def cross_val_predict_proba(estimator, X, y, groups = None, cv = None,
n_jobs = 1, verbose = 0, fit_params = None, pre_dispatch = '2*n_jobs'):
'''
Gets class probability predictions for test examples
over cross validations runs.
Adapted from mne.decoding.base.cross_val_multiscore(). See that func's
documentation for details on inputs.
'''
import time
import numbers
from mne.parallel import parallel_func
from mne.fixes import is_classifier
from sklearn.base import clone
from sklearn.utils import indexable
from sklearn.model_selection._split import check_cv
# check arguments
X, y, groups = indexable(X, y, groups)
cv = check_cv(cv, y, classifier = is_classifier(estimator))
cv_iter = list(cv.split(X, y, groups))
# We clone the estimator to make sure that all the folds are
# independent, and that it is pickle-able.
# Note: this parallelization is implemented using MNE Parallel
parallel, p_func, n_jobs = parallel_func(_predict_proba, n_jobs,
pre_dispatch = pre_dispatch)
preds = parallel(p_func(clone(estimator), X, y, train, test,
0, None, fit_params)
for train, test in cv_iter)
# flatten over parallel output
y_hat = np.concatenate([p[0] for p in preds], axis = 0)
is_y_true = True
try:
y_true = np.concatenate([p[1] for p in preds], axis = 0)
except: # learner was unsupervised
is_y_true = False
# return results
if is_y_true:
return y_hat, y_true
else:
return y_hat
def test_get_coef():
"""Test getting linear coefficients (filters/patterns) from estimators."""
from sklearn.base import TransformerMixin, BaseEstimator
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import Ridge, LinearRegression
lm = LinearModel()
assert (is_classifier(lm))
lm = LinearModel(Ridge())
assert (is_regressor(lm))
# Define a classifier, an invertible transformer and an non-invertible one.
class Clf(BaseEstimator):
def fit(self, X, y):
return self
class NoInv(TransformerMixin):
def fit(self, X, y):
return self
def transform(self, X):
return X
class Inv(NoInv):
def inverse_transform(self, X):
return X
X, y, A = _make_data(n_samples=2000, n_features=3, n_targets=1)
# I. Test inverse function
# Check that we retrieve the right number of inverse functions even if
# there are nested pipelines
good_estimators = [
(1, make_pipeline(Inv(), Clf())),
(2, make_pipeline(Inv(), Inv(), Clf())),
(3, make_pipeline(Inv(), make_pipeline(Inv(), Inv()), Clf())),
]
for expected_n, est in good_estimators:
est.fit(X, y)
assert (expected_n == len(_get_inverse_funcs(est)))
bad_estimators = [
Clf(), # no preprocessing
Inv(), # final estimator isn't classifier
make_pipeline(NoInv(), Clf()), # first step isn't invertible
make_pipeline(Inv(), make_pipeline(Inv(), NoInv()),
Clf()), # nested step isn't invertible
]
for est in bad_estimators:
est.fit(X, y)
invs = _get_inverse_funcs(est)
assert_equal(invs, list())
# II. Test get coef for simple estimator and pipelines
for clf in (lm, make_pipeline(StandardScaler(), lm)):
clf.fit(X, y)
# Retrieve final linear model
filters = get_coef(clf, 'filters_', False)
if hasattr(clf, 'steps'):
coefs = clf.steps[-1][-1].model.coef_
else:
coefs = clf.model.coef_
assert_array_equal(filters, coefs[0])
patterns = get_coef(clf, 'patterns_', False)
assert (filters[0] != patterns[0])
n_chans = X.shape[1]
assert_array_equal(filters.shape, patterns.shape, [n_chans, n_chans])
# Inverse transform linear model
filters_inv = get_coef(clf, 'filters_', True)
assert (filters[0] != filters_inv[0])
patterns_inv = get_coef(clf, 'patterns_', True)
assert (patterns[0] != patterns_inv[0])
# Check with search_light and combination of preprocessing ending with sl:
slider = SlidingEstimator(make_pipeline(StandardScaler(), lm))
X = np.transpose([X, -X], [1, 2, 0]) # invert X across 2 time samples
clfs = (make_pipeline(Scaler(None, scalings='mean'), slider), slider)
for clf in clfs:
clf.fit(X, y)
for inverse in (True, False):
patterns = get_coef(clf, 'patterns_', inverse)
filters = get_coef(clf, 'filters_', inverse)
assert_array_equal(filters.shape, patterns.shape, X.shape[1:])
# the two time samples get inverted patterns
assert_equal(patterns[0, 0], -patterns[0, 1])
for t in [0, 1]:
assert_array_equal(get_coef(clf.estimators_[t], 'filters_', False),
filters[:, t])
# Check patterns with more than 1 regressor
for n_features in [1, 5]:
for n_targets in [1, 3]:
X, Y, A = _make_data(n_samples=5000, n_features=5, n_targets=3)
lm = LinearModel(LinearRegression()).fit(X, Y)
assert_array_equal(lm.filters_.shape, lm.patterns_.shape)
assert_array_equal(lm.filters_.shape, [3, 5])
assert_array_almost_equal(A, lm.patterns_.T, decimal=2)
lm = LinearModel(Ridge(alpha=1)).fit(X, Y)
assert_array_almost_equal(A, lm.patterns_.T, decimal=2)
# Check can pass fitting parameters
lm.fit(X, Y, sample_weight=np.ones(len(Y)))
def test_get_coef():
"""Test getting linear coefficients (filters/patterns) from estimators."""
