d_data_test = dict()
settings = Settings()
print settings
for i in range(0, 3):
nsubject = i + 1
K = [settings.kfoldCV]
R = settings.repeatCVouter
# XTRAIN, ytrain, aFeatNames, aFiles_tr, plabels, data_q = load_features('train', nsubject, feat_select)
# XTEST, ytest, aFeatNames_ts, dummy4, dummy5, dummy3 = load_features('test', nsubject, feat_select)
d_tr, d_ts = load_features_and_preprocess(nsubject, feat_select[i], settings=settings)
XTRAIN, ytrain, aFeatNames_tr, aFiles_tr, plabels_tr, data_q_tr, ind_nan_tr = d_tr[0], d_tr[1], d_tr[2], d_tr[3], \
d_tr[4], d_tr[5], d_tr[6]
XTEST, ytest, aFeatNames_ts, aFiles_ts, plabels_ts, data_q_ts, ind_nan_ts = d_ts[0], d_ts[1], d_ts[2], d_ts[3], \
d_ts[4], d_ts[5], d_ts[6]
# XTRAIN, ytrain, aFeatNames_tr, aFiles_tr, plabels_tr, data_q_tr = load_features('train', nsubject, feat_select[i])
# XTEST, ytest, aFeatNames_ts, aFiles_ts, plabels_ts, data_q_ts = load_features('test', nsubject, feat_select[i])
# pp.fit(XTRAIN, XTEST, drop_nan=True)
#
# print '####### Subject: ', nsubject
# print '-- Original dataset'
# print XTRAIN.shape
# print ytrain.shape
#
settings = Settings()
print settings
K = settings.kfoldCV
R = settings.repeatCV
# settings.remove_covariate_shift = False
nr_bins = 25
# prob_calib_alg = settings.prob_calib_alg
# prob_calib_alg = None
prob_calib_alg = 'rank'
# prob_calib_alg = 'median_centered'
d_tr, d_ts = load_features_and_preprocess(nsubject,
feat_select_unique,
settings=settings,
verbose=False)
XTRAIN_ALL, ytrain, aFeatNames_tr_all, aFiles_tr, plabels_tr, data_q_tr, ind_nan_tr = d_tr[0], d_tr[1], d_tr[2], d_tr[3], \
d_tr[4], d_tr[5], d_tr[6]
XTEST_ALL, ytest, aFeatNames_ts_all, aFiles_ts, plabels_ts, data_q_ts, ind_nan_ts = d_ts[0], d_ts[1], d_ts[2], d_ts[3], \
d_ts[4], d_ts[5], d_ts[6]
y_all_clf = np.zeros((XTRAIN_ALL.shape[0], len(aclf)))
auc_all = np.zeros((len(aclf), 1))
for i, clf in enumerate(aclf):
print XTRAIN_ALL.shape
XTRAIN, aFeatNames_tr, dummy3 = select_feature_group(
XTRAIN_ALL,
aFeatNames_tr_all,
return vals
df = pd.DataFrame(columns=['feat_group', 'electrode', 'total', 'removed'],
index=range(0, 200))
# print df
index = -1
nsubject = 2
for sfeat in afeat_select:
d_tr, dummy1 = load_features_and_preprocess(nsubject, [sfeat],
settings=settings,
verbose=False)
feat_names = d_tr[2]
feat_names_removed = load_removed_features(nsubject, [sfeat])
# feat_names_removed += load_removed_features(nsubject, ['stat_spectral_sp_entropy_mfj_corr'])
nr_total = get_nr_feat_electrode(feat_names)
nr_removed = get_nr_feat_electrode(feat_names_removed)
for iel in range(0, 16):
index += 1
df['feat_group'].loc[index] = sfeat
df['total'].loc[index] = nr_total[iel, 0]
df['electrode'].loc[index] = iel + 1
df['removed'].loc[index] = nr_removed[iel, 0]
# print("TRAIN:", train_index, "TEST:", test_index)
# # print X[train_index]
# # print X[test_index]
# # X_train, X_test = X[train_index], X[test_index]
# # y_train, y_test = y[train_index], y[test_index]
from utils import load_features_and_preprocess
from spp_ut_settings import Settings
# from sklearn.utils import shuffle
settings = Settings()
settings.remove_outliers = False
settings.standardize = False
settings.drop_nan = False
d_tr, d_ts = load_features_and_preprocess(3, ['stat'], settings, verbose=True)
XTRAIN, ytrain, aFeatNames_tr, aFiles_tr, plabels_tr, data_q_tr, ind_nan_tr = d_tr[0], d_tr[1], d_tr[2], d_tr[3], \
d_tr[4], d_tr[5], d_tr[6]
ytrain = ytrain.ravel()
XTRAIN, ytrain, plabels_tr = insert_pathol_to_normal_random_keep_order(XTRAIN, ytrain, plabels_tr)
tscv = TimeSeriesSplitGroupSafe(n_splits=100)
p = np.unique(plabels_tr)
for train_index, test_index in tscv.split(XTRAIN, ytrain, plabels_tr):
# pass
print("TRAIN:", train_index, "TEST:", test_index)
print("Groups TRAIN:", plabels_tr[train_index], "Groups TEST:", plabels_tr[test_index])
