def default_setting(self):
"""
A default setting for data loading when performing adversarial ltr
"""
unknown_as_zero = False
binary_rele = False # using the original values
train_presort, validation_presort, test_presort = True, True, True
train_rough_batch_size, validation_rough_batch_size, test_rough_batch_size = 1, 100, 100
scale_data, scaler_id, scaler_level = get_scaler_setting(
data_id=self.data_id)
# more data settings that are rarely changed
self.data_dict = dict(
data_id=self.data_id,
dir_data=self.dir_data,
min_docs=10,
min_rele=1,
unknown_as_zero=unknown_as_zero,
binary_rele=binary_rele,
train_presort=train_presort,
validation_presort=validation_presort,
test_presort=test_presort,
train_rough_batch_size=train_rough_batch_size,
validation_rough_batch_size=validation_rough_batch_size,
test_rough_batch_size=test_rough_batch_size,
scale_data=scale_data,
scaler_id=scaler_id,
scaler_level=scaler_level)
data_meta = get_data_meta(data_id=self.data_id) # add meta-information
if self.debug: data_meta['fold_num'] = 2
self.data_dict.update(data_meta)
return self.data_dict
def grid_search(self):
if self.use_json:
scaler_id = self.json_dict['scaler_id']
choice_min_docs = self.json_dict['min_docs']
choice_min_rele = self.json_dict['min_rele']
choice_binary_rele = self.json_dict['binary_rele']
choice_unknown_as_zero = self.json_dict['unknown_as_zero']
choice_tr_batch_size = self.json_dict[
'tr_batch_size'] # train_rough_batch_size
# hard-coding for rarely changed settings
base_data_dict = dict(data_id=self.data_id,
dir_data=self.json_dict["dir_data"],
train_presort=True,
test_presort=True,
validation_presort=True,
validation_rough_batch_size=100,
test_rough_batch_size=100)
else:
scaler_id = None
choice_min_docs = [10]
choice_min_rele = [1]
choice_binary_rele = [False]
choice_unknown_as_zero = [False]
choice_tr_batch_size = [100]
base_data_dict = dict(data_id=self.data_id,
dir_data=self.dir_data,
train_presort=True,
test_presort=True,
validation_presort=True,
validation_rough_batch_size=100,
test_rough_batch_size=100)
data_meta = get_data_meta(data_id=self.data_id) # add meta-information
if self.debug: data_meta['fold_num'] = 1
base_data_dict.update(data_meta)
scale_data, scaler_id, scaler_level = get_scaler_setting(
data_id=self.data_id, scaler_id=scaler_id)
for min_docs, min_rele, tr_batch_size in product(
choice_min_docs, choice_min_rele, choice_tr_batch_size):
threshold_dict = dict(min_docs=min_docs,
min_rele=min_rele,
train_rough_batch_size=tr_batch_size)
for binary_rele, unknown_as_zero in product(
choice_binary_rele, choice_unknown_as_zero):
custom_dict = dict(binary_rele=binary_rele,
unknown_as_zero=unknown_as_zero)
scale_dict = dict(scale_data=scale_data,
scaler_id=scaler_id,
scaler_level=scaler_level)
self.data_dict = dict()
self.data_dict.update(base_data_dict)
self.data_dict.update(threshold_dict)
self.data_dict.update(custom_dict)
self.data_dict.update(scale_dict)
yield self.data_dict
def grid_search(self):
"""
Iterator of settings for data loading when performing adversarial ltr
"""
if self.use_json:
scaler_id = self.json_dict['scaler_id']
choice_min_docs = self.json_dict['min_docs']
choice_min_rele = self.json_dict['min_rele']
choice_binary_rele = self.json_dict['binary_rele']
choice_unknown_as_zero = self.json_dict['unknown_as_zero']
base_data_dict = dict(data_id=self.data_id,
dir_data=self.json_dict["dir_data"],
train_presort=True,
test_presort=True,
validation_presort=True,
train_rough_batch_size=1,
validation_rough_batch_size=100,
test_rough_batch_size=100)
else:
scaler_id = None
choice_min_docs = [10]
choice_min_rele = [1]
choice_binary_rele = [False]
choice_unknown_as_zero = [False]
