"""
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,
}
[docs]@_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 " +
"h2o4gpu estimator instead of a class.")
else:
raise TypeError("Cannot clone object '%s' (type %s): "
"it does not seem to be a h2o4gpu "
"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 h2o4gpu
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("h2o4gpu 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('h2o4gpu.'):
return dict(state.items(), _h2o4gpu_version=__version__)
else:
return state
def __setstate__(self, state):
if type(self).__module__.startswith('h2o4gpu.'):
pickle_version = state.pop("_h2o4gpu_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__)):
if hasattr(base_class, '_more_tags'):
# need the if because mixins might not have _more_tags
# but might do redundant work in estimators
# (i.e. calling more tags on BaseEstimator multiple times)
more_tags = base_class._more_tags(self)
collected_tags.update(more_tags)
return collected_tags
def _check_n_features(self, X, reset):
"""Set the `n_features_in_` attribute, or check against it.
Parameters
----------
X : {ndarray, sparse matrix} of shape (n_samples, n_features)
The input samples.
reset : bool
If True, the `n_features_in_` attribute is set to `X.shape[1]`.
Else, the attribute must already exist and the function checks
that it is equal to `X.shape[1]`.
"""
n_features = X.shape[1]
if reset:
self.n_features_in_ = n_features
else:
if not hasattr(self, 'n_features_in_'):
raise RuntimeError(
"The reset parameter is False but there is no "
"n_features_in_ attribute. Is this estimator fitted?"
)
if n_features != self.n_features_in_:
raise ValueError(
'X has {} features, but this {} is expecting {} features '
'as input.'.format(n_features, self.__class__.__name__,
self.n_features_in_)
)
def _validate_data(self, X, y=None, reset=True,
validate_separately=False, **check_params):
"""Validate input data and set or check the `n_features_in_` attribute.
Parameters
----------
X : {array-like, sparse matrix, dataframe} of shape \
(n_samples, n_features)
The input samples.
y : array-like of shape (n_samples,), default=None
The targets. If None, `check_array` is called on `X` and
`check_X_y` is called otherwise.
reset : bool, default=True
Whether to reset the `n_features_in_` attribute.
If False, the input will be checked for consistency with data
provided when reset was last True.
validate_separately : False or tuple of dicts, default=False
Only used if y is not None.
If False, call validate_X_y(). Else, it must be a tuple of kwargs
to be used for calling check_array() on X and y respectively.
**check_params : kwargs
Parameters passed to :func:`h2o4gpu.utils.check_array` or
:func:`h2o4gpu.utils.check_X_y`. Ignored if validate_separately
is not False.
Returns
-------
out : {ndarray, sparse matrix} or tuple of these
The validated input. A tuple is returned if `y` is not None.
"""
if y is None:
if self._get_tags()['requires_y']:
raise ValueError(
f"This {self.__class__.__name__} estimator "
f"requires y to be passed, but the target y is None."
)
X = check_array(X, **check_params)
out = X
else:
if validate_separately:
# We need this because some estimators validate X and y
# separately, and in general, separately calling check_array()
# on X and y isn't equivalent to just calling check_X_y()
# :(
check_X_params, check_y_params = validate_separately
X = check_array(X, **check_X_params)
y = check_array(y, **check_y_params)
else:
X, y = check_X_y(X, y, **check_params)
out = X, y
if check_params.get('ensure_2d', True):
self._check_n_features(X, reset=reset)
return out
@property
def _repr_html_(self):
"""HTML representation of estimator.
This is redundant with the logic of `_repr_mimebundle_`. The latter
should be favorted in the long term, `_repr_html_` is only
implemented for consumers who do not interpret `_repr_mimbundle_`.
"""
if get_config()["display"] != 'diagram':
raise AttributeError("_repr_html_ is only defined when the "
"'display' configuration option is set to "
"'diagram'")
return self._repr_html_inner
def _repr_html_inner(self):
"""This function is returned by the @property `_repr_html_` to make
`hasattr(estimator, "_repr_html_") return `True` or `False` depending
on `get_config()["display"]`.