from sklearn.base import TransformerMixin, BaseEstimator
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler
from sklearn import svm
from sklearn.linear_model import Ridge
from sklearn.model_selection import GridSearchCV
lm_classification = LinearModel()
assert (is_classifier(lm_classification))
lm_regression = LinearModel(Ridge())
assert (is_regressor(lm_regression))
parameters = {'kernel': ['linear'], 'C': [1, 10]}
lm_gs_classification = LinearModel(
GridSearchCV(svm.SVC(), parameters, cv=2, refit=True, n_jobs=1))
assert (is_classifier(lm_gs_classification))
lm_gs_regression = LinearModel(
GridSearchCV(svm.SVR(), parameters, cv=2, refit=True, n_jobs=1))
assert (is_regressor(lm_gs_regression))
# Define a classifier, an invertible transformer and an non-invertible one.
class Clf(BaseEstimator):
def fit(self, X, y):
return self
class NoInv(TransformerMixin):
def fit(self, X, y):
return self
def transform(self, X):
return X
class Inv(NoInv):
def inverse_transform(self, X):
return X
X, y, A = _make_data(n_samples=1000, n_features=3, n_targets=1)
# I. Test inverse function
# Check that we retrieve the right number of inverse functions even if
# there are nested pipelines
good_estimators = [
(1, make_pipeline(Inv(), Clf())),
(2, make_pipeline(Inv(), Inv(), Clf())),
(3, make_pipeline(Inv(), make_pipeline(Inv(), Inv()), Clf())),
]
for expected_n, est in good_estimators:
est.fit(X, y)
assert (expected_n == len(_get_inverse_funcs(est)))
bad_estimators = [
Clf(), # no preprocessing
Inv(), # final estimator isn't classifier
make_pipeline(NoInv(), Clf()), # first step isn't invertible
make_pipeline(Inv(), make_pipeline(Inv(), NoInv()),
Clf()), # nested step isn't invertible
]
for est in bad_estimators:
est.fit(X, y)
invs = _get_inverse_funcs(est)
assert_equal(invs, list())
# II. Test get coef for classification/regression estimators and pipelines
rng = np.random.RandomState(0)
for clf in (lm_regression, lm_gs_classification,
make_pipeline(StandardScaler(), lm_classification),
make_pipeline(StandardScaler(), lm_gs_regression)):
# generate some categorical/continuous data
# according to the type of estimator.
if is_classifier(clf):
n, n_features = 1000, 3
X = rng.rand(n, n_features)
y = np.arange(n) % 2
else:
X, y, A = _make_data(n_samples=1000, n_features=3, n_targets=1)
y = np.ravel(y)
clf.fit(X, y)
# Retrieve final linear model
filters = get_coef(clf, 'filters_', False)
if hasattr(clf, 'steps'):
if hasattr(clf.steps[-1][-1].model, 'best_estimator_'):
# Linear Model with GridSearchCV
coefs = clf.steps[-1][-1].model.best_estimator_.coef_
else:
# Standard Linear Model
coefs = clf.steps[-1][-1].model.coef_
else:
if hasattr(clf.model, 'best_estimator_'):
# Linear Model with GridSearchCV
coefs = clf.model.best_estimator_.coef_
else:
# Standard Linear Model
coefs = clf.model.coef_
if coefs.ndim == 2 and coefs.shape[0] == 1:
coefs = coefs[0]
assert_array_equal(filters, coefs)
patterns = get_coef(clf, 'patterns_', False)
assert (filters[0] != patterns[0])
n_chans = X.shape[1]
assert_array_equal(filters.shape, patterns.shape, [n_chans, n_chans])
# Inverse transform linear model
filters_inv = get_coef(clf, 'filters_', True)
assert (filters[0] != filters_inv[0])
patterns_inv = get_coef(clf, 'patterns_', True)
assert (patterns[0] != patterns_inv[0])
def test_generalization_across_time():
"""Test time generalization decoding."""
