from .classes import  MatrixPreferenceDataModel, \
+         MatrixBooleanPrefDataModel
diff --git a/scikits/crab/models/classes.py b/scikits/crab/models/classes.py
diff --git a/scikits/crab/models/tests/test_models.py b/scikits/crab/models/tests/test_models.py
diff --git a/scikits/crab/recommenders/knn/classes.py b/scikits/crab/recommenders/knn/classes.py
@@ -63,7 +63,7 @@ class ItemBasedRecommender(ItemRecommender):
 
     Examples
     -----------
-    >>> from scikits.crab.models.classes import DictPreferenceDataModel
+    >>> from scikits.crab.models.classes import MatrixPreferenceDataModel
     >>> from scikits.crab.recommenders.knn.classes import ItemBasedRecommender
     >>> from scikits.crab.similarities.basic_similarities import ItemSimilarity
     >>> from scikits.crab.recommenders.knn.item_strategies import ItemsNeighborhoodStrategy
@@ -89,7 +89,7 @@ class ItemBasedRecommender(ItemRecommender):
     'Penny Frewman': {'Snakes on a Plane':4.5,'You, Me and Dupree':1.0, \
     'Superman Returns':4.0}, \
     'Maria Gabriela': {}}
-    >>> model = DictPreferenceDataModel(movies)
+    >>> model = MatrixPreferenceDataModel(movies)
     >>> items_strategy = ItemsNeighborhoodStrategy()
     >>> similarity = ItemSimilarity(model, euclidean_distances)
     >>> recsys = ItemBasedRecommender(model, similarity, items_strategy)
@@ -389,7 +389,7 @@ class UserBasedRecommender(UserRecommender):
 
     Examples
     -----------
-    >>> from scikits.crab.models.classes import DictPreferenceDataModel
+    >>> from scikits.crab.models.classes import MatrixPreferenceDataModel
     >>> from scikits.crab.recommenders.knn.classes import UserBasedRecommender
     >>> from scikits.crab.similarities.basic_similarities import UserSimilarity
     >>> from scikits.crab.recommenders.knn.neighborhood_strategies import NearestNeighborsStrategy
@@ -415,7 +415,7 @@ class UserBasedRecommender(UserRecommender):
     'Penny Frewman': {'Snakes on a Plane':4.5,'You, Me and Dupree':1.0, \
     'Superman Returns':4.0}, \
     'Maria Gabriela': {}}
-    >>> model = DictPreferenceDataModel(movies)
+    >>> model = MatrixPreferenceDataModel(movies)
     >>> nhood_strategy = NearestNeighborsStrategy()
     >>> similarity = UserSimilarity(model, euclidean_distances)
     >>> recsys = UserBasedRecommender(model, similarity, nhood_strategy)

diff --git a/scikits/crab/recommenders/knn/tests/test_classes.py b/scikits/crab/recommenders/knn/tests/test_classes.py
diff --git a/scikits/crab/recommenders/knn/tests/test_item_strategies.py b/scikits/crab/recommenders/knn/tests/test_item_strategies.py
@@ -1,7 +1,7 @@
 import numpy as np
 from numpy.testing import assert_array_equal
 from nose.tools import assert_raises
-from ....models.classes import DictPreferenceDataModel, MatrixPreferenceDataModel
+from ....models.classes import  MatrixPreferenceDataModel
 from ..item_strategies import ItemsNeighborhoodStrategy, AllPossibleItemsStrategy
 from ....models.utils import UserNotFoundError
 
@@ -28,76 +28,43 @@
 
 def test_ItemsNeighborhoodStrategy():
     #Empty Dataset
-    model = DictPreferenceDataModel({})
-    strategy = ItemsNeighborhoodStrategy()
-    assert_raises(UserNotFoundError, strategy.candidate_items, 'Lorena Abreu', model)
-
     model = MatrixPreferenceDataModel({})
     strategy = ItemsNeighborhoodStrategy()
     assert_raises(UserNotFoundError, strategy.candidate_items, 'Lorena Abreu', model)
 
     #Possible candidates
-    model = DictPreferenceDataModel(movies)
-    strategy = ItemsNeighborhoodStrategy()
-    assert_array_equal(np.array(['Lady in the Water']), strategy.candidate_items('Lorena Abreu', model))
-
     model = MatrixPreferenceDataModel(movies)
     strategy = ItemsNeighborhoodStrategy()
     assert_array_equal(np.array(['Lady in the Water']), strategy.candidate_items('Lorena Abreu', model))
 
