def __init__(self, URM_train, ICM_train):
super(ScoresHybridKNNCFKNNCBF, self).__init__(URM_train)
self.URM_train = check_matrix(URM_train.copy(), 'csr')
self.ICM_train = ICM_train
self.itemKNNCF = ItemKNNCFRecommender.ItemKNNCFRecommender(URM_train)
self.itemKNNCBF = ItemKNNCBFRecommender.ItemKNNCBFRecommender(URM_train, ICM_train)
def __init__(self, URM_train, ICM_train):
super(ScoresHybridSpecializedV2Mid, self).__init__(URM_train)
self.URM_train = check_matrix(URM_train.copy(), 'csr')
self.ICM_train = ICM_train
self.P3alpha = P3alphaRecommender.P3alphaRecommender(URM_train)
self.itemKNNCBF = ItemKNNCBFRecommender.ItemKNNCBFRecommender(
URM_train, ICM_train)
"validation_metric": "MAP",
}
# MAP 0.07 Kaggle "topK": 131, "shrink": 2, "similarity": "cosine", "normalize": true}
#recommender = UserKNNCFRecommender.UserKNNCFRecommender(URM_train)
#recommender.fit(**{"topK": 131, "shrink": 2, "similarity": "cosine", "normalize": True})
'''itemKNNCF = ItemKNNCFRecommender.ItemKNNCFRecommender(URM_train)
itemKNNCF.fit(**{"topK": 1000, "shrink": 732, "similarity": "cosine", "normalize": True,
"feature_weighting": "TF-IDF"})
itemKNNCF2 = ItemKNNCFRecommender.ItemKNNCFRecommender(URM_ICM_train)
itemKNNCF2.fit(**{"topK": 1000, "shrink": 732, "similarity": "cosine", "normalize": True,
"feature_weighting": "TF-IDF"})
itemKNNCF3 = ItemKNNCFRecommender.ItemKNNCFRecommender(URM_ICM_train2.T)
itemKNNCF3.fit(**{"topK": 1000, "shrink": 732, "similarity": "cosine", "normalize": True,
"feature_weighting": "TF-IDF"})'''
itemKNNCBF = ItemKNNCBFRecommender.ItemKNNCBFRecommender(
URM_train, URM_train.T)
itemKNNCBF.fit(topK=700,
shrink=200,
similarity='jaccard',
normalize=True,
feature_weighting="TF-IDF")
itemKNNCBF2 = ItemKNNCBFRecommender.ItemKNNCBFRecommender(
URM_train, URM_ICM_train.T)
itemKNNCBF2.fit(topK=700,
shrink=200,
similarity='jaccard',
normalize=True,
feature_weighting="TF-IDF")
itemKNNCBF3 = ItemKNNCBFRecommender.ItemKNNCBFRecommender(
URM_train, URM_ICM_train2)
itemKNNCBF3.fit(topK=700,
def crossval(URM_all, ICM_all, target_ids, k):
seed = 1234 + k #+ int(time.time())
np.random.seed(seed)
tp = 0.75
URM_train, URM_test = train_test_holdout(URM_all, train_perc=tp)
ICM_train, ICM_test = train_test_holdout(ICM_all, train_perc=0.95)
evaluator_validation = EvaluatorHoldout(URM_test,
cutoff_list=[10],
exclude_seen=True)
args = {}
p3alpha = P3alphaRecommender.P3alphaRecommender(URM_train)
try:
args = {
"topK": 991,
"alpha": 0.4705816992313091,
"normalize_similarity": False
}
p3alpha.load_model(
'SavedModels\\', p3alpha.RECOMMENDER_NAME + toFileName(args) +
",s=" + str(seed) + ",tp=" + str(tp) + ".zip")
except:
print("Saved model not found. Fitting a new one...")
