def test_real(n_updates=100):
""" Test RNN with real-valued outputs. """
n_hidden = 10
n_in = 5
n_out = 3
n_steps = 10
n_seq = 1000
np.random.seed(0)
# simple lag test
seq = np.random.randn(n_seq, n_steps, n_in)
print 'seq1'
print seq
targets = np.zeros((n_seq, n_steps, n_out))
targets[:, 1:, 0] = seq[:, :-1, 3] # delayed 1
targets[:, 1:, 1] = seq[:, :-1, 2] # delayed 1
targets[:, 2:, 2] = seq[:, :-2, 0] # delayed 2
targets += 0.01 * np.random.standard_normal(targets.shape)
print 'targets'
print targets
# SequenceDataset wants a list of sequences
# this allows them to be different lengths, but here they're not
seq = [i for i in seq]
print 'seq2'
print seq
targets = [i for i in targets]
gradient_dataset = SequenceDataset([seq, targets], batch_size=None,
number_batches=100)
cg_dataset = SequenceDataset([seq, targets], batch_size=None,
number_batches=20)
model = MetaRNN(n_in=n_in, n_hidden=n_hidden, n_out=n_out,
activation='tanh')
opt = hf_optimizer(p=model.rnn.params, inputs=[model.x, model.y],
s=model.rnn.y_pred,
costs=[model.rnn.loss(model.y)], h=model.rnn.h)
print model
opt.train(gradient_dataset, cg_dataset, num_updates=n_updates)
plt.close('all')
fig = plt.figure()
ax1 = plt.subplot(211)
plt.plot(seq[0])
ax1.set_title('input')
ax2 = plt.subplot(212)
true_targets = plt.plot(targets[0])
guess = model.predict(seq[0])
guessed_targets = plt.plot(guess, linestyle='--')
for i, x in enumerate(guessed_targets):
x.set_color(true_targets[i].get_color())
ax2.set_title('solid: true output, dashed: model output')
def test_Oscillator(n_updates=50):
""" Test RNN with real-valued outputs. """
n_hidden = 250
n_in = 1
n_out = 2
n_steps = 200
n_seq = 1
fracZero = 2
np.random.seed(np.random.randint(200)+52)
baseFreq = np.linspace(0,numpy.pi*4,n_steps)
seq = np.zeros((n_seq,n_steps,n_in))
#sigDecay = np.zeros((n_steps/2))
#sigDecay[:(n_steps/fracZero)/2] = np.linspace(1,0,(n_steps/fracZero)/2)
#seqSig = sigDecay * np.cos(baseFreq)/2 + 1
#seq[:,n_steps/4:n_steps*3/4,0] = np.tile(seqSig,(n_seq,1))
#seq[:,n_steps/4:3*n_steps/4,0]]
seq[:,:n_steps/fracZero,0] = np.tile(np.linspace(1,0,num=n_steps/fracZero) * np.cos(baseFreq[:n_steps/fracZero]),(n_seq,1))
#seq = np.random.randn(n_seq, n_steps, n_in)
targets = np.zeros((n_seq, n_steps, n_out))
targets[:, :, 0] = np.tile(np.cos(baseFreq),(n_seq,1))
targets[:, :, 1] = np.tile(np.sin(baseFreq),(n_seq,1))
# 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=2)
cg_dataset = SequenceDataset([seq, targets], batch_size=None,
number_batches=2)
model = MetaRNN(n_in=n_in, n_hidden=n_hidden, n_out=n_out,
activation='cappedrelu')
opt = hf_optimizer(p=model.rnn.params, inputs=[model.x, model.y],
s=model.rnn.y_pred,
costs=[model.rnn.loss(model.y)], h=model.rnn.h)
opt.train(gradient_dataset, cg_dataset, num_updates=n_updates)
plt.close('all')
fig = plt.figure()
ax1 = plt.subplot(211)
plt.plot(seq[0])
ax1.set_title('input')
ax2 = plt.subplot(212)
true_targets = plt.plot(targets[0])
guess = model.predict(seq[0])
guessed_targets = plt.plot(guess, linestyle='--')
for i, x in enumerate(guessed_targets):
x.set_color(true_targets[i].get_color())
ax2.set_title('solid: true output, dashed: model output')
return model
def test_real(n_updates=100):
""" Test RNN with real-valued outputs. """
n_hidden = 10
n_in = 5
n_out = 3
n_steps = 10
n_seq = 1000
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))
targets[:, 1:, 0] = seq[:, :-1, 3] # delayed 1
targets[:, 1:, 1] = seq[:, :-1, 2] # delayed 1
targets[:, 2:, 2] = seq[:, :-2, 0] # delayed 2
targets += 0.01 * np.random.standard_normal(targets.shape)
# 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=100)
cg_dataset = SequenceDataset([seq, targets],
batch_size=None,
number_batches=20)
model = MetaRNN(n_in=n_in,
n_hidden=n_hidden,
n_out=n_out,
activation='tanh')
opt = hf_optimizer(p=model.rnn.params,
inputs=[model.x, model.y],
s=model.rnn.y_pred,
costs=[model.rnn.loss(model.y)],
h=model.rnn.h)
opt.train(gradient_dataset, cg_dataset, num_updates=n_updates)
