def build_detail_site(data, label_func, j2_env, linestyles, batch=False):
for (name, runs) in data.items():
print("Building '%s'" % name)
all_runs = runs.keys()
label = label_func(name)
data = {"normal": [], "scatter": []}
for plottype in args.plottype:
xn, yn = plot_variants[plottype]
data["normal"].append(
create_plot(runs, xn, yn, convert_linestyle(linestyles),
j2_env))
if args.scatter:
data["scatter"].append(
create_plot(runs, xn, yn, convert_linestyle(linestyles),
j2_env, "Scatterplot ", "bubble"))
# create png plot for summary page
data_for_plot = {}
for k in runs.keys():
data_for_plot[k] = prepare_data(runs[k], 'k-nn', 'qps')
plot.create_plot(
data_for_plot, False, False, True, 'k-nn', 'qps',
args.outputdir + get_algorithm_name(name, batch) + ".png",
linestyles, batch)
with open(args.outputdir + get_algorithm_name(name, batch) + ".html",
"w") as text_file:
text_file.write(
j2_env.get_template("detail_page.html").render(title=label,
plot_data=data,
args=args,
batch=batch))
def build_detail_site(data, label_func, j2_env, linestyles, batch=False):
for (name, runs) in data.items():
print("Building '%s'" % name)
all_runs = runs.keys()
label = label_func(name)
data = {"normal": [], "scatter": []}
for plottype in args.plottype:
xn, yn = plot_variants[plottype]
data["normal"].append(create_plot(
runs, xn, yn, convert_linestyle(linestyles), j2_env))
if args.scatter:
data["scatter"].append(
create_plot(runs, xn, yn, convert_linestyle(linestyles),
j2_env, "Scatterplot ", "bubble"))
# create png plot for summary page
data_for_plot = {}
for k in runs.keys():
data_for_plot[k] = prepare_data(runs[k], 'k-nn', 'qps')
plot.create_plot(
data_for_plot, False,
False, True, 'k-nn', 'qps',
args.outputdir + get_algorithm_name(name, batch) + ".png",
linestyles, batch)
output_path = "".join([args.outputdir,
get_algorithm_name(name, batch),
".html"])
with open(output_path, "w") as text_file:
text_file.write(j2_env.get_template("detail_page.html").
render(title=label, plot_data=data,
args=args, batch=batch))
def run(definition, dataset, count, run_count, batch):
algo = instantiate_algorithm(definition)
assert not definition.query_argument_groups \
or hasattr(algo, "set_query_arguments"), """\
error: query argument groups have been specified for %s.%s(%s), but the \
algorithm instantiated from it does not implement the set_query_arguments \
function""" % (definition.module, definition.constructor, definition.arguments)
D = get_dataset(dataset)
X_train = numpy.array(D['train'])
X_test = numpy.array(D['test'])
distance = D.attrs['distance']
print("type D: ", type(D))
print("type x_train: ", type(X_train))
print("type x_test: ", type(X_test))
print("type distance: ", type(distance))
print('got a train set of size (%d * %d)' % X_train.shape)
print('got %d queries' % len(X_test))
X_train = dataset_transform[distance](X_train)
X_test = dataset_transform[distance](X_test)
try:
prepared_queries = False
if hasattr(algo, "supports_prepared_queries"):
prepared_queries = algo.supports_prepared_queries()
t0 = time.time()
memory_usage_before = algo.get_memory_usage()
algo.fit(X_train)
build_time = time.time() - t0
index_size = algo.get_memory_usage() - memory_usage_before
print('Built index in', build_time)
print('Index size: ', index_size)
query_argument_groups = definition.query_argument_groups
# Make sure that algorithms with no query argument groups still get run
# once by providing them with a single, empty, harmless group
if not query_argument_groups:
query_argument_groups = [[]]
for pos, query_arguments in enumerate(query_argument_groups, 1):
print("Running query argument group %d of %d..." %
(pos, len(query_argument_groups)))
if query_arguments:
algo.set_query_arguments(*query_arguments)
descriptor, results = run_individual_query(algo, X_train, X_test,
distance, count,
run_count, batch)
descriptor["build_time"] = build_time
descriptor["index_size"] = index_size
descriptor["algo"] = get_algorithm_name(definition.algorithm,
batch)
descriptor["dataset"] = dataset
store_results(dataset, count, definition, query_arguments,
descriptor, results, batch)
finally:
algo.done()
