def __init__(self, a=2.155, alpha=0.94, b=0.789, beta=1.0):
super(DoubleBalance, self).__init__()
self.a = a
self.alpha = alpha
self.b = b
self.beta = beta
self.fallback_model = SimpleBalance()
def __init__(self,
a=2.155,
alpha=0.94,
b=0.789,
beta=1.0,
random_state=None):
super(DoubleBalance, self).__init__()
self.a = a
self.alpha = alpha
self.b = b
self.beta = beta
self.fallback_model = SimpleBalance()
self._random_state = get_random_state(random_state)
def __init__(
self,
X,
y=None,
model=None,
query_model=None,
balance_model=None,
feature_model=None,
n_papers=None,
n_instances=DEFAULT_N_INSTANCES,
n_queries=None,
prior_included=[],
prior_excluded=[],
log_file=None,
final_labels=None,
verbose=1,
data_fp=None,
):
""" Initialize base class for systematic reviews.
Arguments
---------
X: np.array
The feature matrix for the current dataset.
y: np.array
Labels of each paper, 1 for included, 0 for excluded.
Can be set to None, to indicate inclusion data is not available.
model: BaseModel
Initialized model to fit the data during active learning.
See asreview.models.utils.py for possible models.
query_model: BaseQueryModel
Initialized model to query new instances for review, such as random
sampling or max sampling.
See asreview.query_strategies.utils.py for query models.
balance_model: BaseBalanceModel
Initialized model to redistribute the training data during the
active learning process. They might either resample or undersample
specific papers.
n_papers: int
Number of papers to review during the active learning process,
excluding the number of initial priors. To review all papers, set
n_papers to None.
n_instances: int
Number of papers to query at each step in the active learning
process.
n_queries: int
Number of steps/queries to perform. Set to None for no limit.
prior_included: list
List of papers (ids) that are included a priori.
prior_excluded: list
List of papers (ids) that are excluded a priori.
log_file: str
Path to log file.
final_labels: np.array
Final labels if we're using a two step inclusion process.
For example, if at one step a paper is considered after reading the
abstract and then at the second step, a final decision is made on
the basis of the full text.
"""
super(BaseReview, self).__init__()
self.X = X
self.y = y
if y is None:
self.y = np.full(X.shape[0], NOT_AVAILABLE)
self.y = np.array(self.y, dtype=np.int)
# Default to Naive Bayes model
if model is None:
model = NBModel()
if query_model is None:
query_model = MaxQuery()
if balance_model is None:
balance_model = SimpleBalance()
if feature_model is None:
raise ValueError("Supply feature model!")
self.model = model
self.balance_model = balance_model
self.query_model = query_model
self.feature_model = feature_model
self.shared = {"query_src": {}, "current_queries": {}}
self.model.shared = self.shared
self.query_model.shared = self.shared
self.balance_model.shared = self.shared
self.n_papers = n_papers
self.n_instances = n_instances
self.n_queries = n_queries
self.log_file = log_file
self.verbose = verbose
self.prior_included = prior_included
self.prior_excluded = prior_excluded
self.query_i = 0
self.train_idx = np.array([], dtype=np.int)
self.model_trained = False
self.data_fp = data_fp
with open_logger(log_file) as logger:
if not logger.is_empty():
y, train_idx, query_src, query_i = logger.review_state()
if X.shape[0] != len(y):
raise ValueError("The log file does not correspond to the "
"given data file, please use another log "
"file or dataset.")
self.y = y
self.train_idx = train_idx
self.shared["query_src"] = query_src
self.query_i = query_i
else:
if final_labels is not None:
logger.set_final_labels(final_labels)
logger.set_labels(self.y)
logger.add_settings(self.settings)
self._prior_knowledge(logger)
self.query_i = 0
def __init__(
self,
as_data,
model=None,
query_model=None,
balance_model=None,
feature_model=None,
n_papers=None,
n_instances=DEFAULT_N_INSTANCES,
n_queries=None,
start_idx=[],
state_file=None,
log_file=None,
):
"""Initialize base class for systematic reviews."""
