item_popularity = np.sort(item_popularity)
pyplot.plot(item_popularity, 'ro')
pyplot.ylabel('Num Interactions ')
pyplot.xlabel('Sorted Item')
pyplot.show()
user_activity = np.ediff1d(URM_all.indptr)
user_activity = np.sort(user_activity)
pyplot.plot(user_activity, 'ro')
pyplot.ylabel('Num Interactions ')
pyplot.xlabel('Sorted User')
pyplot.show()'''
#np.random.seed(1234)
URM_train, URM_test = train_test_holdout(URM_all, train_perc=0.90)
ICM_train, ICM_test = train_test_holdout(ICM_all, train_perc=0.9)
evaluator_validation = EvaluatorHoldout(URM_test,
cutoff_list=[10],
exclude_seen=True)
URM_ICM_train = sps.vstack([URM_train, ICM_all.T])
URM_ICM_train = URM_ICM_train.tocsr()
URM_ICM_train2 = sps.hstack([ICM_all, URM_train.T])
URM_ICM_train2 = URM_ICM_train2.tocsr()
earlystopping_keywargs = {
"validation_every_n": 10,
"stop_on_validation": True,
"evaluator_object": evaluator_validation,
"lower_validations_allowed": 5,
p3Param = {
'topK': 64,
'alpha': 0.5626527178823623,
'min_rating': 0.4999280105627021,
'implicit': [False, False, False]
}
alpha1 = 0.4
alpha2 = 0.5399999999999999
alpha3 = 0.06000000000000005
print(
"***************************Ensure the parameter is good**********************"
)
URM_train, URM_test = train_test_holdout(URM_all, train_perc=0.8)
itemCF_recommender = ItemKNNCFRecommender(URM_train)
itemCF_recommender.fit(**itemCFParam)
slim_recommender = SLIM_BPR_Cython(URM_train, recompile_cython=False)
slim_recommender.fit(**slimParam)
p3_recommender = P3alphaRecommender(URM_train)
p3_recommender.fit(**p3Param)
recommender1 = SimilarityHybridRecommender(URM_train,
itemCF_recommender.W_sparse,
slim_recommender.W_sparse,
p3_recommender.W_sparse)
recommender1.fit(topK=100, alpha1=alpha1, alpha2=alpha2, alpha3=alpha3)
evaluator_validation = EvaluatorHoldout(URM_test, cutoff_list=[10])
eval_res = evaluator_validation.evaluateRecommender(recommender1)
ICM_asset_path = "data/data_ICM_asset.csv"
ICM_asset_file = open(ICM_asset_path, 'r')
ICM_price_path = "data/data_ICM_price.csv"
ICM_price_file = open(ICM_price_path, 'r')
ICM_sub_class = "data/data_ICM_sub_class.csv"
ICM_sub_class_file = open(ICM_sub_class, 'r')
ICM_all, n_items, n_features = get_ICM(ICM_sub_class, URM_all)
print("Number of items is ", str(n_items))
print("n_features is ", str(n_features))
from Notebooks_utils.data_splitter import train_test_holdout
URM_train, URM_test = train_test_holdout(URM_all, train_perc=0.8)
URM_train, URM_validation = train_test_holdout(URM_train, train_perc=0.9)
evaluator_validation = EvaluatorHoldout(URM_validation, cutoff_list=[10])
evaluator_test = EvaluatorHoldout(URM_test, cutoff_list=[10])
recommender_class = ItemKNNCFRecommender
parameterSearch = SearchBayesianSkopt(
recommender_class,
evaluator_validation=evaluator_validation,
evaluator_test=evaluator_test)
output_folder_path = "result_experiments/"