p3alpha.fit(**args)
p3alpha.save_model(
'SavedModels\\', p3alpha.RECOMMENDER_NAME + toFileName(args) +
",s=" + str(seed) + ",tp=" + str(tp))
rp3beta = RP3betaRecommender.RP3betaRecommender(URM_train)
try:
args = {
"topK": 991,
"alpha": 0.4705816992313091,
"beta": 0.37,
"normalize_similarity": False
}
rp3beta.load_model(
'SavedModels\\', rp3beta.RECOMMENDER_NAME + toFileName(args) +
",s=" + str(seed) + ",tp=" + str(tp) + ".zip")
except:
print("Saved model not found. Fitting a new one...")
rp3beta.fit(**args)
rp3beta.save_model(
'SavedModels\\', rp3beta.RECOMMENDER_NAME + toFileName(args) +
",s=" + str(seed) + ",tp=" + str(tp))
itemKNNCF = ItemKNNCFRecommender.ItemKNNCFRecommender(URM_train)
try:
args = {
"topK": 1000,
"shrink": 732,
"similarity": "cosine",
"normalize": True,
"feature_weighting": "TF-IDF"
}
itemKNNCF.load_model(
'SavedModels\\', itemKNNCF.RECOMMENDER_NAME + toFileName(args) +
",s=" + str(seed) + ",tp=" + str(tp) + ".zip")
except:
print("Saved model not found. Fitting a new one...")
itemKNNCF.fit(**args)
itemKNNCF.save_model(
'SavedModels\\', itemKNNCF.RECOMMENDER_NAME + toFileName(args) +
",s=" + str(seed) + ",tp=" + str(tp))
userKNNCF = UserKNNCFRecommender.UserKNNCFRecommender(URM_train)
try:
args = {
"topK": 131,
"shrink": 2,
"similarity": "cosine",
"normalize": True
}
userKNNCF.load_model(
'SavedModels\\', userKNNCF.RECOMMENDER_NAME + toFileName(args) +
",s=" + str(seed) + ",tp=" + str(tp) + ".zip")
except:
print("Saved model not found. Fitting a new one...")
userKNNCF.fit(**args)
userKNNCF.save_model(
'SavedModels\\', userKNNCF.RECOMMENDER_NAME + toFileName(args) +
",s=" + str(seed) + ",tp=" + str(tp))
itemKNNCBF = ItemKNNCBFRecommender.ItemKNNCBFRecommender(
URM_train, ICM_all)
try:
args = {
"topK": 700,
"shrink": 100,
"similarity": 'jaccard',
"normalize": True,
"feature_weighting": "TF-IDF"
}
itemKNNCBF.load_model(
'SavedModels\\', itemKNNCBF.RECOMMENDER_NAME + toFileName(args) +
",s=" + str(seed) + ",tp=" + str(tp) + ".zip")
except:
print("Saved model not found. Fitting a new one...")
itemKNNCBF.fit(**args)
itemKNNCBF.save_model(
'SavedModels\\', itemKNNCBF.RECOMMENDER_NAME + toFileName(args) +
",s=" + str(seed) + ",tp=" + str(tp))
#cfw = CFW_D_Similarity_Linalg.CFW_D_Similarity_Linalg(URM_train, ICM_train, itemKNNCF.W_sparse)
#cfw.fit(show_max_performance=False, logFile=None, loss_tolerance=1e-6,
# iteration_limit=500000, damp_coeff=0.5, topK=900, add_zeros_quota=0.5, normalize_similarity=True)
# Need to change bpr code to avoid memory error, useless since it's bad
# bpr = SLIM_BPR_Cython(URM_train, recompile_cython=False)
# bpr.fit(**{"topK": 1000, "epochs": 130, "symmetric": False, "sgd_mode": "adagrad", "lambda_i": 1e-05,
# "lambda_j": 0.01, "learning_rate": 0.0001})
pureSVD = PureSVDRecommender.PureSVDRecommender(URM_train)
pureSVD.fit(num_factors=1000)
