def crossValidate(logFile, test_size=0.01) :
"""
:param recommender: we assume it has an s_recommend method
:param test_size: how big is the test size in the test split
:return: prints to screen and to logfile the cv average of the metrics
"""
Kaggle = False
if Kaggle == True:
interactionsCsv = pd.read_csv("../input/train.csv")
targetList = pd.read_csv("../input/target_playlists.csv").iloc[:, 0]
tracksCsv = pd.read_csv("../input/tracks.csv")
else:
interactionsCsv = pd.read_csv("input/train.csv")
targetList = pd.read_csv("input/target_playlists.csv").iloc[:, 0]
tracksCsv = pd.read_csv("input/tracks.csv")
cumulative_precision = [None] * 8
cumulative_recall = [None] * 8
cumulative_MAP = [None] * 8
cf_parameters = {'topK': 80,
'alpha': 1,
'beta': 0.27,
'normalize_similarity': True,
'implicit': True,
'norm': 'l1'}
for seed, i in zip([13, 17, 23, 33, 45, 57, 69, 77], range(8)):
X_train, X_test = train_test_split(interactionsCsv, test_size=test_size, random_state=seed)
urm_train = URM(X_train)
urm_test = URM(X_test)
urm = urm_train
rp3b = RP3betaRecommender(urm.getCSR())
rp3b.fit(**cf_parameters)
cumulative_precision[i], cumulative_recall[i], cumulative_MAP[i] = evaluate_algorithm(urm_test, rp3b)
cumulative_precision = np.array(cumulative_precision)
cumulative_recall = np.array(cumulative_recall)
cumulative_MAP = np.array(cumulative_MAP)
print("Recommender, performance is: Precision = {:.4f}, Recall = {:.4f}, MAP = {:.6f}"
.format(cumulative_precision.mean(), cumulative_recall.mean(), cumulative_MAP.mean()))
logFile.write("Test case: {}, Precision = {:.4f}, Recall = {:.4f}, MAP = {:.6f}\n".format(cf_parameters,
cumulative_precision.mean(),
cumulative_recall.mean(),
cumulative_MAP.mean()))
logFile.flush()
'weight_dict' : {'cbi_weight': 0, 'cbu_weight': 0.325, 'cbf_weight': 0.2, 'rp3b_weight': 0.225, 'slim_weight': 0.325},
'loadSLIM': True, 'slimPath': 'slim_G2.pickle'
}
group_param = [group1_param, group2_param]
nphybrid = NewPopulationHybrid(matrices, group1, group2, group1_param, group2_param, enable_dict)
if submission:
print("Preparing submission")
recommended_items = nphybrid.m_recommend(targetList, nRec=10)
generate_output(targetList, recommended_items, path="submission.csv")
else:
cumulative_precision, cumulative_recall, cumulative_MAP = evaluate_algorithm(urm_test, nphybrid)
print("Recommender, performance is: Precision = {:.4f}, Recall = {:.4f}, MAP = {:.6f}"
.format(cumulative_precision, cumulative_recall, cumulative_MAP))
""" Print to File """
logFile = open("Tuning.txt", "a")
logFile.write("Test group {}, params: {}, Precision = {:.4f}, Recall = {:.4f}, MAP = {:.6f}\n"
.format(enable_dict, group_param, cumulative_precision.mean(), cumulative_recall.mean(),
cumulative_MAP.mean()))
logFile.flush()
"""
FOR TUNING AFTER BUILDING MODEL
'CBFNorm': 'l2'
}
groups = [group1, group2, group3]
group_params = [group1_param, group2_param, group3_param]
nphybrid = NewPopulationHybrid(matrices, groups, group_params, enable_dict)
if submission:
print("Preparing submission")
recommended_items = nphybrid.m_recommend(targetList, nRec=10)
generate_output(targetList, recommended_items, path="submission.csv")
else:
cumulative_precision, cumulative_recall, cumulative_MAP = tqdm(
evaluate_algorithm(urm_test, nphybrid))
print(
"Recommender, performance is: Precision = {:.4f}, Recall = {:.4f}, MAP = {:.6f}"
.format(cumulative_precision, cumulative_recall, cumulative_MAP))
""" Print to File """
logFile = open("Tuning_vittorio.txt", "a")
logFile.write(
"Test group {}, params: {}, Precision = {:.4f}, Recall = {:.4f}, MAP = {:.6f}\n"
.format(enable_dict, group2_param, cumulative_precision.mean(),
cumulative_recall.mean(), cumulative_MAP.mean()))
logFile.flush()
"""
FOR TUNING AFTER BUILDING MODEL
for i in range(70):
'group_1_2_TH': group_1_2_TH
}
phy = PopulationHybrid(urm,
urm_t,
icm,
icm2,
enable_dict,
param_dict,
urm_test=urm_test)
if submission:
recommended_items = phy.m_recommend(targetList, nRec=10)
generate_output(targetList, recommended_items)
else:
print("Evaluating")
cumulative_precision, cumulative_recall, cumulative_MAP = evaluate_algorithm(
urm_test, phy)
print(
"Recommender, performance is: Precision = {:.4f}, Recall = {:.4f}, MAP = {:.5f}"
.format(cumulative_precision, cumulative_recall, cumulative_MAP))
elif htype == "uii":
print("Fitting hybrid recommender")
enable_dict = {
'enableSVD': True,
'enableSLIM': True,
'enableCBF2': True,
'enableP3A': False,
'enableLFM': False,
'enableRP3B': True