def perform_experiment(data_file, output_file, exp):
if exp.make_predictions:
X, y, D, Xtest, ytest = gpml.load_mat(data_file)
prediction_file = os.path.join(
exp.results_dir,
os.path.splitext(os.path.split(data_file)[-1])[0] +
"_predictions.mat")
else:
X, y, D = gpml.load_mat(data_file)
perform_kernel_search(X, y, D, data_file, output_file, exp)
best_model = parse_results(output_file)
if exp.make_predictions:
print '\nMaking predictions\n'
predictions = jc.make_predictions(X,
y,
Xtest,
ytest,
best_model,
local_computation=True,
max_jobs=exp.max_jobs,
verbose=exp.verbose,
random_seed=exp.random_seed)
scipy.io.savemat(prediction_file, predictions, appendmat=False)
os.system('reset') # Stop terminal from going invisible.
def perform_experiment(data_file, output_file, exp):
if exp.make_predictions:
X, y, D, Xtest, ytest = gpml.load_mat(data_file, y_dim=1)
prediction_file = os.path.join(
exp.results_dir,
os.path.splitext(os.path.split(data_file)[-1])[0] +
"_predictions.mat")
else:
X, y, D = gpml.load_mat(data_file, y_dim=1)
perform_kernel_search(X, y, D, data_file, output_file, exp)
best_scored_kernel = parse_results(output_file)
if exp.make_predictions:
predictions = jc.make_predictions(
X,
y,
Xtest,
ytest,
best_scored_kernel,
local_computation=exp.local_computation,
max_jobs=exp.max_jobs,
verbose=exp.verbose,
zero_mean=exp.zero_mean,
random_seed=exp.random_seed)
scipy.io.savemat(prediction_file, predictions, appendmat=False)
def make_all_1d_figures(folder, save_folder='../figures/decomposition/', max_level=None, prefix='', rescale=True, data_folder=None):
"""Crawls the results directory, and makes decomposition plots for each file.
prefix is an optional string prepended to the output directory
"""
#### Quick fix to axis scaling
#### TODO - Ultimately this and the shunt below should be removed / made elegant
if rescale:
data_sets = list(exp.gen_all_datasets("../data/1d_data_rescaled/"))
else:
if data_folder is None:
data_sets = list(exp.gen_all_datasets("../data/1d_data/"))
else:
data_sets = list(exp.gen_all_datasets(data_folder))
for r, file in data_sets:
results_file = os.path.join(folder, file + "_result.txt")
# Is the experiment complete
if os.path.isfile(results_file):
# Find best kernel and produce plots
datafile = os.path.join(r,file + ".mat")
X, y, D = gpml.load_mat(datafile)
if rescale:
# Load unscaled data to remove scaling later
unscaled_file = os.path.join('../data/1d_data/', re.sub('-s$', '', file) + '.mat')
data = gpml.load_mat(unscaled_file)
(X_unscaled, y_unscaled) = (data[0], data[1])
(X_mean, X_scale) = (X_unscaled.mean(), X_unscaled.std())
(y_mean, y_scale) = (y_unscaled.mean(), y_unscaled.std())
else:
(X_mean, X_scale, y_mean, y_scale) = (0,1,0,1)
# A shunt to deal with a legacy issue.
if datafile == '../data/1d_data/01-airline-months.mat':
# Scaling should turn months starting at zero into years starting at 1949
print "Special rescaling for airline months data"
X_mean = X_mean + 1949
X_scale = 1.0/12.0
best_kernel = exp.parse_results(os.path.join(folder, file + "_result.txt"), max_level=max_level)
stripped_kernel = fk.strip_masks(best_kernel.k_opt)
if not max_level is None:
fig_folder = os.path.join(save_folder, (prefix + file + '_max_level_%d' % max_level))
else:
fig_folder = os.path.join(save_folder, (prefix + file))
if not os.path.exists(fig_folder):
os.makedirs(fig_folder)
gpml.plot_decomposition(stripped_kernel, X, y, os.path.join(fig_folder, file), best_kernel.noise, X_mean, X_scale, y_mean, y_scale)
else:
print "Cannnot find file %s" % results_file
def repeat_predictions(filename):
"""
A convenience function to re run the predictions from an experiment
"""
expstring = open(filename, 'r').read()
exp = eval(expstring)
print experiment_fields_to_str(exp)
if not exp.make_predictions:
print 'This experiment does not make predictions'
return None
data_sets = list(gen_all_datasets(exp.data_dir))
for r, file in data_sets:
