def test_expand(self):
print 'expand'
print '1d'
k = ff.SqExpKernel(dimension=0, lengthscale=0, sf=0)
expanded = grammar.expand_kernels(1, [k],
base_kernels='SE',
rules=None)
for k in expanded:
print '\n', k.pretty_print(), '\n'
print '2d'
k = ff.SqExpKernel(dimension=0, lengthscale=0, sf=0)
expanded = grammar.expand_kernels(2, [k],
base_kernels='SE',
rules=None)
for k in expanded:
print '\n', k.pretty_print(), '\n'
print '3d'
k = ff.SqExpKernel(dimension=0, lengthscale=0, sf=0)
expanded = grammar.expand_kernels(3, [k],
base_kernels='SE',
rules=None)
for k in expanded:
print '\n', k.pretty_print(), '\n'
print '3d with two SEs'
k = ff.SqExpKernel(dimension=0, lengthscale=0, sf=0)
expanded = grammar.expand_kernels(3, [k + k.copy()],
base_kernels='SE',
rules=None)
for k in expanded:
print '\n', k.pretty_print(), '\n'
def test_expand(self):
print 'expand'
print '1d'
k = ff.SqExpKernel(dimension=0, lengthscale=0, sf=0)
expanded = grammar.expand_kernels(1, [k], base_kernels='SE', rules=None)
for k in expanded:
print '\n', k.pretty_print(), '\n'
print '2d'
k = ff.SqExpKernel(dimension=0, lengthscale=0, sf=0)
expanded = grammar.expand_kernels(2, [k], base_kernels='SE', rules=None)
for k in expanded:
print '\n', k.pretty_print(), '\n'
print '3d'
k = ff.SqExpKernel(dimension=0, lengthscale=0, sf=0)
expanded = grammar.expand_kernels(3, [k], base_kernels='SE', rules=None)
for k in expanded:
print '\n', k.pretty_print(), '\n'
print '3d with two SEs'
k = ff.SqExpKernel(dimension=0, lengthscale=0, sf=0)
expanded = grammar.expand_kernels(3, [k + k.copy()], base_kernels='SE', rules=None)
for k in expanded:
print '\n', k.pretty_print(), '\n'
def perform_search(X,
y,
scheduler,
max_depth,
params,
verbose=False,
output_fname_fn=None):
D = X.shape[1]
current_kernels = list(flexiblekernel.base_kernels(D))
all_scored_kernels = []
scored_kernels_by_level = []
for depth in range(max_depth):
if verbose:
print 'Level', depth + 1
current_kernels = flexiblekernel.add_random_restarts(
current_kernels, params.n_restarts, params.restart_std)
if verbose:
print 'Evaluating kernels...'
scored_kernels = scheduler.evaluate_kernels(current_kernels, X, y)
scored_kernels = remove_nan_scored_kernels(scored_kernels)
scored_kernels.sort(key=flexiblekernel.ScoredKernel.score)
scored_kernels = scored_kernels[:params.num_winners]
if verbose:
print 'Removing duplicates...'
scored_kernels = remove_duplicates(scored_kernels, X,
params.num_subsample,
params.proj_dim, params.rel_cutoff)
scored_kernels.sort(key=flexiblekernel.ScoredKernel.score)
all_scored_kernels += scored_kernels
scored_kernels_by_level.append(scored_kernels)
best_kernels = [k.k_opt for k in scored_kernels[:params.num_expand]]
current_kernels = grammar.expand_kernels(D, best_kernels)
if output_fname_fn is not None:
if verbose:
print 'Saving results...'
fname = output_fname_fn(depth)
cPickle.dump(current_kernels, open(fname, 'wb'), protocol=2)
all_scored_kernels.sort(key=flexiblekernel.ScoredKernel.score)
return all_scored_kernels, scored_kernels_by_level
def perform_search(X, y, scheduler, max_depth, params, verbose=False, output_fname_fn=None):
D = X.shape[1]
current_kernels = list(flexiblekernel.base_kernels(D))
all_scored_kernels = []
scored_kernels_by_level = []
for depth in range(max_depth):
if verbose:
print 'Level', depth + 1
current_kernels = flexiblekernel.add_random_restarts(current_kernels, params.n_restarts,
params.restart_std)
if verbose:
print 'Evaluating kernels...'
scored_kernels = scheduler.evaluate_kernels(current_kernels, X, y)
scored_kernels = remove_nan_scored_kernels(scored_kernels)
scored_kernels.sort(key=flexiblekernel.ScoredKernel.score)
scored_kernels = scored_kernels[:params.num_winners]
if verbose:
print 'Removing duplicates...'
scored_kernels = remove_duplicates(scored_kernels, X, params.num_subsample, params.proj_dim,
params.rel_cutoff)
scored_kernels.sort(key=flexiblekernel.ScoredKernel.score)
all_scored_kernels += scored_kernels
scored_kernels_by_level.append(scored_kernels)
best_kernels = [k.k_opt for k in scored_kernels[:params.num_expand]]
current_kernels = grammar.expand_kernels(D, best_kernels)
if output_fname_fn is not None:
if verbose:
print 'Saving results...'
fname = output_fname_fn(depth)
cPickle.dump(current_kernels, open(fname, 'wb'), protocol=2)
all_scored_kernels.sort(key=flexiblekernel.ScoredKernel.score)
return all_scored_kernels, scored_kernels_by_level
def perform_kernel_search(X, y, D, experiment_data_file_name, results_filename, exp):
'''Search for the best kernel, in parallel on fear or local machine.'''
