/usr/lib/python2.7/dist-packages/sklearn/base.py is in python-sklearn 0.14.1-3.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 | """Base class for all estimators."""
# Author: Gael Varoquaux <gael.varoquaux@normalesup.org>
# License: BSD 3 clause
import copy
import inspect
import warnings
import numpy as np
from scipy import sparse
from .externals import six
###############################################################################
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: estimator object, or list, tuple or set of objects
The estimator or group of estimators to be cloned
safe: boolean, optional
If safe is false, clone will fall back to a deepcopy 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'):
if not safe:
return copy.deepcopy(estimator)
else:
raise TypeError("Cannot clone object '%s' (type %s): "
"it does not seem to be a scikit-learn estimator a"
" it does not implement a 'get_params' methods."
% (repr(estimator), type(estimator)))
klass = estimator.__class__
new_object_params = estimator.get_params(deep=False)
for name, param in six.iteritems(new_object_params):
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 isinstance(param1, np.ndarray):
# For most ndarrays, we do not test for complete equality
if not isinstance(param2, type(param1)):
equality_test = False
elif (param1.ndim > 0
and param1.shape[0] > 0
and isinstance(param2, np.ndarray)
and param2.ndim > 0
and param2.shape[0] > 0):
equality_test = (
param1.shape == param2.shape
and param1.dtype == param2.dtype
# We have to use '.flat' for 2D arrays
and param1.flat[0] == param2.flat[0]
and param1.flat[-1] == param2.flat[-1]
)
else:
equality_test = np.all(param1 == param2)
elif sparse.issparse(param1):
# For sparse matrices equality doesn't work
if not sparse.issparse(param2):
equality_test = False
elif param1.size == 0 or param2.size == 0:
equality_test = (
param1.__class__ == param2.__class__
and param1.size == 0
and param2.size == 0
)
else:
equality_test = (
param1.__class__ == param2.__class__
and param1.data[0] == param2.data[0]
and param1.data[-1] == param2.data[-1]
and param1.nnz == param2.nnz
and param1.shape == param2.shape
)
else:
equality_test = new_object_params[name] == params_set[name]
if not equality_test:
raise RuntimeError('Cannot clone object %s, as the constructor '
'does not seem to set 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
The offset in characters to add at the begin of each line.
printer:
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(six.iteritems(params))):
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(object):
"""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, **kwargs).
"""
@classmethod
def _get_param_names(cls):
"""Get parameter names for the estimator"""
try:
# fetch the constructor or the original constructor before
# deprecation wrapping if any
init = getattr(cls.__init__, 'deprecated_original', cls.__init__)
# introspect the constructor arguments to find the model parameters
# to represent
args, varargs, kw, default = inspect.getargspec(init)
if not varargs is None:
raise RuntimeError("scikit-learn estimators should always "
"specify their parameters in the signature"
" of their __init__ (no varargs)."
" %s doesn't follow this convention."
% (cls, ))
# Remove 'self'
# XXX: This is going to fail if the init is a staticmethod, but
# who would do this?
args.pop(0)
except TypeError:
# No explicit __init__
args = []
args.sort()
return args
def get_params(self, deep=True):
"""Get parameters for this estimator.
Parameters
----------
deep: boolean, optional
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():
# We need deprecation warnings to always be on in order to
# catch deprecated param values.
# This is set in utils/__init__.py but it gets overwritten
# when running under python3 somehow.
warnings.simplefilter("always", DeprecationWarning)
try:
with warnings.catch_warnings(record=True) as w:
value = getattr(self, key, None)
if len(w) and w[0].category == DeprecationWarning:
# if the parameter is deprecated, don't show it
continue
finally:
warnings.filters.pop(0)
# XXX: should we rather test if instance of estimator?
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 former have parameters of the form
``<component>__<parameter>`` so that it's possible to update each
component of a nested object.
