def analysis(name, typ, condition=None, query=None, title=None):
"""Wrapper to ensure that we attribute the same function for each type
of analyses: e.g. categorical, regression, circular regression."""
# Define univariate analysis
erf_function = None # Default is fast_mannwhitneyu
# /!\ for categorical analyses, the contrast is min(y) - max(y)
# e.g. target_present==False - target_present==True
if typ == 'categorize':
# estimator is normalization + l2 Logistic Regression
clf = make_pipeline(
StandardScaler(),
force_predict(LogisticRegression(class_weight='balanced'), axis=1))
scorer = scorer_auc
chance = .5
elif typ == 'regress':
# estimator is normalization + l2 Ridge
clf = make_pipeline(StandardScaler(), Ridge())
scorer = scorer_spearman
chance = 0.
elif typ == 'circ_regress':
# estimator is normalization + l2 Logistic Regression on cos and sin
clf = make_pipeline(StandardScaler(), PolarRegression(Ridge()))
scorer = scorer_angle
chance = 0.
# The univariate analysis needs a different scorer
erf_function = scorer_circlin
if condition is None:
condition = name
return dict(name=name, condition=condition, query=query, clf=clf,
scorer=scorer, chance=chance, erf_function=erf_function,
cv=8, typ=typ, title=title, single_trial=True)
def quick_score(X, y, clf=None, scorer=None):
from sklearn.cross_validation import KFold
regression = (len(np.unique(y)) > 2) & isinstance(y[0], float)
if scorer is None:
scorer = scorer_spearman if regression else scorer_auc
if clf is None:
clf = RidgeCV(alphas=[(2 * C) ** -1 for C in [1e-4, 1e-2, 1]])\
if regression else force_predict(LogisticRegression(), axis=1)
sel = np.where(~np.isnan(y))[0]
X = X[sel, :, :]
y = y[sel]
epochs = mat2mne(X, sfreq=100)
clf = make_pipeline(StandardScaler(), clf)
cv = KFold(len(y), 5) if regression else None
gat = GeneralizationAcrossTime(clf=clf, n_jobs=-1, scorer=scorer, cv=cv)
gat.fit(epochs, y)
gat.score(epochs, y)
return gat
def quick_score(X, y, clf=None, scorer=None):
from sklearn.cross_validation import KFold
regression = (len(np.unique(y)) > 2) & isinstance(y[0], float)
if scorer is None:
scorer = scorer_spearman if regression else scorer_auc
if clf is None:
clf = RidgeCV(alphas=[(2 * C) ** -1 for C in [1e-4, 1e-2, 1]])\
if regression else force_predict(LogisticRegression(), axis=1)
sel = np.where(~np.isnan(y))[0]
X = X[sel, :, :]
y = y[sel]
epochs = mat2mne(X, sfreq=100)
clf = make_pipeline(StandardScaler(), clf)
cv = KFold(len(y), 5) if regression else None
gat = GeneralizationAcrossTime(clf=clf, n_jobs=-1, scorer=scorer, cv=cv)
gat.fit(epochs, y)
gat.score(epochs, y)
return gat
# Compute time frequency decomposition
X = mne.time_frequency.tfr_array_morlet(epochs.get_data(),
sfreq=epochs.info['sfreq'],
freqs=freqs,
output='power',
n_cycles=n_cycles)
n_epochs, n_channels, n_freqs, n_times = X.shape
X = X.reshape(n_epochs, n_channels, -1) # collapse freqs and time
# Run decoding on TFR output
for analysis in analyses:
fname = results_folder +\
'%s_tf_scores_%s_%s.npy' % (subject, 'Cue', analysis)
y = np.array(events_behavior[analysis])
clf = make_pipeline(
StandardScaler(),
force_predict(LogisticRegression(), 'predict_proba', axis=1))
scorer = scorer_auc
kwargs = dict()
le = preprocessing.LabelEncoder()
le.fit(y)
y = le.transform(y)
sel = np.where(y != 0)[0]
td = SlidingEstimator(clf,
scoring=make_scorer(scorer),
n_jobs=24,
**kwargs)
td.fit(X[sel], y[sel])
scores = cross_val_multiscore(td, X[sel], y[sel], cv=StratifiedKFold(12))
scores = scores.mean(axis=0)
scores = np.reshape(scores, (n_freqs, n_times))
# Save cross validated scores
np.random.RandomState(1)
order = np.arange(len(epochs))
np.random.shuffle(order)
epochs = epochs[order]
# decimate data
decim = 2
epochs.decimate(decim)
# only keep data > 0 ms & < 400 ms
epochs.crop(-.100, .750)
######################################################################
# Decoding
# set up a classifier based on a regularized Logistic Regression
clf = LogisticRegression(C=1)
# force the classifer to output a probabilistic prediction
clf = force_predict(clf, axis=1)
# insert a z-score normalization step before the classification
clf = make_pipeline(StandardScaler(), clf)
# initialize the GAT object
gat = GeneralizationAcrossTime(clf=clf, scorer=scorer_auc, n_jobs=-1,
cv=10)
# select the trials where a target is presented
for contrast in ['HL', 'EU', 'PR']:
epochs_ = concatenate_epochs((epochs[contrast[0]],
epochs[contrast[1]]))
y = np.hstack((np.zeros(len(epochs[contrast[0]])),
np.ones(len(epochs[contrast[1]]))))
gat.fit(epochs_, y=y)
fname = op.join(data_path, 's%i_%s_fit.pkl' % (subject, contrast))
with open(fname, 'wb') as f:
