def test_create_ItemBasedRecommender(self):
recSys = ItemRecommender(self.model, self.similarity, self.strategy,
True)
self.assertEquals(recSys.similarity, self.similarity)
self.assertEquals(recSys.capper, True)
self.assertEquals(recSys.strategy, self.strategy)
self.assertEquals(recSys.model, self.model)
def test_recommendedBecause(self):
userID = 'Leopoldo Pires'
itemID = 'Just My Luck'
recSys = ItemRecommender(self.model, self.similarity, self.strategy,
False)
self.assertEquals(['The Night Listener', 'Superman Returns'],
recSys.recommendedBecause(userID, itemID, 2))
def test_allItem_mostSimilarItems(self):
itemIDs = [
'Superman Returns', 'Just My Luck', 'Snakes on a Plane',
'The Night Listener', 'You, Me and Dupree', 'Lady in the Water'
]
recSys = ItemRecommender(self.model, self.similarity, self.strategy,
True)
self.assertEquals([], recSys.mostSimilarItems(itemIDs, 4))
def test_local_not_existing_capper_False_estimatePreference(self):
userID = 'Leopoldo Pires'
itemID = 'You, Me and Dupree'
recSys = ItemRecommender(self.model, self.similarity, self.strategy,
False)
self.assertAlmostEquals(
3.14717875510,
recSys.estimatePreference(userID=userID,
similarity=self.similarity,
itemID=itemID))
def test_local_estimatePreference(self):
userID = 'Marcel Caraciolo'
itemID = 'Superman Returns'
recSys = ItemRecommender(self.model, self.similarity, self.strategy,
True)
self.assertAlmostEquals(
3.5,
recSys.estimatePreference(userID=userID,
similarity=self.similarity,
itemID=itemID))
def test_semi_recommend(self):
userID = 'Leopoldo Pires'
recSys = ItemRecommender(self.model, self.similarity, self.strategy,
False)
self.assertEquals(['Just My Luck'], recSys.recommend(userID, 1))
def test_full_recommend(self):
userID = 'Maria Gabriela'
recSys = ItemRecommender(self.model, self.similarity, self.strategy,
False)
self.assertEquals([], recSys.recommend(userID, 4))
def test_recommend(self):
userID = 'Leopoldo Pires'
recSys = ItemRecommender(self.model, self.similarity, self.strategy,
False)
self.assertEquals(['Just My Luck', 'You, Me and Dupree'],
recSys.recommend(userID, 4))
def test_empty_recommend(self):
userID = 'Marcel Caraciolo'
recSys = ItemRecommender(self.model, self.similarity, self.strategy,
False)
self.assertEquals([], recSys.recommend(userID, 4))
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):
dummy2[a] += temp[a]
def test_Item_IRStatsRecommenderEvaluator(self):
evaluator = IRStatsRecommenderEvaluator()
recommender = ItemRecommender(self.model, self.similarity_item,
self.strategy, False)
result = evaluator.evaluate(recommender, self.model, 2, 1.0)
print result
def test_Item_RMSRecommenderEvaluator(self):
evaluator = RMSRecommenderEvaluator()
recommender = ItemRecommender(self.model, self.similarity_item,
self.strategy, False)
result = evaluator.evaluate(recommender, self.model, 0.7, 1.0)
def test_Item_AvgDistanceRecSys(self):
evaluator = AverageAbsoluteDifferenceRecommenderEvaluator()
recommender = ItemRecommender(self.model, self.similarity_item,
self.strategy, False)
result = evaluator.evaluate(recommender, self.model, 0.7, 1.0)
