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_load_dimreduce_data_fromcl():
csvs = [
"/data/data2/meta_accumulate//fh/mvpa/fh_pca_space_merge_Insula_rt_fast.csv",
"/data/data2/meta_accumulate//fh/mvpa/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
)
assert len(Xs) == 2, "Xs wrong len"
assert len(ys) == 2, "ys wrong len"
assert len(indices) == 2, "indices wrong len"
assert len(cvcodes) == 2, "cvcodes wrong len"
assert Xs[0].shape == (210, 3), "X0 wrong shape"
assert Xs[1].shape == (210, 3), "X1 wrong shape"
assert Xs[0].shape[0] == ys[0].shape[0], "X0 y0 mistmatch"
assert Xs[1].shape[0] == ys[1].shape[0], "X0 y0 mistmatch"
assert ys[0].shape == indices[0].shape, "y0 i0 mistmatch"
assert ys[1].shape == indices[1].shape, "y1 i1 mistmatch"
assert ys[0].shape == cvcodes[0].shape, "y0 cv0 mistmatch"
assert ys[1].shape == cvcodes[1].shape, "y1 cv1 mistmatch"
print("X0, the first few rows\n{0}".format(Xs[0][:5,:]))
print("y0, the first few elements {0}".format(ys[0][:5]))
print("index0, the first few elements {0}".format(indices[0][:5]))
print("cv0, the first few elements {0}".format(cvcodes[0][:5]))
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
parser.add_argument(
"--clf", default="RandomForestClassifier", type=str,
help="Select a classfier"
)
args = parser.parse_args()
prng = np.random.RandomState(42)
# ----
# Load and preprocess data
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"
# ----