# Check if this experiment has already been done.
output_file = os.path.join(exp.results_dir, file + "_result.txt")
if os.path.isfile(output_file):
print 'Predictions for %s' % file
data_file = os.path.join(r, file + ".mat")
X, y, D, Xtest, ytest = gpml.load_mat(data_file)
prediction_file = os.path.join(exp.results_dir, os.path.splitext(os.path.split(data_file)[-1])[0] + "_predictions.mat")
best_model = parse_results(output_file)
predictions = jc.make_predictions(X, y, Xtest, ytest, best_model, local_computation=True,
max_jobs=exp.max_jobs, verbose=exp.verbose, random_seed=exp.random_seed)
scipy.io.savemat(prediction_file, predictions, appendmat=False)
print "Finished file %s" % file
else:
print 'Results not found for %s' % file
def debug_laplace():
# Load data set
X, y, D, Xtest, ytest = gpml.load_mat(
'../data/kfold_data/r_concrete_500_fold_10_of_10.mat', y_dim=1)
# Load the suspicious kernel
sk = fk.repr_string_to_kernel(
'ScoredKernel(k_opt=ProductKernel([ MaskKernel(ndim=8, active_dimension=0, base_kernel=CubicKernel(offset=1.757755, output_variance=7.084045)), MaskKernel(ndim=8, active_dimension=7, base_kernel=SqExpPeriodicKernel(lengthscale=-2.701080, period=-0.380918, output_variance=-0.071214)) ]), nll=6348.096611, laplace_nle=-184450132.068237, bic_nle=12720.630212, noise=[-1.77276072])'
)
# Create some code to evaluate it
if X.ndim == 1: X = X[:, nax]
if y.ndim == 1: y = y[:, nax]
ndata = y.shape[0]
# Create data file
data_file = cblparallel.create_temp_file('.mat')
scipy.io.savemat(data_file, {'X': X, 'y': y}) # Save regression data
# Move to fear
cblparallel.copy_to_remote(data_file)
scripts = [
gpml.OPTIMIZE_KERNEL_CODE % {
'datafile':
data_file.split('/')[-1],
'writefile':
'%(output_file)s', # N.B. cblparallel manages output files
'gpml_path':
cblparallel.gpml_path(local_computation=False),
'kernel_family':
sk.k_opt.gpml_kernel_expression(),
'kernel_params':
'[ %s ]' % ' '.join(str(p) for p in sk.k_opt.param_vector()),
'noise':
str(sk.noise),
'iters':
str(300)
}
]
#### Need to be careful with % signs
#### For the moment, cblparallel expects no single % signs - FIXME
scripts[0] = re.sub('% ', '%% ', scripts[0])
# Test
scripts[0] = re.sub('delta = 1e-6', 'delta = 1e-6', scripts[0])
#scripts[0] = re.sub('hyp.lik = [-1.77276072]', 'hyp.lik = [-0.77276072]', scripts[0])
output_file = cblparallel.run_batch_on_fear(scripts,
language='matlab',
max_jobs=600)[0]
# Read in results
output = gpml.read_outputs(output_file)
result = ScoredKernel.from_matlab_output(output, sk.k_opt.family(), ndata)
print result
print output.hessian
os.remove(output_file)
# Remove temporary data file (perhaps on the cluster server)
cblparallel.remove_temp_file(data_file, local_computation=False)
def perform_experiment(data_file, output_file, exp):
if exp.make_predictions:
X, y, D, Xtest, ytest = gpml.load_mat(data_file, y_dim=1)
prediction_file = os.path.join(exp.results_dir, os.path.splitext(os.path.split(data_file)[-1])[0] + "_predictions.mat")
else:
X, y, D = gpml.load_mat(data_file, y_dim=1)
perform_kernel_search(X, y, D, data_file, output_file, exp)
best_scored_kernel = parse_results(output_file)
if exp.make_predictions:
predictions = jc.make_predictions(X, y, Xtest, ytest, best_scored_kernel, local_computation=exp.local_computation,
max_jobs=exp.max_jobs, verbose=exp.verbose, zero_mean=exp.zero_mean, random_seed=exp.random_seed)
scipy.io.savemat(prediction_file, predictions, appendmat=False)
os.system('reset') # Stop terminal from going invisible.
