def test_load_dataset(self):
""" Tests the load_data function """
# if the dataset doesn't exist
with self.assertRaises(IOError):
ds.load_dataset("this one definitely doesn't exist either",
"")
def augment(dataset, format, shift_size):
"""
Parameters
----------
dataset :
format :
shift_size :
Returns
-------
"""
shift_size *= (math.pi/180.0)
num_shifts = int(2*math.pi / shift_size)
x_train, y_train, x_test, y_test = ds.load_dataset(dataset, format)
augmented_x = np.zeros((x_train.shape[0]*num_shifts, x_train.shape[1]))
augmented_y = np.zeros((y_train.shape[0]*num_shifts, y_train.shape[1]))
for ix, line in enumerate(x_train):
if (ix+1)%1000 == 0: print ix+1
for s in xrange(num_shifts):
shift = s * shift_size
augmented_x[ix*num_shifts+s] = [verify_angle(val+shift) if index%4==2 else val for index,val in enumerate(line)]
augmented_y[ix*num_shifts+s] = y_train[ix]
tr.shuffle_in_unison(augmented_x, augmented_y)
output_path = os.path.join(ds.get_path_to_dataset(dataset), "augmented_{}.npz".format(format))
np.savez(output_path, x_train=augmented_x, x_test=x_test, y_train=augmented_y, y_test=y_test)
def _save_by_jet_num(dataset, num_jets):
data, format = dataset.split('/')
x_train, y_train, x_test, y_test = ds.load_dataset(data, format)
if num_jets.endswith("+"):
val = lambda x: x >= int(num_jets[:-1])
elif num_jets.endswith("-"):
val = lambda x: x <= int(num_jets[:-1])
else:
val = lambda x: x == int(num_jets)
all_x = np.concatenate((x_train, x_test), axis=0)
all_y = np.concatenate((y_train, y_test), axis=0)
nulls = np.zeros((all_x.shape[0], all_x.shape[1]/4), dtype=np.bool)
for y in xrange(all_x.shape[1]/4):
for ix, row in enumerate((x_train > 0)[:, y*4:(y+1)*4]):
nulls[ix, y] = all(row == 0)
events_with_x_jets = val(np.array([row[:-2].sum() for row in ~nulls]))
all_x, all_y = all_x[events_with_x_jets], all_y[events_with_x_jets]
tr.shuffle_in_unison(all_x, all_y)
cutoff = int(all_x.shape[0] * 0.8) # 80% training 20% testing
train_x = all_x[:cutoff]
train_y = all_y[:cutoff]
test_x = all_x[cutoff:]
test_y = all_y[cutoff:]
output_path = os.path.join(ds.get_path_to_dataset(data), "{}jets_{}.npz".format(num_jets, format))
np.savez(output_path, x_train=train_x, x_test=test_x, y_train=train_y, y_test=test_y)
def _save_by_jet_num(dataset, num_jets):
data, format = dataset.split('/')
x_train, y_train, x_test, y_test = ds.load_dataset(data, format)
if num_jets.endswith("+"):
val = lambda x: x >= int(num_jets[:-1])
elif num_jets.endswith("-"):
val = lambda x: x <= int(num_jets[:-1])
else:
val = lambda x: x == int(num_jets)
all_x = np.concatenate((x_train, x_test), axis=0)
all_y = np.concatenate((y_train, y_test), axis=0)
nulls = np.zeros((all_x.shape[0], all_x.shape[1]/4), dtype=np.bool)
for y in xrange(all_x.shape[1]/4):
for ix, row in enumerate((x_train > 0)[:, y*4:(y+1)*4]):
nulls[ix, y] = all(row == 0)
events_with_x_jets = val(np.array([row[:-2].sum() for row in ~nulls]))
all_x, all_y = all_x[events_with_x_jets], all_y[events_with_x_jets]
tr.shuffle_in_unison(all_x, all_y)
cutoff = int(all_x.shape[0] * 0.8) # 80% training 20% testing
train_x = all_x[:cutoff]
train_y = all_y[:cutoff]
test_x = all_x[cutoff:]
test_y = all_y[cutoff:]
output_path = os.path.join(ds.get_path_to_dataset(data), "{}jets_{}.npz".format(num_jets, format))
np.savez(output_path, x_train=train_x, x_test=test_x, y_train=train_y, y_test=test_y)
def augment(dataset, format, shift_size):
shift_size *= (math.pi/180.0)
num_shifts = int(2*math.pi / shift_size)
x_train, y_train, x_test, y_test = ds.load_dataset(dataset, format)
augmented_x = np.zeros((x_train.shape[0]*num_shifts, x_train.shape[1]))
