def HFTest(seq, targets, t_seq, t_targets, n_hidden=10, n_updates=250):
""" Test RNN with hessian free optimization """
n_in = 2
n_out = 2
n_classes = 10
# SequenceDataset wants a list of sequences
# this allows them to be different lengths, but here they're not
seq = [i for i in seq]
targets = [i for i in targets]
gradient_dataset = SequenceDataset([seq, targets], batch_size=None,
number_batches=500)
cg_dataset = SequenceDataset([seq, targets], batch_size=None,
number_batches=100)
model = MetaRNN(n_in=n_in, n_hidden=n_hidden, n_out=n_out,
activation='tanh', output_type='softmax',
use_symbolic_softmax=True)
# optimizes negative log likelihood
# but also reports zero-one error
opt = hf_optimizer(p=model.rnn.params, inputs=[model.x, model.y],
s=model.rnn.y_pred,
costs=[model.rnn.loss(model.y),
model.rnn.errors(model.y)], h=model.rnn.h)
mse_updates = []
for i in range(n_updates):
opt.train(gradient_dataset, cg_dataset, num_updates=1)
mse = 0
for t in range(len(t_seq)):
guess = model.predict_proba(t_seq[t])
if guess != t_target:
mse += 1
mse_updates.append(mse)
print i
return (mse_updates, model)
# optimizes negative log likelihood
# but also reports zero-one error
opt = hf_optimizer(p=model.rnn.params, inputs=[model.x, model.y],
s=model.rnn.y_pred,
n_in=n_in, word2vec=word2vec, word2label=word2label,
costs=[model.rnn.loss(model.y),
model.rnn.errors(model.y)], h=model.rnn.h)
print("Training ...")
opt.train(gradient_dataset, cg_dataset, num_updates=n_updates, save_progress='save_param')
seqs = range(10)
plt.close('all')
for seq_num in seqs:
fig = plt.figure()
ax1 = plt.subplot(211)
plt.plot(x_seq_list[seq_num])
ax1.set_title('input')
ax2 = plt.subplot(212)
# blue line will represent true classes
true_targets = plt.step(range(n_steps), y_seq_list[seq_num], marker='o')
# show probabilities (in b/w) output by model
guess = model.predict_proba(x_seq_list[seq_num])
guessed_probs = plt.imshow(guess.T, interpolation='nearest',
cmap='gray')
ax2.set_title('blue: true class, grayscale: probs assigned by model')
print("Elapsed time: %f" % (time.time() - t0))
def test_binary(multiple_out=False, n_updates=250):
""" Test RNN with binary outputs. """
n_hidden = 10
n_in = 5
if multiple_out:
n_out = 2
else:
n_out = 1
n_steps = 10
n_seq = 100
np.random.seed(0)
# simple lag test
seq = np.random.randn(n_seq, n_steps, n_in)
targets = np.zeros((n_seq, n_steps, n_out), dtype='int32')
# whether lag 1 (dim 3) is greater than lag 2 (dim 0)
targets[:, 2:, 0] = np.cast[np.int32](seq[:, 1:-1, 3] > seq[:, :-2, 0])
if multiple_out:
# whether product of lag 1 (dim 4) and lag 1 (dim 2)
# is less than lag 2 (dim 0)
targets[:, 2:, 1] = np.cast[np.int32](
(seq[:, 1:-1, 4] * seq[:, 1:-1, 2]) > seq[:, :-2, 0])
# SequenceDataset wants a list of sequences
# this allows them to be different lengths, but here they're not
seq = [i for i in seq]
targets = [i for i in targets]
gradient_dataset = SequenceDataset([seq, targets], batch_size=None,
number_batches=500)
cg_dataset = SequenceDataset([seq, targets], batch_size=None,
number_batches=100)
model = MetaRNN(n_in=n_in, n_hidden=n_hidden, n_out=n_out,
activation='tanh', output_type='binary')
# optimizes negative log likelihood
# but also reports zero-one error
opt = hf_optimizer(p=model.rnn.params, inputs=[model.x, model.y],
s=model.rnn.y_pred,
costs=[model.rnn.loss(model.y),
model.rnn.errors(model.y)], h=model.rnn.h)
# using settings of initial_lambda and mu given in Nicolas' RNN example
# seem to do a little worse than the default
opt.train(gradient_dataset, cg_dataset, num_updates=n_updates)
seqs = xrange(10)
plt.close('all')
for seq_num in seqs:
fig = plt.figure()
ax1 = plt.subplot(211)
plt.plot(seq[seq_num])
ax1.set_title('input')
ax2 = plt.subplot(212)
true_targets = plt.step(xrange(n_steps), targets[seq_num], marker='o')
guess = model.predict_proba(seq[seq_num])
guessed_targets = plt.step(xrange(n_steps), guess)
plt.setp(guessed_targets, linestyle='--', marker='d')
for i, x in enumerate(guessed_targets):
