/usr/lib/python3/dist-packages/sklearn/ensemble/partial_dependence.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 | """Partial dependence plots for tree ensembles. """
# Authors: Peter Prettenhofer
# License: BSD 3 clause
from itertools import count
import numbers
import numpy as np
from scipy.stats.mstats import mquantiles
from ..utils.extmath import cartesian
from ..externals.joblib import Parallel, delayed
from ..externals import six
from ..externals.six.moves import map, range, zip
from ..utils import check_array
from ..tree._tree import DTYPE
from ._gradient_boosting import _partial_dependence_tree
from .gradient_boosting import BaseGradientBoosting
def _grid_from_X(X, percentiles=(0.05, 0.95), grid_resolution=100):
"""Generate a grid of points based on the ``percentiles of ``X``.
The grid is generated by placing ``grid_resolution`` equally
spaced points between the ``percentiles`` of each column
of ``X``.
Parameters
----------
X : ndarray
The data
percentiles : tuple of floats
The percentiles which are used to construct the extreme
values of the grid axes.
grid_resolution : int
The number of equally spaced points that are placed
on the grid.
Returns
-------
grid : ndarray
All data points on the grid; ``grid.shape[1] == X.shape[1]``
and ``grid.shape[0] == grid_resolution * X.shape[1]``.
axes : seq of ndarray
The axes with which the grid has been created.
"""
if len(percentiles) != 2:
raise ValueError('percentile must be tuple of len 2')
if not all(0. <= x <= 1. for x in percentiles):
raise ValueError('percentile values must be in [0, 1]')
axes = []
for col in range(X.shape[1]):
uniques = np.unique(X[:, col])
if uniques.shape[0] < grid_resolution:
# feature has low resolution use unique vals
axis = uniques
else:
emp_percentiles = mquantiles(X, prob=percentiles, axis=0)
# create axis based on percentiles and grid resolution
axis = np.linspace(emp_percentiles[0, col],
emp_percentiles[1, col],
num=grid_resolution, endpoint=True)
axes.append(axis)
return cartesian(axes), axes
def partial_dependence(gbrt, target_variables, grid=None, X=None,
percentiles=(0.05, 0.95), grid_resolution=100):
"""Partial dependence of ``target_variables``.
Partial dependence plots show the dependence between the joint values
of the ``target_variables`` and the function represented
by the ``gbrt``.
Read more in the :ref:`User Guide <partial_dependence>`.
Parameters
----------
gbrt : BaseGradientBoosting
A fitted gradient boosting model.
target_variables : array-like, dtype=int
The target features for which the partial dependecy should be
computed (size should be smaller than 3 for visual renderings).
grid : array-like, shape=(n_points, len(target_variables))
The grid of ``target_variables`` values for which the
partial dependecy should be evaluated (either ``grid`` or ``X``
must be specified).
X : array-like, shape=(n_samples, n_features)
The data on which ``gbrt`` was trained. It is used to generate
a ``grid`` for the ``target_variables``. The ``grid`` comprises
``grid_resolution`` equally spaced points between the two
``percentiles``.
percentiles : (low, high), default=(0.05, 0.95)
The lower and upper percentile used create the extreme values
for the ``grid``. Only if ``X`` is not None.
grid_resolution : int, default=100
The number of equally spaced points on the ``grid``.
Returns
-------
pdp : array, shape=(n_classes, n_points)
The partial dependence function evaluated on the ``grid``.
For regression and binary classification ``n_classes==1``.
axes : seq of ndarray or None
The axes with which the grid has been created or None if
the grid has been given.
Examples
--------
>>> samples = [[0, 0, 2], [1, 0, 0]]
>>> labels = [0, 1]
>>> from sklearn.ensemble import GradientBoostingClassifier
>>> gb = GradientBoostingClassifier(random_state=0).fit(samples, labels)
>>> kwargs = dict(X=samples, percentiles=(0, 1), grid_resolution=2)
>>> partial_dependence(gb, [0], **kwargs) # doctest: +SKIP
(array([[-4.52..., 4.52...]]), [array([ 0., 1.])])
