def test_class(self):
import numpy as np
from kamrecsys.datasets import load_movielens_mini
from kamrecsys.tm.plsa_multi import EventScorePredictor
data = load_movielens_mini()
rcmdr = EventScorePredictor(tol=1e-8, k=2, random_state=1234)
self.assertDictEqual(
vars(rcmdr), {
'k': 2,
'tol': 1e-8,
'maxiter': 100,
'alpha': 1.0,
'random_state': 1234,
'_rng': None,
'iid': None,
'eid': None,
'n_objects': None,
'n_otypes': 0,
'n_score_levels_': 0,
'i_loss_': np.inf,
'f_loss_': np.inf,
'n_iter_': 0,
'pZ_': None,
'pYgZ_': None,
'pRgZ_': None,
'pXgZ_': None,
'n_events_': 0,
'n_users_': 0,
'n_items_': 0,
'_q': None,
'score_levels_': None,
'use_expectation': True
})
# import logging
# logging.getLogger('kamrecsys').addHandler(logging.StreamHandler())
rcmdr.fit(data)
self.assertAlmostEqual(rcmdr.i_loss_, 5.41836900049, delta=1e-5)
self.assertAlmostEqual(rcmdr.f_loss_, 5.17361298499, delta=1e-5)
assert_allclose(rcmdr.score_levels_, [1, 2, 3, 4, 5], rtol=1e-5)
# known user and item
self.assertAlmostEqual(rcmdr.predict((1, 7)),
3.64580117249,
delta=1e-5)
self.assertAlmostEqual(rcmdr.predict((1, 9)), 3.6587422493, delta=1e-5)
self.assertAlmostEqual(rcmdr.predict((5, 7)),
3.60707987724,
delta=1e-5)
self.assertAlmostEqual(rcmdr.predict((5, 9)),
3.62184516985,
delta=1e-5)
# known user and unknown item
self.assertAlmostEqual(rcmdr.predict((1, 11)),
3.66032199689,
delta=1e-5)
self.assertAlmostEqual(rcmdr.predict((5, 12)),
3.62387542269,
delta=1e-5)
# unknown user and known item
self.assertAlmostEqual(rcmdr.predict((3, 7)),
3.60821491793,
delta=1e-5)
self.assertAlmostEqual(rcmdr.predict((11, 9)),
3.62304301551,
delta=1e-5)
# unknown user and item
self.assertAlmostEqual(rcmdr.predict((3, 11)),
3.62507437787,
delta=1e-5)
x = np.array([[1, 7], [1, 9], [1, 11], [3, 7], [3, 9], [3, 11], [5, 7],
[5, 9], [5, 11]])
assert_allclose(rcmdr.predict(x), [
3.64580117249, 3.6587422493, 3.66032199689, 3.60821491793,
3.62304301551, 3.62507437787, 3.60707987724, 3.62184516985,
3.62387542269
],
rtol=1e-5)
rcmdr.use_expectation = False
assert_allclose(rcmdr.predict(x), [4., 5., 5., 4., 4., 4., 4., 4., 4.],
rtol=1e-5)
def training(opt, ev, tsc, event_feature=None, fold=0):
"""
training model
Parameters
----------
opt : dict
parsed command line options
ev : array, size=(n_events, 2), dtype=np.int
array of events in external ids
tsc : array, size=(n_events,), dtype=np.float
true scores
event_feature : optional, structured array
structured array of event features
fold : int, default=0
fold No.