# If directory does not exist, create
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]
def gethyb():
start_time = time.time()
URM_all, user_id_unique, item_id_unique = RecSys2020Reader.load_urm()
ICM_all = RecSys2020Reader.load_icm_asset()
target_ids = RecSys2020Reader.load_target()
np.random.seed(12341288)
URM_train, URM_test = train_test_holdout(URM_all, train_perc=0.8)
# ICM_train, ICM_test = train_test_holdout(ICM_all, train_perc=0.995)
evaluator_validation = EvaluatorHoldout(URM_test,
cutoff_list=[10],
exclude_seen=True)
#URM_train = URM_all
ICM_train = ICM_all
URM_ICM_train = sps.vstack([URM_train, ICM_all.T])
URM_ICM_train = URM_ICM_train.tocsr()
l_list = []
profile_length = np.ediff1d(URM_train.indptr)
block_size = int(len(profile_length) * 0.2)
sorted_users = np.argsort(profile_length)
groups = 5
rec_list = []
arg_list = []
name_list = []
for group_id in range(0, groups):
start_pos = group_id * block_size
end_pos = min((group_id + 1) * block_size, len(profile_length))
users_in_group = sorted_users[start_pos:end_pos]
users_in_group_p_len = profile_length[users_in_group]
l_list.append(len(users_in_group))
print("Group {}, average p.len {:.2f}, min {}, max {}".format(
group_id, users_in_group_p_len.mean(), users_in_group_p_len.min(),
users_in_group_p_len.max()))
hyb_warm = ScoresHybridRP3betaKNNCBF.ScoresHybridRP3betaKNNCBF(
URM_ICM_train, URM_ICM_train.T)
hyb_warmV2 = ScoresHybridP3alphaKNNCBF.ScoresHybridP3alphaKNNCBF(
URM_ICM_train, URM_ICM_train.T)
# Warm of Kaggle MAP 0.09466
'''hyb_warm_args = {"topK_P": 127, "alpha_P": 0.35309465855346317, "normalize_similarity_P": False, "topK": 805,
"shrink": 307, "similarity": "tversky", "normalize": False, "alpha": 0.486665735781842, "feature_weighting": "TF-IDF"}
hyb_warmV2_args = {"topK_P": 1496, "alpha_P": 0.4384309705759645, "normalize_similarity_P": False, "topK": 1023,
"shrink": 261, "similarity": "asymmetric", "normalize": False, "alpha": 0.7211670365702352, "feature_weighting": "TF-IDF"}'''
hyb_warm_args = {
"topK_P": 2000,
"alpha_P": 0.5202318972174075,
"normalize_similarity_P": False,
"topK": 2000,
"shrink": 2000,
"similarity": "tversky",
"normalize": True,
"alpha": 1.0,
"beta_P": 0.33040913500424834,
"feature_weighting": "none"
}
hyb_warmV2_args = {
"topK_P": 1238,
"alpha_P": 0.580501466821829,
"normalize_similarity_P": False,
"topK": 1043,
"shrink": 163,
"similarity": "asymmetric",
"normalize": False,
"alpha": 0.25081946305309705,
"feature_weighting": "BM25"
}
#{"topK_P": 2000, "alpha_P": 0.5292482627931302, "normalize_similarity_P": False, "topK": 2000, "shrink": 0,
#"similarity": "tanimoto", "normalize": True, "alpha": 0.7963434906265208, "beta_P": 0.2692980157925566, "feature_weighting": "BM25"}
hyb_cold = ScoresHybridRP3betaKNNCBF.ScoresHybridRP3betaKNNCBF(
URM_ICM_train, URM_ICM_train.T)
