/usr/lib/python3/dist-packages/sklearn/manifold/mds.py is in python3-sklearn 0.17.0-4.
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 | """
Multi-dimensional Scaling (MDS)
"""
# author: Nelle Varoquaux <nelle.varoquaux@gmail.com>
# Licence: BSD
import numpy as np
import warnings
from ..base import BaseEstimator
from ..metrics import euclidean_distances
from ..utils import check_random_state, check_array, check_symmetric
from ..externals.joblib import Parallel
from ..externals.joblib import delayed
from ..isotonic import IsotonicRegression
def _smacof_single(similarities, metric=True, n_components=2, init=None,
max_iter=300, verbose=0, eps=1e-3, random_state=None):
"""
Computes multidimensional scaling using SMACOF algorithm
Parameters
----------
similarities: symmetric ndarray, shape [n * n]
similarities between the points
metric: boolean, optional, default: True
compute metric or nonmetric SMACOF algorithm
n_components: int, optional, default: 2
number of dimension in which to immerse the similarities
overwritten if initial array is provided.
init: {None or ndarray}, optional
if None, randomly chooses the initial configuration
if ndarray, initialize the SMACOF algorithm with this array
max_iter: int, optional, default: 300
Maximum number of iterations of the SMACOF algorithm for a single run
verbose: int, optional, default: 0
level of verbosity
eps: float, optional, default: 1e-6
relative tolerance w.r.t stress to declare converge
random_state: integer or numpy.RandomState, optional
The generator used to initialize the centers. If an integer is
given, it fixes the seed. Defaults to the global numpy random
number generator.
Returns
-------
X: ndarray (n_samples, n_components), float
coordinates of the n_samples points in a n_components-space
stress_: float
The final value of the stress (sum of squared distance of the
disparities and the distances for all constrained points)
n_iter : int
Number of iterations run.
"""
similarities = check_symmetric(similarities, raise_exception=True)
n_samples = similarities.shape[0]
random_state = check_random_state(random_state)
sim_flat = ((1 - np.tri(n_samples)) * similarities).ravel()
sim_flat_w = sim_flat[sim_flat != 0]
if init is None:
# Randomly choose initial configuration
X = random_state.rand(n_samples * n_components)
X = X.reshape((n_samples, n_components))
else:
# overrides the parameter p
n_components = init.shape[1]
if n_samples != init.shape[0]:
raise ValueError("init matrix should be of shape (%d, %d)" %
(n_samples, n_components))
X = init
old_stress = None
ir = IsotonicRegression()
for it in range(max_iter):
# Compute distance and monotonic regression
dis = euclidean_distances(X)
if metric:
disparities = similarities
else:
dis_flat = dis.ravel()
# similarities with 0 are considered as missing values
dis_flat_w = dis_flat[sim_flat != 0]
# Compute the disparities using a monotonic regression
disparities_flat = ir.fit_transform(sim_flat_w, dis_flat_w)
disparities = dis_flat.copy()
disparities[sim_flat != 0] = disparities_flat
disparities = disparities.reshape((n_samples, n_samples))
disparities *= np.sqrt((n_samples * (n_samples - 1) / 2) /
(disparities ** 2).sum())
# Compute stress
stress = ((dis.ravel() - disparities.ravel()) ** 2).sum() / 2
# Update X using the Guttman transform
dis[dis == 0] = 1e-5
ratio = disparities / dis
B = - ratio
B[np.arange(len(B)), np.arange(len(B))] += ratio.sum(axis=1)
X = 1. / n_samples * np.dot(B, X)
dis = np.sqrt((X ** 2).sum(axis=1)).sum()
if verbose >= 2:
print('it: %d, stress %s' % (it, stress))
if old_stress is not None:
if(old_stress - stress / dis) < eps:
if verbose:
print('breaking at iteration %d with stress %s' % (it,
stress))
break
old_stress = stress / dis
return X, stress, it + 1
def smacof(similarities, metric=True, n_components=2, init=None, n_init=8,
n_jobs=1, max_iter=300, verbose=0, eps=1e-3, random_state=None,
return_n_iter=False):
"""
Computes multidimensional scaling using SMACOF (Scaling by Majorizing a
Complicated Function) algorithm
The SMACOF algorithm is a multidimensional scaling algorithm: it minimizes
a objective function, the *stress*, using a majorization technique. The
Stress Majorization, also known as the Guttman Transform, guarantees a
monotone convergence of Stress, and is more powerful than traditional
techniques such as gradient descent.
