def _objective_FW2S_MDL(trial, train, changepoints, tolerance_delay,
params): # FW2S_MDL
nml_gaussian = partial(sdmdl_nml.nml_gaussian,
mu_max=params["mu_max"],
div_min=params["div_min"],
div_max=params["div_max"])
complexity_gaussian = partial(sdmdl_nml.complexity_gaussian,
mu_max=params["mu_max"],
div_min=params["div_min"],
div_max=params["div_max"])
window_size_1 = trial.suggest_int('window_size_1', 10, 500)
window_size_2 = trial.suggest_int('window_size_2', 10, 500)
retrospective_first = sdmdl.Retrospective(
h=window_size_1,
encoding_func=nml_gaussian,
complexity_func=complexity_gaussian,
order=0)
retrospective_second = sdmdl.Retrospective(
h=window_size_2,
encoding_func=nml_gaussian,
complexity_func=complexity_gaussian,
order=0)
retrospective = fw2s_mdl.Retrospective(retrospective_first,
retrospective_second)
scores = retrospective.calc_scores(train)
AUC = calc_AUC(scores, changepoints, tolerance_delay)
return -AUC
def conduct_FW2S_MDL(n_trials, n_samples, dataset, changepoints,
tolerance_delay, params): # FW2S_MDL
# hyperparameter tuning
objective_FW2S_MDL = partial(_objective_FW2S_MDL,
train=dataset[0],
changepoints=changepoints,
tolerance_delay=tolerance_delay,
params=params)
study = optuna.create_study()
study.optimize(objective_FW2S_MDL, n_trials=n_trials, n_jobs=-1)
opt_window_size_1 = study.best_params['window_size_1']
opt_window_size_2 = study.best_params['window_size_2']
nml_gaussian = partial(sdmdl_nml.nml_gaussian,
mu_max=params["mu_max"],
div_min=params["div_min"],
div_max=params["div_max"])
complexity_gaussian = partial(sdmdl_nml.complexity_gaussian,
mu_max=params["mu_max"],
div_min=params["div_min"],
div_max=params["div_max"])
retrospective_first = sdmdl.Retrospective(
h=opt_window_size_1,
encoding_func=nml_gaussian,
complexity_func=complexity_gaussian,
order=0)
retrospective_second = sdmdl.Retrospective(
h=opt_window_size_2,
encoding_func=nml_gaussian,
complexity_func=complexity_gaussian,
order=0)
retrospective = fw2s_mdl.Retrospective(retrospective_first,
retrospective_second)
# calculate metrics
calc_metrics = partial(_calc_metrics,
dataset=dataset,
changepoints=changepoints,
tolerance_delay=tolerance_delay,
retrospective=retrospective)
p = Pool(multi.cpu_count() - 1)
args = list(range(1, n_samples))
res = np.array(p.map(calc_metrics, args))
p.close()
print("AUC: ", np.mean(res[:]), "±", np.std(res[:]))
row = pd.DataFrame({
"method": ["FW2S_MDL"],
"AUC_mean": np.mean(res[:]),
"AUC_std": np.std(res[:])
})
return row
def _objective_FW2S_MDL(trial, train, changepoints, tolerance_delay, params):
nml_multgaussian = partial(sdmdl_nml.nml_multgaussian,
R=params["R"],
lambda_min=params["lambda_min"])
complexity_multgaussian = partial(sdmdl_nml.complexity_multgaussian,
m=8,
R=params["R"],
lambda_min=params["lambda_min"])
nml_gaussian = partial(sdmdl_nml.nml_gaussian,
mu_max=params["mu_max"],
div_min=params["div_min"],
div_max=params["div_max"])
complexity_gaussian = partial(sdmdl_nml.complexity_gaussian,
mu_max=params["mu_max"],
div_min=params["div_min"],
div_max=params["div_max"])
delta_0 = trial.suggest_uniform('delta_0', 0.001, 0.499)
window_size_1 = trial.suggest_int('window_size_1', 100, 300)
window_size_2 = trial.suggest_int('window_size_2', 100, 300)
retrospective_first = sdmdl.Retrospective(
h=window_size_1,
