def test_RANK_Spearman_different_list_sizes(self):
TEST_DATA = ['classical', 'invented', 'baroque']
GT_DATA = ['classical', 'instrumental', 'piano', 'baroque']
spearman = SpearmanRho()
spearman.load_ground_truth(GT_DATA)
spearman.load_test(TEST_DATA)
assert_raises(ValueError, spearman.compute) #Raise: GT & TEST list have different sizes
def __init__(self):
super(TestRanking, self).__init__()
# Rank-based metrics: KendallTau, SpearmanRho, MeanReciprocalRank, ReciprocalRank
self.kendall = KendallTau()
self.kendall.load(self.GT_RANKING, self.TEST_RANKING)
self.spearman = SpearmanRho()
self.spearman.load(self.GT_RANKING, self.TEST_RANKING)
self.mrr = MeanReciprocalRank()
for elem in self.TEST_DECISION:
self.mrr.load(self.GT_DECISION, elem)
def test_RANK_Spearman_load_ground_truth(self):
spearman = SpearmanRho()
spearman.load_ground_truth(self.GT_DATA)
assert_equal(len(spearman.get_ground_truth()), len(self.TEST_DATA))
def test_RANK_Spearman_load_test(self):
spearman = SpearmanRho()
spearman.load_test(self.TEST_DATA)
assert_equal(len(spearman.get_test()), len(self.TEST_DATA))
def test_RANK_Spearman_compute_floats(self):
spearman = SpearmanRho(self.DATA_PRED)
assert_equal(spearman.compute(), 0.947368) #0.95 ?
MIN_RATING = 0.0
MAX_RATING = 5.0
ITEMID = 1
USERID = 1
print svd.predict(ITEMID, USERID, MIN_RATING,
MAX_RATING) # predicted rating value
print svd.get_matrix().value(ITEMID, USERID) # real rating value
print ''
print 'GENERATING RECOMMENDATION'
print svd.recommend(USERID, n=5, only_unknowns=True, is_row=False)
#Evaluation using prediction-based metrics
rmse = RMSE()
mae = MAE()
spearman = SpearmanRho()
kendall = KendallTau()
#decision = PrecisionRecallF1()
for rating, item_id, user_id in test.get():
try:
pred_rating = svd.predict(item_id, user_id)
rmse.add(rating, pred_rating)
mae.add(rating, pred_rating)
spearman.add(rating, pred_rating)
kendall.add(rating, pred_rating)
except KeyError:
continue
print ''
print 'EVALUATION RESULT'
print 'RMSE=%s' % rmse.compute()