from sklearn.svm import SVC
# KernelRidge is used for testing 1) regression analyses 2) n-dimensional
# predictions.
from sklearn.kernel_ridge import KernelRidge
from sklearn.preprocessing import LabelEncoder
from sklearn.metrics import roc_auc_score, mean_squared_error
epochs = make_epochs()
y_4classes = np.hstack((epochs.events[:7, 2], epochs.events[7:, 2] + 1))
if check_version('sklearn', '0.18'):
from sklearn.model_selection import (KFold, StratifiedKFold,
ShuffleSplit, LeaveOneGroupOut)
cv = LeaveOneGroupOut()
cv_shuffle = ShuffleSplit()
# XXX we cannot pass any other parameters than X and y to cv.split
# so we have to build it before hand
cv_lolo = [(train, test) for train, test in cv.split(
y_4classes, y_4classes, y_4classes)]
# With sklearn >= 0.17, `clf` can be identified as a regressor, and
# the scoring metrics can therefore be automatically assigned.
scorer_regress = None
else:
from sklearn.cross_validation import (KFold, StratifiedKFold,
ShuffleSplit, LeaveOneLabelOut)
cv_shuffle = ShuffleSplit(len(epochs))
cv_lolo = LeaveOneLabelOut(y_4classes)
# With sklearn < 0.17, `clf` cannot be identified as a regressor, and
# therefore the scoring metrics cannot be automatically assigned.
scorer_regress = mean_squared_error
# Test default running
with warnings.catch_warnings(record=True): # dep
gat = GeneralizationAcrossTime(picks='foo')
assert_equal("<GAT | no fit, no prediction, no score>", "%s" % gat)
assert_raises(ValueError, gat.fit, epochs)
with warnings.catch_warnings(record=True):
# check classic fit + check manual picks
gat.picks = [0]
gat.fit(epochs)
# check optional y as array
gat.picks = None
gat.fit(epochs, y=epochs.events[:, 2])
# check optional y as list
gat.fit(epochs, y=epochs.events[:, 2].tolist())
assert_equal(len(gat.picks_), len(gat.ch_names), 1)
assert_equal("<GAT | fitted, start : -0.200 (s), stop : 0.499 (s), no "
"prediction, no score>", '%s' % gat)
assert_equal(gat.ch_names, epochs.ch_names)
# test different predict function:
with warnings.catch_warnings(record=True): # dep
gat = GeneralizationAcrossTime(predict_method='decision_function')
gat.fit(epochs)
# With classifier, the default cv is StratifiedKFold
assert_true(gat.cv_.__class__ == StratifiedKFold)
gat.predict(epochs)
assert_array_equal(np.shape(gat.y_pred_), (15, 15, 14, 1))
gat.predict_method = 'predict_proba'
gat.predict(epochs)
assert_array_equal(np.shape(gat.y_pred_), (15, 15, 14, 2))
gat.predict_method = 'foo'
assert_raises(NotImplementedError, gat.predict, epochs)
gat.predict_method = 'predict'
gat.predict(epochs)
assert_array_equal(np.shape(gat.y_pred_), (15, 15, 14, 1))
assert_equal("<GAT | fitted, start : -0.200 (s), stop : 0.499 (s), "
"predicted 14 epochs, no score>",
"%s" % gat)
gat.score(epochs)
assert_true(gat.scorer_.__name__ == 'accuracy_score')