encoding_func=nml_multgaussian,
complexity_func=complexity_multgaussian,
delta_0=delta_0,
order=0)
retrospective_second = sdmdl.Retrospective(
h=window_size_2,
encoding_func=nml_gaussian,
complexity_func=complexity_gaussian,
order=0)
retrospective = fw2s_mdl.Retrospective(retrospective_first,
retrospective_second)
scores = retrospective.calc_scores(train)
n = len(scores)
scores[2 * (window_size_1 +
window_size_2):n] = scores[window_size_1 + window_size_2:n -
(window_size_1 + window_size_2)]
scores[0:2 * (window_size_1 + window_size_2)] = np.nan
AUC = calc_AUC(scores, changepoints, tolerance_delay, both=both)
return -AUC
def conduct_SDMDL(n_trials, n_samples, dataset, changepoints, tolerance_delay,
params): # S-MDL
# hyperparameter tuning
objective_SDMDL = partial(_objective_SDMDL,
train=dataset[0],
changepoints=changepoints,
tolerance_delay=tolerance_delay,
params=params)
study = optuna.create_study()
study.optimize(objective_SDMDL, n_trials=n_trials, n_jobs=-1)
opt_window_size = study.best_params['window_size']
nml_gaussian = partial(sdmdl_nml.nml_gaussian,
mu_max=params["mu_max"],
div_min=params["div_min"],
div_max=params["div_max"])
complexity_gaussian = partial(sdmdl_nml.complexity_gaussian,
mu_max=params["mu_max"],
div_min=params["div_min"],
div_max=params["div_max"])
retrospective = sdmdl.Retrospective(h=opt_window_size,
encoding_func=nml_gaussian,
complexity_func=complexity_gaussian,
order=params["order"])
# calculate metrics
calc_metrics = partial(_calc_metrics,
dataset=dataset,
changepoints=changepoints,
tolerance_delay=tolerance_delay,
retrospective=retrospective)
p = Pool(multi.cpu_count() - 1)
args = list(range(1, n_samples))
res = np.array(p.map(calc_metrics, args))
p.close()
print("AUC: ", np.mean(res[:]), "±", np.std(res[:]))
if params["order"] == 0:
method_name = "SDMDL_0"
elif params["order"] == 1:
method_name = "SDMDL_1"
else:
method_name = "SDMDL_2"
row = pd.DataFrame({
"method": [method_name],
"AUC_mean": np.mean(res[:]),
"AUC_std": np.std(res[:])
})
return row
def _objective_SDMDL(trial, train, changepoints, tolerance_delay, params):
nml_gaussian = partial(sdmdl_nml.nml_gaussian, mu_max=params[
"mu_max"], div_min=params["div_min"], div_max=params["div_max"])
complexity_gaussian = partial(sdmdl_nml.complexity_gaussian, mu_max=params[
"mu_max"], div_min=params["div_min"], div_max=params["div_max"])
window_size = trial.suggest_int('window_size', 5, 60)
retrospective = sdmdl.Retrospective(h=window_size, encoding_func=nml_gaussian,
complexity_func=complexity_gaussian, order=params["order"])
scores = retrospective.calc_scores(train)
n = len(scores)
scores[2 * window_size - 1: n] = scores[window_size - 1: n - window_size]
scores[0:2 * window_size] = np.nan
AUC = calc_AUC(scores, changepoints, tolerance_delay, both=both)
return -AUC
def _objective_AW2S_MDL(trial, train, changepoints, tolerance_delay):
window_size = trial.suggest_int('window_size', 10, 500)
sigma_given = trial.suggest_uniform('sigma_given', 0.1, 2)
nml_gaussian = partial(sdmdl_nml.nml_gaussian,
mu_max=1e8,
div_min=1e-8,
div_max=1e8)
complexity_gaussian = partial(sdmdl_nml.complexity_gaussian,
mu_max=1e8,
div_min=1e-8,
div_max=1e8)
retrospective_first = sdmdl.Retrospective(
h=window_size,
encoding_func=nml_gaussian,
complexity_func=complexity_gaussian,
order=0)
