"""
Base classes for all estimators.
Used for VotingClassifier
"""
# Author: Gael Varoquaux <gael.varoquaux@normalesup.org>
# License: BSD 3 clause
import copy
import warnings
from collections import defaultdict
import platform
import inspect
import re
import numpy as np
from . import __version__
from ._config import get_config
from .utils import _IS_32BIT
from .utils.validation import check_X_y
from .utils.validation import check_array
from .utils._estimator_html_repr import estimator_html_repr
from .utils.validation import _deprecate_positional_args
_DEFAULT_TAGS = {
'non_deterministic': False,
'requires_positive_X': False,
'requires_positive_y': False,
'X_types': ['2darray'],
'poor_score': False,
'no_validation': False,
'multioutput': False,
"allow_nan": False,
'stateless': False,
'multilabel': False,
'_skip_test': False,
'_xfail_checks': False,
'multioutput_only': False,
'binary_only': False,
'requires_fit': True,
'requires_y': False,
}
@_deprecate_positional_args
def clone(estimator, *, safe=True):
"""Constructs a new estimator with the same parameters.
Clone does a deep copy of the model in an estimator
without actually copying attached data. It yields a new estimator
with the same parameters that has not been fit on any data.
Parameters
----------
estimator : {list, tuple, set} of estimator objects or estimator object
The estimator or group of estimators to be cloned.
safe : bool, default=True
If safe is false, clone will fall back to a deep copy on objects
that are not estimators.
"""
estimator_type = type(estimator)
# XXX: not handling dictionaries
if estimator_type in (list, tuple, set, frozenset):
return estimator_type([clone(e, safe=safe) for e in estimator])
elif not hasattr(estimator, 'get_params') or isinstance(estimator, type):
if not safe:
return copy.deepcopy(estimator)
else:
if isinstance(estimator, type):
raise TypeError("Cannot clone object. " +
"You should provide an instance of " +
"scikit-learn estimator instead of a class.")
else:
raise TypeError("Cannot clone object '%s' (type %s): "
"it does not seem to be a scikit-learn "
"estimator as it does not implement a "
"'get_params' method."
% (repr(estimator), type(estimator)))
klass = estimator.__class__
new_object_params = estimator.get_params(deep=False)
for name, param in new_object_params.items():
new_object_params[name] = clone(param, safe=False)
new_object = klass(**new_object_params)
params_set = new_object.get_params(deep=False)
# quick sanity check of the parameters of the clone
for name in new_object_params:
param1 = new_object_params[name]
param2 = params_set[name]
if param1 is not param2:
raise RuntimeError('Cannot clone object %s, as the constructor '
'either does not set or modifies parameter %s' %
(estimator, name))
return new_object
def _pprint(params, offset=0, printer=repr):
"""Pretty print the dictionary 'params'
Parameters
----------
params : dict
The dictionary to pretty print
offset : int, default=0
The offset in characters to add at the begin of each line.
printer : callable, default=repr
The function to convert entries to strings, typically
the builtin str or repr
"""
# Do a multi-line justified repr:
options = np.get_printoptions()
np.set_printoptions(precision=5, threshold=64, edgeitems=2)
params_list = list()
this_line_length = offset
line_sep = ',\n' + (1 + offset // 2) * ' '
for i, (k, v) in enumerate(sorted(params.items())):
if type(v) is float:
# use str for representing floating point numbers
# this way we get consistent representation across
# architectures and versions.
this_repr = '%s=%s' % (k, str(v))
else:
# use repr of the rest
this_repr = '%s=%s' % (k, printer(v))
if len(this_repr) > 500:
this_repr = this_repr[:300] + '...' + this_repr[-100:]
if i > 0:
if (this_line_length + len(this_repr) >= 75 or '\n' in this_repr):
params_list.append(line_sep)
this_line_length = len(line_sep)
else:
params_list.append(', ')
this_line_length += 2
params_list.append(this_repr)
this_line_length += len(this_repr)
np.set_printoptions(**options)
lines = ''.join(params_list)
# Strip trailing space to avoid nightmare in doctests
lines = '\n'.join(l.rstrip(' ') for l in lines.split('\n'))
return lines
class BaseEstimator:
"""Base class for all estimators in scikit-learn
Notes
-----
All estimators should specify all the parameters that can be set
at the class level in their ``__init__`` as explicit keyword
arguments (no ``*args`` or ``**kwargs``).
"""
@classmethod
def _get_param_names(cls):
"""Get parameter names for the estimator"""
# fetch the constructor or the original constructor before
# deprecation wrapping if any
init = getattr(cls.__init__, 'deprecated_original', cls.__init__)
if init is object.__init__:
# No explicit constructor to introspect
return []
# introspect the constructor arguments to find the model parameters
# to represent
init_signature = inspect.signature(init)
# Consider the constructor parameters excluding 'self'
parameters = [p for p in init_signature.parameters.values()
if p.name != 'self' and p.kind != p.VAR_KEYWORD]
for p in parameters:
if p.kind == p.VAR_POSITIONAL:
raise RuntimeError("scikit-learn estimators should always "
"specify their parameters in the signature"
" of their __init__ (no varargs)."
" %s with constructor %s doesn't "
" follow this convention."
% (cls, init_signature))
# Extract and sort argument names excluding 'self'
return sorted([p.name for p in parameters])
def get_params(self, deep=True):
"""
Get parameters for this estimator.
Parameters
----------
deep : bool, default=True
If True, will return the parameters for this estimator and
contained subobjects that are estimators.
Returns
-------
params : mapping of string to any
Parameter names mapped to their values.
"""
out = dict()
for key in self._get_param_names():
try:
value = getattr(self, key)
except AttributeError:
warnings.warn('From version 0.24, get_params will raise an '
'AttributeError if a parameter cannot be '
'retrieved as an instance attribute. Previously '
'it would return None.',
FutureWarning)
value = None
if deep and hasattr(value, 'get_params'):
deep_items = value.get_params().items()
out.update((key + '__' + k, val) for k, val in deep_items)
out[key] = value
return out
def set_params(self, **params):
"""
Set the parameters of this estimator.
The method works on simple estimators as well as on nested objects
(such as pipelines). The latter have parameters of the form
``<component>__<parameter>`` so that it's possible to update each
component of a nested object.
Parameters
----------
**params : dict
Estimator parameters.
Returns
-------
self : object
Estimator instance.
"""
if not params:
# Simple optimization to gain speed (inspect is slow)
return self
valid_params = self.get_params(deep=True)
nested_params = defaultdict(dict) # grouped by prefix
for key, value in params.items():
key, delim, sub_key = key.partition('__')
if key not in valid_params:
raise ValueError('Invalid parameter %s for estimator %s. '
'Check the list of available parameters '
'with `estimator.get_params().keys()`.' %
(key, self))
if delim:
nested_params[key][sub_key] = value
else:
setattr(self, key, value)
valid_params[key] = value
for key, sub_params in nested_params.items():
valid_params[key].set_params(**sub_params)
return self
def __repr__(self, N_CHAR_MAX=700):
# N_CHAR_MAX is the (approximate) maximum number of non-blank
# characters to render. We pass it as an optional parameter to ease
# the tests.
from .utils._pprint import _EstimatorPrettyPrinter
N_MAX_ELEMENTS_TO_SHOW = 30 # number of elements to show in sequences
# use ellipsis for sequences with a lot of elements
pp = _EstimatorPrettyPrinter(
compact=True, indent=1, indent_at_name=True,
n_max_elements_to_show=N_MAX_ELEMENTS_TO_SHOW)
repr_ = pp.pformat(self)
# Use bruteforce ellipsis when there are a lot of non-blank characters
n_nonblank = len(''.join(repr_.split()))
if n_nonblank > N_CHAR_MAX:
lim = N_CHAR_MAX // 2 # apprx number of chars to keep on both ends
regex = r'^(\s*\S){%d}' % lim
# The regex '^(\s*\S){%d}' % n
# matches from the start of the string until the nth non-blank
# character:
# - ^ matches the start of string
# - (pattern){n} matches n repetitions of pattern
# - \s*\S matches a non-blank char following zero or more blanks
left_lim = re.match(regex, repr_).end()
right_lim = re.match(regex, repr_[::-1]).end()
if '\n' in repr_[left_lim:-right_lim]:
# The left side and right side aren't on the same line.
# To avoid weird cuts, e.g.:
# categoric...ore',
# we need to start the right side with an appropriate newline
# character so that it renders properly as:
# categoric...
# handle_unknown='ignore',
# so we add [^\n]*\n which matches until the next \n
regex += r'[^\n]*\n'
right_lim = re.match(regex, repr_[::-1]).end()
ellipsis = '...'
if left_lim + len(ellipsis) < len(repr_) - right_lim:
# Only add ellipsis if it results in a shorter repr
repr_ = repr_[:left_lim] + '...' + repr_[-right_lim:]
return repr_
def __getstate__(self):
try:
state = super().__getstate__()
except AttributeError:
state = self.__dict__.copy()
if type(self).__module__.startswith('sklearn.'):
return dict(state.items(), _sklearn_version=__version__)
else:
return state
def __setstate__(self, state):
if type(self).__module__.startswith('sklearn.'):
pickle_version = state.pop("_sklearn_version", "pre-0.18")
if pickle_version != __version__:
warnings.warn(
"Trying to unpickle estimator {0} from version {1} when "
"using version {2}. This might lead to breaking code or "
"invalid results. Use at your own risk.".format(
self.__class__.__name__, pickle_version, __version__),
UserWarning)
try:
super().__setstate__(state)
except AttributeError:
self.__dict__.update(state)
def _more_tags(self):
return _DEFAULT_TAGS
def _get_tags(self):
collected_tags = {}
for base_class in reversed(inspect.getmro(self.__class__)):
Loading ...