def calculate_model_fits(data_file, output_file, exp):
prediction_file = os.path.join(exp.results_dir, os.path.splitext(os.path.split(data_file)[-1])[0] + "_predictions.mat")
X, y, D, = gpml.load_mat(data_file, y_dim=1)
Xtest = X
ytest = y
best_scored_kernel = parse_results(output_file)
predictions = jc.make_predictions(X, y, Xtest, ytest, best_scored_kernel, local_computation=exp.local_computation,
max_jobs=exp.max_jobs, verbose=exp.verbose, zero_mean=exp.zero_mean, random_seed=exp.random_seed)
scipy.io.savemat(prediction_file, predictions, appendmat=False)
os.system('reset') # Stop terminal from going invisible.
def debug_laplace():
# Load data set
X, y, D, Xtest, ytest = gpml.load_mat('../data/kfold_data/r_concrete_500_fold_10_of_10.mat', y_dim=1)
# Load the suspicious kernel
sk = fk.repr_string_to_kernel('ScoredKernel(k_opt=ProductKernel([ MaskKernel(ndim=8, active_dimension=0, base_kernel=CubicKernel(offset=1.757755, output_variance=7.084045)), MaskKernel(ndim=8, active_dimension=7, base_kernel=SqExpPeriodicKernel(lengthscale=-2.701080, period=-0.380918, output_variance=-0.071214)) ]), nll=6348.096611, laplace_nle=-184450132.068237, bic_nle=12720.630212, noise=[-1.77276072])')
# Create some code to evaluate it
if X.ndim == 1: X = X[:, nax]
if y.ndim == 1: y = y[:, nax]
ndata = y.shape[0]
# Create data file
data_file = cblparallel.create_temp_file('.mat')
scipy.io.savemat(data_file, {'X': X, 'y': y}) # Save regression data
# Move to fear
cblparallel.copy_to_remote(data_file)
scripts = [gpml.OPTIMIZE_KERNEL_CODE % {'datafile': data_file.split('/')[-1],
'writefile': '%(output_file)s', # N.B. cblparallel manages output files
'gpml_path': cblparallel.gpml_path(local_computation=False),
'kernel_family': sk.k_opt.gpml_kernel_expression(),
'kernel_params': '[ %s ]' % ' '.join(str(p) for p in sk.k_opt.param_vector()),
'noise': str(sk.noise),
'iters': str(300)}]
#### Need to be careful with % signs
#### For the moment, cblparallel expects no single % signs - FIXME
scripts[0] = re.sub('% ', '%% ', scripts[0])
# Test
scripts[0] = re.sub('delta = 1e-6', 'delta = 1e-6', scripts[0])
#scripts[0] = re.sub('hyp.lik = [-1.77276072]', 'hyp.lik = [-0.77276072]', scripts[0])
output_file = cblparallel.run_batch_on_fear(scripts, language='matlab', max_jobs=600)[0]
# Read in results
output = gpml.read_outputs(output_file)
result = ScoredKernel.from_matlab_output(output, sk.k_opt.family(), ndata)
print result
print output.hessian
os.remove(output_file)
# Remove temporary data file (perhaps on the cluster server)
cblparallel.remove_temp_file(data_file, local_computation=False)
def repeat_predictions(filename):
"""
A convenience function to re run the predictions from an experiment
"""
expstring = open(filename, 'r').read()
exp = eval(expstring)
print experiment_fields_to_str(exp)
if not exp.make_predictions:
print 'This experiment does not make predictions'
return None
data_sets = list(gen_all_datasets(exp.data_dir))
for r, file in data_sets:
# Check if this experiment has already been done.
output_file = os.path.join(exp.results_dir, file + "_result.txt")
if os.path.isfile(output_file):
print 'Predictions for %s' % file
data_file = os.path.join(r, file + ".mat")
X, y, D, Xtest, ytest = gpml.load_mat(data_file)
prediction_file = os.path.join(
exp.results_dir,
os.path.splitext(os.path.split(data_file)[-1])[0] +
"_predictions.mat")
best_model = parse_results(output_file)
predictions = jc.make_predictions(X,
y,
Xtest,
ytest,
best_model,
local_computation=True,
max_jobs=exp.max_jobs,
verbose=exp.verbose,
random_seed=exp.random_seed)
scipy.io.savemat(prediction_file, predictions, appendmat=False)
print "Finished file %s" % file
else:
print 'Results not found for %s' % file
def perform_experiment(data_file, output_file, exp):
if exp.make_predictions:
X, y, D, Xtest, ytest = gpml.load_mat(data_file)
prediction_file = os.path.join(exp.results_dir, os.path.splitext(os.path.split(data_file)[-1])[0] + "_predictions.mat")
else:
X, y, D = gpml.my_load_mat(data_file)
import time
start_time = time.time()
perform_kernel_search(X, y, D, data_file, output_file, exp)
elapse_time = time.time() - start_time
print ('Elapsed time: {}'.format(elapse_time))
best_model = parse_results(output_file)
if exp.make_predictions:
print '\nMaking predictions\n'
predictions = jc.make_predictions(X, y, Xtest, ytest, best_model, local_computation=True,
max_jobs=exp.max_jobs, verbose=exp.verbose, random_seed=exp.random_seed)
scipy.io.savemat(prediction_file, predictions, appendmat=False)
os.system('reset') # Stop terminal from going invisible.
def make_all_1d_figures(folders, save_folder='../figures/decomposition/', prefix='', rescale=False, data_folder=None, skip_kernel_evaluation=False, unit='year', all_depths=False):
"""Crawls the results directory, and makes decomposition plots for each file.
prefix is an optional string prepended to the output directory
"""
if not isinstance(folders, list):
folders = [folders] # Backward compatibility with specifying one folder
#### Quick fix to axis scaling
#### TODO - Ultimately this and the shunt below should be removed / made elegant
if rescale:
data_sets = list(exp.gen_all_datasets("../data/1d_data_rescaled/"))
else:
if data_folder is None:
data_sets = list(exp.gen_all_datasets("../data/1d_data/"))
else:
data_sets = list(exp.gen_all_datasets(data_folder))
for r, file in data_sets:
results_files = []
for folder in folders:
results_file = os.path.join(folder, file + "_result.txt")
if os.path.isfile(results_file):
results_files.append(results_file)
# Is the experiment complete
if len(results_files) > 0:
# Find best kernel and produce plots
datafile = os.path.join(r,file + ".mat")
data = gpml.load_mat(datafile)
X = data[0]
y = data[1]
D = data[2]
assert D == 1
if rescale:
# Load unscaled data to remove scaling later
unscaled_file = os.path.join('../data/1d_data/', re.sub('-s$', '', file) + '.mat')
data = gpml.load_mat(unscaled_file)
(X_unscaled, y_unscaled) = (data[0], data[1])
(X_mean, X_scale) = (X_unscaled.mean(), X_unscaled.std())
(y_mean, y_scale) = (y_unscaled.mean(), y_unscaled.std())
else:
(X_mean, X_scale, y_mean, y_scale) = (0,1,0,1)
if all_depths:
# A quick version for now TODO - write correct code
models = [exp.parse_results(results_files, max_level=depth) for depth in range(10)]
suffices = ['-depth-%d' % (depth+1) for depth in range(len(models))]
else:
models = [exp.parse_results(results_files)]
suffices = ['']
for (model, suffix) in zip(models, suffices):
model = model.simplified().canonical()
kernel_components = model.kernel.break_into_summands()