lnml_gaussian = partial(hsdmdl2_nml.lnml_gaussian, sigma_given=sigma_given)
retrospective_second = hsdmdl2.Retrospective(encoding_func=lnml_gaussian,
d=2,
M=5,
min_datapoints=5,
delta_0=0.05,
delta_1=0.05,
delta_2=0.05,
how_to_drop='all',
order=0,
reliability=True)
retrospective = aw2s_mdl.Retrospective(retrospective_first,
retrospective_second)
alarms = retrospective.make_alarms(train)
scores = np.zeros(len(train))
scores[alarms] = 1
F1_score, _, _ = calc_F1_score(scores,
changepoints,
tolerance_delay,
tuned_threshold=0.5)
return -F1_score
def _objective_SDMDL(trial, train, changepoints, tolerance_delay,
params): # S-MDL
nml_gaussian = partial(sdmdl_nml.nml_gaussian,
mu_max=params["mu_max"],
div_min=params["div_min"],
div_max=params["div_max"])
complexity_gaussian = partial(sdmdl_nml.complexity_gaussian,
mu_max=params["mu_max"],
div_min=params["div_min"],
div_max=params["div_max"])
window_size = trial.suggest_int('window_size', 10, 500)
retrospective = sdmdl.Retrospective(h=window_size,
encoding_func=nml_gaussian,
complexity_func=complexity_gaussian,
order=params["order"])
scores = retrospective.calc_scores(train)
AUC = calc_AUC(scores, changepoints, tolerance_delay)
return -AUC
tolerance_delay=tolerance_delay,
params=params)
study = optuna.create_study()
study.optimize(objective_SDMDL, n_trials=n_trials, n_jobs=-1)
opt_window_size = study.best_params['window_size']
nml_multgaussian = partial(sdmdl_nml.nml_multgaussian,
R=params["R"],
lambda_min=params["lambda_min"])
complexity_multgaussian = partial(sdmdl_nml.complexity_multgaussian,
m=8,
R=params["R"],
lambda_min=params["lambda_min"])
retrospective = sdmdl.Retrospective(h=opt_window_size,
encoding_func=nml_multgaussian,
complexity_func=complexity_multgaussian,
order=params["order"])
sdmdl_0_scores = retrospective.calc_scores(X.T)
n = len(sdmdl_0_scores)
sdmdl_0_scores[2 * opt_window_size -
1:n] = sdmdl_0_scores[opt_window_size - 1:n - opt_window_size]
sdmdl_0_scores[0:2 * opt_window_size] = np.nan
# 1st D-MDL
params = {"R": R, "lambda_min": lambda_min, "order": 1}
# hyperparameter tuning
objective_SDMDL = partial(_objective_SDMDL,
train=X.T,
changepoints=changepoints,
def conduct_AW2S_MDL(n_trials, n_samples, dataset, changepoints,
tolerance_delay): # AW2S-MDL
# hyperparameter tuning
objective_AW2S_MDL = partial(_objective_AW2S_MDL,
train=dataset[0],
changepoints=changepoints,
tolerance_delay=tolerance_delay)
study = optuna.create_study()
study.optimize(objective_AW2S_MDL, n_trials=n_trials, n_jobs=-1)
opt_window_size = study.best_params['window_size']
opt_sigma_given = study.best_params['sigma_given']
nml_gaussian = partial(sdmdl_nml.nml_gaussian,
mu_max=1e8,
div_min=1e-8,
div_max=1e8)
complexity_gaussian = partial(sdmdl_nml.complexity_gaussian,
mu_max=1e8,
div_min=1e-8,
div_max=1e8)
retrospective_first = sdmdl.Retrospective(
h=opt_window_size,
encoding_func=nml_gaussian,
complexity_func=complexity_gaussian,
order=0)
lnml_gaussian = partial(hsdmdl2_nml.lnml_gaussian,
sigma_given=opt_sigma_given)
retrospective_second = hsdmdl2.Retrospective(encoding_func=lnml_gaussian,
d=2,
M=5,
min_datapoints=5,
delta_0=0.05,
delta_1=0.05,
delta_2=0.05,
how_to_drop='all',
order=0,
reliability=True)
retrospective = aw2s_mdl.Retrospective(retrospective_first,
retrospective_second)