base_data_dict = dict(data_id=self.data_id,
dir_data=self.dir_data,
train_presort=True,
test_presort=True,
validation_presort=True,
train_rough_batch_size=1,
validation_rough_batch_size=100,
test_rough_batch_size=100)
data_meta = get_data_meta(data_id=self.data_id) # add meta-information
base_data_dict.update(data_meta)
scale_data, scaler_id, scaler_level = get_scaler_setting(
data_id=self.data_id, scaler_id=scaler_id)
for min_docs, min_rele in product(choice_min_docs, choice_min_rele):
threshold_dict = dict(min_docs=min_docs, min_rele=min_rele)
for binary_rele, unknown_as_zero in product(
choice_binary_rele, choice_unknown_as_zero):
custom_dict = dict(binary_rele=binary_rele,
unknown_as_zero=unknown_as_zero)
scale_dict = dict(scale_data=scale_data,
scaler_id=scaler_id,
scaler_level=scaler_level)
self.data_dict = dict()
self.data_dict.update(base_data_dict)
self.data_dict.update(threshold_dict)
self.data_dict.update(custom_dict)
self.data_dict.update(scale_dict)
yield self.data_dict
def grid_search(self):
if self.use_json:
scaler_id = self.json_dict['scaler_id']
choice_min_docs = self.json_dict['min_docs']
choice_min_rele = self.json_dict['min_rele']
choice_binary_rele = self.json_dict['binary_rele']
choice_unknown_as_zero = self.json_dict['unknown_as_zero']
choice_train_presort = self.json_dict['train_presort']
choice_train_batch_size = self.json_dict['train_batch_size']
# hard-coding for rarely changed settings
base_data_dict = dict(data_id=self.data_id, dir_data=self.json_dict["dir_data"], test_presort=True,
validation_presort=True, validation_batch_size=1, test_batch_size=1)
else:
scaler_id = None
choice_min_docs = [10]
choice_min_rele = [1]
choice_binary_rele = [False]
choice_unknown_as_zero = [False]
choice_train_presort = [True]
choice_train_batch_size = [1] # number of sample rankings per query
base_data_dict = dict(data_id=self.data_id, dir_data=self.dir_data, test_presort=True,
validation_presort=True, validation_batch_size=1, test_batch_size=1)
data_meta = get_data_meta(data_id=self.data_id) # add meta-information
base_data_dict.update(data_meta)
choice_scale_data, choice_scaler_id, choice_scaler_level = \
get_scaler_setting(data_id=self.data_id, grid_search=True, scaler_id=scaler_id)
for min_docs, min_rele, train_batch_size in product(choice_min_docs, choice_min_rele, choice_train_batch_size):
threshold_dict = dict(min_docs=min_docs, min_rele=min_rele, train_batch_size=train_batch_size)
for binary_rele, unknown_as_zero, train_presort in product(choice_binary_rele, choice_unknown_as_zero, choice_train_presort):
custom_dict = dict(binary_rele=binary_rele, unknown_as_zero=unknown_as_zero, train_presort=train_presort)
for scale_data, _scaler_id, scaler_level in product(choice_scale_data, choice_scaler_id, choice_scaler_level):
scale_dict = dict(scale_data=scale_data, scaler_id=_scaler_id, scaler_level=scaler_level)
self.data_dict = dict()
self.data_dict.update(base_data_dict)
self.data_dict.update(threshold_dict)
self.data_dict.update(custom_dict)
self.data_dict.update(scale_dict)
yield self.data_dict
def default_setting(self):
"""
A default setting for data loading
:return:
"""
scaler_id = None
unknown_as_zero = False # using original labels, e.g., w.r.t. semi-supervised dataset
binary_rele = False # using original labels
train_presort, validation_presort, test_presort = True, True, True
train_batch_size, validation_batch_size, test_batch_size = 1, 1, 1
scale_data, scaler_id, scaler_level = get_scaler_setting(data_id=self.data_id, scaler_id=scaler_id)
# more data settings that are rarely changed
self.data_dict = dict(data_id=self.data_id, dir_data=self.dir_data, min_docs=10, min_rele=1,