augmented_y = np.zeros((y_train.shape[0]*num_shifts, y_train.shape[1]))
for ix, line in enumerate(x_train):
if (ix+1)%1000 == 0: print ix+1
for s in xrange(num_shifts):
shift = s * shift_size
augmented_x[ix*num_shifts+s] = [verify_angle(val+shift) if index%4==2 else val for index,val in enumerate(line)]
augmented_y[ix*num_shifts+s] = y_train[ix]
tr.shuffle_in_unison(augmented_x, augmented_y)
output_path = os.path.join(ds.get_path_to_dataset(dataset), "augmented_{}.npz".format(format))
np.savez(output_path, x_train=augmented_x, x_test=x_test, y_train=augmented_y, y_test=y_test)
def permutate_individual_sorted(dataset):
""" Only use this for sorted data! Also, this takes up a significant amount of RAM """
data, format = dataset.split('/')
x_train, y_train, x_test, y_test = ds.load_dataset(data, format)
# Generate permutations, transforms, and alter the dataset
perms = list(gen_permutations(2, 7, 2))
num_perms = len(perms)
aperms = np.array(perms)
labels = np.zeros(aperms.shape)
r = np.arange(11)
for i,p in enumerate(aperms):
labels[i] = (p == r).astype('int32')
transforms = np.zeros((44, 44 * num_perms))
for i, p in enumerate(perms):
transforms[:, i * 44:(i + 1) * 44] = E(p)
# For the training data
sorted_train_x = np.zeros((x_train.shape[0] * num_perms, x_train.shape[1]))
sorted_train_y = np.zeros((sorted_train_x.shape[0], 2))
for i, batch in enumerate(x_train):
event = np.dot(batch, transforms).reshape((num_perms, x_train.shape[1]))
arange = np.arange(num_perms)
np.random.shuffle(arange)
sorted_train_x[i * num_perms:(i + 1) * num_perms] = event[arange]
sorted_train_y[i * num_perms:(i + 1) * num_perms] = labels[arange]
# For the testing data
sorted_test_x = np.zeros((x_test.shape[0] * num_perms, x_test.shape[1]))
sorted_test_y = np.zeros((sorted_test_x.shape[0], 2))
for i, batch in enumerate(x_test):
event = np.dot(batch, transforms).reshape((num_perms, x_test.shape[1]))
arange = np.arange(num_perms)
np.random.shuffle(arange)
sorted_test_x[i * num_perms:(i + 1) * num_perms] = event[arange]
sorted_test_y[i * num_perms:(i + 1) * num_perms] = labels[arange]
output_path = os.path.join(ds.get_path_to_dataset(data), "{}_{}.npz".format(format, "Permuted"))
np.savez(output_path, x_train=sorted_train_x, x_test=sorted_test_x, y_train=sorted_train_y, y_test=sorted_test_y)
cutoff = 1-i*(1/datapoints)
e_b[i], e_s[i] = efficiencies(model, data, cutoff)[:,1]
if experiment_epoch:
point = experiment_epoch.curve.add()
point.signal = e_s[i]
point.background = e_b[i]
point.cutoff = cutoff
if save:
plt.plot(e_b, e_s)
plt.title("Efficiency Curve")
plt.ylabel("Signal Efficiency")
plt.xlabel("Background Inefficiency")
plt.savefig(save, format="png")
return trapz(e_s,e_b)
# ""
def confusion_matrix(model, data, offset='', **kwargs):
eff = efficiencies(model, data, **kwargs)
return MATRIX.format(offset, *(eff*100).flatten())
if __name__ == "__main__":
from deep_learning.trainNN import load_model
model = load_model("ttHLep/U_Optimal")
x_train, y_train, x_test, y_test = ds.load_dataset("ttHLep", "Unsorted")
x_train, x_test = tr.transform(x_train, x_test)
data = (x_train, y_train, x_test, y_test)
print significance(model, data)
print AUC(model, data)
print confusion_matrix(model, data)
print confusion_matrix(model, data, over_rows=False)
def save_ratios(dataset, ratios, buffer=1000):
"""
Divides a certain dataset into subsets of data with certain ratios of backgrond to signal. For a ratio list of
length n, the counting index, i, for the background starts from index 0, and the counting index, j, for the signal
starts at n-1. The ratio for each iteration is then i to j (i/j). Generates a temporary file to accomplish this.