# check clf / predict_method combinations for which the scoring metrics
# cannot be inferred.
gat.scorer = None
gat.predict_method = 'decision_function'
assert_raises(ValueError, gat.score, epochs)
# Check specifying y manually
gat.predict_method = 'predict'
gat.score(epochs, y=epochs.events[:, 2])
gat.score(epochs, y=epochs.events[:, 2].tolist())
assert_equal("<GAT | fitted, start : -0.200 (s), stop : 0.499 (s), "
"predicted 14 epochs,\n scored "
"(accuracy_score)>", "%s" % gat)
with warnings.catch_warnings(record=True):
gat.fit(epochs, y=epochs.events[:, 2])
old_mode = gat.predict_mode
gat.predict_mode = 'super-foo-mode'
assert_raises(ValueError, gat.predict, epochs)
gat.predict_mode = old_mode
gat.score(epochs, y=epochs.events[:, 2])
assert_true("accuracy_score" in '%s' % gat.scorer_)
epochs2 = epochs.copy()
# check _DecodingTime class
assert_equal("<DecodingTime | start: -0.200 (s), stop: 0.499 (s), step: "
"0.050 (s), length: 0.050 (s), n_time_windows: 15>",
"%s" % gat.train_times_)
assert_equal("<DecodingTime | start: -0.200 (s), stop: 0.499 (s), step: "
"0.050 (s), length: 0.050 (s), n_time_windows: 15 x 15>",
"%s" % gat.test_times_)
# the y-check
gat.predict_mode = 'mean-prediction'
epochs2.events[:, 2] += 10
gat_ = copy.deepcopy(gat)
with use_log_level('error'):
assert_raises(ValueError, gat_.score, epochs2)
gat.predict_mode = 'cross-validation'
# Test basics
# --- number of trials
assert_true(gat.y_train_.shape[0] ==
gat.y_true_.shape[0] ==
len(gat.y_pred_[0][0]) == 14)
# --- number of folds
assert_true(np.shape(gat.estimators_)[1] == gat.cv)
# --- length training size
assert_true(len(gat.train_times_['slices']) == 15 ==
np.shape(gat.estimators_)[0])
# --- length testing sizes
assert_true(len(gat.test_times_['slices']) == 15 ==
np.shape(gat.scores_)[0])
assert_true(len(gat.test_times_['slices'][0]) == 15 ==
np.shape(gat.scores_)[1])
# Test score_mode
gat.score_mode = 'foo'
assert_raises(ValueError, gat.score, epochs)
gat.score_mode = 'fold-wise'
scores = gat.score(epochs)
assert_array_equal(np.shape(scores), [15, 15, 5])
gat.score_mode = 'mean-sample-wise'
scores = gat.score(epochs)
assert_array_equal(np.shape(scores), [15, 15])
gat.score_mode = 'mean-fold-wise'
scores = gat.score(epochs)
assert_array_equal(np.shape(scores), [15, 15])
gat.predict_mode = 'mean-prediction'
with warnings.catch_warnings(record=True) as w:
gat.score(epochs)
assert_true(any("score_mode changed from " in str(ww.message)
for ww in w))
# Test longer time window
with warnings.catch_warnings(record=True): # dep
gat = GeneralizationAcrossTime(train_times={'length': .100})
with warnings.catch_warnings(record=True):
gat2 = gat.fit(epochs)
assert_true(gat is gat2) # return self
assert_true(hasattr(gat2, 'cv_'))
assert_true(gat2.cv_ != gat.cv)
with warnings.catch_warnings(record=True): # not vectorizing
scores = gat.score(epochs)
assert_true(isinstance(scores, np.ndarray)) # type check
assert_equal(len(scores[0]), len(scores)) # shape check
assert_equal(len(gat.test_times_['slices'][0][0]), 2)
# Decim training steps
with warnings.catch_warnings(record=True): # dep
gat = GeneralizationAcrossTime(train_times={'step': .100})
with warnings.catch_warnings(record=True):
gat.fit(epochs)
gat.score(epochs)
assert_true(len(gat.scores_) == len(gat.estimators_) == 8) # training time
assert_equal(len(gat.scores_[0]), 15) # testing time
# Test start stop training & test cv without n_fold params
y_4classes = np.hstack((epochs.events[:7, 2], epochs.events[7:, 2] + 1))
train_times = dict(start=0.090, stop=0.250)
with warnings.catch_warnings(record=True): # dep
gat = GeneralizationAcrossTime(cv=cv_lolo, train_times=train_times)
# predict without fit
assert_raises(RuntimeError, gat.predict, epochs)
with warnings.catch_warnings(record=True):
gat.fit(epochs, y=y_4classes)
gat.score(epochs)
assert_equal(len(gat.scores_), 4)
assert_equal(gat.train_times_['times'][0], epochs.times[6])
assert_equal(gat.train_times_['times'][-1], epochs.times[9])
# Test score without passing epochs & Test diagonal decoding
with warnings.catch_warnings(record=True): # dep
gat = GeneralizationAcrossTime(test_times='diagonal')
with warnings.catch_warnings(record=True): # not vectorizing
gat.fit(epochs)
assert_raises(RuntimeError, gat.score)
with warnings.catch_warnings(record=True): # not vectorizing
gat.predict(epochs)
scores = gat.score()
assert_true(scores is gat.scores_)
assert_equal(np.shape(gat.scores_), (15, 1))
assert_array_equal([tim for ttime in gat.test_times_['times']
for tim in ttime], gat.train_times_['times'])
# Test generalization across conditions
with warnings.catch_warnings(record=True): # dep
gat = GeneralizationAcrossTime(predict_mode='mean-prediction', cv=2)
with warnings.catch_warnings(record=True):
gat.fit(epochs[0:6])
with warnings.catch_warnings(record=True):
# There are some empty test folds because of n_trials
gat.predict(epochs[7:])
gat.score(epochs[7:])
# Test training time parameters
gat_ = copy.deepcopy(gat)
# --- start stop outside time range
gat_.train_times = dict(start=-999.)