     #Empty candidates
-    model = DictPreferenceDataModel(movies)
-    strategy = ItemsNeighborhoodStrategy()
-    assert_array_equal(np.array([], dtype='|S'), strategy.candidate_items('Marcel Caraciolo', model))
-
     model = MatrixPreferenceDataModel(movies)
     strategy = ItemsNeighborhoodStrategy()
     assert_array_equal(np.array([], dtype='|S'), strategy.candidate_items('Marcel Caraciolo', model))
 
     #Empty candidates
-    model = DictPreferenceDataModel(movies)
-    strategy = ItemsNeighborhoodStrategy()
-    assert_array_equal(np.array([], dtype=bool), strategy.candidate_items('Maria Gabriela', model))
-
     model = MatrixPreferenceDataModel(movies)
     strategy = ItemsNeighborhoodStrategy()
     assert_array_equal(np.array([], dtype=bool), strategy.candidate_items('Maria Gabriela', model))
 
 
 def test_AllPossibleItemsStrategy():
     #Empty Dataset
-    model = DictPreferenceDataModel({})
-    strategy = AllPossibleItemsStrategy()
-    assert_raises(UserNotFoundError, strategy.candidate_items, 'Lorena Abreu', model)
-
     model = MatrixPreferenceDataModel({})
     strategy = AllPossibleItemsStrategy()
     assert_raises(UserNotFoundError, strategy.candidate_items, 'Lorena Abreu', model)
 
     #Possible candidates
-    model = DictPreferenceDataModel(movies)
-    strategy = AllPossibleItemsStrategy()
-    assert_array_equal(np.array(['Lady in the Water']), strategy.candidate_items('Lorena Abreu', model))
-
     model = MatrixPreferenceDataModel(movies)
     strategy = AllPossibleItemsStrategy()
     assert_array_equal(np.array(['Lady in the Water']), strategy.candidate_items('Lorena Abreu', model))
 
     #Empty candidates
-    model = DictPreferenceDataModel(movies)
-    strategy = AllPossibleItemsStrategy()
-    assert_array_equal(np.array([], dtype='|S'), strategy.candidate_items('Marcel Caraciolo', model))
-
     model = MatrixPreferenceDataModel(movies)
     strategy = AllPossibleItemsStrategy()
     assert_array_equal(np.array([], dtype='|S'), strategy.candidate_items('Marcel Caraciolo', model))
 
     #Empty candidates
-    model = DictPreferenceDataModel(movies)
-    strategy = AllPossibleItemsStrategy()
-    assert_array_equal(np.array(['Just My Luck', 'Lady in the Water', 'Snakes on a Plane',
-       'Superman Returns', 'The Night Listener', 'You, Me and Dupree']), strategy.candidate_items('Maria Gabriela', model))
-
     model = MatrixPreferenceDataModel(movies)
     strategy = AllPossibleItemsStrategy()
     assert_array_equal(np.array(['Just My Luck', 'Lady in the Water', 'Snakes on a Plane',

diff --git a/scikits/crab/recommenders/knn/tests/test_neighborhood_strategies.py b/scikits/crab/recommenders/knn/tests/test_neighborhood_strategies.py
@@ -1,9 +1,7 @@
 import numpy as np
 from numpy.testing import assert_array_equal
-from nose.tools import assert_raises
-from ....models.classes import DictPreferenceDataModel, MatrixPreferenceDataModel
+from ....models.classes import MatrixPreferenceDataModel
 from ..neighborhood_strategies import AllNeighborsStrategy, NearestNeighborsStrategy
-from ....models.utils import UserNotFoundError
 
 
 movies = {'Marcel Caraciolo': {'Lady in the Water': 2.5, 'Snakes on a Plane': 3.5,
@@ -28,20 +26,11 @@
 
 def test_AllNeighborsStrategy():
     #Empty Dataset
-    model = DictPreferenceDataModel({})
-    strategy = AllNeighborsStrategy()
-    assert_array_equal(np.array([]), strategy.user_neighborhood('Lorena Abreu', model))
-
     model = MatrixPreferenceDataModel({})
     strategy = AllNeighborsStrategy()
     assert_array_equal(np.array([]), strategy.user_neighborhood('Lorena Abreu', model))
 