Returns
-------
self
"""
if not params:
# Simple optimisation to gain speed (inspect is slow)
return self
valid_params = self.get_params(deep=True)
for key, value in six.iteritems(params):
split = key.split('__', 1)
if len(split) > 1:
# nested objects case
name, sub_name = split
if not name in valid_params:
raise ValueError('Invalid parameter %s for estimator %s' %
(name, self))
sub_object = valid_params[name]
sub_object.set_params(**{sub_name: value})
else:
# simple objects case
if not key in valid_params:
raise ValueError('Invalid parameter %s ' 'for estimator %s'
% (key, self.__class__.__name__))
setattr(self, key, value)
return self
def __repr__(self):
class_name = self.__class__.__name__
return '%s(%s)' % (class_name, _pprint(self.get_params(deep=False),
offset=len(class_name),),)
def __str__(self):
class_name = self.__class__.__name__
return '%s(%s)' % (class_name,
_pprint(self.get_params(deep=True),
offset=len(class_name), printer=str,),)
###############################################################################
class ClassifierMixin(object):
"""Mixin class for all classifiers in scikit-learn."""
def score(self, X, y):
"""Returns the mean accuracy on the given test data and labels.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training set.
y : array-like, shape = [n_samples]
Labels for X.
Returns
-------
z : float
"""
from .metrics import accuracy_score
return accuracy_score(y, self.predict(X))
###############################################################################
class RegressorMixin(object):
"""Mixin class for all regression estimators in scikit-learn."""
def score(self, X, y):
"""Returns the coefficient of determination R^2 of the prediction.
The coefficient R^2 is defined as (1 - u/v), where u is the regression
sum of squares ((y_true - y_pred) ** 2).sum() and v is the residual
sum of squares ((y_true - y_true.mean()) ** 2).sum().
Best possible score is 1.0, lower values are worse.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training set.
y : array-like, shape = [n_samples]
Returns
-------
z : float
"""
from .metrics import r2_score
return r2_score(y, self.predict(X))
###############################################################################
class ClusterMixin(object):
"""Mixin class for all cluster estimators in scikit-learn."""
def fit_predict(self, X, y=None):
"""Performs clustering on X and returns cluster labels.
Parameters
----------
X : ndarray, shape (n_samples, n_features)
Input data.
Returns
-------
y : ndarray, 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(object):
"""Mixin class for all bicluster estimators in scikit-learn"""
@property
def biclusters_(self):
"""Convenient way to get row and column indicators together."""
return self.rows_, self.columns_
def get_indices(self, i):
"""Returns the row and column indices of bicluster `i`.
Only works if ``rows_`` and ``columns`` attributes exist.
"""
from .cluster.bicluster.utils import get_indices
return get_indices(self.rows_[i], self.columns_[i])
def get_shape(self, i):
"""Returns shape of bicluster `i`."""
from .cluster.bicluster.utils import get_shape
return get_shape(self.rows_[i], self.columns_[i])
def get_submatrix(self, i, data):
"""Returns the submatrix corresponding to bicluster `i`.
Works with sparse matrices. Only works if ``rows_`` and
``columns`` attributes exist.
"""
from .cluster.bicluster.utils import get_submatrix
return get_submatrix(self.rows_[i], self.columns_[i], data)
###############################################################################
class TransformerMixin(object):
"""Mixin class for all transformers in scikit-learn."""
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 : numpy array of shape [n_samples, n_features]
Training set.
y : numpy array of shape [n_samples]
Target values.
Returns
-------
X_new : numpy 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 MetaEstimatorMixin(object):
"""Mixin class for all meta estimators in scikit-learn."""
# this is just a tag for the moment
###############################################################################
# XXX: Temporary solution to figure out if an estimator is a classifier
def _get_sub_estimator(estimator):
"""Returns the final estimator if there is any."""
if hasattr(estimator, 'estimator'):
# GridSearchCV and other CV-tuned estimators
return _get_sub_estimator(estimator.estimator)
if hasattr(estimator, 'steps'):
# Pipeline
return _get_sub_estimator(estimator.steps[-1][1])
return estimator
def is_classifier(estimator):
"""Returns True if the given estimator is (probably) a classifier."""
estimator = _get_sub_estimator(estimator)
return isinstance(estimator, ClassifierMixin)
|