with use_log_level('error'):
assert_raises(ValueError, gat_.fit, epochs)
gat_.train_times = dict(start=999.)
assert_raises(ValueError, gat_.fit, epochs)
# --- impossible slices
gat_.train_times = dict(step=.000001)
assert_raises(ValueError, gat_.fit, epochs)
gat_.train_times = dict(length=.000001)
assert_raises(ValueError, gat_.fit, epochs)
gat_.train_times = dict(length=999.)
assert_raises(ValueError, gat_.fit, epochs)
# Test testing time parameters
# --- outside time range
gat.test_times = dict(start=-999.)
with warnings.catch_warnings(record=True): # no epochs in fold
assert_raises(ValueError, gat.predict, epochs)
gat.test_times = dict(start=999.)
with warnings.catch_warnings(record=True): # no test epochs
assert_raises(ValueError, gat.predict, epochs)
# --- impossible slices
gat.test_times = dict(step=.000001)
with warnings.catch_warnings(record=True): # no test epochs
assert_raises(ValueError, gat.predict, epochs)
gat_ = copy.deepcopy(gat)
gat_.train_times_['length'] = .000001
gat_.test_times = dict(length=.000001)
with warnings.catch_warnings(record=True): # no test epochs
assert_raises(ValueError, gat_.predict, epochs)
# --- test time region of interest
gat.test_times = dict(step=.150)
with warnings.catch_warnings(record=True): # not vectorizing
gat.predict(epochs)
assert_array_equal(np.shape(gat.y_pred_), (15, 5, 14, 1))
# --- silly value
gat.test_times = 'foo'
with warnings.catch_warnings(record=True): # no test epochs
assert_raises(ValueError, gat.predict, epochs)
assert_raises(RuntimeError, gat.score)
# --- unmatched length between training and testing time
gat.test_times = dict(length=.150)
assert_raises(ValueError, gat.predict, epochs)
# --- irregular length training and testing times
# 2 estimators, the first one is trained on two successive time samples
# whereas the second one is trained on a single time sample.
train_times = dict(slices=[[0, 1], [1]])
# The first estimator is tested once, the second estimator is tested on
# two successive time samples.
test_times = dict(slices=[[[0, 1]], [[0], [1]]])
with warnings.catch_warnings(record=True): # dep
gat = GeneralizationAcrossTime(train_times=train_times,
test_times=test_times)
gat.fit(epochs)
with warnings.catch_warnings(record=True): # not vectorizing
gat.score(epochs)
assert_array_equal(np.shape(gat.y_pred_[0]), [1, len(epochs), 1])
assert_array_equal(np.shape(gat.y_pred_[1]), [2, len(epochs), 1])
# check cannot Automatically infer testing times for adhoc training times
gat.test_times = None
assert_raises(ValueError, gat.predict, epochs)
svc = SVC(C=1, kernel='linear', probability=True)
with warnings.catch_warnings(record=True): # dep
gat = GeneralizationAcrossTime(clf=svc, predict_mode='mean-prediction')
with warnings.catch_warnings(record=True):
gat.fit(epochs)