Parameters
----------
dataset <string> : the name of the dataset (/-separated)
ratios <list> : a list of integers that define ratios of background to signal.
buffer <int> : an integer defining the number of data points to load into memory at a time.
"""
ratios = [ratios] if type(ratios) is str else ratios
ratios = map(lambda x: map(float, x.split(':')), ratios)
data = dataset.split('/')[0]
format = '/'.join(dataset.split('/')[1:])
main_file, (x_train, y_train, x_test, y_test) = ds.load_dataset(data, format, mode='a')
bkg_test, sig_test = sum_cols(y_test)
bkg_train, sig_train = sum_cols(y_train)
TEST_UPPER_LIMIT = int(1.5 * bkg_test) if bkg_test < sig_test else int(1.5 * sig_test)
TRAIN_UPPER_LIMIT = int(1.5 * bkg_train) if bkg_train < sig_train else int(1.5 * sig_train)
temp_h_file, temp_h_data = add_group_hdf5(".deep_learning.temp.h5", "Temp",
[(bkg_train, x_train.shape[1]),
(bkg_train, y_train.shape[1]),
(sig_train, x_train.shape[1]),
(sig_train, y_train.shape[1]),
(bkg_test, x_test.shape[1]),
(bkg_test, y_test.shape[1]),
(sig_test, x_test.shape[1]),
(sig_test, y_test.shape[1])],
names=["train_bkg_x",
"train_bkg_y",
"train_sig_x",
"train_sig_y",
"test_bkg_x",
"test_bkg_y",
"test_sig_x",
"test_sig_y"])
print "Generating temporary files..."
for i in xrange(int(math.ceil(x_train.shape[0] / buffer))):
# index should be same shape and need to reshape the result :/
train_bkg_index = np.array([[False]*x_train.shape[1]]*x_train.shape[0])
train_sig_index = np.array([[False]*x_train.shape[1]]*x_train.shape[0])
test_bkg_index = np.array([[False]*x_test.shape[1]]*x_test.shape[0])
test_sig_index = np.array([[False]*x_test.shape[1]]*x_test.shape[0])
for j in xrange(x_train.shape[1]):
train_bkg_index[i * buffer:(i + 1) * buffer, j] = y_train[i * buffer:(i + 1) * buffer, 0] == 1
train_sig_index[i * buffer:(i + 1) * buffer, j] = y_train[i * buffer:(i + 1) * buffer, 1] == 1
for j in xrange(x_test.shape[1]):
test_bkg_index[i * buffer:(i + 1) * buffer, j] = y_test[i * buffer:(i + 1) * buffer, 0] == 1
test_sig_index[i * buffer:(i + 1) * buffer, j] = y_test[i * buffer:(i + 1) * buffer, 1] == 1
selection = x_train[train_bkg_index]
temp_h_data[0].append(selection.reshape((selection.size/x_train.shape[1], x_train.shape[1])))
selection = y_train[train_bkg_index[:, :y_train.shape[1]]]
temp_h_data[1].append(selection.reshape((selection.size/y_train.shape[1], y_train.shape[1])))
selection = x_train[train_sig_index]
temp_h_data[2].append(selection.reshape((selection.size/x_train.shape[1], x_train.shape[1])))
selection = y_train[train_sig_index[:, :y_train.shape[1]]]
temp_h_data[3].append(selection.reshape((selection.size/y_train.shape[1], y_train.shape[1])))
selection = x_test[test_bkg_index]
temp_h_data[4].append(selection.reshape((selection.size/x_test.shape[1], x_test.shape[1])))
selection = y_test[test_bkg_index[:, :y_test.shape[1]]]
temp_h_data[5].append(selection.reshape((selection.size/y_test.shape[1], y_test.shape[1])))
selection = x_test[test_sig_index]
temp_h_data[6].append(selection.reshape((selection.size/x_test.shape[1], x_test.shape[1])))
selection = y_test[test_sig_index[:, :y_test.shape[1]]]
temp_h_data[7].append(selection.reshape((selection.size/y_test.shape[1], y_test.shape[1])))
# Perform all of this in archive so that you write to file every iteration
buffer_reset = buffer