hyb = ItemKNNScoresHybridRecommender.ItemKNNScoresHybridRecommender(
URM_train, p3alpha, itemKNNCBF)
hyb.fit(alpha=0.5)
# Kaggle MAP 0.084 rp3beta, itemKNNCBF
hyb2 = ItemKNNScoresHybridRecommender.ItemKNNScoresHybridRecommender(
URM_train, pureSVD, itemKNNCBF)
hyb2.fit(alpha=0.5)
# Kaggle MAP 0.08667
hyb3 = ItemKNNScoresHybridRecommender.ItemKNNScoresHybridRecommender(
URM_train, hyb, hyb2)
hyb3.fit(alpha=0.5)
#hyb3 = ItemKNNScoresHybridRecommender.ItemKNNScoresHybridRecommender(URM_train, p3alpha, userKNNCF)
#hyb3.fit(alpha=0.5)
hyb5 = ScoresHybridP3alphaKNNCBF.ScoresHybridP3alphaKNNCBF(
URM_train, ICM_all)
# Kaggle MAP 0.08856
try:
# Full values: "alpha_P": 0.4108657561671193, "alpha": 0.6290871066510789
args = {
"topK_P": 903,
"alpha_P": 0.41086575,
"normalize_similarity_P": False,
"topK": 448,
"shrink": 20,
"similarity": "tversky",
"normalize": True,
"alpha": 0.6290871,
"feature_weighting": "TF-IDF"
}
hyb5.load_model(
'SavedModels\\', hyb5.RECOMMENDER_NAME + toFileName(args) + ",s=" +
str(seed) + ",tp=" + str(tp) + ".zip")
except:
print("Saved model not found. Fitting a new one...")
hyb5.fit(**args)
hyb5.save_model(
'SavedModels\\', hyb5.RECOMMENDER_NAME + toFileName(args) + ",s=" +
str(seed) + ",tp=" + str(tp))
# hyb5.fit(**{"topK_P": 1000, "alpha_P": 0.5432601071314623, "normalize_similarity_P": True, "topK": 620, "shrink": 0,
# "similarity": "tversky", "normalize": False, "alpha": 0.5707347522847057, "feature_weighting": "BM25"})
# Kaggle MAP 0.086 :(
#hyb6 = ScoresHybrid3Recommender.ScoresHybrid3Recommender(URM_train, rp3beta, itemKNNCBF, p3alpha)
#hyb6.fit()
hyb6 = ScoresHybridRP3betaKNNCBF.ScoresHybridRP3betaKNNCBF(
URM_train, ICM_all)
try:
# Full values: "alpha_P": 0.5081918012150626, "alpha": 0.44740093610861603
args = {
"topK_P": 623,
"alpha_P": 0.5081918,
"normalize_similarity_P": False,
"topK": 1000,
"shrink": 1000,
"similarity": "tversky",
"normalize": True,
"alpha": 0.4474009,
"beta_P": 0.0,
"feature_weighting": "TF-IDF"
}
hyb6.load_model(
'SavedModels\\', hyb6.RECOMMENDER_NAME + toFileName(args) + ",s=" +
str(seed) + ",tp=" + str(tp) + ".zip")
except:
print("Saved model not found. Fitting a new one...")
hyb6.fit(**args)
hyb6.save_model(
'SavedModels\\', hyb6.RECOMMENDER_NAME + toFileName(args) + ",s=" +
str(seed) + ",tp=" + str(tp))
v0 = evaluator_validation.evaluateRecommender(hyb)[0][10]["MAP"]
v1 = evaluator_validation.evaluateRecommender(hyb2)[0][10]["MAP"]
v2 = evaluator_validation.evaluateRecommender(hyb3)[0][10]["MAP"]
v3 = evaluator_validation.evaluateRecommender(hyb5)[0][10]["MAP"]
v4 = evaluator_validation.evaluateRecommender(hyb6)[0][10]["MAP"]
#item_list = hyb3.recommend(target_ids, cutoff=10)
#CreateCSV.create_csv(target_ids, item_list, 'ItemKNNCBF__RP3beta')
return [v0, v1, v2, v3, v4]
"topK": 1000,
"shrink": 732,
"similarity": "cosine",
"normalize": True,
"feature_weighting": "TF-IDF"
