def setUp(self):
#SIMILARITY BY RATES.
movies = {
'Marcel Caraciolo': {
'Lady in the Water': 2.5,
'Snakes on a Plane': 3.5,
'Just My Luck': 3.0,
'Superman Returns': 3.5,
'You, Me and Dupree': 2.5,
'The Night Listener': 3.0
},
'Luciana Nunes': {
'Lady in the Water': 3.0,
'Snakes on a Plane': 3.5,
'Just My Luck': 1.5,
'Superman Returns': 5.0,
'The Night Listener': 3.0,
'You, Me and Dupree': 3.5
},
'Leopoldo Pires': {
'Lady in the Water': 2.5,
'Snakes on a Plane': 3.0,
'Superman Returns': 3.5,
'The Night Listener': 4.0
},
'Lorena Abreu': {
'Snakes on a Plane': 3.5,
'Just My Luck': 3.0,
'The Night Listener': 4.5,
'Superman Returns': 4.0,
'You, Me and Dupree': 2.5
},
'Steve Gates': {
'Lady in the Water': 3.0,
'Snakes on a Plane': 4.0,
'Just My Luck': 2.0,
'Superman Returns': 3.0,
'The Night Listener': 3.0,
'You, Me and Dupree': 2.0
},
'Sheldom': {
'Lady in the Water': 3.0,
'Snakes on a Plane': 4.0,
'The Night Listener': 3.0,
'Superman Returns': 5.0,
'You, Me and Dupree': 3.5
},
'Penny Frewman': {
'Snakes on a Plane': 4.5,
'You, Me and Dupree': 1.0,
'Superman Returns': 4.0
},
'Maria Gabriela': {}
}
self.model = DictDataModel(movies)
self.similarity = ItemSimilarity(self.model, sim_euclidian)
self.strategy = PreferredItemsNeighborhoodStrategy()
def test_full_candidateItems(self): userID = 'Marcel Caraciolo' strategy = PreferredItemsNeighborhoodStrategy() self.assertEquals([],strategy.candidateItems(userID,self.model))
def test_semi_candidateItems(self): userID = 'Leopoldo Pires' strategy = PreferredItemsNeighborhoodStrategy() self.assertEquals(['Just My Luck', 'You, Me and Dupree'],strategy.candidateItems(userID,self.model))
def test_empty_candidateItems(self): userID = 'Maria Gabriela' strategy = PreferredItemsNeighborhoodStrategy() self.assertEquals([],strategy.candidateItems(userID,self.model))
for i in range(0, 10):
if (len(df) > 100000):
test = df.sample(100000).groupby('userId')
else:
test = df.groupby('userId')
data = {}
for key, grp in test:
Test = grp.drop('userId', axis=1)
data[key] = Test.set_index('movieId').T.to_dict('records')[0]
model = DictDataModel(data)
similarity = ItemSimilarity(
model,
topicSimilarityCache,
topicDistribution=joblib.load('cache/JSD.pkl'),
movieIndex=movieId)
items_strategy = PreferredItemsNeighborhoodStrategy()
recSys = ItemRecommender(model, similarity, items_strategy)
evaluator = AverageAbsoluteDifferenceRecommenderEvaluator()
temp = Parallel(n_jobs=3)(
delayed(parallel)(evaluator, recSys, model, i)
for i in range(6, 10))
for a in range(0, 4):
dummy[a] += temp[a]
similarity = ItemSimilarity(model, sim_euclidian)
items_strategy = PreferredItemsNeighborhoodStrategy()
recSys = ItemRecommender(model, similarity, items_strategy)
evaluator = AverageAbsoluteDifferenceRecommenderEvaluator()
temp = Parallel(n_jobs=3)(
delayed(parallel)(evaluator, recSys, model, i)
for i in range(6, 10))
for a in range(0, 4):
def test_semi_candidateItems(self):
userID = 'Leopoldo Pires'
strategy = PreferredItemsNeighborhoodStrategy()
self.assertEquals(['Just My Luck', 'You, Me and Dupree'],
strategy.candidateItems(userID, self.model))
def test_full_candidateItems(self):
userID = 'Marcel Caraciolo'
strategy = PreferredItemsNeighborhoodStrategy()
self.assertEquals([], strategy.candidateItems(userID, self.model))
def test_empty_candidateItems(self):
userID = 'Maria Gabriela'
strategy = PreferredItemsNeighborhoodStrategy()
self.assertEquals([], strategy.candidateItems(userID, self.model))