for rat in ratios:
print "Creating ratio {:d}/{:d} ...".format(*map(int, rat))
h_file, h_data = add_group_hdf5(ds.get_path_to_dataset(data)+os.sep+data+".h5",
"{}to{}".format(*map(int, rat)),
[(TRAIN_UPPER_LIMIT, x_train.shape[1]),
(TRAIN_UPPER_LIMIT, y_train.shape[1]),
(TEST_UPPER_LIMIT, x_test.shape[1]),
(TEST_UPPER_LIMIT, y_test.shape[1])],
where='/{}'.format(format))
test_bkg_indices = np.arange(bkg_test)
test_sig_indices = np.arange(sig_test)
train_bkg_indices = np.arange(bkg_train)
train_sig_indices = np.arange(sig_train)
train_count = 0
buffer = buffer_reset
while train_count < TRAIN_UPPER_LIMIT:
if TRAIN_UPPER_LIMIT - train_count < buffer:
buffer = TRAIN_UPPER_LIMIT - train_count
# Indices to NOT include
train_bkg_ix = np.random.choice(train_bkg_indices,
train_bkg_indices.size - (rat[0] * buffer / sum(rat)),
replace=False)
train_sig_ix = np.random.choice(train_sig_indices,
train_sig_indices.size - (rat[1] * buffer / sum(rat)),
replace=False)
# Indices to keep
k_train_bkg = np.setdiff1d(train_bkg_indices, train_bkg_ix)
k_train_sig = np.setdiff1d(train_sig_indices, train_sig_ix)
train_small_x_sig = temp_h_data[2][k_train_sig]
train_small_y_sig = temp_h_data[3][k_train_sig]
train_small_x_bkg = temp_h_data[0][k_train_bkg]
train_small_y_bkg = temp_h_data[1][k_train_bkg]
train_x = np.concatenate((train_small_x_bkg, train_small_x_sig))
train_y = np.concatenate((train_small_y_bkg, train_small_y_sig))
tr.shuffle_in_unison(train_x, train_y)
h_data[0].append(train_x)
h_data[1].append(train_y)
train_count += k_train_bkg.size + k_train_sig.size
train_bkg_indices = train_bkg_ix
train_sig_indices = train_sig_ix
test_count = 0
buffer = buffer_reset
while test_count < TEST_UPPER_LIMIT:
if TEST_UPPER_LIMIT - test_count < buffer:
buffer = TEST_UPPER_LIMIT - test_count
# Indices to NOT include
test_bkg_ix = np.random.choice(test_bkg_indices, test_bkg_indices.size - (rat[0] * buffer / sum(rat)),
replace=False)
test_sig_ix = np.random.choice(test_sig_indices, test_sig_indices.size - (rat[1] * buffer / sum(rat)),
replace=False)
# Indices to keep
k_test_bkg = np.setdiff1d(test_bkg_indices, test_bkg_ix)
k_test_sig = np.setdiff1d(test_sig_indices, test_sig_ix)
test_small_x_sig = temp_h_data[6][k_test_sig]
test_small_y_sig = temp_h_data[7][k_test_sig]
test_small_x_bkg = temp_h_data[4][k_test_bkg]
test_small_y_bkg = temp_h_data[5][k_test_bkg]
test_x = np.concatenate((test_small_x_bkg, test_small_x_sig))
test_y = np.concatenate((test_small_y_bkg, test_small_y_sig))
tr.shuffle_in_unison(test_x, test_y)
h_data[2].append(test_x)
h_data[3].append(test_y)
test_count += k_test_bkg.size + k_test_sig.size
test_bkg_indices = test_bkg_ix
test_sig_indices = test_sig_ix
print "Created Group: {}/{}to{}".format(format, *map(int, rat))
h_file.flush()
h_file.close()
main_file.close()
temp_h_file.close()
os.remove(".deep_learning.temp.h5")
def run(model, exp, terms, save_freq=5, data=None):
exp_dir = ds.get_path_to_dataset(pb.Experiment.Dataset.Name(exp.dataset))
save_dir = os.path.join(exp_dir, exp.description)
##
# Load data from .npz archive created by invoking
# deep_learning/utils/archive.py
##
if data:
x_train, y_train, x_test, y_test = data
x_train, x_test = tr.transform(x_train, x_test)
else:
h_file, (x_train, y_train, x_test, y_test) = ds.load_dataset(