})
userKNNCF = UserKNNCFRecommender.UserKNNCFRecommender(URM_train)
userKNNCF.fit(**{
"topK": 131,
"shrink": 2,
"similarity": "cosine",
"normalize": True
})
itemKNNCBF = ItemKNNCBFRecommender.ItemKNNCBFRecommender(
URM_train, ICM_train)
itemKNNCBF.fit(topK=700,
shrink=200,
similarity='jaccard',
normalize=True,
feature_weighting="TF-IDF")
hyb = ItemKNNScoresHybridRecommender.ItemKNNScoresHybridRecommender(
URM_train, itemKNNCBF, userKNNCF)
hyb.fit(alpha=0.5)
# Kaggle MAP 0.081
hyb2 = ItemKNNScoresHybridRecommender.ItemKNNScoresHybridRecommender(
URM_train, hyb, itemKNNCF)
hyb2.fit(alpha=0.5)
def crossval(URM_all, ICM_all, target_ids, k):
seed = 1234 + k #+ int(time.time())
np.random.seed()
URM_train, URM_test = train_test_holdout(URM_all, train_perc=0.90)
ICM_train, ICM_test = train_test_holdout(ICM_all, train_perc=0.95)
evaluator_validation = EvaluatorHoldout(URM_test,
cutoff_list=[10],
exclude_seen=True)
args = {}
p3alpha = P3alphaRecommender.P3alphaRecommender(URM_train)
args = {
"topK": 991,
"alpha": 0.4705816992313091,
"normalize_similarity": False
}
p3alpha.fit(**args)
#p3alpha2 = P3alphaRecommender.P3alphaRecommender(URM_train)
#args = {"topK": 400, "alpha": 0.5305816992313091, "normalize_similarity": False}
#p3alpha2.fit(**args)
#rp3beta = RP3betaRecommender.RP3betaRecommender(URM_train)
#args = {"topK": 991, "alpha": 0.4705816992313091, "beta": 0.15, "normalize_similarity": False}
#rp3beta.fit(**args)
itemKNNCF = ItemKNNCFRecommender.ItemKNNCFRecommender(URM_train)
args = {
"topK": 1000,
"shrink": 732,
"similarity": "cosine",
"normalize": True,
"feature_weighting": "TF-IDF"
}
itemKNNCF.fit(**args)
userKNNCF = UserKNNCFRecommender.UserKNNCFRecommender(URM_train)
args = {
"topK": 131,
"shrink": 2,
"similarity": "cosine",
"normalize": True
}
userKNNCF.fit(**args)
itemKNNCBF = ItemKNNCBFRecommender.ItemKNNCBFRecommender(
URM_train, ICM_all)
args = {
"topK": 700,
"shrink": 100,
"similarity": 'jaccard',
"normalize": True,
"feature_weighting": "TF-IDF"
}
itemKNNCBF.fit(**args)
itemKNNCBF2 = ItemKNNCBFRecommender.ItemKNNCBFRecommender(
URM_train, ICM_all)
args = {
"topK": 200,
"shrink": 15,
"similarity": 'jaccard',
"normalize": True,
"feature_weighting": "TF-IDF"
}
itemKNNCBF2.fit(**args)
#cfw = CFW_D_Similarity_Linalg.CFW_D_Similarity_Linalg(URM_train, ICM_train, itemKNNCF.W_sparse)
#cfw.fit(show_max_performance=False, logFile=None, loss_tolerance=1e-6,
# iteration_limit=500000, damp_coeff=0.5, topK=900, add_zeros_quota=0.5, normalize_similarity=True)
# Need to change bpr code to avoid memory error, useless since it's bad
#bpr = SLIM_BPR_Cython(URM_train, recompile_cython=False)
#bpr.fit(**{"topK": 1000, "epochs": 130, "symmetric": False, "sgd_mode": "adagrad", "lambda_i": 1e-05,
# "lambda_j": 0.01, "learning_rate": 0.0001})
pureSVD = PureSVDRecommender.PureSVDRecommender(URM_train)