# sklearn needs it: c.f.
# https://github.com/scikit-learn/scikit-learn/issues/2723
# and http://bit.ly/1u7t8UT
with use_log_level('error'):
assert_raises(ValueError, gat.score, epochs2)
gat.score(epochs)
assert_true(0.0 <= np.min(scores) <= 1.0)
assert_true(0.0 <= np.max(scores) <= 1.0)
# Test that error if cv is not partition
with warnings.catch_warnings(record=True): # dep
gat = GeneralizationAcrossTime(cv=cv_shuffle,
predict_mode='cross-validation')
gat.fit(epochs)
assert_raises(ValueError, gat.predict, epochs)
with warnings.catch_warnings(record=True): # dep
gat = GeneralizationAcrossTime(cv=cv_shuffle,
predict_mode='mean-prediction')
gat.fit(epochs)
gat.predict(epochs)
# Test that gets error if train on one dataset, test on another, and don't
# specify appropriate cv:
with warnings.catch_warnings(record=True): # dep
gat = GeneralizationAcrossTime()
gat.fit(epochs)
with warnings.catch_warnings(record=True):
gat.fit(epochs)
gat.predict(epochs)
assert_raises(ValueError, gat.predict, epochs[:10])
# Make CV with some empty train and test folds:
# --- empty test fold(s) should warn when gat.predict()
gat._cv_splits[0] = [gat._cv_splits[0][0], np.empty(0)]
with warnings.catch_warnings(record=True) as w:
gat.predict(epochs)
assert_true(len(w) > 0)
assert_true(any('do not have any test epochs' in str(ww.message)
for ww in w))
# --- empty train fold(s) should raise when gat.fit()
with warnings.catch_warnings(record=True): # dep
gat = GeneralizationAcrossTime(cv=[([0], [1]), ([], [0])])
assert_raises(ValueError, gat.fit, epochs[:2])
# Check that still works with classifier that output y_pred with
# shape = (n_trials, 1) instead of (n_trials,)
if check_version('sklearn', '0.17'): # no is_regressor before v0.17
with warnings.catch_warnings(record=True): # dep
gat = GeneralizationAcrossTime(clf=KernelRidge(), cv=2)
epochs.crop(None, epochs.times[2])
gat.fit(epochs)
# With regression the default cv is KFold and not StratifiedKFold
assert_true(gat.cv_.__class__ == KFold)
gat.score(epochs)
# with regression the default scoring metrics is mean squared error
assert_true(gat.scorer_.__name__ == 'mean_squared_error')
# Test combinations of complex scenarios
# 2 or more distinct classes
n_classes = [2, 4] # 4 tested
# nicely ordered labels or not
le = LabelEncoder()
y = le.fit_transform(epochs.events[:, 2])
y[len(y) // 2:] += 2
ys = (y, y + 1000)
# Univariate and multivariate prediction
svc = SVC(C=1, kernel='linear', probability=True)
reg = KernelRidge()
def scorer_proba(y_true, y_pred):
return roc_auc_score(y_true, y_pred[:, 0])
# We re testing 3 scenario: default, classifier + predict_proba, regressor
scorers = [None, scorer_proba, scorer_regress]
predict_methods = [None, 'predict_proba', None]
clfs = [svc, svc, reg]
# Test all combinations
for clf, predict_method, scorer in zip(clfs, predict_methods, scorers):
for y in ys:
for n_class in n_classes:
for predict_mode in ['cross-validation', 'mean-prediction']:
# Cannot use AUC for n_class > 2
if (predict_method == 'predict_proba' and n_class != 2):
continue
y_ = y % n_class
with warnings.catch_warnings(record=True):
gat = GeneralizationAcrossTime(
cv=2, clf=clf, scorer=scorer,
predict_mode=predict_mode)
gat.fit(epochs, y=y_)
gat.score(epochs, y=y_)
# Check that scorer is correctly defined manually and
# automatically.
scorer_name = gat.scorer_.__name__
if scorer is None:
if is_classifier(clf):
assert_equal(scorer_name, 'accuracy_score')
else:
assert_equal(scorer_name, 'mean_squared_error')
else:
assert_equal(scorer_name, scorer.__name__)
def test_get_coef():
"""Test getting linear coefficients (filters/patterns) from estimators."""
