def read_data_split_and_search():
"""
This function provides a simple example on how to tune parameters of a given algorithm
The BayesianSearch object will save:
- A .txt file with all the cases explored and the recommendation quality
- A _best_model file which contains the trained model and can be loaded with recommender.load_model()
- A _best_parameter file which contains a dictionary with all the fit parameters, it can be passed to recommender.fit(**_best_parameter)
- A _best_result_validation file which contains a dictionary with the results of the best solution on the validation
- A _best_result_test file which contains a dictionary with the results, on the test set, of the best solution chosen using the validation set
"""
dataReader = Builder()
URM_train = dataReader.get_URM_train()
URM_validation = dataReader.get_URM_validation()
URM_test = dataReader.get_URM_test()
output_root_path = "result_experiments/"
# If directory does not exist, create
if not os.path.exists(output_root_path):
os.makedirs(output_root_path)
collaborative_algorithm_list = [HybridRec]
from ParameterTuning.AbstractClassSearch import EvaluatorWrapper
from Base.Evaluation.Evaluator import SequentialEvaluator
evaluator_validation_earlystopping = SequentialEvaluator(URM_validation,
cutoff_list=[5])
evaluator_test = SequentialEvaluator(URM_test, cutoff_list=[5, 10])
evaluator_validation = EvaluatorWrapper(evaluator_validation_earlystopping)
evaluator_test = EvaluatorWrapper(evaluator_test)
runParameterSearch_Collaborative_partial = partial(
runParameterSearch_Collaborative,
URM_train=URM_train,
metric_to_optimize="MAP",
evaluator_validation_earlystopping=evaluator_validation_earlystopping,
evaluator_validation=evaluator_validation,
evaluator_test=evaluator_test,
output_root_path=output_root_path)
# pool = multiprocessing.Pool(processes=int(multiprocessing.cpu_count()), maxtasksperchild=1)
# resultList = pool.map(runParameterSearch_Collaborative_partial, collaborative_algorithm_list)
for recommender_class in collaborative_algorithm_list:
try:
runParameterSearch_Collaborative_partial(recommender_class)
except Exception as e:
print("On recommender {} Exception {}".format(
recommender_class, str(e)))
traceback.print_exc()
from KNN.UserKNNCFRecommender import UserKNNCFRecommender
from ParameterTuning.AbstractClassSearch import writeLog
from data_splitter import train_test_holdout
import itertools
data = Data()
URM = data.get_URM()
ICM = data.get_ICM()
URM_train, URM_test = train_test_holdout(URM, train_perc=0.8)
print("Shape : {}".format(URM_train.__sizeof__()))
evaluator_test = SequentialEvaluator(URM_test, cutoff_list=[10])
evaluator_test = EvaluatorWrapper(evaluator_test)
output_root_path = "result_experiments/"
filename = P3alphaRecommender.RECOMMENDER_NAME \
+ ItemKNNCBFRecommender.RECOMMENDER_NAME \
+ ItemKNNCFRecommender.RECOMMENDER_NAME \
+ "hybrid_opt"
output_root_path += filename
output_file = open(output_root_path, "a")
P3alpha = P3alphaRecommender(URM_train)
P3alpha.fit(topK=100, alpha=0.7905462550621185, implicit=True, normalize_similarity=True)
# print("-------------------")
# print("--P3alpha fitted---")
def hybrid_repo(is_test):
b = Builder()
ev = Evaluator()
ev.split()
ICM = b.build_ICM()
URM_train, URM_test = train_test_holdout(b.get_URM(), train_perc=0.8)
URM_train, URM_validation = train_test_holdout(URM_train, train_perc=0.9)
from ParameterTuning.AbstractClassSearch import EvaluatorWrapper
from Base.Evaluation.Evaluator import SequentialEvaluator
evaluator_validation = SequentialEvaluator(URM_validation, cutoff_list=[5])
evaluator_test = SequentialEvaluator(URM_test, cutoff_list=[5, 10])
evaluator_validation = EvaluatorWrapper(evaluator_validation)
evaluator_test = EvaluatorWrapper(evaluator_test)
from KNN.ItemKNNCFRecommender import ItemKNNCFRecommender
from ParameterTuning.BayesianSearch import BayesianSearch
recommender_class = ItemKNNCFRecommender
parameterSearch = BayesianSearch(recommender_class,
evaluator_validation=evaluator_validation,
evaluator_test=evaluator_test)
from ParameterTuning.AbstractClassSearch import DictionaryKeys
hyperparamethers_range_dictionary = {}
hyperparamethers_range_dictionary["topK"] = [
5, 10, 20, 50, 100, 150, 200, 300, 400, 500, 600, 700, 800
]
hyperparamethers_range_dictionary["shrink"] = [
0, 10, 50, 100, 200, 300, 500, 1000
]
hyperparamethers_range_dictionary["similarity"] = ["cosine"]
hyperparamethers_range_dictionary["normalize"] = [True, False]
recommenderDictionary = {
DictionaryKeys.CONSTRUCTOR_POSITIONAL_ARGS: [URM_train],
DictionaryKeys.CONSTRUCTOR_KEYWORD_ARGS: {},
DictionaryKeys.FIT_POSITIONAL_ARGS: dict(),
DictionaryKeys.FIT_KEYWORD_ARGS: dict(),
