def __init__(self, features=None, excluded_features=None, num_bits=18,
output_column_name='hashed_features'):
# Process and make a copy of the features, exclude.
_features, _exclude = _internal_utils.process_features(
features, excluded_features)
# Type checking
_raise_error_if_not_of_type(num_bits, [int])
_raise_error_if_not_of_type(output_column_name, [str])
# Set up options
opts = {
'num_bits': num_bits,
'output_column_name': output_column_name,
}
if _exclude:
opts['exclude'] = True
opts['features'] = _exclude
else:
opts['exclude'] = False
opts['features'] = _features
# Initialize object
proxy = _gl.extensions._FeatureHasher()
proxy.init_transformer(opts)
super(FeatureHasher, self).__init__(proxy, self.__class__)
def __init__(self, features=None, excluded_features=None,
max_categories=None, output_column_name = 'encoded_features'):
# Process and make a copy of the features, exclude.
_features, _exclude = _internal_utils.process_features(
features, excluded_features)
# Type checking
_raise_error_if_not_of_type(max_categories, [int, _NoneType])
_raise_error_if_not_of_type(output_column_name, [str])
# Set up options
opts = {
'max_categories': max_categories,
'output_column_name': output_column_name,
}
if _exclude:
opts['exclude'] = True
opts['features'] = _exclude
else:
opts['exclude'] = False
opts['features'] = _features
# Initialize object
proxy = _gl.extensions._OneHotEncoder()
proxy.init_transformer(opts)
super(OneHotEncoder, self).__init__(proxy, self.__class__)
def __init__(self, features=None, excluded_features=None,
strategy='logarithmic', num_bins=10,
output_column_prefix=None):
# Process and make a copy of the features, exclude.
_features, _exclude = _internal_utils.process_features(features, excluded_features)
# Type checking
_raise_error_if_not_of_type(num_bins, [int])
_raise_error_if_not_of_type(strategy, [str])
# Set up options
opts = {
'strategy': strategy,
'num_bins': num_bins,
'output_column_prefix': output_column_prefix
}
if _exclude:
opts['exclude'] = True
opts['features'] = _exclude
else:
opts['exclude'] = False
opts['features'] = _features
# Initialize object
proxy = _gl.extensions._FeatureBinner()
proxy.init_transformer(opts)
super(FeatureBinner, self).__init__(proxy, self.__class__)
def __init__(self, features=None, excluded_features=None, threshold=1,
output_category_name=None, output_column_prefix=None):
# Process and make a copy of the features, exclude.
_features, _exclude = _internal_utils.process_features(
features, excluded_features)
# Type checking
_raise_error_if_not_of_type(threshold, [int, _NoneType])
# Set up options
opts = {
'threshold': threshold,
'output_category_name': output_category_name,
'output_column_prefix': output_column_prefix
}
if _exclude:
opts['exclude'] = True
opts['features'] = _exclude
else:
opts['exclude'] = False
opts['features'] = _features
# Initialize object
proxy = _gl.extensions._CountThresholder()
proxy.init_transformer(opts)
super(CountThresholder, self).__init__(proxy, self.__class__)
def __init__(
self,
features=None,
excluded_features=None,
min_document_frequency=0.0,
max_document_frequency=1.0,
output_column_prefix=None,
):
# Process and make a copy of the features, exclude.
_features, _exclude = _internal_utils.process_features(features, excluded_features)
# Type checking
_raise_error_if_not_of_type(min_document_frequency, [float, int])
_raise_error_if_not_of_type(max_document_frequency, [float, int])
_raise_error_if_not_of_type(output_column_prefix, [str, _NoneType])
# Set up options
opts = {
"min_document_frequency": min_document_frequency,
"max_document_frequency": max_document_frequency,
"output_column_prefix": output_column_prefix,
}
if _exclude:
opts["exclude"] = True
opts["features"] = _exclude
else:
opts["exclude"] = False
opts["features"] = _features
# Initialize object
proxy = _gl.extensions._TFIDF()
proxy.init_transformer(opts)
super(TFIDF, self).__init__(proxy, self.__class__)
def __init__(
self,
features=None,
excluded_features=None,
to_lower=False,
delimiters=["\r", "\v", "\n", "\f", "\t", " "],
output_column_prefix=None,
):
