def load_test_data(score_domain=(1.0, 5.0, 0.5)):
from kamrecsys.data import EventWithScoreData
from kamrecsys.datasets import SAMPLE_PATH
infile = os.path.join(SAMPLE_PATH, 'pci.event')
dtype = np.dtype([('event', 'U18', 2), ('score', float)])
x = np.genfromtxt(fname=infile, delimiter='\t', dtype=dtype)
data = EventWithScoreData(n_otypes=2, event_otypes=np.array([0, 1]))
data.set_event(x['event'], x['score'], score_domain=score_domain)
return data, x
def load_test_data(score_domain=(1.0, 5.0, 0.5)):
from kamrecsys.data import EventWithScoreData
from kamrecsys.datasets import SAMPLE_PATH
infile = os.path.join(SAMPLE_PATH, 'pci.event')
dtype = np.dtype([('event', 'U18', 2), ('score', float)])
x = np.genfromtxt(fname=infile, delimiter='\t', dtype=dtype)
data = EventWithScoreData(n_otypes=2, event_otypes=np.array([0, 1]))
data.set_event(x['event'], x['score'], score_domain=score_domain)
return data, x
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_opt_outputs' not in opt:
opt.learning_opt_outputs = [None] * 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
rcmdr = EventScorePredictor(C=opt.C,
k=opt.k,
tol=opt.tol,
maxiter=opt.maxiter,
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_opt_outputs[fold] = rcmdr.opt_outputs_
return rcmdr
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_opt_outputs' not in opt:
opt.learning_opt_outputs = [None] * 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
rcmdr = EventScorePredictor(
C=opt.C, k=opt.k, tol=opt.tol, maxiter=opt.maxiter,
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_opt_outputs[fold] = rcmdr.opt_outputs_
return rcmdr
