def recommend(algo, users, n, candidates=None, *, nprocs=None, dask_result=False, **kwargs):
"""
Batch-recommend for multiple users. The provided algorithm should be a
:py:class:`algorithms.Recommender`.
Args:
algo: the algorithm
users(array-like): the users to recommend for
n(int): the number of recommendations to generate (None for unlimited)
candidates:
the users' candidate sets. This can be a function, in which case it will
be passed each user ID; it can also be a dictionary, in which case user
IDs will be looked up in it. Pass ``None`` to use the recommender's
built-in candidate selector (usually recommended).
nprocs(int):
The number of processes to use for parallel recommendations. Passed as
``n_jobs`` to :cls:`joblib.Parallel`. The default, ``None``, will make
the process sequential _unless_ called inside the :func:`joblib.parallel_backend`
context manager.
dask_result(bool):
Whether to return a Dask data frame instead of a Pandas one.
Returns:
A frame with at least the columns ``user``, ``rank``, and ``item``; possibly also
``score``, and any other columns returned by the recommender.
"""
rec_algo = Recommender.adapt(algo)
if candidates is None and rec_algo is not algo:
warnings.warn('no candidates provided and algo is not a recommender, unlikely to work')
del algo # don't need reference any more
if 'ratings' in kwargs:
warnings.warn('Providing ratings to recommend is not supported', DeprecationWarning)
candidates = __standard_cand_fun(candidates)
loop = Parallel(n_jobs=nprocs)
path = None
try:
with loop:
backend = loop._backend.__class__.__name__
njobs = loop._effective_n_jobs()
_logger.info('parallel backend %s, effective njobs %s',
backend, njobs)
using_dask = backend == 'DaskDistributedBackend'
if using_dask:
_logger.debug('pre-scattering algorithm %s', rec_algo)
futures = loop._backend.client.scatter([rec_algo], broadcast=True, hash=False)
rec_algo = _AlgoKey('future', futures[0])
elif njobs > 1:
fd, path = tempfile.mkstemp(prefix='lkpy-predict', suffix='.pkl')
path = pathlib.Path(path)
os.close(fd)
_logger.debug('pre-serializing algorithm %s to %s', rec_algo, path)
dump(rec_algo, path)
rec_algo = _AlgoKey('file', path)
_logger.info('recommending for %d users (nprocs=%s)', len(users), nprocs)
timer = util.Stopwatch()
results = loop(delayed(_recommend_user)(rec_algo, user, n, candidates(user))
for user in users)
if using_dask or dask_result:
results = ddf.concat(results, interleave_partitions=True)
if not dask_result: # only if we're running inside dask, but don't want results
results = results.compute()
else:
results = pd.concat(results, ignore_index=True)
_logger.info('recommended for %d users in %s', len(users), timer)
finally:
util.delete_sometime(path)
return results
def predict(algo, pairs, *, nprocs=None):
"""
Generate predictions for user-item pairs. The provided algorithm should be a
:py:class:`algorithms.Predictor` or a function of two arguments: the user ID and
a list of item IDs. It should return a dictionary or a :py:class:`pandas.Series`
mapping item IDs to predictions.
To use this function, provide a pre-fit algorithm::
>>> from lenskit.algorithms.basic import Bias
>>> from lenskit.metrics.predict import rmse
>>> ratings = util.load_ml_ratings()
>>> bias = Bias()
>>> bias.fit(ratings[:-1000])
<lenskit.algorithms.basic.Bias object at ...>
>>> preds = predict(bias, ratings[-1000:])
>>> preds.head()
user item rating timestamp prediction
99004 664 8361 3.0 1393891425 3.288286
99005 664 8528 3.5 1393891047 3.559119
99006 664 8529 4.0 1393891173 3.573008
99007 664 8636 4.0 1393891175 3.846268
99008 664 8641 4.5 1393890852 3.710635
>>> rmse(preds['prediction'], preds['rating'])
0.8326992222...
Args:
algo(lenskit.algorithms.Predictor):
A rating predictor function or algorithm.
pairs(pandas.DataFrame):
A data frame of (``user``, ``item``) pairs to predict for. If this frame also
contains a ``rating`` column, it will be included in the result.
nprocs(int):
The number of processes to use for parallel batch prediction. Passed as
``n_jobs`` to :cls:`joblib.Parallel`. The default, ``None``, will make
the process sequential _unless_ called inside the :func:`joblib.parallel_backend`
context manager.