pb.Experiment.Dataset.Name(exp.dataset),
exp.coordinates + '/transformed')
data = x_train, y_train, x_test, y_test
exp_file_name = exp.description + '.exp'
# Start training
train_length = x_train.shape[0]
num_batches = int(ceil(train_length / exp.batch_size))
valid = Validator(exp, terms)
eTimes = np.array([])
valid._clock = clock()
model.summary()
while valid.check():
t = clock()
if valid._num_epochs:
print("Epoch {}/{}".format(valid.epochs + 1, valid._num_epochs))
else:
print("Epoch {}".format(valid.epochs + 1))
bETA = 0
bTimes = np.array([])
#print("\t Training: ")
for b in xrange(num_batches):
bt = clock()
# Update progress bar
progress(b, num_batches, exp.batch_size, bETA)
# Train on a batch
x_batch = x_train[b * exp.batch_size:b * exp.batch_size +
exp.batch_size, :]
y_batch = y_train[b * exp.batch_size:b * exp.batch_size +
exp.batch_size, :]
model.train_on_batch(x_batch, y_batch)
bTimes = np.append(bTimes, clock() - bt)
bETA = np.median(bTimes) * (num_batches - b - 1)
# Finish progress bar
progress(num_batches,
num_batches,
exp.batch_size,
0,
end='\n',
time=clock() - t)
# Calculate stats and add the epoch results to the experiment object
epoch = exp.results.add()
timer = clock()
print("Evaluating Train")
epoch.train_loss, epoch.train_accuracy = model.evaluate_generator(
((x_train[i * exp.batch_size:(i + 1) * exp.batch_size],
y_train[i * exp.batch_size:(i + 1) * exp.batch_size])
for i in xrange(num_batches)),
num_batches,
max_q_size=min((num_batches // 2, 10)))
#print("Finished {:.2f}s".format(clock()-timer))
timer = clock()
print("Evaluating Test")
epoch.test_loss, epoch.test_accuracy = model.evaluate_generator(
((x_test[i * exp.batch_size:(i + 1) * exp.batch_size],
y_test[i * exp.batch_size:(i + 1) * exp.batch_size])
for i in xrange(int(ceil(x_test.shape[0] / exp.batch_size)))),
int(ceil(x_test.shape[0] / exp.batch_size)),
max_q_size=min(
(int(ceil(x_test.shape[0] / exp.batch_size)) // 2, 10)))
#print("Finished {:.2f}s".format(clock() - timer))
timer = clock()
print("Calculating Sig")
epoch.s_b = st.significance(model, data)
#print("Finished {:.2f}".format(clock() - timer))
#timer = clock()
#print("Calculating AUC {:.2f}".format(clock()))
#epoch.auc = st.AUC(model, data, experiment_epoch=epoch)
#print("Finished {:.2f}".format(clock() - timer))
timer = clock()
for r in st.num_of_each_cell(model, data):
epoch.matrix.add().columns.extend(r)
print("Making CFM")
matrix = st.confusion_matrix(model, data, offset='\t ')
#print("Finished {:.2f}".format(clock() - timer))
epoch.num_seconds = clock() - t
timer = clock()
print("Getting output")
output = st.get_output_distro(model, data)
epoch.output.background.extend(output["background"])
epoch.output.signal.extend(output["signal"])
#print("Finished {:.2f}".format(clock() - timer))
# Print statistics
print("\t Train Accuracy: {:.3f}\tTest Accuracy: {:.3f}".format(
epoch.train_accuracy, epoch.test_accuracy))
if valid.update_w():
print("\t Slope: {:.5f} (test_accuracy / second)".format(
valid.slope))
print("\t Time this epoch: {:.2f}s".format(epoch.num_seconds), end='')
if valid._num_epochs:
eTimes = np.append(eTimes, epoch.num_seconds)
print("\tFinal ETA: {}".format(
convert_seconds(
np.median(eTimes) * (valid._num_epochs - valid.epochs))))
else:
print()