# Cold of Kaggle MAP 0.09466
hyb_coldV2 = ScoresHybridRP3betaKNNCBF.ScoresHybridRP3betaKNNCBF(
URM_ICM_train, URM_ICM_train.T)
'''hyb_cold_args = {"topK_P": 482, "alpha_P": 0.4999498678468517, "normalize_similarity_P": False, "topK": 1500,
"shrink": 212, "similarity": "cosine", "normalize": False, "alpha": 0.6841610038073574,
"feature_weighting": "BM25"}
# Cold of Kaggle MAP 0.09466
hyb_coldV2_args = {"topK_P": 326, "alpha_P": 0.5120656418370607, "normalize_similarity_P": False, "topK": 151,
"shrink": 183, "similarity": "tversky", "normalize": True, "alpha": 0.6290067931193662, "feature_weighting": "BM25"}'''
hyb_cold_args = {
"topK_P": 2093,
"alpha_P": 0.8263868403373367,
"normalize_similarity_P": False,
"topK": 298,
"shrink": 1954,
"similarity": "tanimoto",
"normalize": False,
"alpha": 0.608862998163905,
"beta_P": 0.34975586706651757,
"feature_weighting": "TF-IDF"
}
# Cold of Kaggle MAP 0.09466
hyb_coldV2_args = {
"topK_P": 1490,
"alpha_P": 0.5832972099071866,
"normalize_similarity_P": False,
"topK": 1533,
"shrink": 1100,
"similarity": "tanimoto",
"normalize": False,
"alpha": 0.15358895478386428,
"beta_P": 0.002234792201790459,
"feature_weighting": "BM25"
}
'''hyb_midV2 = ScoresHybridP3alphaKNNCBF.ScoresHybridP3alphaKNNCBF(URM_ICM_train, URM_ICM_train.T)
# Cold of Kaggle MAP 0.09466
hyb_midV2_args = {"topK_P": 2064, "alpha_P": 1.9131180703120496, "normalize_similarity_P": False, "topK": 154, "shrink": 620,
"similarity": "asymmetric", "normalize": True, "alpha": 0.013221786654690208, "feature_weighting": "TF-IDF"}
#{"topK_P": 1577, "alpha_P": 0.1835912052126545, "normalize_similarity_P": false, "topK": 1439, "shrink": 3626,
#"similarity": "cosine", "normalize": false, "alpha": 0.1507714323088927, "feature_weighting": "BM25"}'''
rec_list.append(hyb_cold)
arg_list.append(hyb_cold_args)
name_list.append("hyb_cold")
rec_list.append(hyb_warm)
arg_list.append(hyb_warm_args)
name_list.append("hyb_warm")
rec_list.append(hyb_warmV2)
arg_list.append(hyb_warmV2_args)
name_list.append("hyb_warmV2")
rec_list.append(hyb_coldV2)
arg_list.append(hyb_coldV2_args)
name_list.append("hyb_coldV2")
'''rec_list.append(hyb_midV2)
arg_list.append(hyb_midV2_args)
name_list.append("hyb_midV2")'''
hyb5 = ScoresHybridP3alphaKNNCBF.ScoresHybridP3alphaKNNCBF(
URM_train, ICM_train)
hyb5_args = {
"topK_P": 903,
"alpha_P": 0.4108657561671193,
"normalize_similarity_P": False,
"topK": 448,
"shrink": 5,
"similarity": "tversky",
"normalize": True,
"alpha": 0.6290871066510789,
"feature_weighting": "TF-IDF"
}
rec_list.append(hyb5)
arg_list.append(hyb5_args)
name_list.append("hyb5")
tot_args = zip(rec_list, arg_list, name_list)
pool = PoolWithSubprocess(processes=5, maxtasksperchild=1)
resultList = pool.map(fitRec, tot_args)
pool.close()
pool.join()
for el in resultList:
if el[1] == "hyb_cold":
hyb_cold = el[0]
elif el[1] == "hyb_warm":
hyb_warm = el[0]