"""
return estimator_html_repr(self)
def _repr_mimebundle_(self, **kwargs):
"""Mime bundle used by jupyter kernels to display estimator"""
output = {"text/plain": repr(self)}
if get_config()["display"] == 'diagram':
output["text/html"] = estimator_html_repr(self)
return output
class ClassifierMixin:
"""Mixin class for all classifiers in h2o4gpu."""
_estimator_type = "classifier"
def score(self, X, y, sample_weight=None):
"""
Return the mean accuracy on the given test data and labels.
In multi-label classification, this is the subset accuracy
which is a harsh metric since you require for each sample that
each label set be correctly predicted.
Parameters
----------
X : array-like of shape (n_samples, n_features)
Test samples.
y : array-like of shape (n_samples,) or (n_samples, n_outputs)
True labels for X.
sample_weight : array-like of shape (n_samples,), default=None
Sample weights.
Returns
-------
score : float
Mean accuracy of self.predict(X) wrt. y.
"""
from .metrics import accuracy_score
return accuracy_score(y, self.predict(X), sample_weight=sample_weight)
def _more_tags(self):
return {'requires_y': True}
class RegressorMixin:
"""Mixin class for all regression estimators in h2o4gpu."""
_estimator_type = "regressor"
def score(self, X, y, sample_weight=None):
"""Return the coefficient of determination R^2 of the prediction.
The coefficient R^2 is defined as (1 - u/v), where u is the residual
sum of squares ((y_true - y_pred) ** 2).sum() and v is the total
sum of squares ((y_true - y_true.mean()) ** 2).sum().
The best possible score is 1.0 and it can be negative (because the
model can be arbitrarily worse). A constant model that always
predicts the expected value of y, disregarding the input features,
would get a R^2 score of 0.0.
Parameters
----------
X : array-like of shape (n_samples, n_features)
Test samples. For some estimators this may be a
precomputed kernel matrix or a list of generic objects instead,
shape = (n_samples, n_samples_fitted),
where n_samples_fitted is the number of
samples used in the fitting for the estimator.
y : array-like of shape (n_samples,) or (n_samples, n_outputs)
True values for X.
sample_weight : array-like of shape (n_samples,), default=None
Sample weights.
Returns
-------
score : float
R^2 of self.predict(X) wrt. y.
Notes
-----
The R2 score used when calling ``score`` on a regressor uses
``multioutput='uniform_average'`` from version 0.23 to keep consistent
with default value of :func:`~h2o4gpu.metrics.r2_score`.
This influences the ``score`` method of all the multioutput
regressors (except for
:class:`~h2o4gpu.multioutput.MultiOutputRegressor`).
"""
from .metrics import r2_score
y_pred = self.predict(X)
return r2_score(y, y_pred, sample_weight=sample_weight)
def _more_tags(self):
return {'requires_y': True}
class ClusterMixin:
"""Mixin class for all cluster estimators in h2o4gpu."""
_estimator_type = "clusterer"
def fit_predict(self, X, y=None):
"""
Perform clustering on X and returns cluster labels.
Parameters
----------
X : array-like of shape (n_samples, n_features)
Input data.
y : Ignored
Not used, present for API consistency by convention.
Returns
-------
labels : ndarray of shape (n_samples,)
Cluster labels.
"""
# non-optimized default implementation; override when a better
# method is possible for a given clustering algorithm
self.fit(X)
return self.labels_
class BiclusterMixin:
"""Mixin class for all bicluster estimators in h2o4gpu"""
@property
def biclusters_(self):
"""Convenient way to get row and column indicators together.
Returns the ``rows_`` and ``columns_`` members.
"""
return self.rows_, self.columns_
def get_indices(self, i):
"""Row and column indices of the i'th bicluster.
Only works if ``rows_`` and ``columns_`` attributes exist.
Parameters
----------
i : int
The index of the cluster.
Returns
-------
row_ind : ndarray, dtype=np.intp
Indices of rows in the dataset that belong to the bicluster.
col_ind : ndarray, dtype=np.intp
Indices of columns in the dataset that belong to the bicluster.
"""
rows = self.rows_[i]
columns = self.columns_[i]
return np.nonzero(rows)[0], np.nonzero(columns)[0]
def get_shape(self, i):
"""Shape of the i'th bicluster.