kernel_components = ff.SumKernel(kernel_components).simplified().canonical().operands
print model.pretty_print()
fig_folder = os.path.join(save_folder, (prefix + file + suffix))
if not os.path.exists(fig_folder):
os.makedirs(fig_folder)
# First ask GPML to order the components
print 'Determining order of components'
(component_order, mae_data) = gpml.order_by_mae(model, kernel_components, X, y, D, os.path.join(fig_folder, file + suffix), skip_kernel_evaluation=skip_kernel_evaluation)
print 'Plotting decomposition and computing basic stats'
component_data = gpml.component_stats(model, kernel_components, X, y, D, os.path.join(fig_folder, file + suffix), component_order, skip_kernel_evaluation=skip_kernel_evaluation)
print 'Computing model checking stats'
checking_stats = gpml.checking_stats(model, kernel_components, X, y, D, os.path.join(fig_folder, file + suffix), component_order, make_plots=True, skip_kernel_evaluation=skip_kernel_evaluation)
# Now the kernels have been evaluated we can translate the revelant ones
evaluation_data = mae_data
evaluation_data.update(component_data)
evaluation_data.update(checking_stats)
evaluation_data['vars'] = evaluation_data['vars'].ravel()
evaluation_data['cum_vars'] = evaluation_data['cum_vars'].ravel()
evaluation_data['cum_resid_vars'] = evaluation_data['cum_resid_vars'].ravel()
evaluation_data['MAEs'] = evaluation_data['MAEs'].ravel()
evaluation_data['MAE_reductions'] = evaluation_data['MAE_reductions'].ravel()
evaluation_data['monotonic'] = evaluation_data['monotonic'].ravel()
evaluation_data['acf_min_p'] = evaluation_data['acf_min_p'].ravel()
evaluation_data['acf_min_loc_p'] = evaluation_data['acf_min_loc_p'].ravel()
evaluation_data['pxx_max_p'] = evaluation_data['pxx_max_p'].ravel()
evaluation_data['pxx_max_loc_p'] = evaluation_data['pxx_max_loc_p'].ravel()
evaluation_data['qq_d_max_p'] = evaluation_data['qq_d_max_p'].ravel()
evaluation_data['qq_d_min_p'] = evaluation_data['qq_d_min_p'].ravel()
i = 1
short_descriptions = []
while os.path.isfile(os.path.join(fig_folder, '%s_%d.fig' % (file + suffix, i))):
# Describe this component
(summary, sentences, extrap_sentences) = translation.translate_additive_component(kernel_components[component_order[i-1]], X, evaluation_data['monotonic'][i-1], evaluation_data['gradients'][i-1], unit)
short_descriptions.append(summary)
paragraph = '.\n'.join(sentences) + '.'
extrap_paragraph = '.\n'.join(extrap_sentences) + '.'
with open(os.path.join(fig_folder, '%s_%d_description.tex' % (file + suffix, i)), 'w') as description_file:
description_file.write(paragraph)
with open(os.path.join(fig_folder, '%s_%d_extrap_description.tex' % (file + suffix, i)), 'w') as description_file:
description_file.write(extrap_paragraph)
with open(os.path.join(fig_folder, '%s_%d_short_description.tex' % (file + suffix, i)), 'w') as description_file:
description_file.write(summary + '.')
i += 1
# Produce the summary LaTeX document
print 'Producing LaTeX document'
latex_summary = translation.produce_summary_document(file + suffix, i-1, evaluation_data, short_descriptions)
with open(os.path.join(save_folder, '%s.tex' % (file + suffix)), 'w') as latex_file:
latex_file.write(latex_summary)
print 'Saving to ' + (os.path.join(save_folder, '%s.tex' % (file + suffix)))
else:
print "Cannnot find results for %s" % file
def make_all_1d_figures(folders,
save_folder='../figures/decomposition/',
prefix='',
rescale=False,
data_folder=None,
skip_kernel_evaluation=False,
unit='year',
all_depths=False):
"""Crawls the results directory, and makes decomposition plots for each file.
