log.addHandler(fh)
data_path = os.path.join(FILE_PATH, './model', MODEL_NAME)
try:
## load model and dataset
X = pickle.load(
open(
data_path + "/x_set" + str(lstm.IN_TIMESTEPS) +
str(lstm.OUT_TIMESTEPS_RANGE[-1]) + ".pkl", "rb"))
Y = pickle.load(
open(
data_path + "/y_set" + str(lstm.IN_TIMESTEPS) +
str(lstm.OUT_TIMESTEPS_RANGE[-1]) + ".pkl", "rb"))
except:
## generate train/val/test datasets based on raw data
X, Y = generate_data('./reg_fmt_datasets.pkl')
# save dataset
os.mkdir(data_path)
pickle.dump(
X,
open(
data_path + "/x_set" + str(lstm.IN_TIMESTEPS) +
str(lstm.OUT_TIMESTEPS_RANGE[-1]) + ".pkl", "wb"))
pickle.dump(
Y,
open(
data_path + "/y_set" + str(lstm.IN_TIMESTEPS) +
str(lstm.OUT_TIMESTEPS_RANGE[-1]) + ".pkl", "wb"))
print("Save data successfully!")
## build the lstm model
from data_processing import generate_data
tf.logging.set_verbosity(tf.logging.INFO)
LOG_DIR = './ops_logs/sin'
TIMESTEPS = 3
RNN_LAYERS = [{'num_units': 5}]
DENSE_LAYERS = None
TRAINING_STEPS = 10000
PRINT_STEPS = TRAINING_STEPS / 10
BATCH_SIZE = 100
regressor = learn.SKCompat(
learn.Estimator(
model_fn=lstm_model(TIMESTEPS, RNN_LAYERS, DENSE_LAYERS),
model_dir=LOG_DIR))
X, y = generate_data(
np.sin,
np.linspace(0, 100, 10000, dtype=np.float32),
TIMESTEPS,
seperate=False)
# create a lstm instance and validation monitor
validation_monitor = learn.monitors.ValidationMonitor(X['val'], y['val'], every_n_steps=PRINT_STEPS, early_stopping_rounds=1000)
print(X['train'])
print(y['train'])
regressor.fit(
X['train'],
y['train'],
monitors=[validation_monitor],
batch_size=BATCH_SIZE,
steps=TRAINING_STEPS)
BATCH_SIZE = 100
LOG_DIR = './ops_logs/lstm/' + str(TIMESTEPS) + str(OUTPUT_TIMESTEPS)
# MODEL_SAVED_PATH = './snapshot/model.ckpt'
# MODEL_SAVED_DIR = './snapshot'
def mse(pred, true):
return np.sqrt(((pred - true)**2).mean())
## build the lstm model
model_fn = lstm_model(TIMESTEPS, RNN_LAYERS, DENSE_LAYERS)
## generate train/val/test datasets based on raw data
X, y = generate_data('./reg_fmt_datasets.pkl', TIMESTEPS, OUTPUT_TIMESTEPS)
estimator = learn.Estimator(model_fn=model_fn, model_dir=LOG_DIR)
# estimator = tf.estimator.Estimator(model_fn = model_fn, model_dir = LOG_DIR)
regressor = learn.SKCompat(estimator)
## create a validation monitor
validation_monitor = learn.monitors.ValidationMonitor(
X['val'], y['val'], every_n_steps=PRINT_STEPS)
## fit the train dataset
regressor.fit(X['train'],
y['train'],
monitors=[validation_monitor],
batch_size=BATCH_SIZE,
steps=TRAINING_STEPS)
import numpy as np
from data_processing import process_data, generate_data, histogram
from Decision_stump import one_dimension_decision_stump, multi_dimension_decision_stump, check_accuracy,Out_of_sample_error
if __name__ == '__main__':
#Q17, Q18
E_in_list = []
E_out_list = []
for i in range(5000):
X, Y = generate_data(10, 5)
score, s, theta = one_dimension_decision_stump(X, Y)
E_in_list.append((10-float(score))/10)
E_out_list.append(Out_of_sample_error(s, theta))
histogram(E_in_list, 'qustion 17', 'in sample error', 'frequency')
print "Question 17: average in sample error: %f" % (sum(E_in_list)/5000)
histogram(E_out_list, 'qustion 18', 'out of sample error', 'frequency')
print "Question 18: average out of sample error: %f" % (sum(E_out_list)/5000)
#Q19
X_train, Y_train = process_data('./hw2_train.dat')
X_test, Y_test = process_data('./hw2_test.dat')
best_record, s, theta, index = multi_dimension_decision_stump(X_train, Y_train)
print "Qustion 19: index: %d, h = %d * sign(x - %f), in sample error: %f" % (index, s, theta, (len(Y_train)-float(best_record))/len(Y_train))
X_test_trans = np.transpose(X_test)
accuracy = check_accuracy(s, theta, X_test_trans[index], Y_test)
print "Qustion 20: out of sample error: %f" % (1 - accuracy)
# construct learner and train
encoder = RNN(input_dim=4,
h_dim=100,
o_dim=22,
bptt_truncate=4,
rnn_role='encoder')
decoder = RNN(input_dim=22,
h_dim=100,
o_dim=22,
bptt_truncate=4,
rnn_role='decoder')
seq_2_seq_learner = Seq2Seq(encoder, decoder)
# training data prep
data = generate_data(n=data_size, encoded=encoded)
loss = []
for i in range(epoch):
print("\nEpoch {} ...".format(i))
current_loss = seq_2_seq_learner.train(
data,
learning_rate=learning_rate,
reverse_input=False,
stop_vec=ptn_stop_vec,
data_print_interval=data_print_interval)
loss.append((i, current_loss))
if i % epoch_print_interval == 0:
print("Current Loss after epoch {}: {}\n".format(i, current_loss))
# prepare test data
test_cdna_file = "data/cDNA_CFTR.fa"
os.makedirs(FLAGS.sample_dir)
# the current file path
FILE_PATH = os.path.dirname(__file__)
TASK_NAME_LIST = []
data_path = os.path.join(FILE_PATH, './model', FLAGS.model_name)
if FLAGS.run_mode is 0:
try:
## load model and dataset
X = pickle.load(open(data_path + "/x_set_train" + ".pkl", "rb"))
Y = pickle.load(open(data_path + "/y_set_train" + ".pkl", "rb"))
except:
## generate train/val/test datasets based on raw data
X, Y = generate_data('./reg_fmt_datasets_1spd.pkl')
# save dataset
# os.mkdir(data_path)
pickle.dump(X, open(data_path + "/x_set_train" + ".pkl", "wb"))
pickle.dump(Y, open(data_path + "/y_set_train" + ".pkl", "wb"))
print("Save data successfully!")
else:
try:
## load model and dataset
X = pickle.load(open(data_path + "/x_set_test" + ".pkl", "rb"))
Y = pickle.load(open(data_path + "/y_set_test" + ".pkl", "rb"))
except:
## generate train/val/test datasets based on raw data
X, Y = generate_data('./reg_fmt_datasets_6spd.pkl')
# save dataset
# os.mkdir(data_path)