def learnModel(self, X):
learner = WARPMFRecommender(self.k, self.alpha, self.lmbda, self.batchSize, self.maxTrials)
learner.fit(X)
return learner.U, learner.V
def learnModel(self, X):
learner = WARPMFRecommender(self.k, self.alpha, self.lmbda,
self.batchSize, self.maxTrials)
learner.fit(X)
return learner.U, learner.V
def testPredictionMethods(train_filename, eval_item_filename, user_means_filename):
'''
compare predictions generated by the different approaches
computes pairwise list overlap and average recall for each method
'''
logging.info('testing predictions with data files {0}; {1}; {2}...'.format(train_filename, eval_item_filename, user_means_filename))
mrec_train_data = load_fast_sparse_matrix('tsv', train_filename)
mrec_recommender = CosineKNNRecommender(config.NEIGHBOURHOOD_SIZE)
mrec_recommender.fit(mrec_train_data)
warp_recommender = WARPMFRecommender(d=50, gamma=0.01, C=100.0)
warp_recommender.fit(mrec_train_data.X)
train_data = trainData.TrainData(train_filename, user_means_filename)
_, _, Q = sparsesvd(train_data.rating_matrix.tocsc(), config.FACTOR_MODEL_SIZE)
recalls = {}
overlaps = {}
top_recs = {}
user_counter = 0.0
methods = ['mrec', 'warp', 'mf', 'ub_classic', 'ib_classic', 'ub_damping', 'ib_damping', 'ub_non', 'ib_non']
with open(eval_item_filename,'rb') as eval_file:
for line in eval_file:
data = line.split('\t')
user_id = data[0]
ground_truth_items = data[1].split(',')
random_unrated_items = data[2].rstrip('\n').split(',')
evaluation_item_ids = ground_truth_items + random_unrated_items
# for each prediction method, compute topN recommendations once per user
predictions1 = mrec_recommender.recommend_items(mrec_train_data.X, int(user_id)-config.MREC_INDEX_OFFSET, max_items=10000, return_scores=True)
top_recs['mrec'] = topNLists.getTopNList(predictions1, evaluation_item_ids=evaluation_item_ids)
predictions2 = warp_recommender.recommend_items(mrec_train_data.X, int(user_id)-config.MREC_INDEX_OFFSET, max_items=10000, return_scores=True)
top_recs['warp'] = topNLists.getTopNList(predictions2, evaluation_item_ids=evaluation_item_ids)
predictions3 = train_data.getFactorBasedRecommendations(user_id, Q, evaluation_item_ids)
top_recs['mf'] = topNLists.getTopNList(predictions3)
predictions4 = train_data.getUserBasedRecommendations(user_id, evaluation_item_ids, 'classic')
top_recs['ub_classic'] = topNLists.getTopNList(predictions4)
predictions5 = train_data.getItemBasedRecommendations(user_id, evaluation_item_ids, 'classic')
top_recs['ib_classic'] = topNLists.getTopNList(predictions5)
predictions6 = train_data.getUserBasedRecommendations(user_id, evaluation_item_ids, 'self_damping')
top_recs['ub_damping'] = topNLists.getTopNList(predictions6)
predictions7 = train_data.getItemBasedRecommendations(user_id, evaluation_item_ids, 'self_damping')
top_recs['ib_damping'] = topNLists.getTopNList(predictions7)
predictions8 = train_data.getUserBasedRecommendations(user_id, evaluation_item_ids, 'non_normalized')
top_recs['ub_non'] = topNLists.getTopNList(predictions8)
predictions9 = train_data.getItemBasedRecommendations(user_id, evaluation_item_ids, 'non_normalized')
top_recs['ib_non'] = topNLists.getTopNList(predictions9)
# then, use the computed topN lists to update recall and overlap values
for method1 in methods:
if method1 in recalls:
recalls[method1] += topNLists.getRecall(ground_truth_items, top_recs[method1])
else:
recalls[method1] = topNLists.getRecall(ground_truth_items, top_recs[method1])
for method2 in methods:
dict_key = method1 + '_' + method2
if dict_key in overlaps:
overlaps[dict_key] += topNLists.computeRecommendationListOverlap(top_recs[method1], top_recs[method2])
else:
overlaps[dict_key] = topNLists.computeRecommendationListOverlap(top_recs[method1], top_recs[method2])
user_counter += 1.0
logging.info('Tested user {0}. Current recalls: {1}. Current overlaps: {2}'.\
format(user_id, [(k, v/user_counter) for k,v in recalls.items()], [(k, v/user_counter) for k,v in overlaps.items()]))
return recalls, overlaps
filenames = dataPreprocessing.loadData(mode='beyond_accuracy')
# 5-fold cross-validation
for iteration, (train_filename, test_filename, user_means_filename,
eval_item_filename) in enumerate(filenames, 1):
mrec_train_data = load_fast_sparse_matrix('tsv', train_filename)
# create the training data and required recommendation models
train_data = trainData.TrainData(train_filename, user_means_filename)
for factor_value, C_value, gamma_value in product(
factor_values, C_values, gamma_values):
warp_recommender = WARPMFRecommender(d=factor_value,
gamma=gamma_value,
C=C_value)
warp_recommender.fit(mrec_train_data.X)
logging.info('running fold {0} with f={1}, C={2}, g={3}...'.format(
iteration, factor_value, C_value, gamma_value))
recall = 0
evaluation_cases = 0
with open(eval_item_filename, 'rb') as eval_file:
for line in eval_file:
data = line.split('\t')
user_id = data[0]
ground_truth_items = data[1].split(',')
random_unrated_items = data[2].rstrip('\n').split(',')
# THIS IS A FIX FOR THE FEW USERS IN LAST.FM WHO HAVE IDENTICAL RATINGS FOR ALL TRAIN ITEMS