def __init__(self, *args, **kwargs):
name = kwargs.pop('name', None)
if name is None:
self.name = 'BooleanRuleMatcher' + '_' + get_ts()
else:
self.name = name
self.rules = OrderedDict()
self.rule_source = OrderedDict()
self.rule_conjunct_list = OrderedDict()
self.rule_cnt = 0
def __init__(self, *args, **kwargs):
super(SVMMatcher, self).__init__()
# If the name is given, then pop it
name = kwargs.pop('name', None)
if name is None:
# If the name of the matcher is give, then create one.
# Currently, we use a constant string + a random number.
self.name = 'SVM' + '_' + get_ts()
else:
# Set the name of the matcher, with the given name.
self.name = name
# Set the classifier to the scikit-learn classifier.
self.clf = SVC(*args, **kwargs)
def __init__(self, *args, **kwargs):
super(SVMMatcher, self).__init__()
# If the name is given, then pop it
name = kwargs.pop('name', None)
if name is None:
# If the name of the matcher is give, then create one.
# Currently, we use a constant string + a random number.
self.name = 'SVM'+ '_' + get_ts()
else:
# Set the name of the matcher, with the given name.
self.name = name
# Set the classifier to the scikit-learn classifier.
self.clf = SVC(*args, **kwargs)
def __init__(self, *args, **kwargs):
name = kwargs.pop('name', None)
if name is None:
self.name = 'BooleanRuleMatcher' + '_' + get_ts()
else:
self.name = name
self.rules = OrderedDict()
self.rule_source = OrderedDict()
self.rule_conjunct_list = OrderedDict()
self.rule_cnt = 0
feature_table = kwargs.pop('feature_table', None)
self.feature_table = feature_table
self.rule_ft = OrderedDict()
def __init__(self, *args, **kwargs):
super(LinRegMatcher, self).__init__()
# If the name is given, then pop it
name = kwargs.pop('name', None)
if name is None:
# If the name is not given, then create one.
# Currently, we use a constant string + a random number.
self.name = 'LinearRegression' + '_' + get_ts()
else:
# set the name for the matcher.
self.name = name
# Wrap the class implementing linear regression classifer.
self.clf = LinRegClassifierSKLearn(*args, **kwargs)
def __init__(self, *args, **kwargs):
super(LinRegMatcher, self).__init__()
# If the name is given, then pop it
name = kwargs.pop('name', None)
if name is None:
# If the name is not given, then create one.
# Currently, we use a constant string + a random number.
self.name = 'LinearRegression' + '_' + get_ts()
else:
# set the name for the matcher.
self.name = name
# Wrap the class implementing linear regression classifer.
self.clf = LinRegClassifierSKLearn(*args, **kwargs)
def __init__(self, *args, **kwargs):
# If the name is given, then pop it
name = kwargs.pop('name', None)
if name is None:
# If the name of the matcher is give, then create one.
# Currently, we use a constant string + a random number.
self.name = 'LogisticRegression'+ '_' + get_ts()
else:
# Set the name of the matcher, with the given name.
self.name = name
super(LogRegMatcher, self).__init__()
# Set the classifier to the scikit-learn classifier.
self.clf = LogisticRegression(*args, **kwargs)
self.clf.classes_ = [0, 1]
def __init__(self, *args, **kwargs):
# If the name is given, then pop it
name = kwargs.pop('name', None)
if name is None:
# If the name of the matcher is give, then create one.
# Currently, we use a constant string + a random number.
self.name = 'LogisticRegression' + '_' + get_ts()
else:
# Set the name of the matcher, with the given name.
self.name = name
super(LogRegMatcher, self).__init__()
# Set the classifier to the scikit-learn classifier.
self.clf = LogisticRegression(*args, **kwargs)
self.clf.classes_ = [0, 1]
def __init__(self, *args, **kwargs):
logger.warning(
"WARNING THIS MATCHER IS EXPERIMENTAL AND NOT TESTED. USE AT YOUR OWN RISK.")
# If the name is given, then pop it
name = kwargs.pop('name', None)
if name is None:
# If the name of the matcher is give, then create one.
# Currently, we use a constant string + a random number.
self.name = 'NaiveBayes'+ '_' + get_ts()
else:
# Set the name of the matcher, with the given name.
self.name = name
super(DaskNBMatcher, self).__init__()
# Set the classifier to the scikit-learn classifier.
self.clf = GaussianNB(*args, **kwargs)
def __init__(self, *args, **kwargs):
logger.warning(
"WARNING THIS MATCHER IS EXPERIMENTAL AND NOT TESTED. USE AT YOUR OWN RISK."
)
# If the name is given, then pop it
name = kwargs.pop('name', None)
if name is None:
# If the name of the matcher is give, then create one.
# Currently, we use a constant string + a random number.
self.name = 'NaiveBayes' + '_' + get_ts()
else:
# Set the name of the matcher, with the given name.
self.name = name
super(DaskNBMatcher, self).__init__()
# Set the classifier to the scikit-learn classifier.
self.clf = GaussianNB(*args, **kwargs)
def __init__(self, *args, **kwargs):
super(XGBoostMatcher, self).__init__()
# If the name is given, then pop it
name = kwargs.pop('name', None)
if name is None:
# If the name of the matcher is give, then create one.
# Currently, we use a constant string + a random number.
self.name = 'xgboost' + '_' + get_ts()
else:
# Set the name of the matcher, with the given name.
self.name = name
# Set the classifier to the scikit-learn classifier.
try:
from xgboost.sklearn import XGBClassifier
except ImportError:
raise ImportError(
'Check if xgboost library is installed. You can install xgboost '
'by following the instructions at http://xgboost.readthedocs.io/en/latest/build.html'
)
self.clf = XGBClassifier(*args, **kwargs)
def __init__(self, *args, **kwargs):
logger.warning(
"WARNING THIS MATCHER IS EXPERIMENTAL AND NOT TESTED. USE AT YOUR OWN RISK.")
super(DaskXGBoostMatcher, self).__init__()
# If the name is given, then pop it
name = kwargs.pop('name', None)
if name is None:
# If the name of the matcher is give, then create one.
# Currently, we use a constant string + a random number.
self.name = 'xgboost' + '_' + get_ts()
else:
# Set the name of the matcher, with the given name.
self.name = name
# Set the classifier to the scikit-learn classifier.
try:
from xgboost.sklearn import XGBClassifier
except ImportError:
raise ImportError(
'Check if xgboost library is installed. You can install xgboost '
'by following the instructions at http://xgboost.readthedocs.io/en/latest/build.html')
self.clf = XGBClassifier(*args, **kwargs)