# Initialise random seeds - randomness may be used in e.g. data subsetting
utils.misc.set_all_random_seeds(exp.random_seed)
# Initialise kernels to be all base kernels along all dimensions.
current_kernels = list(fk.base_kernels(D, exp.base_kernels))
# Create location, scale and minimum period parameters to pass around for initialisations
data_shape = {}
data_shape['input_location'] = [np.mean(X[:,dim]) for dim in range(X.shape[1])]
data_shape['output_location'] = np.mean(y)
data_shape['input_scale'] = np.log([np.std(X[:,dim]) for dim in range(X.shape[1])])
data_shape['output_scale'] = np.log(np.std(y))
# Initialise period at a multiple of the shortest / average distance between points, to prevent Nyquist problems.
if exp.use_min_period:
data_shape['min_period'] = np.log([max(exp.period_heuristic * utils.misc.min_abs_diff(X[:,i]), exp.period_heuristic * np.ptp(X[:,i]) / X.shape[0]) for i in range(X.shape[1])])
else:
data_shape['min_period'] = None
#### TODO - make the below and above more elegant
if exp.use_constraints:
data_shape['min_alpha'] = exp.alpha_heuristic
data_shape['min_lengthscale'] = exp.lengthscale_heuristic + data_shape['input_scale']
else:
data_shape['min_alpha'] = None
data_shape['min_lengthscale'] = None
all_results = []
results_sequence = [] # List of lists of results, indexed by level of expansion.
# Perform search
for depth in range(exp.max_depth):
if exp.debug==True:
current_kernels = current_kernels[0:4]
# Add random restarts to kernels
current_kernels = fk.add_random_restarts(current_kernels, exp.n_rand, exp.sd, data_shape=data_shape)
# Score the kernels
new_results = jc.evaluate_kernels(current_kernels, X, y, verbose=exp.verbose, local_computation=exp.local_computation,
zip_files=False, max_jobs=exp.max_jobs, iters=exp.iters, zero_mean=exp.zero_mean, random_seed=exp.random_seed)
# Enforce the period heuristic
#### TODO - Concept of parameter constraints is more general than this - make it so
if exp.use_min_period:
new_results = [sk for sk in new_results if not sk.k_opt.out_of_bounds(data_shape)]
# Some of the scores may have failed - remove nans to prevent sorting algorithms messing up
new_results = remove_nan_scored_kernels(new_results)
assert(len(new_results) > 0) # FIXME - Need correct control flow if this happens
# Sort the new all_results
new_results = sorted(new_results, key=ScoredKernel.score, reverse=True)
print 'All new results:'
for result in new_results:
print result.nll, result.laplace_nle, result.bic_nle, result.k_opt.pretty_print()
# Remove near duplicates from these all_results (top m all_results only for efficiency)
if exp.k > 1:
# Only remove duplicates if they affect the search
new_results = remove_duplicates(new_results, X, local_computation=exp.local_computation, verbose=exp.verbose)
print 'All new results after duplicate removal:'
for result in new_results:
print result.nll, result.laplace_nle, result.bic_nle, result.k_opt.pretty_print()
all_results = all_results + new_results
all_results = sorted(all_results, key=ScoredKernel.score, reverse=True)
results_sequence.append(all_results)
if exp.verbose:
print 'Printing all results'
for result in all_results:
print result.nll, result.laplace_nle, result.bic_nle, result.k_opt.pretty_print()
# Extract the best k kernels from the new all_results
best_results = sorted(new_results, key=ScoredKernel.score)[0:exp.k]
best_kernels = [r.k_opt for r in best_results]
current_kernels = grammar.expand_kernels(D, best_kernels, verbose=exp.verbose, debug=exp.debug, base_kernels=exp.base_kernels)
if exp.debug==True:
current_kernels = current_kernels[0:4]
# Write all_results to a temporary file at each level.
all_results = sorted(all_results, key=ScoredKernel.score, reverse=True)
with open(results_filename + '.unfinished', 'w') as outfile:
outfile.write('Experiment all_results for\n datafile = %s\n\n %s \n\n' \
% (experiment_data_file_name, experiment_fields_to_str(exp)))
for (i, all_results) in enumerate(results_sequence):
outfile.write('\n%%%%%%%%%% Level %d %%%%%%%%%%\n\n' % i)
if exp.verbose_results:
for result in all_results:
print >> outfile, result
else:
# Only print top k kernels - i.e. those used to seed the next level of the search
for result in best_results:
print >> outfile, result
# Rename temporary results file to actual results file
os.rename(results_filename + '.unfinished', results_filename)
def test_kernel_expand_multi_d():
D = 3
k_base = list(fk.base_kernels(3))
k_expanded = grammar.expand_kernels(3, k_base)
assert len(k_expanded) > len(k_base)
def test_kernel_expand():
k = fk.Carls_Mauna_kernel()
k_expanded = grammar.expand_kernels(1, [k])
assert len(k_expanded) > 1
def test_kernel_expand_multi_d():
D = 3
k_base = list(fk.base_kernels(3))
k_expanded = grammar.expand_kernels(3, k_base)
assert len(k_expanded) > len(k_base)
def test_kernel_expand():
k = fk.Carls_Mauna_kernel()
k_expanded = grammar.expand_kernels(1, [k])
assert len(k_expanded) > 1