     #Possible candidates
-    model = DictPreferenceDataModel(movies)
-    strategy = AllNeighborsStrategy()
-    assert_array_equal(np.array(['Leopoldo Pires', 'Luciana Nunes', 'Marcel Caraciolo',
-       'Maria Gabriela', 'Penny Frewman', 'Sheldom', 'Steve Gates']), strategy.user_neighborhood('Lorena Abreu', model))
-
     model = MatrixPreferenceDataModel(movies)
     strategy = AllNeighborsStrategy()
     assert_array_equal(np.array(['Leopoldo Pires', 'Luciana Nunes', 'Marcel Caraciolo',
@@ -50,21 +39,11 @@ def test_AllNeighborsStrategy():
 
 def test_NearestNeighborsStrategy():
     #Empty Dataset
-    model = DictPreferenceDataModel({})
-    strategy = NearestNeighborsStrategy()
-    assert_array_equal(np.array([]), strategy.user_neighborhood('Lorena Abreu', model))
-
     model = MatrixPreferenceDataModel({})
     strategy = NearestNeighborsStrategy()
     assert_array_equal(np.array([]), strategy.user_neighborhood('Lorena Abreu', model))
 
     #Possible candidates
-    model = DictPreferenceDataModel(movies)
-    strategy = NearestNeighborsStrategy()
-    assert_array_equal(np.array(['Leopoldo Pires', 'Marcel Caraciolo', 'Penny Frewman',
-     'Sheldom', 'Steve Gates', 'Luciana Nunes'], dtype='|S16'),
-        strategy.user_neighborhood('Lorena Abreu', model))
-
     model = MatrixPreferenceDataModel(movies)
     strategy = NearestNeighborsStrategy()
     assert_array_equal(np.array(['Leopoldo Pires', 'Marcel Caraciolo', 'Penny Frewman',
@@ -84,31 +63,21 @@ def test_NearestNeighborsStrategy():
     assert_array_equal(np.array(['Leopoldo Pires']),
         strategy.user_neighborhood(user_id='Lorena Abreu', data_model=model,
                 minimal_similarity=0.4))
-    #Empty candidates
-    model = DictPreferenceDataModel(movies)
-    strategy = NearestNeighborsStrategy()
-    assert_array_equal(np.array(['Leopoldo Pires', 'Steve Gates', 'Lorena Abreu', 'Penny Frewman',
-    'Sheldom', 'Luciana Nunes'], dtype='|S14'),
-        strategy.user_neighborhood('Marcel Caraciolo', model))
 
+    #Empty candidates
     model = MatrixPreferenceDataModel(movies)
     strategy = NearestNeighborsStrategy()
     assert_array_equal(np.array(['Leopoldo Pires', 'Steve Gates', 'Lorena Abreu', 'Penny Frewman',
     'Sheldom', 'Luciana Nunes'], dtype='|S14'),
         strategy.user_neighborhood('Marcel Caraciolo', model))
 
     #Empty candidates
-    model = DictPreferenceDataModel(movies)
+    model = MatrixPreferenceDataModel(movies)
     strategy = NearestNeighborsStrategy()
     assert_array_equal(np.array([], dtype=bool), strategy.user_neighborhood('Maria Gabriela', model))
 
     #Raise exception with an invalid similarity
     #Empty candidates
-    model = DictPreferenceDataModel(movies)
-    strategy = NearestNeighborsStrategy()
-    assert_raises(ValueError, strategy.user_neighborhood,
-            user_id='Lorena Abreu', data_model=model, n_similarity='item_similarity')
-
     model = MatrixPreferenceDataModel(movies)
     strategy = NearestNeighborsStrategy()
     assert_array_equal(np.array([], dtype=bool), strategy.user_neighborhood('Maria Gabriela', model))
diff --git a/scikits/crab/recommenders/svd/tests/test_classes.py b/scikits/crab/recommenders/svd/tests/test_classes.py
@@ -1,9 +1,9 @@
 import numpy as np
 from numpy.testing import assert_array_equal
-from nose.tools import assert_raises, assert_equals, assert_almost_equals
+from nose.tools import assert_equals, assert_almost_equals
 from ...knn.item_strategies import AllPossibleItemsStrategy, ItemsNeighborhoodStrategy
-from ....models.classes import DictPreferenceDataModel, MatrixPreferenceDataModel, \
-    DictBooleanPrefDataModel, MatrixBooleanPrefDataModel
+from ....models.classes import  MatrixPreferenceDataModel, \
+     MatrixBooleanPrefDataModel
 from ..classes import MatrixFactorBasedRecommender
 