prefix is an optional string prepended to the output directory
"""
if not isinstance(folders, list):
folders = [folders
] # Backward compatibility with specifying one folder
#### Quick fix to axis scaling
#### TODO - Ultimately this and the shunt below should be removed / made elegant
if rescale:
data_sets = list(exp.gen_all_datasets("../data/1d_data_rescaled/"))
else:
if data_folder is None:
data_sets = list(exp.gen_all_datasets("../data/1d_data/"))
else:
data_sets = list(exp.gen_all_datasets(data_folder))
for r, file in data_sets:
results_files = []
for folder in folders:
results_file = os.path.join(folder, file + "_result.txt")
if os.path.isfile(results_file):
results_files.append(results_file)
# Is the experiment complete
if len(results_files) > 0:
# Find best kernel and produce plots
datafile = os.path.join(r, file + ".mat")
data = gpml.my_load_mat(datafile)
X = data[0]
y = data[1]
M = y.shape[1]
D = data[2]
iiii = 1
y = y[:, iiii]
assert D == 1
if rescale:
# Load unscaled data to remove scaling later
unscaled_file = os.path.join('../data/1d_data/',
re.sub('-s$', '', file) + '.mat')
data = gpml.load_mat(unscaled_file)
(X_unscaled, y_unscaled) = (data[0], data[1])
(X_mean, X_scale) = (X_unscaled.mean(), X_unscaled.std())
(y_mean, y_scale) = (y_unscaled.mean(), y_unscaled.std())
else:
(X_mean, X_scale, y_mean, y_scale) = (0, 1, 0, 1)
if all_depths:
# A quick version for now TODO - write correct code
models = [
exp.parse_results(results_files, max_level=depth)[0]
for depth in range(10)
]
suffices = [
'-depth-%d' % (depth + 1) for depth in range(len(models))
]
else:
models = [exp.parse_results(results_files)[0]]
try:
suffices = ['-' + str(data[5][iiii]).replace(" ", "")]
#suffices = ['-'+str(data[5][iiii][0][0]).replace(" ","")] uncomment this if you test given dataset(house, stock and so on)
except:
suffices = ['-' + str(iiii)]
#suffices = ['-'+str(iiii)]
best_depth = exp.parse_results(results_files)[1]
params_filename = '/home/heechan/gpss-research-srkl' + results_files[
0][2:] + 'lvl_' + str(best_depth) + '_0.mat1.mat'
scale_params = scipy.io.loadmat(params_filename)['scale']
scl1 = scale_params[0][iiii][0][0]
scl2 = scale_params[0][iiii][1][0]
for (model, suffix) in zip(models, suffices):
model = model.simplified().canonical()
model.kernel = model.kernel * ff.ConstKernel(
sf=scl2) + ff.ConstKernel(sf=scl1)
kernel_components = model.kernel.break_into_summands()
kernel_components = ff.SumKernel(
kernel_components).simplified().canonical().operands
print model.pretty_print()
fig_folder = os.path.join(save_folder,
(prefix + file + suffix))
if not os.path.exists(fig_folder):
os.makedirs(fig_folder)
# First ask GPML to order the components
print 'Determining order of components'
(component_order, mae_data) = gpml.order_by_mae(
model,
kernel_components,
X,
y,
D,
os.path.join(fig_folder, file + suffix),
skip_kernel_evaluation=skip_kernel_evaluation)
print 'Plotting decomposition and computing basic stats'
component_data = gpml.component_stats(
model,
kernel_components,
X,
y,
D,
os.path.join(fig_folder, file + suffix),
component_order,
skip_kernel_evaluation=skip_kernel_evaluation)
print 'Computing model checking stats'
checking_stats = gpml.checking_stats(
model,
kernel_components,
X,
y,
D,
os.path.join(fig_folder, file + suffix),
component_order,
make_plots=True,
skip_kernel_evaluation=skip_kernel_evaluation)
# Now the kernels have been evaluated we can translate the revelant ones
evaluation_data = mae_data
evaluation_data.update(component_data)
evaluation_data.update(checking_stats)
evaluation_data['vars'] = evaluation_data['vars'].ravel()
evaluation_data['cum_vars'] = evaluation_data[
'cum_vars'].ravel()
evaluation_data['cum_resid_vars'] = evaluation_data[
'cum_resid_vars'].ravel()
evaluation_data['MAEs'] = evaluation_data['MAEs'].ravel()
evaluation_data['MAE_reductions'] = evaluation_data[
'MAE_reductions'].ravel()
evaluation_data['monotonic'] = evaluation_data[
'monotonic'].ravel()
evaluation_data['acf_min_p'] = evaluation_data[
'acf_min_p'].ravel()
evaluation_data['acf_min_loc_p'] = evaluation_data[
'acf_min_loc_p'].ravel()
evaluation_data['pxx_max_p'] = evaluation_data[
'pxx_max_p'].ravel()
evaluation_data['pxx_max_loc_p'] = evaluation_data[
'pxx_max_loc_p'].ravel()
evaluation_data['qq_d_max_p'] = evaluation_data[
'qq_d_max_p'].ravel()
evaluation_data['qq_d_min_p'] = evaluation_data[
'qq_d_min_p'].ravel()
i = 1
short_descriptions = []
while os.path.isfile(
os.path.join(fig_folder,
'%s_%d.fig' % (file + suffix, i))):
# Describe this component
(summary, sentences, extrap_sentences
) = translation.translate_additive_component(
kernel_components[component_order[i - 1]], X,
evaluation_data['monotonic'][i - 1],
evaluation_data['gradients'][i - 1], unit)
short_descriptions.append(summary)
paragraph = '.\n'.join(sentences) + '.'