# calculate metrics
calc_metrics = partial(_calc_AW2S_MDL_metrics,
dataset=dataset,
changepoints=changepoints,
tolerance_delay=tolerance_delay,
threshold=0.5,
retrospective=retrospective)
p = Pool(multi.cpu_count() - 1)
args = list(range(1, n_samples))
res = np.array(p.map(calc_metrics, args))
p.close()
# result
print("F1 score: ", np.mean(res[:, 0]), "±", np.std(res[:, 0]))
print("precision: ", np.mean(res[:, 1]), "±", np.std(res[:, 1]))
print("recall: ", np.mean(res[:, 2]), "±", np.std(res[:, 2]))
row = pd.DataFrame({
"method": ["AW2S_MDL"],
"F1_score_mean": np.mean(res[:, 0]),
"F1_score_std": np.std(res[:, 0]),
"precision_mean": np.mean(res[:, 1]),
"precision_std": np.std(res[:, 1]),
"recall_mean": np.mean(res[:, 2]),
"recall_std": np.std(res[:, 2])
})
return row
def test_main():
np.random.seed(0)
tolerance_delay = 100
transition_period = 200
data, changepoints = one_mean_changing(transition_period=transition_period)
name = "ChangeFinder"
retrospective = changefinder.Retrospective(r=0.1, order=5, smooth=5)
_calc_metrics_draw_figure(
name, data, changepoints, tolerance_delay=tolerance_delay, retrospective=retrospective)
name = "BOCPD"
h = partial(bocpd.constant_hazard, 1000)
lik = bocpd.StudentT(0.5, 5, 5, 0)
retrospective = bocpd.Retrospective(hazard_func=h, likelihood_func=lik)
_calc_metrics_draw_figure(
name, data, changepoints, tolerance_delay=tolerance_delay, retrospective=retrospective)
name = "SDMDL_0th"
nml_gaussian = partial(sdmdl_nml.nml_gaussian, mu_max=1e8,
div_min=1e-8, div_max=1e8)
complexity_gaussian = partial(sdmdl_nml.complexity_gaussian, mu_max=1e8,
div_min=1e-8, div_max=1e8)
retrospective = sdmdl.Retrospective(h=100, encoding_func=nml_gaussian,
complexity_func=complexity_gaussian, order=0)
_calc_metrics_draw_figure(
name, data, changepoints, tolerance_delay=tolerance_delay, retrospective=retrospective)
name = "SDMDL_1st"
nml_gaussian = partial(sdmdl_nml.nml_gaussian, mu_max=1e8,
div_min=1e-8, div_max=1e8)
complexity_gaussian = partial(sdmdl_nml.complexity_gaussian, mu_max=1e8,
div_min=1e-8, div_max=1e8)
retrospective = sdmdl.Retrospective(h=100, encoding_func=nml_gaussian,
complexity_func=complexity_gaussian, order=1)
_calc_metrics_draw_figure(
name, data, changepoints, tolerance_delay=tolerance_delay, retrospective=retrospective)
name = "SDMDL_2nd"
nml_gaussian = partial(sdmdl_nml.nml_gaussian, mu_max=1e8,
div_min=1e-8, div_max=1e8)
complexity_gaussian = partial(sdmdl_nml.complexity_gaussian, mu_max=1e8,
div_min=1e-8, div_max=1e8)
retrospective = sdmdl.Retrospective(h=100, encoding_func=nml_gaussian,
complexity_func=complexity_gaussian, order=2)
_calc_metrics_draw_figure(
name, data, changepoints, tolerance_delay=tolerance_delay, retrospective=retrospective)
name = "Hierarchical_SCAW1_0th"
lnml_gaussian = partial(hsdmdl1_nml.lnml_gaussian)
retrospective = hsdmdl1.Retrospective(encoding_func=lnml_gaussian, d=2, min_datapoints=5, delta_0=0.05,
delta_1=0.05, delta_2=0.05, how_to_drop='all', order=0, reliability=True)
_calc_metrics_draw_figure(
name, data, changepoints, tolerance_delay=tolerance_delay, retrospective=retrospective)
name = "Hierarchical_SCAW1_1st"
lnml_gaussian = partial(hsdmdl1_nml.lnml_gaussian)
retrospective = hsdmdl1.Retrospective(encoding_func=lnml_gaussian, d=2, min_datapoints=5, delta_0=0.05,
