def test_explicit_period():
period = 200
s = sequences.sine(1.0, period, CYCLES, period // 3)
# wrong but plausible
seasons, _ = seasonal.fit_seasons(s, period=period - 2)
assert seasons is not None and len(seasons) == period - 2
# flat out wrong
seasons, _ = seasonal.fit_seasons(s, period=period // 2)
assert seasons is None
def test_explicit_period():
period = 200
s = sequences.sine(1.0, period, CYCLES, period / 3)
# wrong but plausible
seasons, _ = seasonal.fit_seasons(s, period=period - 2)
assert seasons is not None and len(seasons) == period - 2
# flat out wrong
seasons, _ = seasonal.fit_seasons(s, period=period / 2)
assert seasons is None
def test_sine_trend():
"""a linear trend with sine wave superimposed"""
for kind in ["mean", "median", "spline", "line"]:
for period in PERIODS:
for slope in SLOPES:
s = sequences.sine(AMP, period, CYCLES, period / 3)
trend = np.arange(len(s)) * slope / len(s)
s += trend
a = fit_trend(s, kind=kind)
rmse = np.sqrt(np.mean((a - trend) ** 2))
assert rmse <= s.std() / 2.0
def test_sine_trend():
"""a linear trend with sine wave superimposed"""
for kind in ["mean", "median", "spline", "line"]:
for period in PERIODS:
for slope in SLOPES:
s = sequences.sine(AMP, period, CYCLES, period // 3)
trend = np.arange(len(s)) * slope / len(s)
s += trend
a = fit_trend(s, kind=kind)
rmse = np.sqrt(np.mean((a - trend) ** 2))
assert rmse <= s.std() / 2.0
def try_sine(period, noise=0.0, reps=1):
npass = 0
s = sequences.sine(1.0, period, CYCLES, period / 3)
for _ in range(reps):
ns = sequences.add_noise(sequences.mix(s, 0, noise), noise)
ns = ns - ns.mean()
p = fit_period(ns)
if period - EPS <= p and p <= period + EPS:
npass += 1
print "try_sine noise {0} period {1} -> {2}%".format(
noise, period, (100 * npass) / reps)
return npass
def try_sine(period, noise=0.0, reps=1):
npass = 0
s = sequences.sine(1.0, period, CYCLES, period // 3)
for _ in range(reps):
ns = sequences.add_noise(sequences.mix(s, 0, noise), noise)
ns = ns - ns.mean()
p = fit_period(ns)
if period - EPS <= p and p <= period + EPS:
npass += 1
print("try_sine noise {0} period {1} -> {2}%".format(
noise, period, (100 * npass) / reps))
return npass
def test_sine_bend():
"""trend up then down, with sine wave superimposed"""
for kind in ["mean", "median", "spline"]:
for period in PERIODS:
for slope in SLOPES:
s = sequences.sine(AMP, period, CYCLES, period / 3)
trend = np.arange(len(s)+1) * slope / len(s)
trend = np.concatenate((trend[::2], trend[::-2]))[:len(s)]
s += trend
a = fit_trend(s, kind=kind)
rmse = np.sqrt(np.mean((a - trend) ** 2))
print kind, period, slope, rmse, s.std()
assert rmse <= s.std() / 2.0
def test_sine_bend():
"""trend up then down, with sine wave superimposed"""
for kind in ["mean", "median", "spline"]:
for period in PERIODS:
for slope in SLOPES:
s = sequences.sine(AMP, period, CYCLES, period // 3)
trend = np.arange(len(s)+1) * slope / len(s)
trend = np.concatenate((trend[::2], trend[::-2]))[:len(s)]
s += trend
a = fit_trend(s, kind=kind)
rmse = np.sqrt(np.mean((a - trend) ** 2))
print(kind, period, slope, rmse, s.std())
assert rmse <= s.std() / 2.0
# adjust_seasons() handles a variety of optional arguments.
# verify that adjust_trend() correctly calledfor different option combinations.
#
# No noise in this test set.
#
from __future__ import division
import numpy as np
from seasonal import fit_trend, adjust_seasons # pylint:disable=import-error
from seasonal.sequences import sine # pylint:disable=import-error
PERIOD = 25
CYCLES = 4
AMP = 1.0
TREND = AMP / PERIOD
LEVEL = 1000.0
SEASONS = sine(AMP, PERIOD, 1)
DATA = LEVEL + np.arange(PERIOD * CYCLES) * TREND + np.tile(SEASONS, CYCLES)
ZEROS = np.zeros(PERIOD * CYCLES)
def iszero(a):
return np.all(np.isclose(a, ZEROS))
def isseasons(a):
return np.all(np.isclose(a, SEASONS))
def test_auto():
adjusted = adjust_seasons(DATA)
assert adjusted.std() < DATA.std()
def test_trend_line():
adjusted = adjust_seasons(DATA, trend="line")
def test_sine():
for period in PERIODS:
s = sequences.sine(1.0, period, CYCLES, period / 3)
p = periodogram_peaks(s, thresh=1.0)
assert len(p) == 1 and p[0][2] <= period and p[0][3] >= period
def test_sine():
for period in PERIODS:
s = sequences.sine(1.0, period, CYCLES, period // 3)
p = periodogram_peaks(s, thresh=1.0)
assert len(p) == 1 and p[0][2] <= period and p[0][3] >= period
