def __init__(self, q = 10, variables = None):
if not isinstance(q, int):
raise ValueError('q must be an integer')
self.q = q
self.variables = _define_variables(variables)
def __init__(self, imputation_method='median', variables = None):
if imputation_method not in ['median', 'mean']:
raise ValueError("Imputation method takes only values 'median' or 'mean'")
self.imputation_method = imputation_method
self.variables = _define_variables(variables)
def __init__(self, exp = 0.5, variables = None):
if not isinstance(exp, float) and not isinstance(exp, int):
raise ValueError('exp must be a float or an int')
self.exp = exp
self.variables = _define_variables(variables)
def __init__(self,
variables=None,
random_state=None,
seed='general',
seeding_method='add'):
if seed not in ['general', 'observation']:
raise ValueError(
"seed takes only values 'general' or 'observation'")
if seeding_method not in ['add', 'multiply']:
raise ValueError(
"seeding_method takes only values 'add' or 'multiply'")
if seed == 'general' and random_state:
if not isinstance(random_state, int):
raise ValueError(
"if the seed == 'general' the random state must take an integer"
)
if isinstance(random_state, str):
random_state = list(random_state)
self.variables = _define_variables(variables)
self.random_state = random_state
self.seed = seed
self.seeding_method = seeding_method
def __init__(self, arbitrary_number = -999, variables = None):
if isinstance(arbitrary_number, int) or isinstance(arbitrary_number, float):
self.arbitrary_number = arbitrary_number
else:
raise ValueError('Arbitrary number must be numeric of type int or float')
self.variables = _define_variables(variables)
def __init__(self, encoding_method='count', variables=None):
if encoding_method not in ['count', 'frequency']:
raise ValueError(
"encoding_method takes only values 'count' and 'frequency'")
self.encoding_method = encoding_method
self.variables = _define_variables(variables)
def __init__(self, encoding_method='woe', variables=None):
if encoding_method not in ['woe', 'ratio']:
raise ValueError(
"encoding_method takes only values 'woe' and 'ratio'")
self.encoding_method = encoding_method
self.variables = _define_variables(variables)
def __init__(self, encoding_method='ordered', variables=None):
if encoding_method not in ['ordered', 'arbitrary']:
raise ValueError(
"encoding_method takes only values 'ordered' and 'arbitrary'")
self.encoding_method = encoding_method
self.variables = _define_variables(variables)
def __init__(self, bins = 10, variables = None, return_object=False):
if not isinstance(bins, int):
raise ValueError('q must be an integer')
self.bins = bins
self.variables = _define_variables(variables)
self.return_object = return_object
def __init__(self, cv = 3, scoring='neg_mean_squared_error', variables = None, regression=True):
if not isinstance(cv, int) or cv < 0:
raise ValueError('cv can only take only positive integers')
if not isinstance(regression, bool):
raise ValueError('regression can only True or False')
self.cv = cv
self.scoring = scoring
self.regression = regression
self.variables = _define_variables(variables)
def __init__(self, tol=0.05, n_categories=10, variables=None):
if tol < 0 or tol > 1:
raise ValueError("tol takes values between 0 and 1")
if n_categories < 0 or not isinstance(n_categories, int):
raise ValueError(
"n_categories takes only positive integer numbers")
self.tol = tol
self.n_categories = n_categories
self.variables = _define_variables(variables)
def __init__(self, top_categories=None, variables=None, drop_last=False):
if top_categories:
if not isinstance(top_categories, int):
raise ValueError(
"top_categories takes only integer numbers, 1, 2, 3, etc.")
self.top_categories = top_categories
if drop_last not in [True, False]:
raise ValueError("drop_last takes only True or False")
self.drop_last = drop_last
self.variables = _define_variables(variables)
def __init__(self, distribution='gaussian', tail='right', fold=3, variables = None):
if distribution not in ['gaussian', 'skewed']:
raise ValueError("distribution takes only values 'gaussian' or 'skewed'")
if tail not in ['right', 'left']:
raise ValueError("tail takes only values 'right' or 'left'")
if fold <=0 :
raise ValueError("fold takes only positive numbers")
self.distribution = distribution
self.tail = tail
self.fold = fold
self.variables = _define_variables(variables)
def __init__(self, cv = 3, scoring='neg_mean_squared_error',
variables = None, param_grid = {'max_depth': [1,2,3,4]},
regression=True, random_state=None):
if not isinstance(cv, int) or cv < 0:
raise ValueError('cv can only take only positive integers')
if not isinstance(regression, bool):
raise ValueError('regression can only take True or False')
self.cv = cv
self.scoring = scoring
self.regression = regression
self.variables = _define_variables(variables)
self.param_grid = param_grid
self.random_state = random_state
def __init__(self, variables=None):
self.variables = _define_variables(variables)
def __init__(self, variables=None, random_state=0):
self.variables = _define_variables(variables)
self.random_state = random_state