def run(definition, dataset, count, run_count, batch):
algo = instantiate_algorithm(definition)
assert not definition.query_argument_groups \
or hasattr(algo, "set_query_arguments"), """\
error: query argument groups have been specified for %s.%s(%s), but the \
algorithm instantiated from it does not implement the set_query_arguments \
function""" % (definition.module, definition.constructor, definition.arguments)
D = get_dataset(dataset)
X_train = numpy.array(D['train'])
X_test = numpy.array(D['test'])
distance = D.attrs['distance']
print('got a train set of size (%d * %d)' % X_train.shape)
print('got %d queries' % len(X_test))
try:
prepared_queries = False
if hasattr(algo, "supports_prepared_queries"):
prepared_queries = algo.supports_prepared_queries()
t0 = time.time()
memory_usage_before = algo.get_memory_usage()
algo.fit(X_train)
build_time = time.time() - t0
index_size = algo.get_memory_usage() - memory_usage_before
print('Built index in', build_time)
print('Index size: ', index_size)
query_argument_groups = definition.query_argument_groups
# Make sure that algorithms with no query argument groups still get run
# once by providing them with a single, empty, harmless group
if not query_argument_groups:
query_argument_groups = [[]]
for pos, query_arguments in enumerate(query_argument_groups, 1):
print("Running query argument group %d of %d..." %
(pos, len(query_argument_groups)))
if query_arguments:
algo.set_query_arguments(*query_arguments)
descriptor, results = run_individual_query(
algo, X_train, X_test, distance, count, run_count, batch)
descriptor["build_time"] = build_time
descriptor["index_size"] = index_size
descriptor["algo"] = get_algorithm_name(
definition.algorithm, batch)
descriptor["dataset"] = dataset
store_results(dataset, count, definition,
query_arguments, descriptor, results, batch)
finally:
algo.done()
def run(definition, dataset, count, run_count, batch):
algo = instantiate_algorithm(definition)
assert not definition.query_argument_groups \
or hasattr(algo, "set_query_arguments"), """\
error: query argument groups have been specified for %s.%s(%s), but the \
algorithm instantiated from it does not implement the set_query_arguments \
function""" % (definition.module, definition.constructor, definition.arguments)
D = get_dataset(dataset)
X_train = numpy.array(D['train'])
X_test = numpy.array(D['test'])
if algo.builds_graph():
# Test data first to avoid converting test set index to graph index
X_train = numpy.concatenate((X_test, X_train))
# The protocol expects the count to be given at query time, so it has
# to be set as a parameter beforehand.
algo.set_count(count)
distance = D.attrs['distance']
print('got a train set of size (%d * %d)' % X_train.shape)
print('got %d queries' % len(X_test))
try:
prepared_queries = False
if hasattr(algo, "supports_prepared_queries"):
prepared_queries = algo.supports_prepared_queries()
t0 = time.time()
memory_usage_before = algo.get_memory_usage()
algo.fit(X_train)
build_time = time.time() - t0
index_size = algo.get_memory_usage() - memory_usage_before
print('Built index in', build_time)
print('Index size: ', index_size)
query_argument_groups = definition.query_argument_groups
# Make sure that algorithms with no query argument groups still get run
# once by providing them with a single, empty, harmless group
if not query_argument_groups:
query_argument_groups = [[]]
for pos, query_arguments in enumerate(query_argument_groups, 1):
print("Running query argument group %d of %d..." %
(pos, len(query_argument_groups)))
if query_arguments:
algo.set_query_arguments(*query_arguments)
if algo.builds_graph():
descriptor, results = check_graph(algo, X_train, X_test, distance, count)
else:
descriptor, results = run_individual_query(algo, X_train, X_test,
distance, count, run_count, batch)
descriptor["build_time"] = build_time
descriptor["index_size"] = index_size
descriptor["algo"] = get_algorithm_name(definition.algorithm, batch)
descriptor["dataset"] = dataset
descriptor["count"] = int(count)
descriptor["batch_mode"] = batch
store_results(dataset, count, definition,
query_arguments, descriptor, results, batch)
finally:
algo.done()