x.set_color(true_targets[i].get_color())
ax2.set_ylim((-0.1, 1.1))
ax2.set_title('solid: true output, dashed: model output (prob)')
def test_softmax(n_updates=250):
""" Test RNN with softmax outputs. """
n_hidden = 10
n_in = 5
n_steps = 10
n_seq = 100
n_classes = 3
n_out = n_classes # restricted to single softmax per time step
np.random.seed(0)
# simple lag test
seq = np.random.randn(n_seq, n_steps, n_in)
targets = np.zeros((n_seq, n_steps), dtype='int32')
thresh = 0.5
# if lag 1 (dim 3) is greater than lag 2 (dim 0) + thresh
# class 1
# if lag 1 (dim 3) is less than lag 2 (dim 0) - thresh
# class 2
# if lag 2(dim0) - thresh <= lag 1 (dim 3) <= lag2(dim0) + thresh
# class 0
targets[:, 2:][seq[:, 1:-1, 3] > seq[:, :-2, 0] + thresh] = 1
targets[:, 2:][seq[:, 1:-1, 3] < seq[:, :-2, 0] - thresh] = 2
#targets[:, 2:, 0] = np.cast[np.int](seq[:, 1:-1, 3] > seq[:, :-2, 0])
# SequenceDataset wants a list of sequences
# this allows them to be different lengths, but here they're not
seq = [i for i in seq]
targets = [i for i in targets]
gradient_dataset = SequenceDataset([seq, targets], batch_size=None,
number_batches=500)
cg_dataset = SequenceDataset([seq, targets], batch_size=None,
number_batches=100)
model = MetaRNN(n_in=n_in, n_hidden=n_hidden, n_out=n_out,
activation='tanh', output_type='softmax',
use_symbolic_softmax=True)
# optimizes negative log likelihood
# but also reports zero-one error
opt = hf_optimizer(p=model.rnn.params, inputs=[model.x, model.y],
s=model.rnn.y_pred,
costs=[model.rnn.loss(model.y),
model.rnn.errors(model.y)], h=model.rnn.h)
# using settings of initial_lambda and mu given in Nicolas' RNN example
# seem to do a little worse than the default
opt.train(gradient_dataset, cg_dataset, num_updates=n_updates)
seqs = xrange(10)
plt.close('all')
for seq_num in seqs:
fig = plt.figure()
ax1 = plt.subplot(211)
plt.plot(seq[seq_num])
ax1.set_title('input')
ax2 = plt.subplot(212)
# blue line will represent true classes
true_targets = plt.step(xrange(n_steps), targets[seq_num], marker='o')
# show probabilities (in b/w) output by model
guess = model.predict_proba(seq[seq_num])
guessed_probs = plt.imshow(guess.T, interpolation='nearest',
cmap='gray')
ax2.set_title('blue: true class, grayscale: probs assigned by model')
# optimizes negative log likelihood
# but also reports zero-one error
opt = hf_optimizer(p=model.rnn.params, inputs=[model.x, model.y],
s=model.rnn.y_pred, n_in=n_in,
costs=[model.rnn.loss(model.y),
model.rnn.errors(model.y)], h=model.rnn.h)
print("Training ...")
opt.train(gradient_dataset, cg_dataset, initial_lambda=1.0, num_updates=n_updates, save_progress='save_param')
seqs = range(10)
plt.close('all')
for seq_num in seqs:
fig = plt.figure()
ax1 = plt.subplot(211)
plt.plot(x_seq_list[seq_num])
ax1.set_title('input')
ax2 = plt.subplot(212)
# blue line will represent true classes
true_targets = plt.step(range(n_steps), y_seq_list[seq_num], marker='o')
# show probabilities (in b/w) output by model
guess = model.predict_proba(x_seq_list[seq_num])
guessed_probs = plt.imshow(guess.T, interpolation='nearest',
cmap='gray')
ax2.set_title('blue: true class, grayscale: probs assigned by model')
print("Elapsed time: %f" % (time.time() - t0))
def RNN_k_fold_croos_validation(sample, lable, n_updates=20):
X = sample
y = lable
kf = KFold(n_splits=5, shuffle=True)
split_num = kf.get_n_splits(X)
k = 1
G1, G2, S, Total = 0, 0, 0, 0
for train_index, test_index in kf.split(X):
# print("TRAIN:", train_index, "TEST:", test_index)
X_train, X_test = X[train_index], X[test_index]
y_train, y_test = y[train_index], y[test_index]
n_hidden = 10
n_in = 40
n_classes = 3
n_out = n_classes # restricted to single softmax per time step
np.random.seed(0)
train_sample = [i for i in X_train]
train_lable = [i for i in y_train]
gradient_dataset = SequenceDataset([train_sample, train_lable],
batch_size=None,
number_batches=500)
cg_dataset = SequenceDataset([train_sample, train_lable],
batch_size=None,