Parameters
----------
i : int
The index of the cluster.
Returns
-------
shape : tuple (int, int)
Number of rows and columns (resp.) in the bicluster.
"""
indices = self.get_indices(i)
return tuple(len(i) for i in indices)
def get_submatrix(self, i, data):
"""Return the submatrix corresponding to bicluster `i`.
Parameters
----------
i : int
The index of the cluster.
data : array-like
The data.
Returns
-------
submatrix : ndarray
The submatrix corresponding to bicluster i.
Notes
-----
Works with sparse matrices. Only works if ``rows_`` and
``columns_`` attributes exist.
"""
from .utils.validation import check_array
data = check_array(data, accept_sparse='csr')
row_ind, col_ind = self.get_indices(i)
return data[row_ind[:, np.newaxis], col_ind]
class TransformerMixin:
"""Mixin class for all transformers in h2o4gpu."""
def fit_transform(self, X, y=None, **fit_params):
"""
Fit to data, then transform it.
Fits transformer to X and y with optional parameters fit_params
and returns a transformed version of X.
Parameters
----------
X : {array-like, sparse matrix, dataframe} of shape \
(n_samples, n_features)
y : ndarray of shape (n_samples,), default=None
Target values.
**fit_params : dict
Additional fit parameters.
Returns
-------
X_new : ndarray array of shape (n_samples, n_features_new)
Transformed array.
"""
# non-optimized default implementation; override when a better
# method is possible for a given clustering algorithm
if y is None:
# fit method of arity 1 (unsupervised transformation)
return self.fit(X, **fit_params).transform(X)
else:
# fit method of arity 2 (supervised transformation)
return self.fit(X, y, **fit_params).transform(X)
class DensityMixin:
"""Mixin class for all density estimators in h2o4gpu."""
_estimator_type = "DensityEstimator"
def score(self, X, y=None):
"""Return the score of the model on the data X
Parameters
----------
X : array-like of shape (n_samples, n_features)
y : Ignored
Not used, present for API consistency by convention.
Returns
-------
score : float
"""
pass
class OutlierMixin:
"""Mixin class for all outlier detection estimators in h2o4gpu."""
_estimator_type = "outlier_detector"
def fit_predict(self, X, y=None):
"""Perform fit on X and returns labels for X.
Returns -1 for outliers and 1 for inliers.
Parameters
----------
X : {array-like, sparse matrix, dataframe} of shape \
(n_samples, n_features)
y : Ignored
Not used, present for API consistency by convention.
Returns
-------
y : ndarray of shape (n_samples,)
1 for inliers, -1 for outliers.
"""
# override for transductive outlier detectors like LocalOulierFactor
return self.fit(X).predict(X)
class MetaEstimatorMixin:
_required_parameters = ["estimator"]
"""Mixin class for all meta estimators in h2o4gpu."""
class MultiOutputMixin:
"""Mixin to mark estimators that support multioutput."""
def _more_tags(self):
return {'multioutput': True}
class _UnstableArchMixin:
"""Mark estimators that are non-determinstic on 32bit or PowerPC"""
def _more_tags(self):
return {'non_deterministic': (
_IS_32BIT or platform.machine().startswith(('ppc', 'powerpc')))}
def is_classifier(estimator):
"""Return True if the given estimator is (probably) a classifier.
Parameters
----------
estimator : object
Estimator object to test.
Returns
-------
out : bool
True if estimator is a classifier and False otherwise.
"""
return getattr(estimator, "_estimator_type", None) == "classifier"
def is_regressor(estimator):
"""Return True if the given estimator is (probably) a regressor.
Parameters
----------
estimator : object
Estimator object to test.
Returns
-------
out : bool
True if estimator is a regressor and False otherwise.
"""
return getattr(estimator, "_estimator_type", None) == "regressor"
def is_outlier_detector(estimator):
"""Return True if the given estimator is (probably) an outlier detector.
Parameters
----------
estimator : object
Estimator object to test.
Returns
-------
out : bool
True if estimator is an outlier detector and False otherwise.
"""
return getattr(estimator, "_estimator_type", None) == "outlier_detector"