data = datasets.loadDatasets(dataset, 'interval')
# Try different thresholds for interval proposing
results = OrderedDict()
for propmeth in PROPMETHODS:
results[propmeth] = OrderedDict()
for sd_th in THS:
ygts = []
regions = []
for ftype in data:
for func in data[ftype]:
ygts.append(func['gt'])
ts = preproc.normalize_time_series(func['ts'])
if td_dim > 1:
ts = preproc.td(ts, td_dim, td_lag)
regions.append(list(pointwiseRegionProposals(ts, method = propmeth, sd_th = sd_th,
extint_min_len = 10, extint_max_len = extint_max_len)))
results[propmeth][sd_th] = eval.recall_precision(ygts, regions, multiAsFP = False)
# Print results as table
labels = ('Recall', 'Precision', 'F1-Score')
hdiv_len = 5 + sum(len(lbl) + 3 for lbl in labels) # length of horizontal divider
for propmeth, res in results.items():
print('\n-- {} --\n'.format(propmeth))
print(' |' + '|'.join(' {} '.format(lbl) for lbl in labels))
print('{:-<{}s}'.format('', hdiv_len))
print('Testing on synthetic data: {} <method = gaussian_cov> <dataset> <td-embed = 1>'.format(sys.argv[0]))
print('Methods: gaussian_cov, gaussian_cov_ts, gaussian_global_cov, gaussian_id_cov, gaussian_id_cov_normalized, parzen, compare')
exit()
methods = ['parzen', 'gaussian_id_cov', 'gaussian_cov', 'gaussian_cov_ts'] if method == 'compare' else [method]
if dataset == 'noise':
# Sample a time series consisting of pure white noise
np.random.seed(0)
ts = np.random.randn(dim, n)
else:
import datasets
ts = datasets.loadSyntheticTestbench()[dataset][0]['ts']
# Retrieve scores for all intervals
pts = preproc.td(ts, td_embed) if td_embed > 1 else ts
scores = dict()
for meth in methods:
proposals = maxdiv.denseRegionProposals(pts, extint_min_len, extint_max_len)
if meth == 'gaussian_id_cov_normalized':
norm_scores = maxdiv.maxdiv_gaussian(pts, proposals, mode = 'I_OMEGA', gaussian_mode = 'ID_COV')
# Compute theoretical means and standard deviations of the chi^2 distributions
X = np.arange(extint_min_len, extint_max_len + 1)
scales = 1.0 / X - 1.0 / (pts.shape[1] - X)
chi_mean = pts.shape[0] * scales
chi_sd = np.sqrt(2 * pts.shape[0] * (scales ** 2))
# Normalize scores
for i, (a, b, score) in enumerate(norm_scores):
ind = b - a - extint_min_len
norm_scores[i] = (a, b, (score - chi_mean[ind]) / chi_sd[ind])
# Add a constant offset to avoid negative scores
if __name__ == '__main__':
import sys
method = sys.argv[1] if len(sys.argv) > 1 else 'gaussian_cov_ts'
propmeth = sys.argv[2] if len(sys.argv) > 2 else 'dense'
# Load data
data, dates = read_hpw_csv('HPW_2012_41046.csv')
data = preproc.normalize_time_series(data)
# Detect
if method in ['hotellings_t', 'kde']:
if method == 'kde':
scores = baselines_noninterval.pointwiseKDE(preproc.td(data))
else:
scores = baselines_noninterval.hotellings_t(preproc.td(data))
regions = baselines_noninterval.pointwiseScoresToIntervals(scores, 24)
elif method == 'gaussian_cov_ts':
regions = maxdiv.maxdiv(data,
'gaussian_cov',
mode='TS',
td_dim=3,
td_lag=1,
proposals=propmeth,
extint_min_len=24,
extint_max_len=72,
num_intervals=5)
else:
regions = maxdiv.maxdiv(data,
else:
dataset = 'synthetic'
try:
data = datasets.loadDatasets(dataset)
except:
print('Unknown dataset: {}'.format(dataset))
exit()
if ftype not in data:
print('Unknown extreme type: {}'.format(ftype))
exit()
# Detect and plot anomaly boundaries
for func in data[ftype]:
# Compute scores for each point
scores = METHODS[method](preproc.td(func['ts'], embed_dim))
# Score statistics
score_mean = np.mean(scores)
score_sd = np.std(scores)
score_median = np.median(scores)
score_mad = 1.4826 * np.median(np.abs(scores - score_median))
# Compute gradient of scores
pad = (len(GRAD_FILTER) - 1) // 2
padded_scores = np.concatenate((scores[:pad], scores, scores[-pad:]))
score_gradient = np.abs(
np.convolve(padded_scores, GRAD_FILTER, 'valid'))
score_gradient_mean = np.mean(score_gradient)
score_gradient_sd = np.std(score_gradient)
score_gradient_median = np.median(score_gradient)