number_batches=100)
model = MetaRNN(n_in=n_in,
n_hidden=n_hidden,
n_out=n_out,
activation='tanh',
output_type='softmax',
use_symbolic_softmax=True)
opt = hf_optimizer(
p=model.rnn.params,
inputs=[model.x, model.y],
s=model.rnn.y_pred,
costs=[model.rnn.loss(model.y),
model.rnn.errors(model.y)],
h=model.rnn.h)
opt.train(gradient_dataset, cg_dataset, num_updates=n_updates)
right, first, second, third = 0, 0, 0, 0
first_sum, second_sum, third_sum = 0, 0, 0
for count in range(0, X_test.shape[0]):
guess = model.predict_proba(X_test[count])
tmp_list = np.ndarray.tolist(guess.T)
# print test_sample.shape
if (y_test[count][0] == 0):
first_sum += 1
if (tmp_list.index(max(tmp_list)) == y_test[count][0]):
print True
first += 1
right += 1
else:
print k, False
elif (y_test[count][0] == 1):
second_sum += 1
if (tmp_list.index(max(tmp_list)) == y_test[count][0]):
print True
second += 1
right += 1
else:
print False
else:
third_sum += 1
if (tmp_list.index(max(tmp_list)) == y_test[count][0]):
print True
third += 1
right += 1
else:
print False
print "...................................................................................................."
print k, "interation"
print "...................................................................................................."
G1 = G1 + 1.0 * first / first_sum
S = S + 1.0 * second / second_sum
G2 = G2 + 1.0 * third / third_sum
Total = Total + 1.0 * right / X_test.shape[0]
print "class G1:", G1 / k
print "class S:", S / k
print "class G2:", G2 / k
print "class total:", Total / k
k += 1
print "...................................................................................................."
print "Final Result:"
print "...................................................................................................."
print "class G1:", G1 / split_num
print "class S:", S / split_num
print "class G2:", G2 / split_num
print "class total:", Total / split_num
def RNN_leave_one_cross_validation(seq, targets, n_updates=250, n_seq=182):
""" Test RNN with softmax outputs. """
length = len(seq)
right, first, second, third = 0, 0, 0, 0
false_list = []
for k in range(0, length):
n_hidden = 10
n_in = 40
n_classes = 3
n_out = n_classes # restricted to single softmax per time step
np.random.seed(0)
train_sample = copy.deepcopy(seq)
train_lable = copy.deepcopy(targets)
test_sample = seq[k]
train_sample = np.delete(train_sample, k, 0)
train_lable = np.delete(train_lable, k, 0)
train_sample = [i for i in train_sample]
train_lable = [i for i in train_lable]
gradient_dataset = SequenceDataset([train_sample, train_lable],
batch_size=None,
number_batches=500)
cg_dataset = SequenceDataset([train_sample, train_lable],
batch_size=None,
number_batches=100)
model = MetaRNN(n_in=n_in,
n_hidden=n_hidden,
n_out=n_out,
activation='tanh',
output_type='softmax',
use_symbolic_softmax=True)
opt = hf_optimizer(
p=model.rnn.params,
inputs=[model.x, model.y],
s=model.rnn.y_pred,
costs=[model.rnn.loss(model.y),
model.rnn.errors(model.y)],
h=model.rnn.h)
opt.train(gradient_dataset, cg_dataset, num_updates=n_updates)
guess = model.predict_proba(test_sample)
tmp_list = np.ndarray.tolist(guess.T)
# print tmp_list
if (targets[k][0] == 0):
if (tmp_list.index(max(tmp_list)) == targets[k][0]):
print k, True
first += 1
right += 1
else:
print k, False
false_list.append(k)
elif (targets[k][0] == 1):
if (tmp_list.index(max(tmp_list)) == targets[k][0]):
print k, True
second += 1
right += 1
else:
print k, False
false_list.append(k)
else:
if (tmp_list.index(max(tmp_list)) == targets[k][0]):
print k, True
third += 1
right += 1
else:
print k, False
false_list.append(k)
print "class G1:", 1.0 * first / 59
print "class S:", 1.0 * second / 58
print "class G2:", 1.0 * third / 65
print "class total:", 1.0 * right / length
print false_list
def test_binary(multiple_out=False, n_updates=250):
""" Test RNN with binary outputs. """
n_hidden = 10
n_in = 5
if multiple_out:
n_out = 2
else:
n_out = 1
n_steps = 10
n_seq = 100
np.random.seed(0)