plt.close('all')
fig = plt.figure()
ax1 = plt.subplot(211)
plt.plot(seq[0])
ax1.set_title('input')
ax2 = plt.subplot(212)
true_targets = plt.plot(targets[0])
guess = model.predict(seq[0])
guessed_targets = plt.plot(guess, linestyle='--')
for i, x in enumerate(guessed_targets):
x.set_color(true_targets[i].get_color())
ax2.set_title('solid: true output, dashed: model output')
model = MetaRNN(n_in=n_in,
n_mul=n_hidden,
n_out=n_out,
activation='tanh')
opt = hf_optimizer(p=model.rnn.params,
inputs=[model.x, model.y],
s=model.rnn.y_pred,
costs=[model.rnn.loss(model.y)],
h=model.rnn.h)
opt.train(gradient_dataset, cg_dataset, num_updates=30)
path = '/root/chentian/share/201605/one_ped1/%d' % index
os.mkdir(path)
path0 = path + '/predict.csv'
f3 = file(path0, "a")
for seq_num in range(0, n_seq):
guess = model.predict(test_seqs[seq_num])
np.savetxt(f3, guess, delimiter=',')
f3.close()
pre_f = file(path0, "r")
pre = np.loadtxt(pre_f, delimiter=',')
pre_f.close()
path3 = path + "/error.csv"
f8 = file(path3, "a")
error = (pre - test_target)**2
np.savetxt(f8, error, delimiter=',')
f8.close()
print "traning over"
print "Elapsed time: %f" % (time.time() - t0)
n_out = 1 # K
n_steps = 1 # the length of each sequence
n_seq = len(food_sel_scaled_train) # the number of datapoints (i.e. sequences)
#Creating input and output arrays for training RNN
rating = np.array(food_sel_scaled_train[['rating','price.tier','stats.checkinsCount']]).reshape(n_seq,n_steps,n_in)
score = np.array(food_sel_scaled_train['SCORE']).reshape(n_seq,n_steps,n_out)
#Creating the model and feeding it with training data set
model = MetaRNN(n_in=n_in, n_hidden=n_hidden, n_out=n_out,
learning_rate=0.001, learning_rate_decay=0.999,
n_epochs=50, activation='tanh')
model.fit(rating, score, validation_frequency=5000)
guess = model.predict(rating.reshape(len(rating), n_in))
scores_pred = pd.DataFrame(guess)
scores_pred.columns = ['predictions']
scores_pred.predictions.plot(kind='hist', bins=20, figsize=(6,4), grid=True, title = "Histogram of predicted DOH normalized Scores (IS)", alpha=0.8)
food_sel_scaled_train.SCORE.plot(kind='hist', bins=20, figsize=(6,4), grid=True, title = "Histogram of actual DOH normalized Scores (IS)", alpha=0.8)
#Creating parameters for training RNN
n_hidden = 5 # M
n_in = 3 # D
n_out = 1 # K
n_steps = 1 # the length of each sequence
n_seq = len(food_sel_scaled_test) # the number of datapoints (i.e. sequences)
opt = hf_optimizer(p=model.rnn.params,
inputs=[model.x, model.y],
s=model.rnn.y_pred,
costs=[model.rnn.loss(model.y)],
h=model.rnn.h)
opt.train(gradient_dataset, cg_dataset, num_updates=300)
print "traning over"
path = '/root/chentian/share/201605/ped1'
# os.makedirs(path)
path0 = path + '/predict.csv'
f3 = file(path0, "a")
for k in range(0, n_seqs):
guess = model.predict(test_seqs[k])
np.savetxt(f3, guess, delimiter=',')
f3.close()
error1 = np.zeros([6800, 1104])
pre_f = file(path0, "r")
pre = np.loadtxt(pre_f, delimiter=',')
pre_f.close()
path3 = path + "/error.csv"
f8 = file(path3, "a")
error = (pre - test_targets)**2
for i in range(0, 46):
error1[:, i * 24:(i + 1) * 24] = error[i * 6800:(i + 1) * 6800, :]
np.savetxt(f8, error1, delimiter=',')
f8.close()
rating = np.array(food_sel_scaled_train[[
'rating', 'price.tier', 'stats.checkinsCount'
]]).reshape(n_seq, n_steps, n_in)
score = np.array(food_sel_scaled_train['SCORE']).reshape(n_seq, n_steps, n_out)
#Creating the model and feeding it with training data set
model = MetaRNN(n_in=n_in,
n_hidden=n_hidden,
n_out=n_out,
learning_rate=0.001,
learning_rate_decay=0.999,
n_epochs=50,
activation='tanh')
model.fit(rating, score, validation_frequency=5000)
guess = model.predict(rating.reshape(len(rating), n_in))
scores_pred = pd.DataFrame(guess)
scores_pred.columns = ['predictions']
scores_pred.predictions.plot(
kind='hist',
bins=20,
figsize=(6, 4),
grid=True,
title="Histogram of predicted DOH normalized Scores (IS)",
alpha=0.8)
food_sel_scaled_train.SCORE.plot(
kind='hist',
bins=20,
