def instantiate(opts, implicit):
nnbrs, smin = opts
if implicit:
return ItemItem(nnbrs, min_sim=smin, save_nbrs=10000,
aggregate='sum', center=False)
else:
return ItemItem(nnbrs, min_sim=smin, save_nbrs=10000)
def test_store_iknn(store_cls):
algo = ItemItem(10)
algo = Recommender.adapt(algo)
algo.fit(lktu.ml_test.ratings)
with store_cls() as store:
k = store.put_model(algo)
client = store.client()
a2 = client.get_model(k)
assert a2 is not algo
del a2
def test_adv_fill_users():
rla = topn.RecListAnalysis()
rla.add_metric(topn.precision)
rla.add_metric(topn.recall)
a_uu = UserUser(30, min_nbrs=10)
a_uu = Recommender.adapt(a_uu)
a_ii = ItemItem(20, min_nbrs=4)
a_ii = Recommender.adapt(a_ii)
splits = xf.sample_users(ml_test.ratings, 2, 50, xf.SampleN(5))
all_recs = {}
all_test = {}
for i, (train, test) in enumerate(splits):
a_uu.fit(train)
rec_users = test['user'].sample(50).unique()
all_recs[(i + 1, 'UU')] = batch.recommend(a_uu, rec_users, 25)
a_ii.fit(train)
rec_users = test['user'].sample(50).unique()
all_recs[(i + 1, 'II')] = batch.recommend(a_ii, rec_users, 25)
all_test[i + 1] = test
recs = pd.concat(all_recs, names=['part', 'algo'])
recs.reset_index(['part', 'algo'], inplace=True)
recs.reset_index(drop=True, inplace=True)
test = pd.concat(all_test, names=['part'])
test.reset_index(['part'], inplace=True)
test.reset_index(drop=True, inplace=True)
scores = rla.compute(recs, test, include_missing=True)
inames = scores.index.names
scores.sort_index(inplace=True)
assert len(scores) == 50 * 4
assert all(scores['ntruth'] == 5)
assert scores['recall'].isna().sum() > 0
_log.info('scores:\n%s', scores)
ucounts = scores.reset_index().groupby('algo')['user'].agg(
['count', 'nunique'])
assert all(ucounts['count'] == 100)
assert all(ucounts['nunique'] == 100)
mscores = rla.compute(recs, test)
mscores = mscores.reset_index().set_index(inames)
mscores.sort_index(inplace=True)
assert len(mscores) < len(scores)
_log.info('mscores:\n%s', mscores)
recall = scores.loc[scores['recall'].notna(), 'recall'].copy()
recall, mrecall = recall.align(mscores['recall'])
assert all(recall == mrecall)
def __init__(self,
nnbrs,
min_nbrs=1,
min_sim=1e-06,
save_nbrs=None,
center=True,
aggregate='weighted-average'):
algo = ItemItem(nnbrs, min_nbrs, min_sim, save_nbrs, center, aggregate)
fallback = Bias()
Fallback.__init__(self, [algo, fallback])
def default(implicit):
if implicit:
return ItemItem(20, save_nbrs=10000,
aggregate='sum', center=False)
else:
return ItemItem(20, save_nbrs=10000)
def __str__(self):
return ItemItem.__str__(self)