Returns:
pandas.DataFrame:
a frame with columns ``user``, ``item``, and ``prediction`` containing
the prediction results. If ``pairs`` contains a `rating` column, this
result will also contain a `rating` column.
"""
loop = Parallel(n_jobs=nprocs)
path = None
try:
if loop._effective_n_jobs() > 1:
fd, path = tempfile.mkstemp(prefix='lkpy-predict', suffix='.pkl')
path = pathlib.Path(path)
os.close(fd)
_logger.debug('pre-serializing algorithm %s to %s', algo, path)
dump(algo, path)
algo = _AlgoKey('file', path)
results = loop(
delayed(_predict_user)(algo, user, udf)
for (user, udf) in pairs.groupby('user'))
results = pd.concat(results, ignore_index=True)
finally:
util.delete_sometime(path)
if 'rating' in pairs:
return pairs.join(results.set_index(['user', 'item']),
on=('user', 'item'))
return results
def predict(algo, pairs, *, n_jobs=None, **kwargs):
"""
Generate predictions for user-item pairs. The provided algorithm should be a
:py:class:`algorithms.Predictor` or a function of two arguments: the user ID and
a list of item IDs. It should return a dictionary or a :py:class:`pandas.Series`
mapping item IDs to predictions.
To use this function, provide a pre-fit algorithm::
>>> from lenskit.algorithms.basic import Bias
>>> from lenskit.metrics.predict import rmse
>>> from lenskit import datasets
>>> ratings = datasets.MovieLens('ml-latest-small').ratings
>>> bias = Bias()
>>> bias.fit(ratings[:-1000])
<lenskit.algorithms.basic.Bias object at ...>
>>> preds = predict(bias, ratings[-1000:])
>>> preds.head()
user item rating timestamp prediction
99004 664 8361 3.0 1393891425 3.288286
99005 664 8528 3.5 1393891047 3.559119
99006 664 8529 4.0 1393891173 3.573008
99007 664 8636 4.0 1393891175 3.846268
99008 664 8641 4.5 1393890852 3.710635
>>> rmse(preds['prediction'], preds['rating'])
0.8326992222...
Args:
algo(lenskit.algorithms.Predictor):
A rating predictor function or algorithm.
pairs(pandas.DataFrame):
A data frame of (``user``, ``item``) pairs to predict for. If this frame also
contains a ``rating`` column, it will be included in the result.
n_jobs(int):
The number of processes to use for parallel batch prediction. Passed as
``n_jobs`` to :class:`joblib.Parallel`. The default, ``None``, will result
in a call to :func:`util.proc_count`(``None``), so the process will be
the process sequential _unless_ called inside the :func:`joblib.parallel_backend`
context manager or the ``LK_NUM_PROCS`` environment variable is set.
Returns:
pandas.DataFrame:
a frame with columns ``user``, ``item``, and ``prediction`` containing
the prediction results. If ``pairs`` contains a `rating` column, this
result will also contain a `rating` column.
"""
if n_jobs is None and 'nprocs' in kwargs:
n_jobs = kwargs['nprocs']
warnings.warn('nprocs is deprecated, use n_jobs', DeprecationWarning)
if n_jobs is None:
n_jobs = util.proc_count(None)
loop = Parallel(n_jobs=n_jobs)
path = None
try:
store = get_store(in_process=loop._effective_n_jobs() == 1)
_logger.info('using model store %s', store)
with store:
key = store.put_model(algo)
del algo
client = store.client()
nusers = pairs['user'].nunique()
_logger.info('generating %d predictions for %d users', len(pairs),
nusers)
results = loop(
delayed(_predict_user)(client, key, user, udf.copy())
for (user, udf) in pairs.groupby('user'))
results = pd.concat(results, ignore_index=True, copy=False)
finally:
util.delete_sometime(path)
if 'rating' in pairs:
return pairs.join(results.set_index(['user', 'item']),
on=('user', 'item'))
return results
def recommend(algo, users, n, candidates=None, *, n_jobs=None, **kwargs):
"""
Batch-recommend for multiple users. The provided algorithm should be a
:py:class:`algorithms.Recommender`.
Args:
algo: the algorithm
users(array-like): the users to recommend for
n(int): the number of recommendations to generate (None for unlimited)
candidates:
the users' candidate sets. This can be a function, in which case it will
be passed each user ID; it can also be a dictionary, in which case user
IDs will be looked up in it. Pass ``None`` to use the recommender's
built-in candidate selector (usually recommended).
n_jobs(int):
The number of processes to use for parallel recommendations. Passed as
``n_jobs`` to :cls:`joblib.Parallel`. The default, ``None``, will make
the process sequential _unless_ called inside the :func:`joblib.parallel_backend`
context manager.