Returns
-------
rcmdr : EventScorePredictor
trained recommender
"""
# generate event data
data = EventWithScoreData(n_otypes=2, n_stypes=1)
if np.all(opt.domain == [0, 0, 0]):
score_domain = (
np.min(tsc), np.max(tsc), np.min(np.diff(np.unique(tsc))))
else:
score_domain = tuple(opt.domain)
logger.info("score_domain = " + str(score_domain))
data.set_events(ev, tsc, score_domain=score_domain,
event_feature=event_feature)
# init learning results
if 'training_start_time' not in opt:
opt.training_start_time = [0] * opt.fold
if 'training_end_time' not in opt:
opt.training_end_time = [0] * opt.fold
if 'learning_i_loss' not in opt:
opt.learning_i_loss = [np.inf] * opt.fold
if 'learning_f_loss' not in opt:
opt.learning_f_loss = [np.inf] * opt.fold
if 'learning_n_iter' not in opt:
opt.learning_n_iter = [0] * opt.fold
# set starting time
start_time = datetime.datetime.now()
start_utime = os.times()[0]
opt.training_start_time[fold] = start_time.isoformat()
logger.info("training_start_time = " + start_time.isoformat())
# create and learning model
if opt.method == 'plsam':
rcmdr = EventScorePredictor(
alpha=opt.alpha, k=opt.k, tol=opt.tol, maxiter=opt.maxiter,
use_expectation=True, random_state=opt.rseed)
else:
rcmdr = EventScorePredictor(
alpha=opt.alpha, k=opt.k, tol=opt.tol, maxiter=opt.maxiter,
use_expectation=False, random_state=opt.rseed)
rcmdr.fit(data)
# set end and elapsed time
end_time = datetime.datetime.now()
end_utime = os.times()[0]
elapsed_time = end_time - start_time
elapsed_utime = end_utime - start_utime
opt.training_end_time[fold] = end_time.isoformat()
logger.info("training_end_time = " + end_time.isoformat())
if 'training_elapsed_time' not in opt:
opt.training_elapsed_time = elapsed_time
else:
opt.training_elapsed_time += elapsed_time
logger.info("training_elapsed_time = " + str(opt.training_elapsed_time))
if 'training_elapsed_utime' not in opt:
opt.training_elapsed_utime = elapsed_utime
else:
opt.training_elapsed_utime += elapsed_utime
logger.info("training_elapsed_utime = " + str(opt.training_elapsed_utime))
# preserve optimizer's outputs
opt.learning_i_loss[fold] = rcmdr.i_loss_
opt.learning_f_loss[fold] = rcmdr.f_loss_
opt.learning_n_iter[fold] = rcmdr.n_iter_
return rcmdr
def test_class(self):
import numpy as np
from kamrecsys.datasets import load_movielens_mini
from kamrecsys.tm.plsa_multi import EventScorePredictor
data = load_movielens_mini()
rcmdr = EventScorePredictor(tol=1e-8, k=2, random_state=1234)
self.assertDictEqual(
vars(rcmdr),
{
"k": 2,
"tol": 1e-8,
"maxiter": 100,
"alpha": 1.0,
"random_state": 1234,
"_rng": None,
"iid": None,
"eid": None,
"n_objects": None,
"n_otypes": 0,
"n_score_levels_": 0,
"i_loss_": np.inf,
"f_loss_": np.inf,
"n_iter_": 0,
"pZ_": None,
"pYgZ_": None,
"pRgZ_": None,
"pXgZ_": None,
"n_events_": 0,
"n_users_": 0,
"n_items_": 0,
"_q": None,
"score_levels_": None,
"use_expectation": True,
},
)
# import logging
# logging.getLogger('kamrecsys').addHandler(logging.StreamHandler())
rcmdr.fit(data)
self.assertAlmostEqual(rcmdr.i_loss_, 5.41836900049, delta=1e-5)
self.assertAlmostEqual(rcmdr.f_loss_, 5.17361298499, delta=1e-5)
assert_allclose(rcmdr.score_levels_, [1, 2, 3, 4, 5], rtol=1e-5)
# known user and item
self.assertAlmostEqual(rcmdr.predict((1, 7)), 3.64580117249, delta=1e-5)
self.assertAlmostEqual(rcmdr.predict((1, 9)), 3.6587422493, delta=1e-5)
self.assertAlmostEqual(rcmdr.predict((5, 7)), 3.60707987724, delta=1e-5)
self.assertAlmostEqual(rcmdr.predict((5, 9)), 3.62184516985, delta=1e-5)