elif el[1] == "hyb_coldV2":
hyb_coldV2 = el[0]
elif el[1] == "hyb_midV2":
hyb_midV2 = el[0]
elif el[1] == "hyb_warmV2":
hyb_warmV2 = el[0]
elif el[1] == "hyb5":
hyb5 = el[0]
elif el[1] == "hyb6x":
hyb6x = el[0]
# cold coldv2 mid sono i nuovi
#hyb = hyb_warm
#hyb2 = hyb_cold
hyb3 = ScoresHybridKNNCFKNNCBF.ScoresHybridKNNCFKNNCBF(
URM_ICM_train, URM_ICM_train.T)
hyb3.fit(
**{
"topK_CF": 488,
"shrink_CF": 1500,
"similarity_CF": "tversky",
"normalize_CF": True,
"topK": 1500,
"shrink": 1500,
"similarity": "asymmetric",
"normalize": False,
"alpha": 0.23233349150222427,
"feature_weighting": "BM25"
})
hyb2 = ItemKNNScoresHybridRecommender.ItemKNNScoresHybridRecommender(
URM_train, hyb_warm, hyb5)
hyb2.fit(alpha=0.5)
hyb6 = ItemKNNScoresHybridRecommender.ItemKNNScoresHybridRecommender(
URM_train, hyb_warmV2, hyb5)
hyb6.fit(alpha=0.5)
hyb7 = ItemKNNScoresHybridRecommender.ItemKNNScoresHybridRecommender(
URM_train, hyb6, hyb2)
hyb7.fit(alpha=0.5)
#hyb = ItemKNNScoresHybridRecommender.ItemKNNScoresHybridRecommender(URM_train, hyb3, hyb7)
#hyb.fit(alpha=0.5)
earlystopping_keywargs = {
"validation_every_n": 1,
"stop_on_validation": True,
"evaluator_object": evaluator_validation,
"lower_validations_allowed": 3,
"validation_metric": "MAP",
}
ials = IALSRecommender.IALSRecommender(URM_ICM_train)
ials.fit(**earlystopping_keywargs, num_factors=100, alpha=50)
hyb = ials
hyb7 = ItemKNNScoresHybridRecommender.ItemKNNScoresHybridRecommender(
URM_train, hyb2, ials)
hyb7.fit(alpha=0.5)
hyb3 = ItemKNNScoresHybridRecommender.ItemKNNScoresHybridRecommender(
URM_train, hyb2, ials)
hyb3.fit(alpha=0.85)
MAP_p3alpha_per_group = []
MAP_itemKNNCF_per_group = []
MAP_itemKNNCBF_per_group = []
MAP_pureSVD_per_group = []
MAP_hyb_per_group = []
MAP_hyb2_per_group = []
MAP_hyb3_per_group = []
MAP_hyb5_per_group = []
MAP_hyb6_per_group = []
MAP_hyb7_per_group = []
cutoff = 10
args = {
"block_size": block_size,
"profile_length": profile_length,
"sorted_users": sorted_users,
"cutoff": cutoff,
"URM_test": URM_test,
"hyb": hyb,
"hyb2": hyb2,
"hyb3": hyb3,
"hyb5": hyb5,
"hyb6": hyb6,
"hyb7": hyb7
}
pool = PoolWithSubprocess(processes=multiprocessing.cpu_count() - 1,
maxtasksperchild=1)
compute_group_MAP_partial = partial(compute_group_MAP, args)
resultList = pool.map(compute_group_MAP_partial, range(0, groups))
pool.close()
pool.join()
for el in resultList:
MAP_hyb_per_group.append(el[0])
MAP_hyb2_per_group.append(el[1])
MAP_hyb3_per_group.append(el[2])
MAP_hyb5_per_group.append(el[3])
MAP_hyb6_per_group.append(el[4])
if hyb7 is not None:
MAP_hyb7_per_group.append(el[5])
# Needed because of memory error
'''for group_id in range(0, groups):
start_pos = group_id * block_size
end_pos = min((group_id + 1) * block_size, len(profile_length))
users_in_group = sorted_users[start_pos:end_pos]
users_in_group_p_len = profile_length[users_in_group]