 
@@ -26,9 +26,7 @@
 'Penny Frewman': {'Snakes on a Plane': 4.5, 'You, Me and Dupree': 1.0, 'Superman Returns': 4.0},
 'Maria Gabriela': {}}
 
-dict_model = DictPreferenceDataModel(movies)
 matrix_model = MatrixPreferenceDataModel(movies)
-boolean_model = DictBooleanPrefDataModel(movies)
 boolean_matrix_model = MatrixBooleanPrefDataModel(movies)
 
 
@@ -51,11 +49,6 @@ def test_create_MatrixFactorBasedRecommender():
     assert_equals(recsys.item_factors.shape, (6, 2))
     assert_equals(recsys._global_bias, 3.2285714285714286)
 
-    assert_raises(TypeError, MatrixFactorBasedRecommender,
-        model=dict_model,
-        items_selection_strategy=items_strategy,
-        n_features=2)
-
 
 def test_all_other_items_MatrixFactorBasedRecommender():
     items_strategy = AllPossibleItemsStrategy()

diff --git a/scikits/crab/similarities/basic_similarities.py b/scikits/crab/similarities/basic_similarities.py
@@ -61,7 +61,7 @@ class UserSimilarity(BaseSimilarity):
 
     Examples
     ---------
-    >>> from scikits.crab.models.classes import DictPreferenceDataModel
+    >>> from scikits.crab.models.classes import MatrixPreferenceDataModel
     >>> from scikits.crab.metrics.pairwise import cosine_distances
     >>> from scikits.crab.similarities.basic_similarities import UserSimilarity
     >>> movies = {'Marcel Caraciolo': {'Lady in the Water': 2.5, \
@@ -85,7 +85,7 @@ class UserSimilarity(BaseSimilarity):
     'Penny Frewman': {'Snakes on a Plane':4.5,'You, Me and Dupree':1.0, \
     'Superman Returns':4.0}, \
     'Maria Gabriela': {}}
-    >>> model = DictPreferenceDataModel(movies)
+    >>> model = MatrixPreferenceDataModel(movies)
     >>> similarity = UserSimilarity(model, cosine_distances, 3)
     >>> similarity['Marcel Caraciolo']
     [('Marcel Caraciolo', 1.0), ('Sheldom', 0.99127582693458016),
@@ -165,7 +165,7 @@ class ItemSimilarity(BaseSimilarity):
 
     Examples
     ---------
-    >>> from scikits.crab.models.classes import DictPreferenceDataModel
+    >>> from scikits.crab.models.classes import MatrixPreferenceDataModel
     >>> from scikits.crab.metrics.pairwise import cosine_distances
     >>> from scikits.crab.similarities.basic_similarities import ItemSimilarity
     >>> movies = {'Marcel Caraciolo': {'Lady in the Water': 2.5, \
@@ -189,7 +189,7 @@ class ItemSimilarity(BaseSimilarity):
     'Penny Frewman': {'Snakes on a Plane':4.5,'You, Me and Dupree':1.0, \
     'Superman Returns':4.0}, \
     'Maria Gabriela': {}}
-    >>> model = DictPreferenceDataModel(movies)
+    >>> model = MatrixPreferenceDataModel(movies)
     >>> similarity = ItemSimilarity(model, cosine_distances, 3)
     >>> similarity['The Night Listener']
     [('The Night Listener', 1.0), ('Lady in the Water', 0.98188311415053031),

diff --git a/scikits/crab/similarities/tests/test_basic_similarities.py b/scikits/crab/similarities/tests/test_basic_similarities.py
diff --git a/scikits/crab/utils/__init__.py b/scikits/crab/utils/__init__.py
diff --git a/scikits/crab/utils/testing.py b/scikits/crab/utils/testing.py
@@ -0,0 +1,15 @@
+"""Testing utilities."""
+
+# Copyright (c) 2011 Marcel Caraciolo <marcel@muricoca.com>
+# License: Simplified BSD
+
+
+def assert_in(obj, in_=None, out_=None):
+    """Checks that all names in `in_` as in `obj`, but no name
+    in `out_` is."""
+    if in_ is not None:
+        for name in in_:
+            assert name in obj
+    if out_ is not None:
+        for name in out_:
+            assert name not in obj