DictionaryKeys.FIT_RANGE_KEYWORD_ARGS:
hyperparamethers_range_dictionary
}
output_root_path = "result_experiments/"
import os
# If directory does not exist, create
if not os.path.exists(output_root_path):
os.makedirs(output_root_path)
output_root_path += recommender_class.RECOMMENDER_NAME
n_cases = 2
metric_to_optimize = "MAP"
best_parameters = parameterSearch.search(recommenderDictionary,
n_cases=n_cases,
output_root_path=output_root_path,
metric=metric_to_optimize)
itemKNNCF = ItemKNNCFRecommender(URM_train)
itemKNNCF.fit(**best_parameters)
from FW_Similarity.CFW_D_Similarity_Linalg import CFW_D_Similarity_Linalg
n_cases = 2
metric_to_optimize = "MAP"
best_parameters_ItemKNNCBF = parameterSearch.search(
recommenderDictionary,
n_cases=n_cases,
output_root_path=output_root_path,
metric=metric_to_optimize)
itemKNNCBF = ItemKNNCBFRecommender(ICM, URM_train)
itemKNNCBF.fit(**best_parameters_ItemKNNCBF)
"""
#_____________________________________________________________________
from ParameterTuning.BayesianSearch import BayesianSearch
from ParameterTuning.AbstractClassSearch import DictionaryKeys
from ParameterTuning.AbstractClassSearch import EvaluatorWrapper
evaluator_validation_tuning = EvaluatorWrapper(evaluator_validation)
evaluator_test_tuning = EvaluatorWrapper(evaluator_test)
recommender_class = CFW_D_Similarity_Linalg
parameterSearch = BayesianSearch(recommender_class,
evaluator_validation=evaluator_validation_tuning,
evaluator_test=evaluator_test_tuning)
hyperparamethers_range_dictionary = {}
hyperparamethers_range_dictionary["topK"] = [5, 10, 20, 50, 100, 150, 200, 300, 400, 500, 600, 700, 800]
hyperparamethers_range_dictionary["add_zeros_quota"] = range(0, 1)
hyperparamethers_range_dictionary["normalize_similarity"] = [True, False]
recommenderDictionary = {DictionaryKeys.CONSTRUCTOR_POSITIONAL_ARGS: [URM_train, ICM, itemKNNCF.W_sparse],
DictionaryKeys.CONSTRUCTOR_KEYWORD_ARGS: {},
DictionaryKeys.FIT_POSITIONAL_ARGS: dict(),
DictionaryKeys.FIT_KEYWORD_ARGS: dict(),
DictionaryKeys.FIT_RANGE_KEYWORD_ARGS: hyperparamethers_range_dictionary}
output_root_path = "result_experiments/"
import os
# If directory does not exist, create
if not os.path.exists(output_root_path):
os.makedirs(output_root_path)
output_root_path += recommender_class.RECOMMENDER_NAME
n_cases = 2
metric_to_optimize = "MAP"
best_parameters_CFW_D = parameterSearch.search(recommenderDictionary,
n_cases=n_cases,
output_root_path=output_root_path,
metric=metric_to_optimize)
CFW_weithing = CFW_D_Similarity_Linalg(URM_train, ICM, itemKNNCF.W_sparse)
CFW_weithing.fit(**best_parameters_CFW_D)
#___________________________________________________________________________________________-
"""
from GraphBased.P3alphaRecommender import P3alphaRecommender
P3alpha = P3alphaRecommender(URM_train)
P3alpha.fit()
from MatrixFactorization.PureSVD import PureSVDRecommender
#pureSVD = PureSVDRecommender(URM_train)
#pureSVD.fit()
rec = HybridRec.HybridRec()
S_UCM = b.get_S_UCM_KNN(b.get_UCM(ev.get_URM_train()), 600)
S_ICM = b.build_S_ICM_knn(b.build_ICM(), 250)
rec.fit(ev.get_URM_train(),
ev.get_target_playlists(),
ev.get_target_tracks(),
ev.num_playlists_to_test,
itemKNNCBF.W_sparse,
itemKNNCF.W_sparse,
P3alpha.W_sparse,
is_test=True,
alfa=0.7,
avg=0.3)
train_df = rec.recommend()
if is_test:
map5 = ev.map5(train_df)
print('Hybrid MAP@10:', map5)
return map5
else:
print('Prediction saved!')
train_df.to_csv(os.path.dirname(os.path.realpath(__file__))[:-19] +
"/all/sub.csv",
sep=',',
index=False)
return 0
#hybridrecommender = ItemKNNSimilarityHybridRecommender(URM_train, itemKNNCF.W_sparse, P3alpha.W_sparse)
#hybridrecommender.fit(alpha=0.5)
#print(evaluator_validation.evaluateRecommender(hybridrecommender))
"""
URM_test = data.get_URM_test()
print("URM_train shape : {}".format(URM_train.shape))
print("URM_test shape : {}".format(URM_test.shape))
print("ICM shape : {}".format(ICM.shape))
#URM_train, URM_validation, URM_test = split_train_validation_test(URM, [0.8, 0.1, 0.1])
# ------------------------
# Instanciating Evaluators
# ------------------------
evaluator_validation = SequentialEvaluator(URM_test, cutoff_list=[10])
#evaluator_test = SequentialEvaluator(URM_test, cutoff_list=[10])
evaluator_validation = EvaluatorWrapper(evaluator_validation)
#evaluator_test = EvaluatorWrapper(evaluator_test)
# ------------------------
# Recommender class definition
# ------------------------
recommender_class = ItemKNNCBFRecommender
# ------------------------
# Instanciating BayesianSearch
# ------------------------
parameterSearch = BayesianSearch(recommender_class,
evaluator_validation=evaluator_validation)