The SMACOF algorithm for metric MDS can summarized by the following steps:
1. Set an initial start configuration, randomly or not.
2. Compute the stress
3. Compute the Guttman Transform
4. Iterate 2 and 3 until convergence.
The nonmetric algorithm adds a monotonic regression steps before computing
the stress.
Parameters
----------
similarities : symmetric ndarray, shape (n_samples, n_samples)
similarities between the points
metric : boolean, optional, default: True
compute metric or nonmetric SMACOF algorithm
n_components : int, optional, default: 2
number of dimension in which to immerse the similarities
overridden if initial array is provided.
init : {None or ndarray of shape (n_samples, n_components)}, optional
if None, randomly chooses the initial configuration
if ndarray, initialize the SMACOF algorithm with this array
n_init : int, optional, default: 8
Number of time the smacof algorithm will be run with different
initialisation. The final results will be the best output of the
n_init consecutive runs in terms of stress.
n_jobs : int, optional, default: 1
The number of jobs to use for the computation. This works by breaking
down the pairwise matrix into n_jobs even slices and computing them in
parallel.
If -1 all CPUs are used. If 1 is given, no parallel computing code is
used at all, which is useful for debugging. For n_jobs below -1,
(n_cpus + 1 + n_jobs) are used. Thus for n_jobs = -2, all CPUs but one
are used.
max_iter : int, optional, default: 300
Maximum number of iterations of the SMACOF algorithm for a single run
verbose : int, optional, default: 0
level of verbosity
eps : float, optional, default: 1e-6
relative tolerance w.r.t stress to declare converge
random_state : integer or numpy.RandomState, optional
The generator used to initialize the centers. If an integer is
given, it fixes the seed. Defaults to the global numpy random
number generator.
return_n_iter : bool
Whether or not to return the number of iterations.
Returns
-------
X : ndarray (n_samples,n_components)
Coordinates of the n_samples points in a n_components-space
stress : float
The final value of the stress (sum of squared distance of the
disparities and the distances for all constrained points)
n_iter : int
The number of iterations corresponding to the best stress.
Returned only if `return_n_iter` is set to True.
Notes
-----
"Modern Multidimensional Scaling - Theory and Applications" Borg, I.;
Groenen P. Springer Series in Statistics (1997)
"Nonmetric multidimensional scaling: a numerical method" Kruskal, J.
Psychometrika, 29 (1964)
"Multidimensional scaling by optimizing goodness of fit to a nonmetric
hypothesis" Kruskal, J. Psychometrika, 29, (1964)
"""
similarities = check_array(similarities)
random_state = check_random_state(random_state)
if hasattr(init, '__array__'):
init = np.asarray(init).copy()
if not n_init == 1:
warnings.warn(
'Explicit initial positions passed: '
'performing only one init of the MDS instead of %d'
% n_init)
n_init = 1
best_pos, best_stress = None, None
if n_jobs == 1:
for it in range(n_init):
pos, stress, n_iter_ = _smacof_single(
similarities, metric=metric,
n_components=n_components, init=init,
max_iter=max_iter, verbose=verbose,
eps=eps, random_state=random_state)
if best_stress is None or stress < best_stress:
best_stress = stress
best_pos = pos.copy()
best_iter = n_iter_
else:
seeds = random_state.randint(np.iinfo(np.int32).max, size=n_init)
results = Parallel(n_jobs=n_jobs, verbose=max(verbose - 1, 0))(
delayed(_smacof_single)(
similarities, metric=metric, n_components=n_components,
init=init, max_iter=max_iter, verbose=verbose, eps=eps,
random_state=seed)
for seed in seeds)
positions, stress, n_iters = zip(*results)
best = np.argmin(stress)
best_stress = stress[best]
best_pos = positions[best]
best_iter = n_iters[best]
if return_n_iter:
return best_pos, best_stress, best_iter
else:
return best_pos, best_stress
class MDS(BaseEstimator):
"""Multidimensional scaling
Read more in the :ref:`User Guide <multidimensional_scaling>`.
