def test_tf_ibmf_batch_accuracy(n_jobs, tf_session):
from lenskit.algorithms import basic
from lenskit.algorithms import bias
import lenskit.crossfold as xf
from lenskit import batch
import lenskit.metrics.predict as pm
ratings = lktu.ml100k.ratings
algo = lktf.IntegratedBiasMF(20, batch_size=1024, epochs=20, rng_spec=42)
algo = basic.Fallback(algo, bias.Bias(damping=10))
def eval(train, test):
_log.info('running training')
algo.fit(train)
_log.info('testing %d users', test.user.nunique())
return batch.predict(algo, test, n_jobs=n_jobs)
folds = xf.partition_users(ratings, 5, xf.SampleFrac(0.2))
preds = pd.concat(eval(train, test) for (train, test) in folds)
mae = pm.mae(preds.prediction, preds.rating)
assert mae == approx(0.73, abs=0.025)
user_rmse = preds.groupby('user').apply(
lambda df: pm.rmse(df.prediction, df.rating))
assert user_rmse.mean() == approx(0.93, abs=0.05)
def test_tf_ibmf_general(tmp_path, tf_session):
"Training, saving, loading, and using an integrated bias model."
fn = tmp_path / 'bias.bpk'
ratings = lktu.ml_test.ratings
original = lktf.IntegratedBiasMF(20,
batch_size=1024,
epochs=20,
rng_spec=42)
original.fit(ratings)
ue = original.model.get_layer('user-embed')
assert ue.get_weights()[0].shape == (ratings.user.nunique(), 20)
ie = original.model.get_layer('item-embed')
assert ie.get_weights()[0].shape == (ratings.item.nunique(), 20)
binpickle.dump(original, fn)
_log.info('serialized to %d bytes', fn.stat().st_size)
algo = binpickle.load(fn)
# does predicting work?
preds = algo.predict_for_user(100, [5, 10, 30])
assert all(preds.notna())
# can we include a nonexistent item?
preds = algo.predict_for_user(100, [5, 10, 230413804])
assert len(preds) == 3
assert all(preds.loc[[230413804]].isna())
assert preds.isna().sum() == 1
def test_tf_isvd(ml20m):
algo = lktf.IntegratedBiasMF(20)
def eval(train, test):
_log.info('running training')
algo.fit(train)
_log.info('testing %d users', test.user.nunique())
return batch.predict(algo, test)
folds = xf.sample_users(ml20m, 2, 5000, xf.SampleFrac(0.2))
preds = pd.concat(eval(train, test) for (train, test) in folds)
mae = pm.mae(preds.prediction, preds.rating)
assert mae == approx(0.60, abs=0.025)
user_rmse = preds.groupby('user').apply(
lambda df: pm.rmse(df.prediction, df.rating))
assert user_rmse.mean() == approx(0.92, abs=0.05)
""" This module defines the algorithms, and their default configurations, that we are going to use. """ from lenskit.algorithms import item_knn, user_knn, als, tf from lenskit.algorithms import basic Bias = basic.Bias(damping=5) Pop = basic.Popular() II = item_knn.ItemItem(20, save_nbrs=2500) UU = user_knn.UserUser(30) ALS = als.BiasedMF(50) IALS = als.ImplicitMF(50) BPR = tf.BPR(50) TFMF = tf.IntegratedBiasMF(50)