super(BaseReview, self).__init__()
# Default to Naive Bayes model
if model is None:
model = NBModel()
if query_model is None:
query_model = MaxQuery()
if balance_model is None:
balance_model = SimpleBalance()
if feature_model is None:
feature_model = Tfidf()
self.as_data = as_data
self.y = as_data.labels
if self.y is None:
self.y = np.full(len(as_data), LABEL_NA)
self.model = model
self.balance_model = balance_model
self.query_model = query_model
self.feature_model = feature_model
self.shared = {"query_src": {}, "current_queries": {}}
self.model.shared = self.shared
self.query_model.shared = self.shared
self.balance_model.shared = self.shared
self.n_papers = n_papers
self.n_instances = n_instances
self.n_queries = n_queries
self.start_idx = start_idx
if log_file is not None:
warnings.warn(
"The log_file argument for BaseReview will be"
" replaced by state_file.",
category=FutureWarning)
self.state_file = log_file
else:
self.state_file = state_file
self.query_i = 0
self.query_i_classified = 0
self.train_idx = np.array([], dtype=np.int)
self.model_trained = False
# Restore the state from a file or initialize said file.
with open_state(self.state_file) as state:
# From file
if not state.is_empty():
startup = state.startup_vals()
# If there are start indices not in the training add them.
if not set(startup["train_idx"]) >= set(start_idx):
new_idx = list(set(start_idx) - set(startup["train_idx"]))
self.classify(new_idx,
self.y[new_idx],
state,
method="initial")
startup = state.startup_vals()
self.train_idx = startup["train_idx"]
self.y = startup["labels"]
self.shared["query_src"] = startup["query_src"]
self.query_i = startup["query_i"]
self.query_i_classified = startup["query_i_classified"]
# From scratch
else:
state.set_labels(self.y)
state.settings = self.settings
self.classify(start_idx,
self.y[start_idx],
state,
method="initial")
self.query_i_classified = len(start_idx)
# Try to retrieve feature matrix from the state file.
try:
self.X = state.get_feature_matrix(as_data.hash())
except KeyError:
self.X = feature_model.fit_transform(as_data.texts,
as_data.headings,
as_data.bodies,
as_data.keywords)
state._add_as_data(as_data, feature_matrix=self.X)
if self.X.shape[0] != len(self.y):
raise ValueError("The state file does not correspond to the "
"given data file, please use another state "
"file or dataset.")
self.load_current_query(state)
class DoubleBalance(BaseBalance):
"""Class for the double balance strategy.
Class to get the two way rebalancing function and arguments.
It super samples ones depending on the number of 0's and total number
of samples in the training data.
Arguments
---------
a: float
Governs the weight of the 1's. Higher values mean linearly more 1's
in your training sample.
alpha: float
Governs the scaling the weight of the 1's, as a function of the
ratio of ones to zeros. A positive value means that the lower the
ratio of zeros to ones, the higher the weight of the ones.
b: float
Governs how strongly we want to sample depending on the total
number of samples. A value of 1 means no dependence on the total
number of samples, while lower values mean increasingly stronger
dependence on the number of samples.
beta: float
Governs the scaling of the weight of the zeros depending on the
number of samples. Higher values means that larger samples are more
strongly penalizing zeros.
"""
name = "double"
def __init__(self, a=2.155, alpha=0.94, b=0.789, beta=1.0):
super(DoubleBalance, self).__init__()
self.a = a
self.alpha = alpha
self.b = b
self.beta = beta
self.fallback_model = SimpleBalance()
def sample(self, X, y, train_idx, shared):
one_idx = train_idx[np.where(y[train_idx] == 1)]
zero_idx = train_idx[np.where(y[train_idx] == 0)]
# Fall back to simple sampling if we have only ones or zeros.
if len(one_idx) == 0 or len(zero_idx) == 0:
self.fallback_model.sample(X, y, train_idx, shared)
n_one = len(one_idx)
n_zero = len(zero_idx)