from sklearn.base import TransformerMixin, BaseEstimator
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import Ridge, LinearRegression
lm = LinearModel()
assert_true(is_classifier(lm))
lm = LinearModel(Ridge())
assert_true(is_regressor(lm))
# Define a classifier, an invertible transformer and an non-invertible one.
class Clf(BaseEstimator):
def fit(self, X, y):
return self
class NoInv(TransformerMixin):
def fit(self, X, y):
return self
def transform(self, X):
return X
class Inv(NoInv):
def inverse_transform(self, X):
return X
X, y, A = _make_data(n_samples=2000, n_features=3, n_targets=1)
# I. Test inverse function
# Check that we retrieve the right number of inverse functions even if
# there are nested pipelines
good_estimators = [
(1, make_pipeline(Inv(), Clf())),
(2, make_pipeline(Inv(), Inv(), Clf())),
(3, make_pipeline(Inv(), make_pipeline(Inv(), Inv()), Clf())),
]
for expected_n, est in good_estimators:
est.fit(X, y)
assert_true(expected_n == len(_get_inverse_funcs(est)))
bad_estimators = [
Clf(), # no preprocessing
Inv(), # final estimator isn't classifier
make_pipeline(NoInv(), Clf()), # first step isn't invertible
make_pipeline(Inv(), make_pipeline(
Inv(), NoInv()), Clf()), # nested step isn't invertible
]
for est in bad_estimators:
est.fit(X, y)
invs = _get_inverse_funcs(est)
assert_equal(invs, list())
# II. Test get coef for simple estimator and pipelines
for clf in (lm, make_pipeline(StandardScaler(), lm)):
clf.fit(X, y)
# Retrieve final linear model
filters = get_coef(clf, 'filters_', False)
if hasattr(clf, 'steps'):
coefs = clf.steps[-1][-1].model.coef_
else:
coefs = clf.model.coef_
assert_array_equal(filters, coefs[0])
patterns = get_coef(clf, 'patterns_', False)
assert_true(filters[0] != patterns[0])
n_chans = X.shape[1]
assert_array_equal(filters.shape, patterns.shape, [n_chans, n_chans])
# Inverse transform linear model
filters_inv = get_coef(clf, 'filters_', True)
assert_true(filters[0] != filters_inv[0])
patterns_inv = get_coef(clf, 'patterns_', True)
assert_true(patterns[0] != patterns_inv[0])
# Check with search_light and combination of preprocessing ending with sl:
slider = SlidingEstimator(make_pipeline(StandardScaler(), lm))
X = np.transpose([X, -X], [1, 2, 0]) # invert X across 2 time samples
clfs = (make_pipeline(Scaler(None, scalings='mean'), slider), slider)
for clf in clfs:
clf.fit(X, y)
for inverse in (True, False):
patterns = get_coef(clf, 'patterns_', inverse)
filters = get_coef(clf, 'filters_', inverse)
assert_array_equal(filters.shape, patterns.shape,
X.shape[1:])
# the two time samples get inverted patterns
assert_equal(patterns[0, 0], -patterns[0, 1])
for t in [0, 1]:
assert_array_equal(get_coef(clf.estimators_[t], 'filters_', False),
filters[:, t])
# Check patterns with more than 1 regressor
for n_features in [1, 5]:
for n_targets in [1, 3]:
X, Y, A = _make_data(n_samples=5000, n_features=5, n_targets=3)
lm = LinearModel(LinearRegression()).fit(X, Y)
assert_array_equal(lm.filters_.shape, lm.patterns_.shape)
assert_array_equal(lm.filters_.shape, [3, 5])
assert_array_almost_equal(A, lm.patterns_.T, decimal=2)
lm = LinearModel(Ridge(alpha=1)).fit(X, Y)
assert_array_almost_equal(A, lm.patterns_.T, decimal=2)
# Check can pass fitting parameters
lm.fit(X, Y, sample_weight=np.ones(len(Y)))
def test_get_coef():
"""Test getting linear coefficients (filters/patterns) from estimators."""
from sklearn.base import TransformerMixin, BaseEstimator
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler
from sklearn import svm
from sklearn.linear_model import Ridge, LinearRegression
from sklearn.model_selection import GridSearchCV
lm_classification = LinearModel()
assert (is_classifier(lm_classification))
lm_regression = LinearModel(Ridge())
assert (is_regressor(lm_regression))
parameters = {'kernel': ['linear'], 'C': [1, 10]}
lm_gs_classification = LinearModel(
GridSearchCV(svm.SVC(),
parameters,
cv=2,
refit=True,
iid=False,
n_jobs=1))
assert (is_classifier(lm_gs_classification))
lm_gs_regression = LinearModel(
GridSearchCV(svm.SVR(),
parameters,
cv=2,
refit=True,
iid=False,
n_jobs=1))
assert (is_regressor(lm_gs_regression))
