def test_mse_2(self):
points = np.array([[0,0], [1,1], [2,2]])
knees = np.array([1])
expected = np.array([[1,1], [2,2]])
result = evaluation.mse(points, knees, expected)
desired = 1/2
self.assertAlmostEqual(result, desired)
def test_mse_1(self):
points = np.array([[0,0], [1,1], [2,2]])
knees = np.array([0,1,2])
expected = np.array([[1,1], [2,2]])
result = evaluation.mse(points, knees, expected, evaluation.Strategy.worst)
desired = 1/3
self.assertAlmostEqual(result, desired)
def main(args):
# get the expected file from the input file
dirname = os.path.dirname(args.i)
filename = os.path.splitext(os.path.basename(args.i))[0]
expected_file = os.path.join(os.path.normpath(dirname),
f'{filename}_expected.csv')
expected = None
if os.path.exists(expected_file):
with open(expected_file, 'r') as f:
reader = csv.reader(f, quoting=csv.QUOTE_NONNUMERIC)
expected = list(reader)
else:
expected = []
points = np.genfromtxt(args.i, delimiter=',')
points_reduced, points_removed = rdp.rdp(points, args.r)
space_saving = round((1.0 - (len(points_reduced) / len(points))) * 100.0,
2)
logger.info('Number of data points after RDP: %s(%s %%)',
len(points_reduced), space_saving)
names = [
'kneedle', 'kneedke(Rec)', 'l-method', 'dfdt', 'menger', 'curvature',
'Tyler (RDP)', 'Tyler', 'RDP'
]
methods = [
kneedle.auto_knees, kneedle.multi_knee, lmethod.multi_knee,
dfdt.multi_knee, menger.multi_knee, curvature.multi_knee, ps.knees
]
knees = []
knees_raw = []
# Elbow methods
for m, n in zip(methods, names):
tmp = m(points_reduced)
knees.append(tmp)
raw_indexes = rdp.mapping(tmp, points_reduced, points_removed)
knees_raw.append(raw_indexes)
# Tyler
candidates = ps.knees(points)
knees.append(candidates)
knees_raw.append(candidates)
# RDP
candidates = np.arange(1, len(points_reduced))
knees.append(candidates)
raw_indexes = rdp.mapping(candidates, points_reduced, points_removed)
knees_raw.append(raw_indexes)
#plot_knees(points, knees_raw, names)
cmethod = {
Clustering.single: clustering.single_linkage,
Clustering.complete: clustering.complete_linkage,
Clustering.average: clustering.average_linkage
}
# Cluster and select points
filtered_knees_raw = []
rankings = []
for k, n in zip(knees, names):
# remove 0 index in the knees:
k = k[k != 0]
if n == 'Tyler':
filtered_knees_raw.append(k)
ranks = np.full(len(k), 1.0)
#rankings.append(ranking.slope_ranking(points, k))
rankings.append(ranks)
else:
t_k = pp.filter_worst_knees(points_reduced, k)
filtered_knees = pp.filter_clustring(points_reduced, t_k,
cmethod[args.c], args.t,
args.m)
rankings.append(
ranking.slope_ranking(points_reduced, filtered_knees))
raw_indexes = rdp.mapping(filtered_knees, points_reduced,
points_removed)
filtered_knees_raw.append(raw_indexes)
logger.info(f'Model MSE(knees) MSE(exp) Cost(tr) Cost(kn)')
logger.info(f'----------------------------------------------------------')
for k, n in zip(filtered_knees_raw, names):
if len(expected) > 0:
error_mse = evaluation.mse(points, k, expected,
evaluation.Strategy.knees)
error_mse_exp = evaluation.mse(points, k, expected,
evaluation.Strategy.expected)
else:
error_mse = math.nan
error_mse_exp = math.nan
_, _, _, _, cost_trace = evaluation.accuracy_trace(points, k)
_, _, _, _, cost_knee = evaluation.accuracy_knee(points, k)
logger.info(
f'{n:<13}| {error_mse:10.2E} {error_mse_exp:10.2E} {cost_trace:10.2E} {cost_knee:10.2E}'
)
plot_knees_ranking(points, filtered_knees_raw, names, rankings, expected)