from KNN.ItemKNNCFRecommender import ItemKNNCFRecommender
from KNN.ItemKNNCBFRecommender import ItemKNNCBFRecommender
from KNN.UserKNNCBFRecommender import UserKNNCBFRecommender
from KNN.UserKNNCFRecommender import UserKNNCFRecommender
import numpy as np
import scipy.sparse as sps
from FeatureWeighting.User_CFW_D_Similarity_Linalg import User_CFW_D_Similarity_Linalg
from Hybrid.HybridGen2Recommender import HybridGen2Recommender
from Hybrid.HybridNormRecommender import HybridNormRecommender
from Hybrid.HybridNorm1Recommender import HybridNorm1Recommender
from Hybrid.HybridNorm2Recommender import HybridNorm2Recommender
Data = DataManager()
urm_train, urm_test = split_train_leave_k_out_user_wise(Data.get_urm(), threshold=10, temperature='normal')
urm_train, urm_valid = split_train_leave_k_out_user_wise(urm_train, threshold=10, temperature='valid')
evaluator_valid = EvaluatorHoldout(urm_valid, cutoff_list=[10])
evaluator_test = EvaluatorHoldout(urm_test, cutoff_list=[10])
recommender = HybridNorm1Recommender
# recommender_3 = UserKNNCFRecommender(urm_train)
# recommender_3.fit(shrink=2, topK=600, normalize=True)
# w_sparse = recommender_3.W_sparse
parameterSearch = SearchBayesianSkopt(recommender,
evaluator_validation=evaluator_valid,
evaluator_test=evaluator_test)
# earlystopping_keywargs = {"validation_every_n": 5,
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 = Movielens10MReader()
#
# URM_train = dataReader.get_URM_train()
# URM_validation = dataReader.get_URM_validation()
# URM_test = dataReader.get_URM_test()
Data = DataManager()
urm_temp, urm_test = split_train_leave_k_out_user_wise(
Data.get_urm(), use_validation_set=False, leave_random_out=True)
urm_train, urm_valid = split_train_leave_k_out_user_wise(
urm_temp, use_validation_set=False, leave_random_out=True)
output_folder_path = "result_experiments/"
# If directory does not exist, create
if not os.path.exists(output_folder_path):
os.makedirs(output_folder_path)
collaborative_algorithm_list = [
# Random,
# TopPop,
# P3alphaRecommender,
# RP3betaRecommender,
# ItemKNNCFRecommender,
# UserKNNCFRecommender,
# MatrixFactorization_BPR_Cython,
# MatrixFactorization_FunkSVD_Cython,
# PureSVDRecommender,
# SLIM_BPR_Cython,
# SLIMElasticNetRecommender
SLIMElasticNetRecommender
]
from Base.Evaluation.Evaluator import EvaluatorHoldout
evaluator_validation = EvaluatorHoldout(urm_valid, cutoff_list=[10])
evaluator_test = EvaluatorHoldout(urm_test, cutoff_list=[10])
runParameterSearch_Collaborative_partial = partial(
runParameterSearch_Collaborative,
URM_train=urm_train,
metric_to_optimize="MAP",
n_cases=10,
evaluator_validation_earlystopping=evaluator_validation,
evaluator_validation=evaluator_validation,
evaluator_test=evaluator_test,
output_folder_path=output_folder_path,
similarity_type_list=["cosine"],
parallelizeKNN=False)
# pool = multiprocessing.Pool(processes=int(multiprocessing.cpu_count()), maxtasksperchild=1)
# 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 FeatureWeighting.CFW_D_Similarity_Linalg import CFW_D_Similarity_Linalg
from Hybrid.HybridNorm1Recommender import HybridNorm1Recommender
from Hybrid.HybridNorm2Recommender import HybridNorm2Recommender
from Hybrid.HybridGen2Recommender import HybridGen2Recommender
from MatrixFactorization.Cython.MatrixFactorization_Cython import MatrixFactorization_BPR_Cython
data_folder = Path(__file__).parent.absolute()
from FeatureWeighting.User_CFW_D_Similarity_Linalg import User_CFW_D_Similarity_Linalg
from Hybrid.HybridNorm3Recommender import HybridNorm3Recommender
from MatrixFactorization.ALSRecommender import ALSRecommender
from MatrixFactorization.BPRRecommender import BPRRecommender
import similaripy as sim
data = DataManager()
urm_train = data.get_urm()
urm_train, urm_test = split_train_leave_k_out_user_wise(data.get_urm(),
temperature='normal')
urm_train, urm_valid = split_train_leave_k_out_user_wise(urm_train,
temperature='valid2')
urm_train_warm = data.create_test_warm_users(urm_train, threshold=10)
urm_test_warm = data.create_test_warm_users(urm_test, threshold=10)
evaluator_test_warm = EvaluatorHoldout(urm_test_warm, cutoff_list=[10])
recommender = UserKNNCFRecommender(urm_train)
recommender.fit(shrink=2, topK=600, normalize=True)
recommender_warm = UserKNNCFRecommender(urm_train_warm)
recommender_warm.fit(shrink=2, topK=500, normalize=True)
result, str_result = evaluator_test_warm.evaluateRecommender(recommender)
from DataManager.DataManager import DataManager
from lightfm.evaluation import auc_score
from DataManager.split_train_validation_leave_k_out import split_train_leave_k_out_user_wise
from Base.Evaluation.Evaluator import EvaluatorHoldout
from Hybrid.LighFm import LighFMRecommender
import matplotlib.pyplot as pyplot
from sklearn import metrics, ensemble
import numpy as np
data = DataManager()
urm = data.get_urm()
threshold = 10
temperature = 'normal'
ucm_age, ucm_region, ucm_all = data.get_ucm()
icm_price, icm_asset, icm_sub, icm_all = data.get_icm()
urm_train, urm_test = split_train_leave_k_out_user_wise(
urm, threshold=threshold, temperature=temperature)
urm_train, urm_valid = split_train_leave_k_out_user_wise(urm_train,
threshold=threshold,
temperature='valid')
evaluator_test = EvaluatorHoldout(urm_test, cutoff_list=[10])
evaluator_valid = EvaluatorHoldout(urm_valid, cutoff_list=[10])
# recommender = LighFMRecommender(urm_train,
# no_components=150,
# loss='warp',
# learning_rate=0.09,
# random_state=2019)
#
#
# recommender.fit(epochs=10, user_features=ucm_all, item_features=icm_sub, num_threads=4)
