def _train(df, args, params):
'''
cross-validation results
'''
_info('Running grid search')
# get X-y from df
subject_list = df['Subject'].unique()
train_list = subject_list[:args.train_size]
test_list = subject_list[args.train_size:]
print('number of subjects = %d' % (len(subject_list)))
features = [ii for ii in df.columns if 'feat' in ii]
k_feat = len(features)
print('number of features = %d' % (k_feat))
args.k_class = len(np.unique(df['y']))
print('number of classes = %d' % (args.k_class))
# length of each clip
clip_time = np.zeros(args.k_class)
for ii in range(args.k_class):
class_df = df[df['y'] == ii]
clip_time[ii] = np.max(np.unique(class_df['timepoint'])) + 1
clip_time = clip_time.astype(int) # df saves float
print('seq lengths = %s' % clip_time)
# results dict init
results = {}
# mean accuracy across time
results['train'] = np.zeros(args.k_fold)
results['val'] = np.zeros(args.k_fold)
# confusion matrices
results['train_conf_mtx'] = np.zeros((args.k_class, args.k_class))
results['val_conf_mtx'] = np.zeros((args.k_class, args.k_class))
# per class temporal accuracy
results['t_train'] = {}
results['t_val'] = {}
for ii in range(args.k_class):
results['t_train'][ii] = np.zeros((args.k_fold, clip_time[ii]))
results['t_val'][ii] = np.zeros((args.k_fold, clip_time[ii]))
i_fold = 0
kf = KFold(n_splits=args.k_fold, random_state=K_SEED)
for train, val in kf.split(train_list):
_info('fold: %d/%d' % (i_fold + 1, args.k_fold))
# ***between-subject train-val split
train_subs = [train_list[ii] for ii in train]
val_subs = [train_list[ii] for ii in val]
# get train, val sequences
X_train, train_len, y_train = _get_seq(df,
train_subs,
args,
shuffle=True)
X_val, val_len, y_val = _get_seq(df, val_subs, args)
'''
train classifier
'''
then = time.time()
model = GRUClassifier(X_train,
k_layers=params['k_layers'],
k_hidden=params['k_hidden'],
k_class=args.k_class)
model.fit(X_train,
y_train,
epochs=args.num_epochs,
validation_split=0.2,
batch_size=args.batch_size,
verbose=1)
print('--- train time = %0.4f seconds ---' % (time.time() - then))
trainable = np.sum([
tf.reshape(params, -1).shape[0]
for params in model.trainable_variables
])
print('Total trainable parameters: %i' % trainable)
'''
results on train data
'''
a, a_t, c_mtx = _gru_acc(model, X_train, y_train, clip_time)
results['train'][i_fold] = a
print('tacc = %0.3f' % a)
for ii in range(args.k_class):
results['t_train'][ii][i_fold] = a_t[ii]
results['train_conf_mtx'] += c_mtx
'''
results on val data
'''
a, a_t, c_mtx = _gru_acc(model, X_val, y_val, clip_time)
results['val'][i_fold] = a
print('vacc = %0.3f' % a)
for ii in range(args.k_class):
results['t_val'][ii][i_fold] = a_t[ii]
results['val_conf_mtx'] += c_mtx
i_fold += 1
return results
def _test(df, args, params):
'''
test subject results
view only for best cross-val parameters
'''
_info('test mode')
# get X-y from df
subject_list = df['Subject'].unique()
train_list = subject_list[:args.train_size]
test_list = subject_list[args.train_size:]
print('number of subjects = %d' % (len(subject_list)))
features = [ii for ii in df.columns if 'feat' in ii]
k_feat = len(features)
print('number of features = %d' % (k_feat))
args.k_class = len(np.unique(df['y']))
print('number of classes = %d' % (args.k_class))
# length of each clip
clip_time = np.zeros(args.k_class)
for ii in range(args.k_class):
class_df = df[df['y'] == ii]
clip_time[ii] = np.max(np.unique(class_df['timepoint'])) + 1
clip_time = clip_time.astype(int) # df saves float
print('seq lengths = %s' % clip_time)
# results dict init
results = {}
# mean accuracy across time
results['train'] = np.zeros(len(test_list))
results['val'] = np.zeros(len(test_list))
# per class temporal accuracy
results['t_train'] = {}
results['t_test'] = {}
for ii in range(args.k_class):
results['t_train'][ii] = np.zeros((len(test_list), clip_time[ii]))
results['t_test'][ii] = np.zeros((len(test_list), clip_time[ii]))
results_prob = {}
for method in 'train test'.split():
results_prob[method] = {}
for measure in 'acc t_prob'.split():
results_prob[method][measure] = {}
'''
init model
'''
# get train, test sequences
X_train, train_len, y_train = _get_seq(df, train_list, args)
X_test, test_len, y_test = _get_seq(df, test_list, args)
X_train = shuffle_ts(X_train, train_len)
#X_test = shuffle_ts(X_test, test_len)
'''
train classifier
'''
then = time.time()
model = GRUClassifier(X_train,
k_layers=params['k_layers'],
k_hidden=params['k_hidden'],
k_class=args.k_class)
model.fit(X_train,
y_train,
epochs=args.num_epochs,
validation_split=0.2,
batch_size=args.batch_size,
verbose=1)
print('--- train time = %0.4f seconds ---' % (time.time() - then))
'''
results on train data
'''
a, a_t, c_mtx = _gru_test_acc(model, X_train, y_train, clip_time,
len(train_list))
results['train'] = a
print('tacc = %0.3f' % np.mean(a))
for ii in range(args.k_class):
results['t_train'][ii] = a_t[ii]
results['train_conf_mtx'] = c_mtx
# train temporal probs
results_prob['train']['acc'] = model.evaluate(X_train, y_train)[1]
X_train_probs = model.predict(X_train)
results_prob['train']['t_prob'] = _get_true_class_prob(
y_train, X_train_probs, train_len)
'''
results on test data
'''
a, a_t, c_mtx = _gru_test_acc(model, X_test, y_test, clip_time,
len(test_list))
results['test'] = a
print('sacc = %0.3f' % np.mean(a))
for ii in range(args.k_class):
results['t_test'][ii] = a_t[ii]
results['test_conf_mtx'] = c_mtx
# test temporal probs
results_prob['test']['acc'] = model.evaluate(X_test, y_test)[1]
X_test_probs = model.predict(X_test)
results_prob['test']['t_prob'] = _get_true_class_prob(
y_test, X_test_probs, test_len)
return results, results_prob, model