def test_extract_trial_features_real():
csvs = [
"./data/fh_pca_space_merge_Insula_rt_fast.csv",
"./data/fh_pca_space_merge_Insula_rt_slow.csv"
]
# load_dimreduce_data_fromcl(csvs, feature_cols, label_col, cv_col, trial_tr_col)
feature_col = range(0,3)
label_col = 5
cv_col = 6
trial_tr_col = 7
Xs, ys, indices, cvcodes = load_dimreduce_data_fromcl(
csvs, feature_col, label_col, cv_col, trial_tr_col
)
X = np.concatenate(Xs)
y = create_y(np.concatenate(ys))
trials = np.concatenate(indices)
windowstr = '0:10'
window = range(*[int(i) for i in windowstr.split(':')])
Xfea, indexfea, otherfea = extract_trial_features(
X, trials, window, [trials], None
)
yea = otherfea[0]
# Xmax, Xmin, Xdiff, Xmean, Xslope
print("Xmax\n{0}".format(Xfea[:,0:3]))
print("Xmin\n{0}".format(Xfea[:,3:6]))
print("Xdiff\n{0}".format(Xfea[:,6:9]))
print("Xmean\n{0}".format(Xfea[:,9:12]))
print("Xslope\n{0}".format(Xfea[:,12:15]))
def test_extract_trial_features_simulated():
prng = np.random.RandomState(43)
# Create data
iti = 2
updown = range(1,4) + range(-2,0)
l = len(updown)
accum2 = np.asarray([0]*iti + updown + [0]*iti + updown)
nullfea = prng.rand(accum2.shape[0])
X = np.vstack([accum2, nullfea]).T
y = np.asarray([0]*iti + [1]*l + [0]*iti + [2]*l)
trials = np.asarray([0]*iti + [1]*l + [0]*iti + [2]*l)
assert y.shape == trials.shape, "y and trials do not match"
assert X.shape[0] == y.shape[0], "y and X do not match"
print("\n*** Test 1: Full window ***")
window=range(l-1)
Xfea, indexfea, otherfea = extract_trial_features(
X, trials, window, [trials], 0
)
yea = otherfea[0]
assert Xfea.shape[0] == 2, "Xfea nrow is wrong"
assert Xfea.shape[1] == 2 * 5, "Xfea wrong feature number"
assert len(yea) == 2, "yfea is off"
assert len(indexfea) == 2, "trialfea is off"
# Xmax, Xmin, Xdiff, Xmean, Xslope
print("Xmax\n{0}".format(Xfea[:,0:2]))
print("Xmin\n{0}".format(Xfea[:,2:4]))
print("Xdiff\n{0}".format(Xfea[:,4:6]))
print("Xmean\n{0}".format(Xfea[:,6:8]))
print("Xslope\n{0}".format(Xfea[:,8:10]))
def _data(csvs, feature_index, window, label_col, trial_tr_col):
"""Data loading and feature selection helper."""
Xs, ys, indices, cvcodes = load_dimreduce_data_fromcl(
csvs, feature_index, label_col,
label_col, trial_tr_col
)
X = np.concatenate(Xs)
y = create_y(np.concatenate(ys))
index = np.concatenate(indices)
cvcode = np.concatenate(cvcodes)
X, index, othermeta = extract_trial_features(X, index,
window, [y, cvcode], None
)
y, _ = othermeta ## toss cvcode, not applicable
return X, y
feature_index = range(*[int(i) for i in args.data.split(':')])
csvs = args.t
# load_dimreduce_data_fromcl(csvs, feature_cols, label_col, cv_col, trial_tr_col)
Xs, ys, indices, cvcodes = load_dimreduce_data_fromcl(
csvs, feature_index, args.labels,
args.cv, args.trial_tr
)
X = np.concatenate(Xs)
y = create_y(np.concatenate(ys))
index = np.concatenate(indices)
cvcode = np.concatenate(cvcodes)
window = range(*[int(i) for i in args.window.split(':')])
X, index, othermeta = extract_trial_features(
X, index, window, [y, cvcode], None
)
y, cvcode = othermeta
assert X.shape[0] == y.shape[0], "X and y length mismatch"
# ----
# Setup CV:
#
# Kfold splitting by label or by custom label
# (probably by participant)
n_fold = 3
if args.labels == args.cv:
cv = KFold(y.shape[0], n_folds=n_fold, indices=True)
else:
uncvcode = np.unique(cvcode)