print("Group {}, average p.len {:.2f}, min {}, max {}".format(group_id,
users_in_group_p_len.mean(),
users_in_group_p_len.min(),
users_in_group_p_len.max()))
users_not_in_group_flag = np.isin(sorted_users, users_in_group, invert=True)
users_not_in_group = sorted_users[users_not_in_group_flag]
evaluator_test = EvaluatorHoldout(URM_test, cutoff_list=[cutoff], ignore_users=users_not_in_group)
results, _ = evaluator_test.evaluateRecommender(hyb7)
MAP_hyb7_per_group.append(results[cutoff]["MAP"])'''
import matplotlib.pyplot as pyplot
'''pyplot.plot(MAP_p3alpha_per_group, label="p3alpha")
pyplot.plot(MAP_itemKNNCF_per_group, label="itemKNNCF")
pyplot.plot(MAP_itemKNNCBF_per_group, label="itemKNNCBF")
pyplot.plot(MAP_pureSVD_per_group, label="pureSVD")'''
pyplot.plot(MAP_hyb_per_group, label="hyb")
pyplot.plot(MAP_hyb2_per_group, label="hyb2")
pyplot.plot(MAP_hyb3_per_group, label="hyb3")
pyplot.plot(MAP_hyb5_per_group, label="hyb5")
pyplot.plot(MAP_hyb6_per_group, label="hyb6")
if hyb7 is not None:
pyplot.plot(MAP_hyb7_per_group, label="hyb7")
pyplot.ylabel('MAP')
pyplot.xlabel('User Group')
pyplot.legend()
pyplot.show()
print(l_list)
evaluator_validation = EvaluatorHoldout(URM_test,
cutoff_list=[10],
exclude_seen=True)
pool = PoolWithSubprocess(processes=multiprocessing.cpu_count() - 1,
maxtasksperchild=1)
if hyb7 is not None:
hyb_list = [hyb, hyb2, hyb3, hyb5, hyb6, hyb7]
else:
hyb_list = [hyb, hyb2, hyb3, hyb5, hyb6]
resultList = pool.map(evaluator_validation.evaluateRecommender, hyb_list)
pool.close()
pool.join()
for el in resultList:
print(el)
'''item_list = hyb7.recommend(target_ids, cutoff=10)
CreateCSV.create_csv(target_ids, item_list, 'Hyb_URM_ICM_cold_warm_V2_more_mix_mid')
item_list = hyb2.recommend(target_ids, cutoff=10)
CreateCSV.create_csv(target_ids, item_list, 'Hyb2')
item_list = hyb6.recommend(target_ids, cutoff=10)
CreateCSV.create_csv(target_ids, item_list, 'Hyb_URM_ICM')'''
print("--- Execution time: %s seconds ---" % (time.time() - start_time))
return hyb2
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]
def gethyb():
start_time = time.time()
URM_all, user_id_unique, item_id_unique = RecSys2020Reader.load_urm()
ICM_all = RecSys2020Reader.load_icm_asset()
target_ids = RecSys2020Reader.load_target()
#np.random.seed(12341288)
URM_train, URM_test = train_test_holdout(URM_all, train_perc=0.8)
# ICM_train, ICM_test = train_test_holdout(ICM_all, train_perc=0.995)
evaluator_validation = EvaluatorHoldout(URM_test, cutoff_list=[10], exclude_seen=True)
#URM_train = URM_all
ICM_train = ICM_all
URM_ICM_train = sps.vstack([URM_train, ICM_all.T])
URM_ICM_train = URM_ICM_train.tocsr()
l_list = []
profile_length = np.ediff1d(URM_train.indptr)
block_size = int(len(profile_length) * 0.2)
sorted_users = np.argsort(profile_length)
groups = 5
rec_list = []
arg_list = []
name_list = []
for group_id in range(0, groups):
start_pos = group_id * block_size
end_pos = min((group_id + 1) * block_size, len(profile_length))
users_in_group = sorted_users[start_pos:end_pos]
users_in_group_p_len = profile_length[users_in_group]
l_list.append(len(users_in_group))
print("Group {}, average p.len {:.2f}, min {}, max {}".format(group_id,
users_in_group_p_len.mean(),
users_in_group_p_len.min(),
users_in_group_p_len.max()))
hyb_warm = ScoresHybridP3alphaKNNCBF.ScoresHybridP3alphaKNNCBF(URM_train, URM_train.T)
hyb_warmV2 = ScoresHybridP3alphaKNNCBF.ScoresHybridP3alphaKNNCBF(URM_train, ICM_train)
# Warm of Kaggle MAP 0.09466
'''hyb_warm_args = {"topK_P": 127, "alpha_P": 0.35309465855346317, "normalize_similarity_P": False, "topK": 805,
"shrink": 307, "similarity": "tversky", "normalize": False, "alpha": 0.486665735781842, "feature_weighting": "TF-IDF"}
hyb_warmV2_args = {"topK_P": 1496, "alpha_P": 0.4384309705759645, "normalize_similarity_P": False, "topK": 1023,
"shrink": 261, "similarity": "asymmetric", "normalize": False, "alpha": 0.7211670365702352, "feature_weighting": "TF-IDF"}'''
hyb_warm_args = {"topK_P": 1500, "alpha_P": 0.499386187332916, "normalize_similarity_P": False, "topK": 1500,
"shrink": 0, "similarity": "cosine", "normalize": False, "alpha": 0.6783844599810798, "feature_weighting": "BM25"}
hyb_warmV2_args = {"topK_P": 1407, "alpha_P": 0.5102184063631549, "normalize_similarity_P": False, "topK": 62,
"shrink": 104, "similarity": "tanimoto", "normalize": False, "alpha": 0.7722938163027667, "feature_weighting": "none"}
hyb_cold = ScoresHybridP3alphaKNNCBF.ScoresHybridP3alphaKNNCBF(URM_train, ICM_train)
# Cold of Kaggle MAP 0.09466
hyb_coldV2 = ScoresHybridP3alphaKNNCBF.ScoresHybridP3alphaKNNCBF(URM_train, ICM_train)
'''hyb_cold_args = {"topK_P": 482, "alpha_P": 0.4999498678468517, "normalize_similarity_P": False, "topK": 1500,
"shrink": 212, "similarity": "cosine", "normalize": False, "alpha": 0.6841610038073574,
"feature_weighting": "BM25"}
# Cold of Kaggle MAP 0.09466
hyb_coldV2_args = {"topK_P": 326, "alpha_P": 0.5120656418370607, "normalize_similarity_P": False, "topK": 151,
"shrink": 183, "similarity": "tversky", "normalize": True, "alpha": 0.6290067931193662, "feature_weighting": "BM25"}'''
hyb_cold_args = {"topK_P": 510, "alpha_P": 0.2857363628982497, "normalize_similarity_P": False, "topK": 483,
"shrink": 1491, "similarity": "asymmetric", "normalize": True, "alpha": 0.7682805033640728, "feature_weighting": "TF-IDF"}
# Cold of Kaggle MAP 0.09466
hyb_coldV2_args = {"topK_P": 1095, "alpha_P": 0.4546298466859472, "normalize_similarity_P": False, "topK": 866,
"shrink": 182, "similarity": "tanimoto", "normalize": False, "alpha": 0.5837079437871213, "feature_weighting": "BM25"}
hyb_midV2 = ScoresHybridP3alphaKNNCBF.ScoresHybridP3alphaKNNCBF(URM_train, ICM_train)