extrap_paragraph = '.\n'.join(extrap_sentences) + '.'
with open(
os.path.join(
fig_folder,
'%s_%d_description.tex' % (file + suffix, i)),
'w') as description_file:
description_file.write(paragraph)
with open(
os.path.join(
fig_folder, '%s_%d_extrap_description.tex' %
(file + suffix, i)), 'w') as description_file:
description_file.write(extrap_paragraph)
with open(
os.path.join(
fig_folder, '%s_%d_short_description.tex' %
(file + suffix, i)), 'w') as description_file:
description_file.write(summary + '.')
i += 1
# Produce the summary LaTeX document
print 'Producing LaTeX document'
latex_summary = translation.produce_summary_document(
file + suffix, i - 1, evaluation_data, short_descriptions)
with open(
os.path.join(save_folder, '%s.tex' % (file + suffix)),
'w') as latex_file:
latex_file.write(latex_summary)
print 'Saving to ' + (os.path.join(save_folder, '%s.tex' %
(file + suffix)))
else:
print "Cannnot find results for %s" % file
def make_all_1d_figures(folder,
save_folder='../figures/decomposition/',
max_level=None,
prefix='',
rescale=True,
data_folder=None):
"""Crawls the results directory, and makes decomposition plots for each file.
prefix is an optional string prepended to the output directory
"""
#### Quick fix to axis scaling
#### TODO - Ultimately this and the shunt below should be removed / made elegant
if rescale:
data_sets = list(exp.gen_all_datasets("../data/1d_data_rescaled/"))
else:
if data_folder is None:
data_sets = list(exp.gen_all_datasets("../data/1d_data/"))
else:
data_sets = list(exp.gen_all_datasets(data_folder))
for r, file in data_sets:
results_file = os.path.join(folder, file + "_result.txt")
# Is the experiment complete
if os.path.isfile(results_file):
# Find best kernel and produce plots
datafile = os.path.join(r, file + ".mat")
X, y, D = gpml.load_mat(datafile)
if rescale:
# Load unscaled data to remove scaling later
unscaled_file = os.path.join('../data/1d_data/',
re.sub('-s$', '', file) + '.mat')
data = gpml.load_mat(unscaled_file)
(X_unscaled, y_unscaled) = (data[0], data[1])
(X_mean, X_scale) = (X_unscaled.mean(), X_unscaled.std())
(y_mean, y_scale) = (y_unscaled.mean(), y_unscaled.std())
else:
(X_mean, X_scale, y_mean, y_scale) = (0, 1, 0, 1)
# A shunt to deal with a legacy issue.
if datafile == '../data/1d_data/01-airline-months.mat':
# Scaling should turn months starting at zero into years starting at 1949
print "Special rescaling for airline months data"
X_mean = X_mean + 1949
X_scale = 1.0 / 12.0
best_kernel = exp.parse_results(os.path.join(
folder, file + "_result.txt"),
max_level=max_level)
stripped_kernel = fk.strip_masks(best_kernel.k_opt)
if not max_level is None:
fig_folder = os.path.join(
save_folder, (prefix + file + '_max_level_%d' % max_level))
else:
fig_folder = os.path.join(save_folder, (prefix + file))
if not os.path.exists(fig_folder):
os.makedirs(fig_folder)
gpml.plot_decomposition(stripped_kernel, X, y,
os.path.join(fig_folder,
file), best_kernel.noise,
X_mean, X_scale, y_mean, y_scale)
else:
print "Cannnot find file %s" % results_file