Parameters
----------
metric : boolean, optional, default: True
compute metric or nonmetric SMACOF (Scaling by Majorizing a
Complicated Function) algorithm
n_components : int, optional, default: 2
number of dimension in which to immerse the similarities
overridden if initial array is provided.
n_init : int, optional, default: 4
Number of time the smacof algorithm will be run with different
initialisation. The final results will be the best output of the
n_init consecutive runs in terms of stress.
max_iter : int, optional, default: 300
Maximum number of iterations of the SMACOF algorithm for a single run
verbose : int, optional, default: 0
level of verbosity
eps : float, optional, default: 1e-6
relative tolerance w.r.t stress to declare converge
n_jobs : int, optional, default: 1
The number of jobs to use for the computation. This works by breaking
down the pairwise matrix into n_jobs even slices and computing them in
parallel.
If -1 all CPUs are used. If 1 is given, no parallel computing code is
used at all, which is useful for debugging. For n_jobs below -1,
(n_cpus + 1 + n_jobs) are used. Thus for n_jobs = -2, all CPUs but one
are used.
random_state : integer or numpy.RandomState, optional
The generator used to initialize the centers. If an integer is
given, it fixes the seed. Defaults to the global numpy random
number generator.
dissimilarity : string
Which dissimilarity measure to use.
Supported are 'euclidean' and 'precomputed'.
Attributes
----------
embedding_ : array-like, shape [n_components, n_samples]
Stores the position of the dataset in the embedding space
stress_ : float
The final value of the stress (sum of squared distance of the
disparities and the distances for all constrained points)
References
----------
"Modern Multidimensional Scaling - Theory and Applications" Borg, I.;
Groenen P. Springer Series in Statistics (1997)
"Nonmetric multidimensional scaling: a numerical method" Kruskal, J.
Psychometrika, 29 (1964)
"Multidimensional scaling by optimizing goodness of fit to a nonmetric
hypothesis" Kruskal, J. Psychometrika, 29, (1964)
"""
def __init__(self, n_components=2, metric=True, n_init=4,
max_iter=300, verbose=0, eps=1e-3, n_jobs=1,
random_state=None, dissimilarity="euclidean"):
self.n_components = n_components
self.dissimilarity = dissimilarity
self.metric = metric
self.n_init = n_init
self.max_iter = max_iter
self.eps = eps
self.verbose = verbose
self.n_jobs = n_jobs
self.random_state = random_state
@property
def _pairwise(self):
return self.kernel == "precomputed"
def fit(self, X, y=None, init=None):
"""
Computes the position of the points in the embedding space
Parameters
----------
X : array, shape=[n_samples, n_features], or [n_samples, n_samples] \
if dissimilarity='precomputed'
Input data.
init : {None or ndarray, shape (n_samples,)}, optional
If None, randomly chooses the initial configuration
if ndarray, initialize the SMACOF algorithm with this array.
"""
self.fit_transform(X, init=init)
return self
def fit_transform(self, X, y=None, init=None):
"""
Fit the data from X, and returns the embedded coordinates
Parameters
----------
X : array, shape=[n_samples, n_features], or [n_samples, n_samples] \
if dissimilarity='precomputed'
Input data.
init : {None or ndarray, shape (n_samples,)}, optional
If None, randomly chooses the initial configuration
if ndarray, initialize the SMACOF algorithm with this array.
"""
X = check_array(X)
if X.shape[0] == X.shape[1] and self.dissimilarity != "precomputed":
warnings.warn("The MDS API has changed. ``fit`` now constructs an"
" dissimilarity matrix from data. To use a custom "
"dissimilarity matrix, set "
"``dissimilarity='precomputed'``.")
if self.dissimilarity == "precomputed":
self.dissimilarity_matrix_ = X
elif self.dissimilarity == "euclidean":
self.dissimilarity_matrix_ = euclidean_distances(X)
else:
raise ValueError("Proximity must be 'precomputed' or 'euclidean'."
" Got %s instead" % str(self.dissimilarity))
self.embedding_, self.stress_, self.n_iter_ = smacof(
self.dissimilarity_matrix_, metric=self.metric,
n_components=self.n_components, init=init, n_init=self.n_init,
n_jobs=self.n_jobs, max_iter=self.max_iter, verbose=self.verbose,
eps=self.eps, random_state=self.random_state,
return_n_iter=True)
return self.embedding_
|