def test_run_variations():
algo = algorithms.algorithm_by_name("LogisticRegression")
res = run_variations(
[algo],
dataset_name="classification",
bench_rows=[100, 200],
bench_dims=[10, 20],
)
assert res.shape[0] == 4
assert (res.n_samples == 100).sum() == 2
assert (res.n_features == 20).sum() == 2
(cfg_in["algo_name"] in algos):
# Pass an actual algo object instead of an algo_name string
cfg = cfg_in.copy()
algo = algorithms.algorithm_by_name(cfg_in["algo_name"])
cfg["algos"] = [algo]
alg_name = cfg["algo_name"]
if alg_name.startswith('Sparse'):
if alg_name.startswith('SparseCSR'):
input_type = 'scipy-sparse-csr'
elif alg_name.startswith('SparseCSC'):
input_type = 'scipy-sparse-csc'
else:
input_type = 'numpy'
del cfg["algo_name"]
res = run_variations(**{
**default_args,
**cfg
},
input_type=input_type)
all_results.append(res)
results_df = pd.concat(all_results)
print(results_df)
if args.update_asv_dir:
report_asv(results_df,
args.update_asv_dir,
cudaVer=args.report_cuda_ver,
pythonVer=args.report_python_ver,
osType=args.report_os_type,
machineName=args.report_machine_name)
if args.algorithms:
algos_to_run = []
for name in args.algorithms:
algo = algorithms.algorithm_by_name(name)
if not algo:
raise ValueError("No %s 'algorithm' found" % name)
algos_to_run.append(algo)
else:
# Run all by default
algos_to_run = algorithms.all_algorithms()
results_df = runners.run_variations(
algos_to_run,
dataset_name=args.dataset,
bench_rows=bench_rows,
bench_dims=bench_dims,
input_type=args.input_type,
test_fraction=args.test_split,
param_override_list=param_override_list,
cuml_param_override_list=cuml_param_override_list,
cpu_param_override_list=cpu_param_override_list,
dataset_param_override_list=dataset_param_override_list,
run_cpu=(not args.skip_cpu),
raise_on_error=args.raise_on_error,
n_reps=args.n_reps
)
if args.csv:
results_df.to_csv(args.csv)
print("Saved results to %s" % args.csv)
param_override_list = extract_param_overrides(args.param_sweep)
cuml_param_override_list = extract_param_overrides(args.cuml_param_sweep)
if args.algorithms:
algos_to_run = []
for name in args.algorithms:
algo = algorithms.algorithm_by_name(name)
if not algo:
raise ValueError("No %s 'algorithm' found" % name)
algos_to_run.append(algo)
else:
# Run all by default
algos_to_run = algorithms.all_algorithms()
results_df = runners.run_variations(
algos_to_run,
dataset_name=args.dataset,
bench_rows=bench_rows,
bench_dims=bench_dims,
input_type=args.input_type,
param_override_list=param_override_list,
cuml_param_override_list=cuml_param_override_list,
run_cpu=(not args.skip_cpu),
raise_on_error=args.raise_on_error
)
if args.csv:
results_df.to_csv(args.csv)
print("Saved results to %s" % args.csv)
args = parser.parse_args()
invalidAlgoNames = (set(args.algo) - allAlgoNames)
if invalidAlgoNames:
raise ValueError("Invalid algo name(s): %s" % invalidAlgoNames)
bench_to_run = bench_config[args.benchmark]
default_args = dict(run_cpu=False, n_reps=args.n_reps)
all_results = []
for cfg_in in bench_to_run:
if (args.algo is None) or ("ALL" in args.algo) or \
(cfg_in["algo_name"] in args.algo):
# Pass an actual algo object instead of an algo_name string
cfg = cfg_in.copy()
algo = algorithms.algorithm_by_name(cfg_in["algo_name"])
cfg["algos"] = [algo]
del cfg["algo_name"]
res = run_variations(**{**default_args, **cfg})
all_results.append(res)
results_df = pd.concat(all_results)
print(results_df)
if args.update_asv_dir:
report_asv(results_df,
args.update_asv_dir,
cudaVer=args.report_cuda_ver,
pythonVer=args.report_python_ver,
osType=args.report_os_type,
machineName=args.report_machine_name)