# known user and unknown item
self.assertAlmostEqual(rcmdr.predict((1, 11)), 3.66032199689, delta=1e-5)
self.assertAlmostEqual(rcmdr.predict((5, 12)), 3.62387542269, delta=1e-5)
# unknown user and known item
self.assertAlmostEqual(rcmdr.predict((3, 7)), 3.60821491793, delta=1e-5)
self.assertAlmostEqual(rcmdr.predict((11, 9)), 3.62304301551, delta=1e-5)
# unknown user and item
self.assertAlmostEqual(rcmdr.predict((3, 11)), 3.62507437787, delta=1e-5)
x = np.array([[1, 7], [1, 9], [1, 11], [3, 7], [3, 9], [3, 11], [5, 7], [5, 9], [5, 11]])
assert_allclose(
rcmdr.predict(x),
[
3.64580117249,
3.6587422493,
3.66032199689,
3.60821491793,
3.62304301551,
3.62507437787,
3.60707987724,
3.62184516985,
3.62387542269,
],
rtol=1e-5,
)
rcmdr.use_expectation = False
assert_allclose(rcmdr.predict(x), [4.0, 5.0, 5.0, 4.0, 4.0, 4.0, 4.0, 4.0, 4.0], rtol=1e-5)
def training(opt, ev, tsc, event_feature=None, fold=0):
"""
training model
Parameters
----------
opt : dict
parsed command line options
ev : array, size=(n_events, 2), dtype=np.int
array of events in external ids
tsc : array, size=(n_events,), dtype=np.float
true scores
event_feature : optional, structured array
structured array of event features
fold : int, default=0
fold No.
Returns
-------
rcmdr : EventScorePredictor
trained recommender
"""
# generate event data
data = EventWithScoreData(n_otypes=2, n_stypes=1)
if np.all(opt.domain == [0, 0, 0]):
score_domain = (np.min(tsc), np.max(tsc),
np.min(np.diff(np.unique(tsc))))
else:
score_domain = tuple(opt.domain)
logger.info("score_domain = " + str(score_domain))
data.set_events(ev,
tsc,
score_domain=score_domain,
event_feature=event_feature)
# init learning results
if 'training_start_time' not in opt:
opt.training_start_time = [0] * opt.fold
if 'training_end_time' not in opt:
opt.training_end_time = [0] * opt.fold
if 'learning_i_loss' not in opt:
opt.learning_i_loss = [np.inf] * opt.fold
if 'learning_f_loss' not in opt:
opt.learning_f_loss = [np.inf] * opt.fold
if 'learning_n_iter' not in opt:
opt.learning_n_iter = [0] * opt.fold
# set starting time
start_time = datetime.datetime.now()
start_utime = os.times()[0]
opt.training_start_time[fold] = start_time.isoformat()
logger.info("training_start_time = " + start_time.isoformat())
# create and learning model
if opt.method == 'plsam':
rcmdr = EventScorePredictor(alpha=opt.alpha,
k=opt.k,
tol=opt.tol,
maxiter=opt.maxiter,
use_expectation=True,
random_state=opt.rseed)
else:
rcmdr = EventScorePredictor(alpha=opt.alpha,
k=opt.k,
tol=opt.tol,
maxiter=opt.maxiter,
use_expectation=False,
random_state=opt.rseed)
rcmdr.fit(data)
# set end and elapsed time
end_time = datetime.datetime.now()
end_utime = os.times()[0]
elapsed_time = end_time - start_time
elapsed_utime = end_utime - start_utime
opt.training_end_time[fold] = end_time.isoformat()
logger.info("training_end_time = " + end_time.isoformat())
if 'training_elapsed_time' not in opt:
opt.training_elapsed_time = elapsed_time
else:
opt.training_elapsed_time += elapsed_time
logger.info("training_elapsed_time = " + str(opt.training_elapsed_time))
if 'training_elapsed_utime' not in opt:
opt.training_elapsed_utime = elapsed_utime
else:
opt.training_elapsed_utime += elapsed_utime
logger.info("training_elapsed_utime = " + str(opt.training_elapsed_utime))
# preserve optimizer's outputs
opt.learning_i_loss[fold] = rcmdr.i_loss_
opt.learning_f_loss[fold] = rcmdr.f_loss_
opt.learning_n_iter[fold] = rcmdr.n_iter_
return rcmdr