def load_physio(feature_funcs):
description = """ Loads a dataset containing physiological data.
It returns a Bunch with the following attributes:
- data: n_samples by n_features 2D array. There are 7890 samples
(patient episodes), and 52 features (mean, standard deviation, max
and min for each of 13 physiological variables)
- c_target: target variable to be used for classification: mortality.
0 indicates survival, 1 indicates death.
- r_target: target variable to be used for regression: length of stay
in days.
- DESCR: a description of this dataset (for now, the docstring of
this function)
"""
headers, episodes = datafiles.load_episodes()
headers, outcomes = datafiles.load_outcomes() # don't care about headers
# construct the prediction dataset
num_samples = len(episodes)
num_features = len(feature_funcs) * datafiles.NUM_VARS
data = np.zeros((num_samples, num_features))
# for each sample (episode)
for i, (episode_id, episode_data) in enumerate(episodes):
# compute its features (stats for each physiological variable)
for v in range(datafiles.NUM_VARS):
start = v * len(feature_funcs)
end = (v + 1) * len(feature_funcs)
data[i, start:end] = _compute_features(episode_data[v],
feature_funcs)
# obtain the target variables
episode_ids, episode_outcomes = unzip(outcomes)
los, mortality, med_los = map(np.asarray, unzip(episode_outcomes))
# mortality, for classification
c_target = mortality
# length of stay, for regression
r_target = np.floor(los / (24 * 60 * 60)) # convert from secs to days
result = Bunch(data=data,
r_target=r_target,
c_target=c_target,
DESCR=description)
return result
def load_physio(feature_funcs):
description = """ Loads a dataset containing physiological data.
It returns a Bunch with the following attributes:
- data: n_samples by n_features 2D array. There are 7890 samples
(patient episodes), and 52 features (mean, standard deviation, max
and min for each of 13 physiological variables)
- c_target: target variable to be used for classification: mortality.
0 indicates survival, 1 indicates death.
- r_target: target variable to be used for regression: length of stay
in days.
- DESCR: a description of this dataset (for now, the docstring of
this function)
"""
headers, episodes = datafiles.load_episodes()
headers, outcomes = datafiles.load_outcomes() # don't care about headers
# construct the prediction dataset
num_samples = len(episodes)
num_features = len(feature_funcs) * datafiles.NUM_VARS
data = np.zeros((num_samples, num_features))
# for each sample (episode)
for i, (episode_id, episode_data) in enumerate(episodes):
# compute its features (stats for each physiological variable)
for v in range(datafiles.NUM_VARS):
start = v * len(feature_funcs)
end = (v + 1) * len(feature_funcs)
data[i, start:end] =_compute_features(episode_data[v],
feature_funcs)
# obtain the target variables
episode_ids, episode_outcomes = unzip(outcomes)
los, mortality, med_los = map(np.asarray, unzip(episode_outcomes))
# mortality, for classification
c_target = mortality
# length of stay, for regression
r_target = np.floor(los / (24 * 60 * 60)) # convert from secs to days
result = Bunch(data=data,
r_target=r_target,
c_target=c_target,
DESCR=description)
return result
def _compute_features(measurements, functions):
""" Compute basic features for a time series of measurements """
features = np.zeros(len(functions))
if measurements:
times, values = map(np.asarray, unzip(measurements))
for i, f in enumerate(functions):
features[i] = f(values, times)
return features
def _compute_features(measurements, functions):
""" Compute basic features for a time series of measurements """
features = np.zeros(len(functions))
if measurements:
times, values = map(np.asarray, unzip(measurements))
for i, f in enumerate(functions):
features[i] = f(values, times)
return features
testing_data = data[training_size:training_size + testing_size]
return training_data, testing_data
training_data, testing_data = get_mnist_data(60000, 10000)
evaluate, train, save = build_mnist_model()
printer = Printer(0.1)
encoder = OneHotEncoder(10)
iterations = 5
batch_sizes = 5
for itr in range(iterations):
# Preparing the training data
np.random.shuffle(training_data)
inputs, targets = unzip(training_data)
input_batches = np.array_split(np.asarray(inputs),
len(inputs) / batch_sizes)
target_batches = np.array_split(np.asarray(targets),
len(targets) / batch_sizes)
if itr == 0:
print 'training with', len(input_batches), 'batches of size', len(
input_batches[0])
total_iteartions = len(input_batches) * iterations
for i, (input_batch,
target_batch) in enumerate(zip(input_batches, target_batches)):
target_batch = encoder.encode(target_batch)
error = train(input_batch, target_batch, 4)
current_iteration = itr * len(input_batches) + i
training_data = data[0:training_size]
testing_data = data[training_size:training_size+testing_size]
return training_data, testing_data
training_data, testing_data = get_mnist_data(60000, 10000)
evaluate, train, save = build_mnist_model()
printer = Printer(0.1)
encoder = OneHotEncoder(10)
iterations = 5
batch_sizes = 5
for itr in range(iterations):
# Preparing the training data
np.random.shuffle(training_data)
inputs, targets = unzip(training_data)
input_batches = np.array_split(np.asarray(inputs), len(inputs) / batch_sizes)
target_batches = np.array_split(np.asarray(targets), len(targets) / batch_sizes)
if itr == 0:
print 'training with', len(input_batches), 'batches of size', len(input_batches[0])
total_iteartions = len(input_batches) * iterations
for i, (input_batch, target_batch) in enumerate(zip(input_batches, target_batches)):
target_batch = encoder.encode(target_batch)
error = train(input_batch, target_batch, 4)
current_iteration = itr*len(input_batches) + i
printer.overwrite('training ' + str(int(current_iteration * 100. / total_iteartions)) + '% - error:' + str(error))
printer.clear()