# Process and make a copy of the features, exclude.
_features, _exclude = _internal_utils.process_features(features, excluded_features)
# Type checking
_raise_error_if_not_of_type(features, [list, str, _NoneType])
_raise_error_if_not_of_type(excluded_features, [list, str, _NoneType])
_raise_error_if_not_of_type(to_lower, [bool])
_raise_error_if_not_of_type(delimiters, [list, _NoneType])
_raise_error_if_not_of_type(output_column_prefix, [str, _NoneType])
if delimiters != None:
for delim in delimiters:
_raise_error_if_not_of_type(delim, str, "delimiters")
if len(delim) != 1:
raise ValueError("Delimiters must be single-character strings")
# Set up options
opts = {
"features": features,
"to_lower": to_lower,
"delimiters": delimiters,
"output_column_prefix": output_column_prefix,
}
if _exclude:
opts["exclude"] = True
opts["features"] = _exclude
else:
opts["exclude"] = False
opts["features"] = _features
# Initialize object
proxy = _gl.extensions._Tokenizer()
proxy.init_transformer(opts)
super(Tokenizer, self).__init__(proxy, self.__class__)
def __init__(self, features=None, excluded_features=None):
# Process and make a copy of the features, exclude.
_features, _exclude = _internal_utils.process_features(features, excluded_features)
# Set up options
opts = {
'features': features
}
if _exclude:
opts['exclude'] = True
opts['features'] = _exclude
else:
opts['exclude'] = False
opts['features'] = _features
# Initialize object
proxy = _gl.extensions._Tokenizer()
proxy.init_transformer(opts)
super(Tokenizer, self).__init__(proxy, self.__class__)
def __init__(self, reference_features=None, feature="feature", verbose=False):
# Process and make a copy of the reference_features
_reference_features, _exclude = _internal_utils.process_features(reference_features, None)
# Type checking
_raise_error_if_not_of_type(feature, [str])
# Set up options
opts = {
'reference_features': reference_features,
'feature': feature,
'verbose': verbose
}
opts['reference_features'] = _reference_features
# Initialize object
proxy = _gl.extensions._CategoricalImputer()
proxy.init_transformer(opts)
super(CategoricalImputer, self).__init__(proxy, self.__class__)
def __init__(self, features=None, excluded_features=None,
n=2, method="word", to_lower=True, ignore_punct=True, ignore_space=True,
delimiters=["\r", "\v", "\n", "\f", "\t", " ",
"!", "#", "$", "%", "&", "'", "(", ")",
"*", "+", ",", "-", ".", "/", ":", ";",
"<", "=", ">", "?", "@", "[", "\\", "]",
"^", "_", "`", "{", "|", "}", "~"],
output_column_prefix=None):
# Process and make a copy of the features, exclude.
_features, _exclude = _internal_utils.process_features(features, excluded_features)
# Type checking
_raise_error_if_not_of_type(features, [list, str, _NoneType])
_raise_error_if_not_of_type(excluded_features, [list, str, _NoneType])
_raise_error_if_not_of_type(n, [int])
_raise_error_if_not_of_type(method, [str])
_raise_error_if_not_of_type(to_lower, [bool])
_raise_error_if_not_of_type(ignore_punct, [bool])
_raise_error_if_not_of_type(ignore_space, [bool])
_raise_error_if_not_of_type(delimiters, [list, _NoneType])
_raise_error_if_not_of_type(output_column_prefix, [str, _NoneType])
if delimiters != None:
for delim in delimiters:
_raise_error_if_not_of_type(delim, str, "delimiters")
if (len(delim) != 1):
raise ValueError("Delimiters must be single-character strings")
if n < 1:
raise ValueError("Input 'n' must be greater than 0")
if n > 5 and method == 'word':
warnings.warn("It is unusual for n-grams to be of size larger than 5.")
if method != "word" and method != "character":
raise ValueError("Invalid 'method' input value. Please input " +
"either 'word' or 'character' ")
# Set up options
opts = {
'n': n,
'features': features,
'ngram_type': method,
'to_lower': to_lower,
'ignore_punct': ignore_punct,
'ignore_space': ignore_space,
'delimiters': delimiters,
'output_column_prefix' : output_column_prefix
}
if _exclude:
opts['exclude'] = True
opts['features'] = _exclude
else:
opts['exclude'] = False
opts['features'] = _features
# Initialize object
proxy = _gl.extensions._NGramCounter()
proxy.init_transformer(opts)
super(NGramCounter, self).__init__(proxy, self.__class__)