# Cold of Kaggle MAP 0.09466
hyb_midV2_args = {"topK_P": 482, "alpha_P": 0.4999498678468517, "normalize_similarity_P": False, "topK": 1500,
"shrink": 212, "similarity": "cosine", "normalize": False, "alpha": 0.6841610038073574, "feature_weighting": "BM25"}
rec_list.append(hyb_cold)
arg_list.append(hyb_cold_args)
name_list.append("hyb_cold")
rec_list.append(hyb_warm)
arg_list.append(hyb_warm_args)
name_list.append("hyb_warm")
rec_list.append(hyb_warmV2)
arg_list.append(hyb_warmV2_args)
name_list.append("hyb_warmV2")
rec_list.append(hyb_coldV2)
arg_list.append(hyb_coldV2_args)
name_list.append("hyb_coldV2")
rec_list.append(hyb_midV2)
arg_list.append(hyb_midV2_args)
name_list.append("hyb_midV2")
hyb5 = ScoresHybridP3alphaKNNCBF.ScoresHybridP3alphaKNNCBF(URM_train, ICM_train)
hyb5_args = {"topK_P": 903, "alpha_P": 0.4108657561671193, "normalize_similarity_P": False, "topK": 448,
"shrink": 5,
"similarity": "tversky", "normalize": True, "alpha": 0.6290871066510789, "feature_weighting": "TF-IDF"}
rec_list.append(hyb5)
arg_list.append(hyb5_args)
name_list.append("hyb5")
tot_args = zip(rec_list, arg_list, name_list)
pool = PoolWithSubprocess(processes=int(multiprocessing.cpu_count()-1), maxtasksperchild=1)
resultList = pool.map(fitRec, tot_args)
pool.close()
pool.join()
for el in resultList:
if el[1] == "hyb_cold":
hyb_cold = el[0]
elif el[1] == "hyb_warm":
hyb_warm = el[0]
elif el[1] == "hyb_coldV2":
hyb_coldV2 = el[0]
elif el[1] == "hyb_midV2":
hyb_midV2 = el[0]
elif el[1] == "hyb_warmV2":
hyb_warmV2 = el[0]
elif el[1] == "hyb5":
hyb5 = el[0]
elif el[1] == "hyb6x":
hyb6x = el[0]
hybuc = ScoresHybridSpecializedV3Warm.ScoresHybridSpecializedV3Warm(URM_train, ICM_all)
hybuc.fit(**{"topK_P": 509, "alpha_P": 1.045671409326966, "normalize_similarity_P": False, "topK": 1291, "shrink": 430,
"similarity": "asymmetric", "normalize": False, "alpha": 0.864672904054673, "feature_weighting": "TF-IDF"})
hyb2 = hyb_warmV2
hyb3 = ScoresHybridSpecializedFusion.ScoresHybridSpecializedFusion(URM_train, hyb_cold, hyb_warm, 5.9)
hyb7 = ScoresHybridSpecializedFusion.ScoresHybridSpecializedFusion(URM_train, hyb_coldV2, hyb_warmV2, 5.9)
hyb6 = ItemKNNScoresHybridRecommender.ItemKNNScoresHybridRecommender(URM_train, hyb7, hyb5)
hyb6.fit(alpha=0.5)
hyb2 = ItemKNNScoresHybridRecommender.ItemKNNScoresHybridRecommender(URM_train, hyb3, hyb6)
hyb2.fit(alpha=0.5)
hyb = ScoresHybridSpecializedFusion.ScoresHybridSpecializedFusion(URM_train, hyb2, hybuc, 300)
MAP_p3alpha_per_group = []
MAP_itemKNNCF_per_group = []
MAP_itemKNNCBF_per_group = []
MAP_pureSVD_per_group = []
MAP_hyb_per_group = []
MAP_hyb2_per_group = []
MAP_hyb3_per_group = []
MAP_hyb5_per_group = []
MAP_hyb6_per_group = []
MAP_hyb7_per_group = []
cutoff = 10
args = {"block_size": block_size, "profile_length": profile_length, "sorted_users": sorted_users, "cutoff": cutoff,
