def initialize_components(self):
self.item_cosineCF_recommender = Cosine_Similarity(self.train,
topK=200,
shrink=15,
normalize=True,
mode='cosine')
self.user_cosineCF_recommender = Cosine_Similarity(self.train.T,
topK=200,
shrink=15,
normalize=True,
mode='cosine')
self.item_bpr_recommender = SLIM_BPR_Cython(self.train,
positive_threshold=0)
self.svd_recommender = PureSVDRecommender(self.train)
self.cbf_bpr_recommender = SLIM_BPR_Cython(self.icm.T,
positive_threshold=0)
self.cbf_recommender = Cosine_Similarity(self.icm.T,
topK=50,
shrink=10,
normalize=True,
mode='cosine')
if self.ensemble_weights["IALS"] == 0:
self.ials_recommender = IALS_numpy(iters=0)
else:
self.ials_recommender = IALS_numpy()
def fit(self, alpha):
evaluator_MF = SequentialEvaluator(URM_test_list=self._URM_test, cutoff_list=[10])
#bprmf = MatrixFactorization_Cython(self._URM_train,
# positive_threshold=0,
# algorithm="MF_BPR",
# )
# self.MF_BPRW, self.MF_BPRH = bprmf.fit(epochs=200,
# num_factors=5,
# batch_size=1,
# sgd_mode='adagrad'
# )
#print(evaluator_MF.evaluateRecommender(bprmf))
self.bpr_WII = SLIM_BPR_Cython(self._URM_train, positive_threshold=0, symmetric=True).fit(epochs=10,
topK=200,
batch_size=200,
sgd_mode='adagrad',
learning_rate=1e-2)
self.bpr_WUU = SLIM_BPR_Cython(self._URM_train.T, positive_threshold=0).fit(epochs=10,
topK=200,
batch_size=200,
sgd_mode='adagrad',
learning_rate=1e-2)
print(self.bpr_WII)
print("\n \n max bprII: {0}".format(self.bpr_WII.max()))
print(self.bpr_WII)
print("\n \n max bprUU: {0}".format(self.bpr_WUU.max()))
self._similarity_matrixUU = Cosine_Similarity(self._URM_train.T,
topK=200,
shrink=15,
normalize=True,
mode='cosine').compute_similarity()
print("\n \n max uu: {0}".format(self._similarity_matrixUU.max()))
# self._similarity_matrixII = Cosine_Similarity(self._URM_train.tocsc(),
# topK=200,
# shrink=10,
# normalize=True,
# mode='cosine').compute_similarity()
# print("\n \n max II: {0}".format(self._similarity_matrixII.max()))
self._similarity_matrixCBF = Cosine_Similarity(self._ICM.T,
topK=10,
shrink=10,
normalize=True,
mode='cosine').compute_similarity()
# print(self._similarity_matrixII)
self.latent_x, self.latent_y = (IALS_numpy()).fit(self._URM_train)
print(self.latent_x.dot(self.latent_y.T))
print("\n \n max IALS: {0}".format(self.latent_x.dot(self.latent_y.T).max()))
def initialize_components(self):
self.train = self.rescale_wrt_insertion_order(self.train)
self.item_cosineCF_recommender = Cosine_Similarity(self.train, topK=200, shrink=15, normalize=True, mode='cosine')
self.user_cosineCF_recommender = Cosine_Similarity(self.train.T, topK=200, shrink=15, normalize=True, mode='cosine')
self.svd_recommender = PureSVDRecommender(self.train)
self.cbf_bpr_recommender = SLIM_BPR_Cython(self.icm.T, positive_threshold=0)
self.cbf_recommender = Cosine_Similarity(self.icm.T, topK=50, shrink=10, normalize=True, mode='cosine')
self.item_rp3b_recommender = RP3betaRecommender(self.train)
self.user_rp3b_recommender = RP3betaRecommender(self.train.T)
self.bpr_mf = BPR_matrix_factorization(factors=800, regularization=0.01, learning_rate=0.01, iterations=300)
self.ials_cg_mf = IALS_CG(iterations=15, calculate_training_loss=True, factors=500, use_cg=True, regularization=1e-3)
self.lightfm = LightFM_Recommender(self.train, self.icm, no_components=200)
def fit(self, k=50, shrink=100, similarity='cosine', normalize=True):
self.k = k
self.shrink = shrink
self.similarity = Cosine_Similarity(self.ICM.T, shrink=shrink, topK=k, normalize=normalize, mode = similarity)
if self.sparse_weights:
self.W_sparse = self.similarity.compute_similarity()
else:
self.W = self.similarity.compute_similarity()
self.W = self.W.toarray()