pureSVD.fit(num_factors=340)
#hyb = ItemKNNScoresHybridRecommender.ItemKNNScoresHybridRecommender(URM_train, p3alpha, itemKNNCBF)
#hyb.fit(alpha=0.5)
hyb = ItemKNNScoresHybridRecommender.ItemKNNScoresHybridRecommender(
URM_train, itemKNNCBF, pureSVD)
hyb.fit(alpha=0.5)
# Kaggle MAP 0.084 rp3beta, itemKNNCBF
#hyb2 = ItemKNNScoresHybridRecommender.ItemKNNScoresHybridRecommender(URM_train, p3alpha, itemKNNCBF)
#hyb2.fit(alpha=0.5)
hyb2 = ItemKNNSimilarityHybridRecommender.ItemKNNSimilarityHybridRecommender(
URM_train, itemKNNCBF.W_sparse, itemKNNCF.W_sparse)
hyb2.fit(topK=1600)
# Kaggle MAP 0.08667
hyb3 = ItemKNNScoresHybridRecommender.ItemKNNScoresHybridRecommender(
URM_train, hyb, hyb2)
hyb3.fit(alpha=0.5)
#hyb3 = RankingHybrid.RankingHybrid(URM_train, hyb, hyb2)
#hyb3 = ItemKNNScoresHybridRecommender.ItemKNNScoresHybridRecommender(URM_train, p3alpha, userKNNCF)
#hyb3.fit(alpha=0.5)
hyb5 = ScoresHybridP3alphaKNNCBF.ScoresHybridP3alphaKNNCBF(
URM_train, ICM_all)
# Kaggle MAP 0.08856
args = {
"topK_P": 903,
"alpha_P": 0.4108657561671193,
"normalize_similarity_P": False,
"topK": 448,
"shrink": 20,
"similarity": "tversky",
"normalize": True,
"alpha": 0.6290871066510789,
"feature_weighting": "TF-IDF"
}
hyb5.fit(**args)
# hyb5.fit(**{"topK_P": 1000, "alpha_P": 0.5432601071314623, "normalize_similarity_P": True, "topK": 620, "shrink": 0,
# "similarity": "tversky", "normalize": False, "alpha": 0.5707347522847057, "feature_weighting": "BM25"})
# Kaggle MAP 0.086 :(
#hyb6 = ItemKNNScoresHybridRecommender.ItemKNNScoresHybridRecommender(URM_train, hyb3, hyb5)
#hyb6.fit()
hyb6 = ScoresHybridP3alphaKNNCBF.ScoresHybridP3alphaKNNCBF(
URM_train, ICM_all)
args = {
"topK_P": 756,
"alpha_P": 0.5292654015790155,
"normalize_similarity_P": False,
"topK": 1000,
"shrink": 47,
"similarity": "tversky",
"normalize": False,
"alpha": 0.5207647439152092,
"feature_weighting": "none"
}
hyb6.fit(**args)
'''hyb6 = ScoresHybridRP3betaKNNCBF.ScoresHybridRP3betaKNNCBF(URM_train, ICM_all)
args = {"topK_P": 623, "alpha_P": 0.5081918012150626, "normalize_similarity_P": False, "topK": 1000,
"shrink": 1000, "similarity": "tversky", "normalize": True, "alpha": 0.44740093610861603, "beta_P": 0.0,
"feature_weighting": "TF-IDF"}
hyb6.fit(**args)'''
hyb7 = RankingHybrid.RankingHybrid(URM_train, hyb6, hyb3)
v0 = evaluator_validation.evaluateRecommender(hyb)[0][10]["MAP"]
v1 = evaluator_validation.evaluateRecommender(hyb2)[0][10]["MAP"]
v2 = evaluator_validation.evaluateRecommender(hyb3)[0][10]["MAP"]
#v2 = 0
v3 = evaluator_validation.evaluateRecommender(hyb5)[0][10]["MAP"]
v4 = evaluator_validation.evaluateRecommender(hyb6)[0][10]["MAP"]
#v4 = 0
v5 = evaluator_validation.evaluateRecommender(hyb7)[0][10]["MAP"]
#item_list = hyb6.recommend(target_ids, cutoff=10)
#CreateCSV.create_csv(target_ids, item_list, 'HybPureSVD')
return [v0, v1, v2, v3, v4, v5]