print("\t Significance (S/sqrt(B)): {:.2f}".format(epoch.s_b))
print("\t Area Under the Curve (efficiency): {:.3f}".format(epoch.auc))
print(matrix)
# Saves the model
if (len(exp.results) % save_freq) == 0:
save(model, exp, save_dir, exp_file_name)
print("\t ", end='')
sys.stdout.flush()
exp.end_date_time = str(datetime.datetime.now())
exp.total_time = valid.time
print("\n" + valid.failed)
print("Total Time: {}".format(convert_seconds(valid.time)))
save(model, exp, save_dir, exp_file_name)
print("\t ", end='')
h_file.close()
def run(model, exp, terms, save_freq=5, data=None):
exp_dir = ds.get_path_to_dataset(pb.Experiment.Dataset.Name(exp.dataset))
save_dir = os.path.join(exp_dir, exp.description)
##
# Load data from .npz archive created by invoking
# deep_learning/utils/archive.py
##
if data:
x_train, y_train, x_test, y_test = data
x_train, x_test = tr.transform(x_train, x_test)
else:
h_file, (x_train, y_train, x_test, y_test) = ds.load_dataset(pb.Experiment.Dataset.Name(exp.dataset), exp.coordinates)
x_train, x_test = tr.transform(x_train, x_test)
data = x_train, y_train, x_test, y_test
exp_file_name = exp.description + '.exp'
train_length = x_train.shape[0]
num_batches = int(ceil(train_length / exp.batch_size))
valid = Validator(exp, terms)
eTimes = np.array([])
valid._clock = clock()
model.summary()
while valid.check():
t = clock()
if valid._num_epochs:
print("Epoch {}/{}".format(valid.epochs+1, valid._num_epochs))
else:
print("Epoch {}".format(valid.epochs+1))
bETA = 0
bTimes = np.array([])
for b in xrange(num_batches):
bt = clock()
# Update progress bar
progress(b, num_batches, exp.batch_size, bETA)
# Train on a batch
model.train_on_batch(x_train[b*exp.batch_size:b*exp.batch_size+exp.batch_size, :],
y_train[b*exp.batch_size:b*exp.batch_size+exp.batch_size, :])
bTimes = np.append(bTimes, clock()-bt)
bETA = np.median(bTimes)*(num_batches-b-1)
# Finish progress bar
progress(num_batches, num_batches, exp.batch_size, 0, end='\n')
# Calculate stats and add the epoch results to the experiment object
epoch = exp.results.add()
epoch.train_loss, epoch.train_accuracy = model.evaluate_generator(((x_train[i*exp.batch_size:(i+1)*exp.batch_size],
y_train[i*exp.batch_size:(i+1)*exp.batch_size]) for i in xrange(int(ceil(x_test.shape[0]/exp.batch_size)))),
int(ceil(x_test.shape[0]/exp.batch_size)))
epoch.test_loss, epoch.test_accuracy = model.evaluate_generator(((x_test[i*exp.batch_size:(i+1)*exp.batch_size],
y_test[i*exp.batch_size:(i+1)*exp.batch_size]) for i in xrange(num_batches)),
num_batches)
epoch.s_b = st.significance(model, data)
epoch.auc = st.AUC(model, data, experiment_epoch=epoch)
for r in st.num_of_each_cell(model, data):
epoch.matrix.add().columns.extend(r)
matrix = st.confusion_matrix(model, data, offset='\t ')
epoch.num_seconds = clock() - t
# Print statistics
print("\t Train Accuracy: {:.3f}\tTest Accuracy: {:.3f}".format(epoch.train_accuracy, epoch.test_accuracy))
if valid.update_w():
print("\t Slope: {:.5f} (test_accuracy / second)".format(valid.slope))
print("\t Time this epoch: {:.2f}s".format(epoch.num_seconds), end='')
if valid._num_epochs:
eTimes = np.append(eTimes, epoch.num_seconds)
print("\tFinal ETA: {}".format(convert_seconds(np.median(eTimes) * (valid._num_epochs - valid.epochs))))
else:
print()
print("\t Significance (S/sqrt(B)): {:.2f}".format(epoch.s_b))