# Define a classifier, an invertible transformer and an non-invertible one.
class Clf(BaseEstimator):
def fit(self, X, y):
return self
class NoInv(TransformerMixin):
def fit(self, X, y):
return self
def transform(self, X):
return X
class Inv(NoInv):
def inverse_transform(self, X):
return X
X, y, A = _make_data(n_samples=1000, n_features=3, n_targets=1)
# I. Test inverse function
# Check that we retrieve the right number of inverse functions even if
# there are nested pipelines
good_estimators = [
(1, make_pipeline(Inv(), Clf())),
(2, make_pipeline(Inv(), Inv(), Clf())),
(3, make_pipeline(Inv(), make_pipeline(Inv(), Inv()), Clf())),
]
for expected_n, est in good_estimators:
est.fit(X, y)
assert (expected_n == len(_get_inverse_funcs(est)))
bad_estimators = [
Clf(), # no preprocessing
Inv(), # final estimator isn't classifier
make_pipeline(NoInv(), Clf()), # first step isn't invertible
make_pipeline(Inv(), make_pipeline(Inv(), NoInv()),
Clf()), # nested step isn't invertible
]
for est in bad_estimators:
est.fit(X, y)
invs = _get_inverse_funcs(est)
assert_equal(invs, list())
# II. Test get coef for classification/regression estimators and pipelines
rng = np.random.RandomState(0)
for clf in (lm_regression, lm_gs_classification,
make_pipeline(StandardScaler(), lm_classification),
make_pipeline(StandardScaler(), lm_gs_regression)):
# generate some categorical/continuous data
# according to the type of estimator.
if is_classifier(clf):
n, n_features = 1000, 3
X = rng.rand(n, n_features)
y = np.arange(n) % 2
else:
X, y, A = _make_data(n_samples=1000, n_features=3, n_targets=1)
y = np.ravel(y)
clf.fit(X, y)
# Retrieve final linear model
filters = get_coef(clf, 'filters_', False)
if hasattr(clf, 'steps'):
if hasattr(clf.steps[-1][-1].model, 'best_estimator_'):
# Linear Model with GridSearchCV
coefs = clf.steps[-1][-1].model.best_estimator_.coef_
else:
# Standard Linear Model
coefs = clf.steps[-1][-1].model.coef_
else:
if hasattr(clf.model, 'best_estimator_'):
# Linear Model with GridSearchCV
coefs = clf.model.best_estimator_.coef_
else:
# Standard Linear Model
coefs = clf.model.coef_
if coefs.ndim == 2 and coefs.shape[0] == 1:
coefs = coefs[0]
assert_array_equal(filters, coefs)
patterns = get_coef(clf, 'patterns_', False)
assert (filters[0] != patterns[0])
n_chans = X.shape[1]
assert_array_equal(filters.shape, patterns.shape, [n_chans, n_chans])
# Inverse transform linear model
filters_inv = get_coef(clf, 'filters_', True)
assert (filters[0] != filters_inv[0])
patterns_inv = get_coef(clf, 'patterns_', True)
assert (patterns[0] != patterns_inv[0])
# Check with search_light and combination of preprocessing ending with sl:
slider = SlidingEstimator(make_pipeline(StandardScaler(), lm_regression))
X = np.transpose([X, -X], [1, 2, 0]) # invert X across 2 time samples
clfs = (make_pipeline(Scaler(None, scalings='mean'), slider), slider)
for clf in clfs:
clf.fit(X, y)
for inverse in (True, False):
patterns = get_coef(clf, 'patterns_', inverse)
filters = get_coef(clf, 'filters_', inverse)
assert_array_equal(filters.shape, patterns.shape, X.shape[1:])
# the two time samples get inverted patterns
assert_equal(patterns[0, 0], -patterns[0, 1])
for t in [0, 1]:
assert_array_equal(get_coef(clf.estimators_[t], 'filters_', False),
filters[:, t])
# Check patterns with more than 1 regressor
for n_features in [1, 5]:
for n_targets in [1, 3]:
X, Y, A = _make_data(n_samples=3000, n_features=5, n_targets=3)
lm = LinearModel(LinearRegression()).fit(X, Y)
assert_array_equal(lm.filters_.shape, lm.patterns_.shape)
assert_array_equal(lm.filters_.shape, [3, 5])
assert_array_almost_equal(A, lm.patterns_.T, decimal=2)
lm = LinearModel(Ridge(alpha=1)).fit(X, Y)
assert_array_almost_equal(A, lm.patterns_.T, decimal=2)
# Check can pass fitting parameters
lm.fit(X, Y, sample_weight=np.ones(len(Y)))
