def load_data(preparer):
dl = DataLoader()
data, target, weights = list(), list(), list()
sequences = dl.loadDirectory('data/sequences/model_train_seq/simulated')
# sequences = dl.loadDirectory('data/sequences/train_sequences')
for _, s_x, a_x, s_y, a_y in sequences:
d, t, _ = preparer.prepare_training_data(s_x, a_x, s_y, a_y)
data += d
target += t
return data, target
def load_data(preparer):
dl = DataLoader()
data, target, weights = list(), list(), list()
sequences = dl.loadDirectory('data/sequences/model_train_seq/simulated')
# sequences = dl.loadDirectory('data/sequences/train_sequences')
for _, s_x, a_x, s_y, a_y in sequences:
d, t, _ = preparer.prepare_training_data(
s_x, a_x, s_y, a_y
)
data += d
target += t
return data, target
def __init__(
self,
preparer,
filename="data/clf/randomforest.clf",
training_data_dir="data/sequences/train_sequences",
params=None,
autotrain=True,
memoization=False,
inverted=False,
use_global_classifier=False,
):
global _global_classifier
"""
@rtype : PairClassifier
"""
self._preparer = None
self.preparer = preparer
self.default_filename = filename
self.training_data_dir = training_data_dir
if params is None:
self.params = config.classifiers[config.classifier_index][2]
else:
self.params = params
self.mem = dict()
self.memoization = memoization
self.inverted = inverted
if _global_classifier is None or not use_global_classifier:
if autotrain and path.exists(self.default_filename):
if path.isfile(self.default_filename):
self.load(self.default_filename)
else:
self.classifier = self._get_classifier()
if autotrain:
sys.stderr.write('Training clasifier\n')
dl = DataLoader()
data, target, weights = list(), list(), list()
sequences = dl.loadDirectory(self.training_data_dir)
for _, s_x, a_x, s_y, a_y in sequences:
d, t, w = self.preparer.prepare_training_data(
s_x, a_x, s_y, a_y
)
data += d
target += t
weights += w
self.fit(data, target, array(weights))
self.save(self.default_filename)
if use_global_classifier:
_global_classifier = self.classifier
else:
self.classifier = _global_classifier
def __init__(
self,
preparer,
filename="data/clf/randomforest.clf",
training_data_dir="data/sequences/train_sequences",
params=None,
autotrain=True,
memoization=False,
inverted=False,
use_global_classifier=False,
):
global _global_classifier
"""
@rtype : PairClassifier
"""
self._preparer = None
self.preparer = preparer
self.default_filename = filename
self.training_data_dir = training_data_dir
if params is None:
self.params = config.classifiers[config.classifier_index][2]
else:
self.params = params
self.mem = dict()
self.memoization = memoization
self.inverted = inverted
if _global_classifier is None or not use_global_classifier:
if autotrain and path.exists(self.default_filename):
if path.isfile(self.default_filename):
self.load(self.default_filename)
else:
self.classifier = self._get_classifier()
if autotrain:
sys.stderr.write('Training clasifier\n')
dl = DataLoader()
data, target, weights = list(), list(), list()
sequences = dl.loadDirectory(self.training_data_dir)
for _, s_x, a_x, s_y, a_y in sequences:
d, t, w = self.preparer.prepare_training_data(
s_x, a_x, s_y, a_y)
data += d
target += t
weights += w
self.fit(data, target, array(weights))
self.save(self.default_filename)
if use_global_classifier:
_global_classifier = self.classifier
else:
self.classifier = _global_classifier
def train(self, dirname):
dl = DataLoader()
sequences = dl.loadDirectory(dirname)
return self.train_multi(sequences)