n_train = n_one + n_zero
# Compute the weights.
one_weight = _one_weight(n_one, n_zero, self.a, self.alpha)
zero_weight = _zero_weight(n_one + n_zero, self.b, self.beta)
tot_zo_weight = one_weight * n_one + zero_weight * n_zero
n_one_train = random_round(
one_weight * n_one * n_train / tot_zo_weight)
n_one_train = max(1, min(n_train - 2, n_one_train))
n_zero_train = n_train - n_one_train
# Get random ones and zeros.
one_train_idx = fill_training(one_idx, n_one_train)
zero_train_idx = fill_training(zero_idx, n_zero_train)
all_idx = np.concatenate([one_train_idx, zero_train_idx])
np.random.shuffle(all_idx)
return X[all_idx], y[all_idx]
def full_hyper_space(self):
from hyperopt import hp
parameter_space = {
"bal_a": hp.lognormal("bal_a", 0, 1),
"bal_alpha": hp.uniform("bal_alpha", 0, 2),
"bal_b": hp.uniform("bal_b", 0, 1),
# "bal_beta": hp.uniform("bal_beta", 0, 2),
}
return parameter_space, {}
def __init__(
self,
as_data,
model=None,
query_model=None,
balance_model=None,
feature_model=None,
n_papers=None,
n_instances=DEFAULT_N_INSTANCES,
n_queries=None,
start_idx=[],
state_file=None,
log_file=None,
# final_labels=None,
verbose=1,
data_fp=None,
):
""" Initialize base class for systematic reviews.
Arguments
---------
X: np.array
The feature matrix for the current dataset.
y: np.array
Labels of each paper, 1 for included, 0 for excluded.
Can be set to None, to indicate inclusion data is not available.
model: BaseModel
Initialized model to fit the data during active learning.
See asreview.models.utils.py for possible models.
query_model: BaseQueryModel
Initialized model to query new instances for review, such as random
sampling or max sampling.
See asreview.query_strategies.utils.py for query models.
balance_model: BaseBalanceModel
Initialized model to redistribute the training data during the
active learning process. They might either resample or undersample
specific papers.
n_papers: int
Number of papers to review during the active learning process,
excluding the number of initial priors. To review all papers, set
n_papers to None.
n_instances: int
Number of papers to query at each step in the active learning
process.
n_queries: int
Number of steps/queries to perform. Set to None for no limit.
prior_included: list
List of papers (ids) that are included a priori.
prior_excluded: list
List of papers (ids) that are excluded a priori.
state_file: str
Path to state file. Replaces log_file argument.
final_labels: np.array
Final labels if we're using a two step inclusion process.
For example, if at one step a paper is considered after reading the
abstract and then at the second step, a final decision is made on
the basis of the full text.
"""
super(BaseReview, self).__init__()
# Default to Naive Bayes model
if model is None:
model = NBModel()
if query_model is None:
query_model = MaxQuery()
if balance_model is None:
balance_model = SimpleBalance()
if feature_model is None:
feature_model = Tfidf()
self.as_data = as_data
self.y = as_data.labels
if self.y is None:
self.y = np.full(len(as_data), LABEL_NA)
self.model = model
self.balance_model = balance_model
self.query_model = query_model
self.feature_model = feature_model
self.shared = {"query_src": {}, "current_queries": {}}
self.model.shared = self.shared
self.query_model.shared = self.shared
self.balance_model.shared = self.shared
self.n_papers = n_papers
self.n_instances = n_instances
self.n_queries = n_queries
self.start_idx = start_idx
if log_file is not None:
warnings.warn(
"The log_file argument for BaseReview will be"
" replaced by state_file.",
category=FutureWarning)
self.state_file = log_file
else:
self.state_file = state_file
self.verbose = verbose
self.query_i = 0
self.query_i_classified = 0
self.train_idx = np.array([], dtype=np.int)
self.model_trained = False
self.data_fp = data_fp
with open_state(self.state_file) as state:
if not state.is_empty():
startup = state.startup_vals()
if not set(startup["train_idx"]) >= set(start_idx):
new_idx = list(set(start_idx) - set(startup["train_idx"]))
self.classify(new_idx,
self.y[new_idx],
state,
method="initial")
startup = state.startup_vals()
self.train_idx = startup["train_idx"]
self.y = startup["labels"]
self.shared["query_src"] = startup["query_src"]
self.query_i = startup["query_i"]
self.query_i_classified = startup["query_i_classified"]
else:
state.set_labels(self.y)
state.settings = self.settings
self.classify(start_idx,
self.y[start_idx],
state,
method="initial")
self.query_i_classified = len(start_idx)
try:
self.X = state.get_feature_matrix(as_data.hash())
except KeyError:
self.X = feature_model.fit_transform(as_data.texts,
as_data.headings,
as_data.bodies,
as_data.keywords)
state._add_as_data(as_data, feature_matrix=self.X)
if self.X.shape[0] != len(self.y):
raise ValueError("The state file does not correspond to the "
"given data file, please use another state "
"file or dataset.")
