def __init__(self, prefix='', postfix='', sklearn_output=False, name=None):
Transformer.__init__(self, sklearn_output=sklearn_output, name=name)
self.prefix = prefix
self.postfix = postfix
# this is need to inverse mapping
self._original_column_names = {'x': {}, 'y': {}}
self._new_column_names = {'x': {}, 'y': {}}
def __init__(self, x_cols='all', y_cols=[], invertible=True, sklearn_output=False, name=None):
Transformer.__init__(self, sklearn_output=sklearn_output, name=name)
self.x_cols = x_cols
self.y_cols = y_cols
self.invertible = invertible
# the inverse mapping is needed to invert the transformation
self._inverse_map = {'x': None, 'y': None}
def __init__(self, x_cols=[], y_cols=[], k=3.0, skipna=True, sklearn_output=False, name=None):
Transformer.__init__(self, sklearn_output=sklearn_output, name=name)
self.x_cols = x_cols
self.y_cols = y_cols
self.k = k
self.skipna = skipna
# the inverse mapping is needed to invert the transformation
self._inverse_map = {'x': {}, 'y': {}}
def __init__(self, x_cols=[], y_cols=[], min_value=-1.0, max_value=1.0, sklearn_output=False, name=None):
Transformer.__init__(self, sklearn_output=sklearn_output, name=name)
self.x_cols = x_cols
self.y_cols = y_cols
self.min_value = min_value
self.max_value = max_value
self._d = self.max_value - self.min_value
# the inverse mapping is needed to invert the transformation
self._inverse_map = {'x': None, 'y': None}
def __init__(self,
how='any',
on_x=True,
on_y=True,
sklearn_output=False,
name=None):
Transformer.__init__(self, sklearn_output=sklearn_output, name=name)
self.how = how
self.on_x = on_x
self.on_y = on_y
def __init__(self,
x_cols=[],
y_cols=[],
skipna=False,
sklearn_output=False,
name=None):
Transformer.__init__(self, sklearn_output=sklearn_output, name=name)
self.x_cols = x_cols
self.y_cols = y_cols
self.skipna = skipna
self._map_category_to_number = {'x': {}, 'y': {}}
self._map_number_to_category = {'x': {}, 'y': {}}
def __init__(self,
x_cols=[],
y_cols=[],
value='median',
method=None,
sklearn_output=False,
name=None):
Transformer.__init__(self, sklearn_output=sklearn_output, name=name)
self.x_cols = x_cols
self.y_cols = y_cols
self.value = value
self.method = method
def __init__(self, x_cols=[], y_cols=[], func=None, inv_func=None, as_dataframe=False, reset_index=True,
sklearn_output=False, name=None):
Transformer.__init__(self, sklearn_output=sklearn_output, name=name)
self.x_cols = x_cols
self.y_cols = y_cols
self.func = func
self.inv_func = inv_func
self.as_dataframe = as_dataframe
self.reset_index = reset_index
# this is need to inverse mapping
self._inverse_map_column_names = {'x': {}, 'y': {}}
def __init__(self,
on_rows=True,
on_cols=True,
on_x=True,
on_y=False,
sklearn_output=False,
name=None):
Transformer.__init__(self, sklearn_output=sklearn_output, name=name)
self.on_rows = on_rows
self.on_cols = on_cols
self.on_x = on_x
self.on_y = on_y
self._drop_indices_row = []
def __init__(self,
x_cols=[],
y_cols=[],
x_levels=2,
y_levels=2,
sklearn_output=False,
name=None):
Transformer.__init__(self, sklearn_output=sklearn_output, name=name)
self.x_cols = x_cols
self.y_cols = y_cols
self.x_levels = x_levels
self.y_levels = y_levels
self._thresholds = {'x': {}, 'y': {}}
def __init__(self,
x_cols=[],
y_cols=[],
k=3,
x_is_categorical=None,
y_is_categorical=None,
sklearn_output=False,
name=None):
Transformer.__init__(self, sklearn_output=sklearn_output, name=name)
self.x_cols = x_cols
self.y_cols = y_cols
self.k = k
self.x_is_categorical = x_is_categorical
self.y_is_categorical = y_is_categorical
self._cat2num = {
'x': None,
'y': None
} # this is needed to deal with potential categorical columns
self._knn_models = {'x': None, 'y': None}
def __init__(self, x_cols=[], y_cols=[], sklearn_output=False, name=None):
Transformer.__init__(self, sklearn_output=sklearn_output, name=name)
self.x_cols = x_cols
self.y_cols = y_cols
self._pdfs = {'x': {}, 'y': {}}
def __init__(self, transformers=[], reset_index=True, sklearn_output=False, name=None):
Pipe.__init__(self, transformers=transformers)
Transformer.__init__(self, sklearn_output=sklearn_output, name=name)
self.reset_index = reset_index
self._original_column_names = {'x': {}, 'y': {}}
def __init__(self, as_type=float, sklearn_output=False, name=None):
Transformer.__init__(self, sklearn_output=sklearn_output, name=name)
self.as_type = as_type
def __init__(self, sequence_len=2, sklearn_output=False, name=None):
Transformer.__init__(self, sklearn_output=sklearn_output, name=name)
self.sequence_len = sequence_len
def __init__(self, transformers=[], sklearn_output=False, name=None):
Pipe.__init__(self, transformers=transformers)
Transformer.__init__(self, sklearn_output=sklearn_output, name=name)