scale_data = scale_data, scaler_id = scaler_id, scaler_level = scaler_level,
train_presort=train_presort, validation_presort=validation_presort, test_presort=test_presort,
train_batch_size=train_batch_size, validation_batch_size=validation_batch_size,
test_batch_size=test_batch_size, unknown_as_zero=unknown_as_zero, binary_rele=binary_rele)
data_meta = get_data_meta(data_id=self.data_id) # add meta-information
self.data_dict.update(data_meta)
return self.data_dict
def default_setting(self):
"""
A default setting for data loading when running lambdaMART
"""
scaler_id = None
unknown_as_zero = True if self.data_id in MSLETOR_SEMI else False # since lambdaMART is a supervised method
binary_rele = False # using the original values
train_presort, validation_presort, test_presort = False, False, False
train_batch_size, validation_batch_size, test_batch_size = 1, 1, 1
scale_data, scaler_id, scaler_level = get_scaler_setting(data_id=self.data_id, scaler_id=scaler_id)
# more data settings that are rarely changed
self.data_dict = dict(data_id=self.data_id, dir_data=self.dir_data, min_docs=10, min_rele=1,
unknown_as_zero=unknown_as_zero, binary_rele=binary_rele, train_presort=train_presort,
validation_presort=validation_presort, test_presort=test_presort, train_batch_size=train_batch_size,
validation_batch_size=validation_batch_size, test_batch_size=test_batch_size,
scale_data=scale_data, scaler_id=scaler_id, scaler_level=scaler_level)
data_meta = get_data_meta(data_id=self.data_id) # add meta-information
self.data_dict.update(data_meta)
return self.data_dict
def default_setting(self):
"""
A default setting for data loading
:return:
"""
if self.use_json:
scaler_id = self.json_dict['scaler_id']
min_docs = self.json_dict['min_docs'][0]
min_rele = self.json_dict['min_rele'][0]
binary_rele = self.json_dict['binary_rele'][0]
unknown_as_zero = self.json_dict['unknown_as_zero'][0]
tr_batch_size = self.json_dict['tr_batch_size'][
0] # train_rough_batch_size
scale_data, scaler_id, scaler_level = get_scaler_setting(
data_id=self.data_id, scaler_id=scaler_id)
# hard-coding for rarely changed settings
self.data_dict = dict(data_id=self.data_id,
dir_data=self.json_dict["dir_data"],
train_presort=True,
test_presort=True,
validation_presort=True,
validation_rough_batch_size=100,
test_rough_batch_size=100,
min_docs=min_docs,
min_rele=min_rele,
train_rough_batch_size=tr_batch_size,
scale_data=scale_data,
scaler_id=scaler_id,
scaler_level=scaler_level,
unknown_as_zero=unknown_as_zero,
binary_rele=binary_rele)
else:
unknown_as_zero = False # using original labels, e.g., w.r.t. semi-supervised dataset
binary_rele = False # using original labels
train_presort, validation_presort, test_presort = True, True, True
#train_rough_batch_size, validation_rough_batch_size, test_rough_batch_size = 1, 100, 100
train_rough_batch_size, validation_rough_batch_size, test_rough_batch_size = 100, 100, 100
scale_data, scaler_id, scaler_level = get_scaler_setting(
data_id=self.data_id)
# more data settings that are rarely changed
self.data_dict = dict(
data_id=self.data_id,
dir_data=self.dir_data,
min_docs=10,
min_rele=1,
scale_data=scale_data,
scaler_id=scaler_id,
scaler_level=scaler_level,
train_presort=train_presort,
validation_presort=validation_presort,
test_presort=test_presort,
train_rough_batch_size=train_rough_batch_size,
validation_rough_batch_size=validation_rough_batch_size,
test_rough_batch_size=test_rough_batch_size,
unknown_as_zero=unknown_as_zero,
binary_rele=binary_rele)
data_meta = get_data_meta(data_id=self.data_id) # add meta-information
if self.debug: data_meta['fold_num'] = 2
self.data_dict.update(data_meta)
return self.data_dict