delta_1=0.05, delta_2=0.05, how_to_drop='all', order=1, reliability=True)
_calc_metrics_draw_figure(
name, data, changepoints, tolerance_delay=tolerance_delay, retrospective=retrospective)
name = "Hierarchical_SCAW1_2nd"
lnml_gaussian = partial(hsdmdl1_nml.lnml_gaussian)
retrospective = hsdmdl1.Retrospective(encoding_func=lnml_gaussian, d=2, min_datapoints=5, delta_0=0.05,
delta_1=0.05, delta_2=0.05, how_to_drop='all', order=2, reliability=True)
_calc_metrics_draw_figure(
name, data, changepoints, tolerance_delay=tolerance_delay, retrospective=retrospective)
name = "Hierarchical_SCAW2_0th"
nml_gaussian = partial(hsdmdl2_nml.nml_gaussian)
retrospective = hsdmdl2.Retrospective(encoding_func=nml_gaussian, d=2, M=5, min_datapoints=5, delta_0=0.05,
delta_1=0.05, delta_2=0.05, how_to_drop='all', order=0, reliability=True)
_calc_metrics_draw_figure(
name, data, changepoints, tolerance_delay=tolerance_delay, retrospective=retrospective)
name = "Hierarchical_SCAW2_1st"
nml_gaussian = partial(hsdmdl2_nml.nml_gaussian)
retrospective = hsdmdl2.Retrospective(encoding_func=nml_gaussian, d=2, M=5, min_datapoints=5, delta_0=0.05,
delta_1=0.05, delta_2=0.05, how_to_drop='all', order=1, reliability=True)
_calc_metrics_draw_figure(
name, data, changepoints, tolerance_delay=tolerance_delay, retrospective=retrospective)
name = "Hierarchical_SCAW2_2nd"
nml_gaussian = partial(hsdmdl2_nml.nml_gaussian)
retrospective = hsdmdl2.Retrospective(encoding_func=nml_gaussian, d=2, M=5, min_datapoints=5, delta_0=0.05,
delta_1=0.05, delta_2=0.05, how_to_drop='all', order=2, reliability=True)
_calc_metrics_draw_figure(
name, data, changepoints, tolerance_delay=tolerance_delay, retrospective=retrospective)
name = "FW2S_MDL"
nml_gaussian = partial(sdmdl_nml.nml_gaussian, mu_max=1e8,
div_min=1e-8, div_max=1e8)
complexity_gaussian = partial(sdmdl_nml.complexity_gaussian, mu_max=1e8,
div_min=1e-8, div_max=1e8)
retrospective_first = sdmdl.Retrospective(h=100, encoding_func=nml_gaussian,
complexity_func=complexity_gaussian, order=0)
nml_gaussian = partial(sdmdl_nml.nml_gaussian, mu_max=1e8,
div_min=1e-8, div_max=1e8)
complexity_gaussian = partial(sdmdl_nml.complexity_gaussian, mu_max=1e8,
div_min=1e-8, div_max=1e8)
retrospective_second = sdmdl.Retrospective(h=100, encoding_func=nml_gaussian,
complexity_func=complexity_gaussian, order=0)
retrospective = fw2s_mdl.Retrospective(
retrospective_first, retrospective_second)
_calc_metrics_draw_figure(
name, data, changepoints, tolerance_delay=tolerance_delay, retrospective=retrospective)
name = "AW2S_MDL"
nml_gaussian = partial(sdmdl_nml.nml_gaussian, mu_max=1e8,
div_min=1e-8, div_max=1e8)
complexity_gaussian = partial(sdmdl_nml.complexity_gaussian, mu_max=1e8,
div_min=1e-8, div_max=1e8)
retrospective_first = sdmdl.Retrospective(h=100, encoding_func=nml_gaussian,
complexity_func=complexity_gaussian, order=0)
lnml_gaussian = partial(hsdmdl2_nml.lnml_gaussian, sigma_given=0.3)
retrospective_second = hsdmdl2.Retrospective(encoding_func=lnml_gaussian, d=2, M=5, min_datapoints=5, delta_0=0.05,
delta_1=0.05, delta_2=0.05, how_to_drop='all', order=0, reliability=True)
retrospective = aw2s_mdl.Retrospective(
retrospective_first, retrospective_second)
_calc_metrics_draw_figure(
name, data, changepoints, tolerance_delay=tolerance_delay, retrospective=retrospective)