"""
if not isinstance(gbrt, BaseGradientBoosting):
raise ValueError('gbrt has to be an instance of BaseGradientBoosting')
if gbrt.estimators_.shape[0] == 0:
raise ValueError('Call %s.fit before partial_dependence' %
gbrt.__class__.__name__)
if (grid is None and X is None) or (grid is not None and X is not None):
raise ValueError('Either grid or X must be specified')
target_variables = np.asarray(target_variables, dtype=np.int32,
order='C').ravel()
if any([not (0 <= fx < gbrt.n_features) for fx in target_variables]):
raise ValueError('target_variables must be in [0, %d]'
% (gbrt.n_features - 1))
if X is not None:
X = check_array(X, dtype=DTYPE, order='C')
grid, axes = _grid_from_X(X[:, target_variables], percentiles,
grid_resolution)
else:
assert grid is not None
# dont return axes if grid is given
axes = None
# grid must be 2d
if grid.ndim == 1:
grid = grid[:, np.newaxis]
if grid.ndim != 2:
raise ValueError('grid must be 2d but is %dd' % grid.ndim)
grid = np.asarray(grid, dtype=DTYPE, order='C')
assert grid.shape[1] == target_variables.shape[0]
n_trees_per_stage = gbrt.estimators_.shape[1]
n_estimators = gbrt.estimators_.shape[0]
pdp = np.zeros((n_trees_per_stage, grid.shape[0],), dtype=np.float64,
order='C')
for stage in range(n_estimators):
for k in range(n_trees_per_stage):
tree = gbrt.estimators_[stage, k].tree_
_partial_dependence_tree(tree, grid, target_variables,
gbrt.learning_rate, pdp[k])
return pdp, axes
def plot_partial_dependence(gbrt, X, features, feature_names=None,
label=None, n_cols=3, grid_resolution=100,
percentiles=(0.05, 0.95), n_jobs=1,
verbose=0, ax=None, line_kw=None,
contour_kw=None, **fig_kw):
"""Partial dependence plots for ``features``.
The ``len(features)`` plots are arranged in a grid with ``n_cols``
columns. Two-way partial dependence plots are plotted as contour
plots.
Read more in the :ref:`User Guide <partial_dependence>`.
Parameters
----------
gbrt : BaseGradientBoosting
A fitted gradient boosting model.
X : array-like, shape=(n_samples, n_features)
The data on which ``gbrt`` was trained.
features : seq of tuples or ints
If seq[i] is an int or a tuple with one int value, a one-way
PDP is created; if seq[i] is a tuple of two ints, a two-way
PDP is created.
feature_names : seq of str
Name of each feature; feature_names[i] holds
the name of the feature with index i.
label : object
The class label for which the PDPs should be computed.
Only if gbrt is a multi-class model. Must be in ``gbrt.classes_``.
n_cols : int
The number of columns in the grid plot (default: 3).
percentiles : (low, high), default=(0.05, 0.95)
The lower and upper percentile used to create the extreme values
for the PDP axes.
grid_resolution : int, default=100
The number of equally spaced points on the axes.
n_jobs : int
The number of CPUs to use to compute the PDs. -1 means 'all CPUs'.
Defaults to 1.
verbose : int
Verbose output during PD computations. Defaults to 0.
ax : Matplotlib axis object, default None
An axis object onto which the plots will be drawn.
line_kw : dict
Dict with keywords passed to the ``pylab.plot`` call.
For one-way partial dependence plots.
contour_kw : dict
Dict with keywords passed to the ``pylab.plot`` call.
For two-way partial dependence plots.
fig_kw : dict
Dict with keywords passed to the figure() call.
Note that all keywords not recognized above will be automatically
included here.
Returns
-------
fig : figure
The Matplotlib Figure object.
axs : seq of Axis objects
A seq of Axis objects, one for each subplot.
Examples
--------
>>> from sklearn.datasets import make_friedman1
>>> from sklearn.ensemble import GradientBoostingRegressor
>>> X, y = make_friedman1()
>>> clf = GradientBoostingRegressor(n_estimators=10).fit(X, y)
>>> fig, axs = plot_partial_dependence(clf, X, [0, (0, 1)]) #doctest: +SKIP
...
