def main():
import pprint
pp = pprint.PrettyPrinter(indent=4)
from scikits.crab import datasets
movies = datasets.load_sample_songs()
print "Movies Data:", pp.pformat(movies)
print "Movies Data Matrix :", pp.pformat(movies.data)
from scikits.crab.models import MatrixPreferenceDataModel
#Build the model
#new_movies = {u'1': [1, 2, 3, 4, 5], u'3': [2, 3, 4, 5, 6], u'2': [1, 2, 3, 4, 5, 6], u'5': [2, 3, 4], u'4': [1, 2, 3, 4, 5, 6], u'7': [1, 2, 4, 5], u'6': [1, 2, 3, 4, 5, 6]}
#print "New moview hash", pp.pformat(new_movies)
#model = MatrixBooleanPrefDataModel(new_movies)
model = MatrixPreferenceDataModel(movies.data)
import json
from scikits.crab.metrics import spearman_coefficient
from scikits.crab.similarities import UserSimilarity, ItemSimilarity
#Build the similarity
user_similarity = UserSimilarity(model, pearson_correlation)
item_similarity = ItemSimilarity(model, pearson_correlation)
from scikits.crab.recommenders.knn import UserBasedRecommender, ItemBasedRecommender
#Build the User based recommender
user_recommender = UserBasedRecommender(model, user_similarity, with_preference=True)
item_recommender = ItemBasedRecommender(model, item_similarity, with_preference=True)
print "recommendations for user 5", user_recommender.recommend("5")
print "recommendations for item 3", item_recommender.recommend("3")
def test_basic_methods_DictPreferenceDataModel():
#Empty Dataset
model = DictPreferenceDataModel({})
assert_equals(model.dataset, {})
assert_array_equal(np.array([]), model.user_ids())
assert_array_equal(np.array([]), model.item_ids())
assert_equals(True, model.has_preference_values())
assert_equals(0, model.users_count())
assert_equals(0, model.items_count())
assert_equals(-np.inf, model.maximum_preference_value())
assert_equals(np.inf, model.minimum_preference_value())
assert("DictPreferenceDataModel (0 by 0)" in model.__str__())
movies = movies_dict()
#Simple DataSet
model = DictPreferenceDataModel(movies)
assert_equals(model.dataset, movies)
assert_array_equal(np.sort(np.array(['Leopoldo Pires', 'Lorena Abreu', 'Luciana Nunes',
'Marcel Caraciolo', 'Maria Gabriela', 'Penny Frewman', 'Sheldom', 'Steve Gates'])),
np.sort(model.user_ids()))
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']), np.sort(model.item_ids()))
assert_equals(True, model.has_preference_values())
assert_equals(8, model.users_count())
assert_equals(6, model.items_count())
assert_equals(5.0, model.maximum_preference_value())
assert_equals(1.0, model.minimum_preference_value())
assert_equals(sorted([('Just My Luck', 3.0), ('Lady in the Water', 2.5),
('Snakes on a Plane', 3.5), ('Superman Returns', 3.5),
('The Night Listener', 3.0), ('You, Me and Dupree', 2.5)]), sorted(model['Marcel Caraciolo']))
elements = [pref for pref in model]
assert_array_equal([('Lady in the Water', 2.5), ('Snakes on a Plane', 3.0), \
('Superman Returns', 3.5), ('The Night Listener', 4.0)], elements[0][1])
assert("DictPreferenceDataModel (8 by 6)" in model.__str__())
#SampleSongs DataSet
songs = load_sample_songs()
model = DictPreferenceDataModel(songs.data)
assert_equals(model.dataset, songs.data)
assert_array_equal(np.array([1, 2, 3, 4, 5, 6, 7, 8]),
model.user_ids())
assert_array_equal(np.array([1, 2, 3, 4, 5, 6, 7, 8]), model.item_ids())
assert_equals(True, model.has_preference_values())
assert_equals(8, model.users_count())
assert_equals(8, model.items_count())
assert_equals(5.0, model.maximum_preference_value())
assert_equals(1.0, model.minimum_preference_value())
assert_equals([(1, 2.5), (2, 3.5), (3, 5.0), (4, 2.0), (5, 4.5), (6, 1.5), (7, 2.0)], model[1])
elements = [pref for pref in model]
assert_array_equal([(1, 2.5), (2, 3.5), (3, 5.0), (4, 2.0), (5, 4.5), (6, 1.5), (7, 2.0)],
elements[0][1])
assert("DictPreferenceDataModel (8 by 8)" in model.__str__())
def test_basic_methods_MatrixBooleanPrefDataModel():
#Empty Dataset