# simple lag test
seq = np.random.randn(n_seq, n_steps, n_in)
targets = np.zeros((n_seq, n_steps, n_out), dtype='int32')
# whether lag 1 (dim 3) is greater than lag 2 (dim 0)
targets[:, 2:, 0] = np.cast[np.int32](seq[:, 1:-1, 3] > seq[:, :-2, 0])
if multiple_out:
# whether product of lag 1 (dim 4) and lag 1 (dim 2)
# is less than lag 2 (dim 0)
targets[:, 2:, 1] = np.cast[np.int32](
(seq[:, 1:-1, 4] * seq[:, 1:-1, 2]) > seq[:, :-2, 0])
# SequenceDataset wants a list of sequences
# this allows them to be different lengths, but here they're not
seq = [i for i in seq]
targets = [i for i in targets]
gradient_dataset = SequenceDataset([seq, targets], batch_size=None,
number_batches=500)
cg_dataset = SequenceDataset([seq, targets], batch_size=None,
number_batches=100)
model = MetaRNN(n_in=n_in, n_hidden=n_hidden, n_out=n_out,
activation='tanh', output_type='binary')
# optimizes negative log likelihood
# but also reports zero-one error
opt = hf_optimizer(p=model.rnn.params, inputs=[model.x, model.y],
s=model.rnn.y_pred,
costs=[model.rnn.loss(model.y),
model.rnn.errors(model.y)], h=model.rnn.h)
# using settings of initial_lambda and mu given in Nicolas' RNN example
# seem to do a little worse than the default
opt.train(gradient_dataset, cg_dataset, num_updates=n_updates)
seqs = range(10)
plt.close('all')
for seq_num in seqs:
fig = plt.figure()
ax1 = plt.subplot(211)
plt.plot(seq[seq_num])
ax1.set_title('input')
ax2 = plt.subplot(212)
true_targets = plt.step(range(n_steps), targets[seq_num], marker='o')
guess = model.predict_proba(seq[seq_num])
guessed_targets = plt.step(range(n_steps), guess)
plt.setp(guessed_targets, linestyle='--', marker='d')
for i, x in enumerate(guessed_targets):
x.set_color(true_targets[i].get_color())
ax2.set_ylim((-0.1, 1.1))
ax2.set_title('solid: true output, dashed: model output (prob)')
def test_softmax(n_updates=250):
""" Test RNN with softmax outputs. """
n_hidden = 10
n_in = 5
n_steps = 10
n_seq = 100
n_classes = 3
n_out = n_classes # restricted to single softmax per time step
np.random.seed(0)
# simple lag test
seq = np.random.randn(n_seq, n_steps, n_in)
targets = np.zeros((n_seq, n_steps), dtype='int32')
thresh = 0.5
# if lag 1 (dim 3) is greater than lag 2 (dim 0) + thresh
# class 1
# if lag 1 (dim 3) is less than lag 2 (dim 0) - thresh
# class 2
# if lag 2(dim0) - thresh <= lag 1 (dim 3) <= lag2(dim0) + thresh
# class 0
targets[:, 2:][seq[:, 1:-1, 3] > seq[:, :-2, 0] + thresh] = 1
targets[:, 2:][seq[:, 1:-1, 3] < seq[:, :-2, 0] - thresh] = 2
#targets[:, 2:, 0] = np.cast[np.int](seq[:, 1:-1, 3] > seq[:, :-2, 0])
# SequenceDataset wants a list of sequences
# this allows them to be different lengths, but here they're not
seq = [i for i in seq]
targets = [i for i in targets]
gradient_dataset = SequenceDataset([seq, targets], batch_size=None,
number_batches=500)
cg_dataset = SequenceDataset([seq, targets], batch_size=None,
number_batches=100)
model = MetaRNN(n_in=n_in, n_hidden=n_hidden, n_out=n_out,
activation='tanh', output_type='softmax',
use_symbolic_softmax=True)
# optimizes negative log likelihood
# but also reports zero-one error
opt = hf_optimizer(p=model.rnn.params, inputs=[model.x, model.y],
s=model.rnn.y_pred,
costs=[model.rnn.loss(model.y),
model.rnn.errors(model.y)], h=model.rnn.h)
# using settings of initial_lambda and mu given in Nicolas' RNN example
# seem to do a little worse than the default
opt.train(gradient_dataset, cg_dataset, num_updates=n_updates)
seqs = range(10)
plt.close('all')
for seq_num in seqs:
fig = plt.figure()
ax1 = plt.subplot(211)
plt.plot(seq[seq_num])
ax1.set_title('input')
ax2 = plt.subplot(212)
# blue line will represent true classes
true_targets = plt.step(range(n_steps), targets[seq_num], marker='o')
# show probabilities (in b/w) output by model
guess = model.predict_proba(seq[seq_num])
guessed_probs = plt.imshow(guess.T, interpolation='nearest',
cmap='gray')
ax2.set_title('blue: true class, grayscale: probs assigned by model')