"""
import matplotlib.pyplot as plt
from matplotlib import transforms
from matplotlib.ticker import MaxNLocator
from matplotlib.ticker import ScalarFormatter
if not isinstance(gbrt, BaseGradientBoosting):
raise ValueError('gbrt has to be an instance of BaseGradientBoosting')
if gbrt.estimators_.shape[0] == 0:
raise ValueError('Call %s.fit before partial_dependence' %
gbrt.__class__.__name__)
# set label_idx for multi-class GBRT
if hasattr(gbrt, 'classes_') and np.size(gbrt.classes_) > 2:
if label is None:
raise ValueError('label is not given for multi-class PDP')
label_idx = np.searchsorted(gbrt.classes_, label)
if gbrt.classes_[label_idx] != label:
raise ValueError('label %s not in ``gbrt.classes_``' % str(label))
else:
# regression and binary classification
label_idx = 0
X = check_array(X, dtype=DTYPE, order='C')
if gbrt.n_features != X.shape[1]:
raise ValueError('X.shape[1] does not match gbrt.n_features')
if line_kw is None:
line_kw = {'color': 'green'}
if contour_kw is None:
contour_kw = {}
# convert feature_names to list
if feature_names is None:
# if not feature_names use fx indices as name
feature_names = [str(i) for i in range(gbrt.n_features)]
elif isinstance(feature_names, np.ndarray):
feature_names = feature_names.tolist()
def convert_feature(fx):
if isinstance(fx, six.string_types):
try:
fx = feature_names.index(fx)
except ValueError:
raise ValueError('Feature %s not in feature_names' % fx)
return fx
# convert features into a seq of int tuples
tmp_features = []
for fxs in features:
if isinstance(fxs, (numbers.Integral,) + six.string_types):
fxs = (fxs,)
try:
fxs = np.array([convert_feature(fx) for fx in fxs], dtype=np.int32)
except TypeError:
raise ValueError('features must be either int, str, or tuple '
'of int/str')
if not (1 <= np.size(fxs) <= 2):
raise ValueError('target features must be either one or two')
tmp_features.append(fxs)
features = tmp_features
names = []
try:
for fxs in features:
l = []
# explicit loop so "i" is bound for exception below
for i in fxs:
l.append(feature_names[i])
names.append(l)
except IndexError:
raise ValueError('features[i] must be in [0, n_features) '
'but was %d' % i)
# compute PD functions
pd_result = Parallel(n_jobs=n_jobs, verbose=verbose)(
delayed(partial_dependence)(gbrt, fxs, X=X,
grid_resolution=grid_resolution,
percentiles=percentiles)
for fxs in features)
# get global min and max values of PD grouped by plot type
pdp_lim = {}
for pdp, axes in pd_result:
min_pd, max_pd = pdp[label_idx].min(), pdp[label_idx].max()
n_fx = len(axes)
old_min_pd, old_max_pd = pdp_lim.get(n_fx, (min_pd, max_pd))
min_pd = min(min_pd, old_min_pd)
max_pd = max(max_pd, old_max_pd)
pdp_lim[n_fx] = (min_pd, max_pd)
# create contour levels for two-way plots
if 2 in pdp_lim:
Z_level = np.linspace(*pdp_lim[2], num=8)
if ax is None:
fig = plt.figure(**fig_kw)
else:
fig = ax.get_figure()
fig.clear()
n_cols = min(n_cols, len(features))
n_rows = int(np.ceil(len(features) / float(n_cols)))
axs = []
for i, fx, name, (pdp, axes) in zip(count(), features, names,
pd_result):
ax = fig.add_subplot(n_rows, n_cols, i + 1)
if len(axes) == 1:
ax.plot(axes[0], pdp[label_idx].ravel(), **line_kw)
else:
# make contour plot
assert len(axes) == 2
XX, YY = np.meshgrid(axes[0], axes[1])
Z = pdp[label_idx].reshape(list(map(np.size, axes))).T
CS = ax.contour(XX, YY, Z, levels=Z_level, linewidths=0.5,
colors='k')
ax.contourf(XX, YY, Z, levels=Z_level, vmax=Z_level[-1],
vmin=Z_level[0], alpha=0.75, **contour_kw)
ax.clabel(CS, fmt='%2.2f', colors='k', fontsize=10, inline=True)
# plot data deciles + axes labels
deciles = mquantiles(X[:, fx[0]], prob=np.arange(0.1, 1.0, 0.1))
trans = transforms.blended_transform_factory(ax.transData,
ax.transAxes)
ylim = ax.get_ylim()
ax.vlines(deciles, [0], 0.05, transform=trans, color='k')
ax.set_xlabel(name[0])
ax.set_ylim(ylim)
# prevent x-axis ticks from overlapping
ax.xaxis.set_major_locator(MaxNLocator(nbins=6, prune='lower'))
tick_formatter = ScalarFormatter()
tick_formatter.set_powerlimits((-3, 4))
ax.xaxis.set_major_formatter(tick_formatter)
if len(axes) > 1:
# two-way PDP - y-axis deciles + labels
deciles = mquantiles(X[:, fx[1]], prob=np.arange(0.1, 1.0, 0.1))
trans = transforms.blended_transform_factory(ax.transAxes,
ax.transData)
xlim = ax.get_xlim()
ax.hlines(deciles, [0], 0.05, transform=trans, color='k')
ax.set_ylabel(name[1])
# hline erases xlim
ax.set_xlim(xlim)
else:
ax.set_ylabel('Partial dependence')
if len(axes) == 1:
ax.set_ylim(pdp_lim[1])
axs.append(ax)
fig.subplots_adjust(bottom=0.15, top=0.7, left=0.1, right=0.95, wspace=0.4,
hspace=0.3)
return fig, axs
|