print("\t Area Under the Curve (efficiency): {:.3f}".format(epoch.auc))
print(matrix)
if (len(exp.results) % save_freq) == 0:
save(model, exp, save_dir, exp_file_name)
print("\t Saved the model\n")
sys.stdout.flush()
exp.end_date_time = str(datetime.datetime.now())
exp.total_time = valid.time
print("\n"+valid.failed)
print("Total Time: {}".format(convert_seconds(valid.time)))
save(model, exp, save_dir, exp_file_name, graph=True)
h_file.close()
def test_load_dataset(self):
""" Tests the load_data function """
# if the dataset doesn't exist
with self.assertRaises(IOError):
ds.load_dataset("this one definitely doesn't exist either", "")
def save_ratios(dataset, ratios, buffer=1000):
ratios = [ratios] if type(ratios) is str else ratios
ratios = map(lambda x: map(float, x.split(':')), ratios)
data, format = dataset.split('/')
main_file, (x_train, y_train, x_test, y_test) = ds.load_dataset(data, format, mode='a')
bkg_test, sig_test = sum_cols(y_test)
bkg_train, sig_train = sum_cols(y_train)
TEST_UPPER_LIMIT = int(1.5 * bkg_test) if bkg_test < sig_test else int(1.5 * sig_test)
TRAIN_UPPER_LIMIT = int(1.5 * bkg_train) if bkg_train < sig_train else int(1.5 * sig_train)
temp_h_file, temp_h_data = add_group_hdf5(".deep_learning.temp.hdf5", "Temp",
[(bkg_train, x_train.shape[1]),
(bkg_train, y_train.shape[1]),
(sig_train, x_train.shape[1]),
(sig_train, y_train.shape[1]),
(bkg_test, x_test.shape[1]),
(bkg_test, y_test.shape[1]),
(sig_test, x_test.shape[1]),
(sig_test, y_test.shape[1])],
names=["train_bkg_x",
"train_bkg_y",
"train_sig_x",
"train_sig_y",
"test_bkg_x",
"test_bkg_y",
"test_sig_x",
"test_sig_y"])
print "Generating temporary files..."
for i in xrange(int(math.ceil(x_train.shape[0] / buffer))):
# index should be same shape and need to reshape the result :/
train_bkg_index = np.array([[False]*x_train.shape[1]]*x_train.shape[0])
train_sig_index = np.array([[False]*x_train.shape[1]]*x_train.shape[0])
test_bkg_index = np.array([[False]*x_test.shape[1]]*x_test.shape[0])
test_sig_index = np.array([[False]*x_test.shape[1]]*x_test.shape[0])
for j in xrange(x_train.shape[1]):
train_bkg_index[i * buffer:(i + 1) * buffer, j] = y_train[i * buffer:(i + 1) * buffer, 0] == 1
train_sig_index[i * buffer:(i + 1) * buffer, j] = y_train[i * buffer:(i + 1) * buffer, 1] == 1
for j in xrange(x_test.shape[1]):
test_bkg_index[i * buffer:(i + 1) * buffer, j] = y_test[i * buffer:(i + 1) * buffer, 0] == 1
test_sig_index[i * buffer:(i + 1) * buffer, j] = y_test[i * buffer:(i + 1) * buffer, 1] == 1
selection = x_train[train_bkg_index]
temp_h_data[0].append(selection.reshape((selection.size/x_train.shape[1], x_train.shape[1])))
selection = y_train[train_bkg_index[:, :y_train.shape[1]]]
temp_h_data[1].append(selection.reshape((selection.size/y_train.shape[1], y_train.shape[1])))
selection = x_train[train_sig_index]
temp_h_data[2].append(selection.reshape((selection.size/x_train.shape[1], x_train.shape[1])))
selection = y_train[train_sig_index[:, :y_train.shape[1]]]
temp_h_data[3].append(selection.reshape((selection.size/y_train.shape[1], y_train.shape[1])))
selection = x_test[test_bkg_index]
temp_h_data[4].append(selection.reshape((selection.size/x_test.shape[1], x_test.shape[1])))
selection = y_test[test_bkg_index[:, :y_test.shape[1]]]