"URM_test": URM_test, "hyb": hyb, "hyb2": hyb2, "hyb3": hyb3, "hyb5": hyb5, "hyb6": hyb6, "hyb7": hyb7}
pool = PoolWithSubprocess(processes=multiprocessing.cpu_count()-1, maxtasksperchild=1)
compute_group_MAP_partial = partial(compute_group_MAP, args)
resultList = pool.map(compute_group_MAP_partial, range(0, groups))
pool.close()
pool.join()
for el in resultList:
MAP_hyb_per_group.append(el[0])
MAP_hyb2_per_group.append(el[1])
MAP_hyb3_per_group.append(el[2])
MAP_hyb5_per_group.append(el[3])
MAP_hyb6_per_group.append(el[4])
if hyb7 is not None:
MAP_hyb7_per_group.append(el[5])
# Needed because of memory error
'''for group_id in range(0, groups):
start_pos = group_id * block_size
end_pos = min((group_id + 1) * block_size, len(profile_length))
users_in_group = sorted_users[start_pos:end_pos]
users_in_group_p_len = profile_length[users_in_group]
print("Group {}, average p.len {:.2f}, min {}, max {}".format(group_id,
users_in_group_p_len.mean(),
users_in_group_p_len.min(),
users_in_group_p_len.max()))
users_not_in_group_flag = np.isin(sorted_users, users_in_group, invert=True)
users_not_in_group = sorted_users[users_not_in_group_flag]
evaluator_test = EvaluatorHoldout(URM_test, cutoff_list=[cutoff], ignore_users=users_not_in_group)
results, _ = evaluator_test.evaluateRecommender(hyb7)
MAP_hyb7_per_group.append(results[cutoff]["MAP"])'''
import matplotlib.pyplot as pyplot
'''pyplot.plot(MAP_p3alpha_per_group, label="p3alpha")
pyplot.plot(MAP_itemKNNCF_per_group, label="itemKNNCF")
pyplot.plot(MAP_itemKNNCBF_per_group, label="itemKNNCBF")
pyplot.plot(MAP_pureSVD_per_group, label="pureSVD")'''
pyplot.plot(MAP_hyb_per_group, label="hyb")
pyplot.plot(MAP_hyb2_per_group, label="hyb2")
pyplot.plot(MAP_hyb3_per_group, label="hyb3")
pyplot.plot(MAP_hyb5_per_group, label="hyb5")
pyplot.plot(MAP_hyb6_per_group, label="hyb6")
if hyb7 is not None:
pyplot.plot(MAP_hyb7_per_group, label="hyb7")
pyplot.ylabel('MAP')
pyplot.xlabel('User Group')
pyplot.legend()
pyplot.show()
print(l_list)
evaluator_validation = EvaluatorHoldout(URM_test, cutoff_list=[10], exclude_seen=True)
pool = PoolWithSubprocess(processes=multiprocessing.cpu_count()-1, maxtasksperchild=1)
if hyb7 is not None:
hyb_list = [hyb, hyb2, hyb3, hyb5, hyb6, hyb7]
else:
hyb_list = [hyb, hyb2, hyb3, hyb5, hyb6]
resultList = pool.map(evaluator_validation.evaluateRecommender, hyb_list)
pool.close()
pool.join()
for el in resultList:
print(el)
'''item_list = hyb7.recommend(target_ids, cutoff=10)
CreateCSV.create_csv(target_ids, item_list, 'Hyb_URM_ICM_cold_warm_V2_more_mix_mid')
item_list = hyb2.recommend(target_ids, cutoff=10)
CreateCSV.create_csv(target_ids, item_list, 'Hyb2')
item_list = hyb6.recommend(target_ids, cutoff=10)
CreateCSV.create_csv(target_ids, item_list, 'Hyb_URM_ICM')'''
print("--- Execution time: %s seconds ---" % (time.time() - start_time))
return hyb2