def cobras_parameter_comparison():
print("making tests")
query_budget = 200
tests = TestCollection()
test_names = ["cobras_no_noise"]
test_dict = {
0.05: [0.96, 0.99],
0.10: [0.96, 0.99],
0.15: [0.91, 0.96, 0.99],
0.20: [0.86, 0.91, 0.96]
}
for p in [0.10, 0.15, 0.20]:
t_values = test_dict[p]
for t in t_values:
test_names.append("cobras_0.10_p{}_t{}_noise_budget{}".format(
p, t, query_budget))
tests.add_10_times_10_fold_test(
"cobras_0.10_p{}_t{}_noise_budget{}".format(
p, t, query_budget),
"COBRAS",
cobras_algorithm_settings_to_string(p, 3, 7, t, t, True,
False),
Dataset.get_non_face_news_spam_names(),
"probability_noise_querier",
probabilistic_noisy_querier_settings_to_string(
0.10, query_budget),
nb_of_runs=1)
run_tests_over_SSH_on_machines(
tests, himecs_generate_computer_info(start_index=3, nb_of_machines=2))
comparison_name = "all_parameter_study"
line_names = [test_name[12:-16] for test_name in test_names]
calculate_aris_and_compare_for_tests(comparison_name,
test_names,
line_names,
nb_of_cores=24,
query_budget=200,
recalculate=False)
def NPU_Cosc_VaryingAmountsOfNoise():
print("making tests")
tests = TestCollection()
query_budget = 100
for noise_percentage in [-1, 0.10]:
noise_text = str(noise_percentage) if noise_percentage != -1 else "no"
tests.add_10_times_10_fold_test(
"NPU_Cosc_{}_noise_budget{}".format(noise_text,
query_budget), "NPU_COSC",
"no_parameters", Dataset.get_non_face_news_spam_names(),
"probability_noise_querier",
probabilistic_noisy_querier_settings_to_string(
noise_percentage, query_budget))
run_tests_over_SSH_on_machines(tests, MACHINES_TO_USE)
comparison_name = "NPU_Cosc_varying_amounts_of_noise"
test_names = [
"NPU_Cosc_no_noise_budget100", "NPU_Cosc_0.1_noise_budget100"
]
line_names = None
calculate_aris_and_compare_for_tests(comparison_name,
test_names,
line_names,
query_budget=query_budget)
def run_tests():
datasets = [
Dataset(name) for name in Dataset.get_non_face_news_spam_names()
]
test_active_clustering_algorithm_n_times_n_fold(
"nCOBRAS_filtering",
COBRAS(minimum_approximation_order=3,
noise_probability=0.10,
maximum_approximation_order=7,
certainty_threshold_reuse=0.91),
ProbabilisticNoisyQuerierBuilder(0.10, 100),
datasets,
n=3)
# test_active_clustering_algorithm_n_times_n_fold("NPU-MPCK-means_no_noise", NPU(MyMPCKMeans(max_iter=10, learn_multiple_full_matrices=False)), NoisyQuerierBuilder(0, 100), datasets, nb_cores=3)
# test_active_clustering_algorithm_n_times_n_fold("NPU-MPCK-means_10%_noise", NPU(MyMPCKMeans(max_iter = 10, learn_multiple_full_matrices=False)), NoisyQuerierBuilder(0.10, 100), datasets, nb_cores=3)
# test_active_clustering_algorithm("dummy_clusterer1", DummyClusterer(), NoisyQuerierBuilder(0.10, 100), datasets )
# test_active_clustering_algorithm("dummy_clusterer2", DummyClusterer(), NoisyQuerierBuilder(0.10, 100), datasets)
test_names = ["nCOBRAS_filtering", "noise_robust_cobras"]
compare_algorithms_and_plot_results_n_times_n_fold("nCOBRAS_filtering",
test_names,
calculate_aris=False)