temp_h_data[5].append(selection.reshape((selection.size/y_test.shape[1], y_test.shape[1])))
selection = x_test[test_sig_index]
temp_h_data[6].append(selection.reshape((selection.size/x_test.shape[1], x_test.shape[1])))
selection = y_test[test_sig_index[:, :y_test.shape[1]]]
temp_h_data[7].append(selection.reshape((selection.size/y_test.shape[1], y_test.shape[1])))
# Perform all of this in archive so that you write to file every iteration
buffer_reset = buffer
for rat in ratios:
print "Creating ratio {:d}/{:d} ...".format(*map(int, rat))
h_file, h_data = add_group_hdf5(ds.get_path_to_dataset(data)+os.sep+data+".hdf5",
"{}to{}".format(*map(int, rat)),
[(TRAIN_UPPER_LIMIT, x_train.shape[1]),
(TRAIN_UPPER_LIMIT, y_train.shape[1]),
(TEST_UPPER_LIMIT, x_test.shape[1]),
(TEST_UPPER_LIMIT, y_test.shape[1])],
where='/{}'.format(format))
test_bkg_indices = np.arange(bkg_test)
test_sig_indices = np.arange(sig_test)
train_bkg_indices = np.arange(bkg_train)
train_sig_indices = np.arange(sig_train)
train_count = 0
buffer = buffer_reset
while train_count < TRAIN_UPPER_LIMIT:
if TRAIN_UPPER_LIMIT - train_count < buffer:
buffer = TRAIN_UPPER_LIMIT - train_count
# Indices to NOT include
train_bkg_ix = np.random.choice(train_bkg_indices,
train_bkg_indices.size - (rat[0] * buffer / sum(rat)),
replace=False)
train_sig_ix = np.random.choice(train_sig_indices,
train_sig_indices.size - (rat[1] * buffer / sum(rat)),
replace=False)
# Indices to keep
k_train_bkg = np.setdiff1d(train_bkg_indices, train_bkg_ix)
k_train_sig = np.setdiff1d(train_sig_indices, train_sig_ix)
train_small_x_sig = temp_h_data[2][k_train_sig]
train_small_y_sig = temp_h_data[3][k_train_sig]
train_small_x_bkg = temp_h_data[0][k_train_bkg]
train_small_y_bkg = temp_h_data[1][k_train_bkg]
train_x = np.concatenate((train_small_x_bkg, train_small_x_sig))
train_y = np.concatenate((train_small_y_bkg, train_small_y_sig))
tr.shuffle_in_unison(train_x, train_y)
h_data[0].append(train_x)
h_data[1].append(train_y)
train_count += k_train_bkg.size + k_train_sig.size
train_bkg_indices = train_bkg_ix
train_sig_indices = train_sig_ix
test_count = 0
buffer = buffer_reset
while test_count < TEST_UPPER_LIMIT:
if TEST_UPPER_LIMIT - test_count < buffer:
buffer = TEST_UPPER_LIMIT - test_count
# Indices to NOT include
test_bkg_ix = np.random.choice(test_bkg_indices, test_bkg_indices.size - (rat[0] * buffer / sum(rat)),
replace=False)
test_sig_ix = np.random.choice(test_sig_indices, test_sig_indices.size - (rat[1] * buffer / sum(rat)),
replace=False)
# Indices to keep
k_test_bkg = np.setdiff1d(test_bkg_indices, test_bkg_ix)
k_test_sig = np.setdiff1d(test_sig_indices, test_sig_ix)
test_small_x_sig = temp_h_data[6][k_test_sig]
test_small_y_sig = temp_h_data[7][k_test_sig]
test_small_x_bkg = temp_h_data[4][k_test_bkg]
test_small_y_bkg = temp_h_data[5][k_test_bkg]
test_x = np.concatenate((test_small_x_bkg, test_small_x_sig))
test_y = np.concatenate((test_small_y_bkg, test_small_y_sig))
tr.shuffle_in_unison(test_x, test_y)
h_data[2].append(test_x)
h_data[3].append(test_y)
test_count += k_test_bkg.size + k_test_sig.size
test_bkg_indices = test_bkg_ix
test_sig_indices = test_sig_ix
print "Created Group: {}/{}to{}".format(format, *map(int, rat))
h_file.flush()
h_file.close()
main_file.close()
temp_h_file.close()
os.remove(".deep_learning.temp.hdf5")