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 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
def filler(ts):
tsC = ts.copy()
filled = tsC.interpolate().fillna(0)
# Find the trend inside the series
trend = fit_trend(filled, kind='spline')
trend = trend - trend.min()
trendSeries = pd.Series(trend, tsC.index)
detrended = tsC - trendSeries
stdseason = detrended.groupby([detrended.index.month, detrended.index.day]).median()
# Create fake yrs
reshape = np.tile(stdseason, 3)
reindex = np.tile(stdseason.index, 3)
t = pd.Series(reshape, reindex)
# TODO decide which filter it's the best one
# Smooth by Savinsky Golet
tSV = savgol_filter(t, 5, 2) # TODO change to parametric
# # Smooth by boxcar
# tSV = t.rolling(5, win_type='bartlett', center=True).mean() #parzen
tsv = tSV[stdseason.count(): 2 * stdseason.count()]
ps = pd.Series(tsv, stdseason.index)
nanlist = tsC[tsC.isnull()]
for index, value in nanlist.iteritems():
nanlist.loc[index] = stdseason.loc[index.month, index.day]
tsC.update(nanlist)
return tsC
def test_explicit_trend():
trend = fit_trend(DATA, kind="line")
adjusted = adjust_seasons(DATA, trend=trend)
assert adjusted.std() < DATA.std()
def test_trend_median():
# median filter doesn't *quite* cancel a straight line
adjusted = DATA - fit_trend(DATA, kind="median")
adjusted = adjusted - adjusted.mean()
assert iszero(adjusted)
def test_trend_mean():
adjusted = DATA - fit_trend(DATA, kind="mean")
adjusted = adjusted - adjusted.mean()
assert iszero(adjusted)
def test_trend_spline():
adjusted = DATA - fit_trend(DATA, kind="spline")
adjusted = adjusted - adjusted.mean()
assert iszero(adjusted)
def test_none():
adjusted = DATA - fit_trend(DATA, kind=None)
assert iszero(DATA - adjusted)
def test_trend_median():
# median filter doesn't *quite* cancel a straight line
fitted = fit_trend(DATA, kind="median")
assert np.isclose(fitted.mean(), MID)
assert iszero(DATA - fitted)
def test_trend_mean():
fitted = fit_trend(DATA, kind="mean")
assert np.isclose(fitted.mean(), MID)
assert iszero(DATA - fitted)
def test_none():
fitted = fit_trend(DATA, kind=None)
assert np.isclose(fitted.mean(), MID)
def test_zero():
adjusted = fit_trend(ZEROS + MID, kind="line")
assert adjusted.mean() == MID