self.load_current_query(state)
class DoubleBalance(BaseBalance):
"""Dynamic Resampling balance strategy.
Class to get the two way rebalancing function and arguments.
It super samples ones depending on the number of 0's and total number
of samples in the training data.
Arguments
---------
a: float
Governs the weight of the 1's. Higher values mean linearly more 1's
in your training sample.
alpha: float
Governs the scaling the weight of the 1's, as a function of the
ratio of ones to zeros. A positive value means that the lower the
ratio of zeros to ones, the higher the weight of the ones.
b: float
Governs how strongly we want to sample depending on the total
number of samples. A value of 1 means no dependence on the total
number of samples, while lower values mean increasingly stronger
dependence on the number of samples.
beta: float
Governs the scaling of the weight of the zeros depending on the
number of samples. Higher values means that larger samples are more
strongly penalizing zeros.
"""
name = "double"
def __init__(self,
a=2.155,
alpha=0.94,
b=0.789,
beta=1.0,
random_state=None):
super(DoubleBalance, self).__init__()
self.a = a
self.alpha = alpha
self.b = b
self.beta = beta
self.fallback_model = SimpleBalance()
self._random_state = get_random_state(random_state)
def sample(self, X, y, train_idx, shared):
"""Resample the training data.
Arguments
---------
X: np.array
Complete feature matrix.
y: np.array
Labels for all papers.
train_idx: np.array
Training indices, that is all papers that have been reviewed.
shared: dict
Dictionary to share data between balancing models and other models.
Returns
-------
np.array, np.array:
X_train, y_train: the resampled matrix, labels.
"""
# Get inclusions and exclusions
one_idx = train_idx[np.where(y[train_idx] == 1)]
zero_idx = train_idx[np.where(y[train_idx] == 0)]
# Fall back to simple sampling if we have only ones or zeroes.
if len(one_idx) == 0 or len(zero_idx) == 0:
self.fallback_model.sample(X, y, train_idx, shared)
n_one = len(one_idx)
n_zero = len(zero_idx)
n_train = n_one + n_zero
# Compute sampling weights.
one_weight = _one_weight(n_one, n_zero, self.a, self.alpha)
zero_weight = _zero_weight(n_one + n_zero, self.b, self.beta)
tot_zo_weight = one_weight * n_one + zero_weight * n_zero
# Number of inclusions to sample.
n_one_train = random_round(
one_weight * n_one * n_train / tot_zo_weight, self._random_state)
# Should be at least 1, and at least two spots should be for exclusions.
n_one_train = max(1, min(n_train - 2, n_one_train))
# Number of exclusions to sample
n_zero_train = n_train - n_one_train
# Sample records of ones and zeroes
one_train_idx = fill_training(one_idx, n_one_train, self._random_state)
zero_train_idx = fill_training(zero_idx, n_zero_train,
self._random_state)
# Merge and shuffle.
all_idx = np.concatenate([one_train_idx, zero_train_idx])
self._random_state.shuffle(all_idx)
# Return resampled feature matrix and labels.
return X[all_idx], y[all_idx]
def full_hyper_space(self):
from hyperopt import hp
parameter_space = {
"bal_a": hp.lognormal("bal_a", 0, 1),
"bal_alpha": hp.uniform("bal_alpha", 0, 2),
"bal_b": hp.uniform("bal_b", 0, 1),
# "bal_beta": hp.uniform("bal_beta", 0, 2),
}
return parameter_space, {}
def __init__(
self,
as_data,
model=None,
query_model=None,
balance_model=None,
feature_model=None,
n_papers=None,
n_instances=DEFAULT_N_INSTANCES,
n_queries=None,
start_idx=[],
state_file=None,
log_file=None,
):
""" Initialize base class for systematic reviews.