model = MatrixBooleanPrefDataModel({})
assert_equals(model.dataset, {})
assert_array_equal(np.array([]), model.user_ids())
assert_array_equal(np.array([]), model.item_ids())
assert_equals(False, model.has_preference_values())
assert_equals(0, model.users_count())
assert_equals(0, model.items_count())
assert("MatrixBooleanPrefDataModel (0 by 0)" in model.__str__())
#Simple DataSet
model = MatrixBooleanPrefDataModel(movies_boolean)
assert_equals(model.dataset, movies_boolean)
assert_array_equal(np.array(['Leopoldo Pires', 'Lorena Abreu', 'Luciana Nunes',
'Marcel Caraciolo', 'Maria Gabriela', 'Penny Frewman', 'Sheldom', 'Steve Gates']),
model.user_ids())
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']), model.item_ids())
assert_equals(False, model.has_preference_values())
assert_equals(8, model.users_count())
assert_equals(6, model.items_count())
assert_array_equal(['Just My Luck', 'Lady in the Water',
'Snakes on a Plane', 'Superman Returns',
'The Night Listener', 'You, Me and Dupree'], model['Marcel Caraciolo'])
elements = [pref for pref in model]
assert_array_equal(['Lady in the Water', 'Snakes on a Plane', \
'Superman Returns', 'The Night Listener'], elements[0][1])
assert("MatrixBooleanPrefDataModel (8 by 6)" in model.__str__())
songs = load_sample_songs()
model = MatrixBooleanPrefDataModel(songs.data)
assert_equals(model.dataset, songs_boolean)
assert_array_equal(np.array([1, 2, 3, 4, 5, 6, 7, 8]),
model.user_ids())
assert_array_equal(np.array([1, 2, 3, 4, 5, 6, 7, 8]), model.item_ids())
assert_equals(False, model.has_preference_values())
assert_equals(8, model.users_count())
assert_equals(8, model.items_count())
assert_equals(1.0, model.maximum_preference_value())
assert_equals(0.0, model.minimum_preference_value())
assert_array_equal([1, 2, 3, 4, 5, 6, 7], model[1])
elements = [pref for pref in model]
assert_array_equal([1, 2, 3, 4, 5, 6, 7],
elements[0][1])
assert("MatrixBooleanPrefDataModel (8 by 8)" in model.__str__())
from scikits.crab import datasets movies = datasets.load_sample_movies() songs = datasets.load_sample_songs() print movies.data print movies.user_ids print movies.item_ids from scikits.crab.models import MatrixPreferenceDataModel #Build the model model = MatrixPreferenceDataModel(movies.data) from scikits.crab.metrics import pearson_correlation from scikits.crab.similarities import UserSimilarity #Build the similarity similarity = UserSimilarity(model, pearson_correlation) print similarity[1] from scikits.crab.metrics.pairwise import euclidean_distances similarity = UserSimilarity(model, euclidean_distances) print similarity[5] from scikits.crab.recommenders.knn import UserBasedRecommender #Build the User based recommender recommender = UserBasedRecommender(model, similarity, with_preference=True) #Recommend items for the user 5 (Toby) recommender.recommend(5)
from scikits.crab import datasets from scikits.crab.models import MatrixPreferenceDataModel from scikits.crab.metrics import pearson_correlation from scikits.crab.recommenders.knn import UserBasedRecommender from scikits.crab.similarities import UserSimilarity movies = datasets.load_sample_movies() songs = datasets.load_sample_songs() print movies.data print movies.user_ids print movies.item_ids # Build the model model = MatrixPreferenceDataModel(movies.data) # Build the similarity similarity = UserSimilarity(model, pearson_correlation) # Build the User based recommender_sample.py recommender = UserBasedRecommender(model, similarity, with_preference=True) # Recommend items for the user 5 (Toby) print recommender.recommend(5)
def test_load_sample_songs(self):
songs = load_sample_songs()
self.assertEquals(len(songs['data']), 8)
self.assertEquals(len(songs['item_ids']), 8)
def test_load_sample_songs(self):
songs = load_sample_songs()
self.assertEquals(len(songs["data"]), 8)
self.assertEquals(len(songs["item_ids"]), 8)