.. note:: ``nprocs`` is accepted as a deprecated alias.
Returns:
A frame with at least the columns ``user``, ``rank``, and ``item``; possibly also
``score``, and any other columns returned by the recommender.
"""
if n_jobs is None and 'nprocs' in kwargs:
n_jobs = kwargs['nprocs']
warnings.warn('nprocs is deprecated, use n_jobs', DeprecationWarning)
rec_algo = Recommender.adapt(algo)
if candidates is None and rec_algo is not algo:
warnings.warn(
'no candidates provided and algo is not a recommender, unlikely to work'
)
del algo # don't need reference any more
if 'ratings' in kwargs:
warnings.warn('Providing ratings to recommend is not supported',
DeprecationWarning)
candidates = __standard_cand_fun(candidates)
loop = Parallel(n_jobs=n_jobs)
path = None
try:
_logger.debug('activating recommender loop')
with loop:
backend = loop._backend.__class__.__name__
njobs = loop._effective_n_jobs()
_logger.info('parallel backend %s, effective njobs %s', backend,
njobs)
astr = str(rec_algo)
if njobs > 1:
fd, path = tempfile.mkstemp(prefix='lkpy-predict',
suffix='.pkl',
dir=util.scratch_dir(joblib=True))
path = pathlib.Path(path)
os.close(fd)
_logger.debug('pre-serializing algorithm %s to %s', rec_algo,
path)
with sharing_mode():
dump(rec_algo, path)
rec_algo = _AlgoKey('file', path)
_logger.info('recommending with %s for %d users (n_jobs=%s)', astr,
len(users), n_jobs)
timer = util.Stopwatch()
results = loop(
delayed(_recommend_user)(rec_algo, user, n, candidates(user))
for user in users)
results = pd.concat(results, ignore_index=True, copy=False)
_logger.info('recommended for %d users in %s', len(users), timer)
finally:
util.delete_sometime(path)
return results
def recommend(algo, users, n, candidates=None, *, n_jobs=None, **kwargs):
"""
Batch-recommend for multiple users. The provided algorithm should be a
:py:class:`algorithms.Recommender`.
Args:
algo: the algorithm
users(array-like): the users to recommend for
n(int): the number of recommendations to generate (None for unlimited)
candidates:
the users' candidate sets. This can be a function, in which case it will
be passed each user ID; it can also be a dictionary, in which case user
IDs will be looked up in it. Pass ``None`` to use the recommender's
built-in candidate selector (usually recommended).
n_jobs(int):
The number of processes to use for parallel recommendations. Passed as
``n_jobs`` to :class:`joblib.Parallel`. The default, ``None``, will result
in a call to :func:`util.proc_count`(``None``), so the process will be
the process sequential _unless_ called inside the :func:`joblib.parallel_backend`
context manager or the ``LK_NUM_PROCS`` environment variable is set.
Returns:
A frame with at least the columns ``user``, ``rank``, and ``item``; possibly also
``score``, and any other columns returned by the recommender.
"""
if n_jobs is None and 'nprocs' in kwargs:
n_jobs = kwargs['nprocs']
warnings.warn('nprocs is deprecated, use n_jobs', DeprecationWarning)
if n_jobs is None:
n_jobs = util.proc_count(None)
rec_algo = Recommender.adapt(algo)
if candidates is None and rec_algo is not algo:
warnings.warn(
'no candidates provided and algo is not a recommender, unlikely to work'
)
del algo # don't need reference any more
if 'ratings' in kwargs:
warnings.warn('Providing ratings to recommend is not supported',
DeprecationWarning)
candidates = __standard_cand_fun(candidates)
loop = Parallel(n_jobs=n_jobs)
path = None
try:
_logger.debug('activating recommender loop')
with loop:
store = get_store(in_process=loop._effective_n_jobs() == 1)
_logger.info('using model store %s', store)
astr = str(rec_algo)
with store:
key = store.put_model(rec_algo)
del rec_algo
client = store.client()
_logger.info('recommending with %s for %d users (n_jobs=%s)',
astr, len(users), n_jobs)
timer = util.Stopwatch()
results = loop(
delayed(_recommend_user)(client, key, user, n,
candidates(user))
for user in users)
results = pd.concat(results, ignore_index=True, copy=False)
_logger.info('recommended for %d users in %s', len(users), timer)
finally:
util.delete_sometime(path)
return results