Arguments
---------
as_data: asreview.ASReviewData
The data object which contains the text, labels, etc.
model: BaseModel
Initialized model to fit the data during active learning.
See asreview.models.utils.py for possible models.
query_model: BaseQueryModel
Initialized model to query new instances for review, such as random
sampling or max sampling.
See asreview.query_strategies.utils.py for query models.
balance_model: BaseBalanceModel
Initialized model to redistribute the training data during the
active learning process. They might either resample or undersample
specific papers.
feature_model: BaseFeatureModel
Feature extraction model that converts texts and keywords to
feature matrices.
n_papers: int
Number of papers to review during the active learning process,
excluding the number of initial priors. To review all papers, set
n_papers to None.
n_instances: int
Number of papers to query at each step in the active learning
process.
n_queries: int
Number of steps/queries to perform. Set to None for no limit.
start_idx: numpy.array
Start the simulation/review with these indices. They are assumed to
be already labeled. Failing to do so might result bad behaviour.
state_file: str
Path to state file. Replaces log_file argument.
"""
super(BaseReview, self).__init__()
# Default to Naive Bayes model
if model is None:
model = NBModel()
if query_model is None:
query_model = MaxQuery()
if balance_model is None:
balance_model = SimpleBalance()
if feature_model is None:
feature_model = Tfidf()
self.as_data = as_data
self.y = as_data.labels
if self.y is None:
self.y = np.full(len(as_data), LABEL_NA)
self.model = model
self.balance_model = balance_model
self.query_model = query_model
self.feature_model = feature_model
self.shared = {"query_src": {}, "current_queries": {}}
self.model.shared = self.shared
self.query_model.shared = self.shared
self.balance_model.shared = self.shared
self.n_papers = n_papers
self.n_instances = n_instances
self.n_queries = n_queries
self.start_idx = start_idx
if log_file is not None:
warnings.warn(
"The log_file argument for BaseReview will be"
" replaced by state_file.",
category=FutureWarning)
self.state_file = log_file
else:
self.state_file = state_file
self.query_i = 0
self.query_i_classified = 0
self.train_idx = np.array([], dtype=np.int)
self.model_trained = False
# Restore the state from a file or initialize said file.
with open_state(self.state_file) as state:
# From file
if not state.is_empty():
startup = state.startup_vals()
# If there are start indices not in the training add them.
if not set(startup["train_idx"]) >= set(start_idx):
new_idx = list(set(start_idx) - set(startup["train_idx"]))
self.classify(new_idx,
self.y[new_idx],
state,
method="initial")
startup = state.startup_vals()
self.train_idx = startup["train_idx"]
self.y = startup["labels"]
self.shared["query_src"] = startup["query_src"]
self.query_i = startup["query_i"]
self.query_i_classified = startup["query_i_classified"]
# From scratch
else:
state.set_labels(self.y)
state.settings = self.settings
self.classify(start_idx,
self.y[start_idx],
state,
method="initial")
self.query_i_classified = len(start_idx)
# Try to retrieve feature matrix from the state file.
try:
self.X = state.get_feature_matrix(as_data.hash())
except KeyError:
self.X = feature_model.fit_transform(as_data.texts,
as_data.headings,
as_data.bodies,
as_data.keywords)
state._add_as_data(as_data, feature_matrix=self.X)
if self.X.shape[0] != len(self.y):
raise ValueError("The state file does not correspond to the "
"given data file, please use another state "
"file or dataset.")
self.load_current_query(state)