def test_boosting_epochs():
"""Test boosting with epoched data"""
ds = datasets.get_uts(True, vector3d=True)
p1 = epoch_impulse_predictor('uts', 'A=="a1"', name='a1', ds=ds)
p0 = epoch_impulse_predictor('uts', 'A=="a0"', name='a0', ds=ds)
p1 = p1.smooth('time', .05, 'hamming')
p0 = p0.smooth('time', .05, 'hamming')
# 1d
for tstart, basis in product((-0.1, 0.1, 0), (0, 0.05)):
print(f"tstart={tstart}, basis={basis}")
res = boosting('uts', [p0, p1], tstart, 0.6, model='A', ds=ds, basis=basis, partitions=10, debug=True)
y = convolve(res.h_scaled, [p0, p1])
assert correlation_coefficient(y, res.y_pred) > .999
r = correlation_coefficient(y, ds['uts'])
assert res.r == approx(r, abs=1e-3)
assert res.partitions == 10
# 2d
res = boosting('utsnd', [p0, p1], 0, 0.6, model='A', ds=ds, partitions=10)
assert len(res.h) == 2
assert res.h[0].shape == (5, 60)
assert res.h[1].shape == (5, 60)
y = convolve(res.h_scaled, [p0, p1])
r = correlation_coefficient(y, ds['utsnd'], ('case', 'time'))
assert_dataobj_equal(res.r, r, decimal=3, name=False)
# vector
res = boosting('v3d', [p0, p1], 0, 0.6, error='l1', model='A', ds=ds, partitions=10)
assert res.residual.ndim == 0
def test_boosting_epochs():
"""Test boosting with epoched data"""
ds = datasets.get_uts(True, vector3d=True)
p1 = epoch_impulse_predictor('uts', 'A=="a1"', name='a1', ds=ds)
p0 = epoch_impulse_predictor('uts', 'A=="a0"', name='a0', ds=ds)
p1 = p1.smooth('time', .05, 'hamming')
p0 = p0.smooth('time', .05, 'hamming')
# 1d
for tstart, basis in product((-0.1, 0.1, 0), (0, 0.05)):
print(f"tstart={tstart}, basis={basis}")
res = boosting('uts', [p0, p1],
tstart,
0.6,
model='A',
ds=ds,
basis=basis,
partitions=10,
debug=True)
y = convolve(res.h_scaled, [p0, p1])
assert correlation_coefficient(y, res.y_pred) > .999
r = correlation_coefficient(y, ds['uts'])
assert res.r == approx(r, abs=1e-3)
assert res.partitions == 10
# prefit
res1 = boosting('uts', p1, 0, 0.6, model='A', ds=ds, partitions=10)
res0 = boosting('uts', p0, 0, 0.6, model='A', ds=ds, partitions=10)
res01 = boosting('uts', [p0, p1],
0,
0.6,
model='A',
ds=ds,
partitions=10,
prefit=res1)
# 2d
res = boosting('utsnd', [p0, p1], 0, 0.6, model='A', ds=ds, partitions=10)
assert len(res.h) == 2
assert res.h[0].shape == (5, 60)
assert res.h[1].shape == (5, 60)
y = convolve(res.h_scaled, [p0, p1])
r = correlation_coefficient(y, ds['utsnd'], ('case', 'time'))
assert_dataobj_equal(res.r, r, decimal=3, name=False)
# vector
res = boosting('v3d', [p0, p1],
0,
0.6,
error='l1',
model='A',
ds=ds,
partitions=10)
assert res.residual.ndim == 0
def test_correlation_coefficient():
ds = datasets.get_uts()
uts = ds['uts']
uts2 = uts.copy()
uts2.x += np.random.normal(0, 1, uts2.shape)
assert correlation_coefficient(uts, uts2) == pytest.approx(
np.corrcoef(uts.x.ravel(), uts2.x.ravel())[0, 1])
assert_allclose(
correlation_coefficient(uts[:10], uts2[:10], 'time').x,
[np.corrcoef(uts.x[i], uts2.x[i])[0, 1] for i in range(10)])
assert_allclose(
correlation_coefficient(uts[:, :-.1], uts2[:, :-.1], 'case').x,
[np.corrcoef(uts.x[:, i], uts2.x[:, i])[0, 1] for i in range(10)])
def test_correlation_coefficient():
ds = datasets.get_uts()
uts = ds['uts']
uts2 = uts.copy()
uts2.x += np.random.normal(0, 1, uts2.shape)
assert_almost_equal(
correlation_coefficient(uts, uts2),
np.corrcoef(uts.x.ravel(), uts2.x.ravel())[0, 1])
assert_allclose(
correlation_coefficient(uts[:10], uts2[:10], 'time').x,
[np.corrcoef(uts.x[i], uts2.x[i])[0, 1] for i in range(10)])
assert_allclose(
correlation_coefficient(uts[:, :-.1], uts2[:, :-.1], 'case').x,
[np.corrcoef(uts.x[:, i], uts2.x[:, i])[0, 1] for i in range(10)])
def test_result():
"Test boosting results"
ds = datasets._get_continuous()
x1 = ds['x1']
# convolve function
y = convolve([ds['h1'], ds['h2']], [ds['x1'], ds['x2']])
assert_dataobj_equal(y, ds['y'], name=False)
# test prediction with res.h and res.h_scaled
res = boosting(ds['y'], ds['x1'], 0, 1)
y1 = convolve(res.h_scaled, ds['x1'])
x_scaled = ds['x1'] / res.x_scale
y2 = convolve(res.h, x_scaled)
y2 *= res.y_scale
y2 += y1.mean() - y2.mean() # mean can't be reconstructed
assert_dataobj_equal(y1, y2, decimal=12)
# reconstruction
res = boosting(x1, y, -1, 0, debug=True)
x1r = convolve(res.h_scaled, y)
assert correlation_coefficient(res.y_pred, x1r) > .999
assert correlation_coefficient(x1r[0.9:], x1[0.9:]) == approx(res.r,
abs=1e-3)
# test NaN checks (modifies data)
ds['x2'].x[1, 50] = np.nan
with pytest.raises(ValueError):
boosting(ds['y'], ds['x2'], 0, .5)
with pytest.raises(ValueError):
boosting(ds['y'], ds['x2'], 0, .5, False)
ds['x2'].x[1, :] = 1
with catch_warnings():
filterwarnings('ignore', category=RuntimeWarning)
with pytest.raises(ValueError):
boosting(ds['y'], ds['x2'], 0, .5)
ds['y'].x[50] = np.nan
with pytest.raises(ValueError):
boosting(ds['y'], ds['x1'], 0, .5)
with pytest.raises(ValueError):
boosting(ds['y'], ds['x1'], 0, .5, False)
def test_result():
"Test boosting results"
ds = datasets._get_continuous()
x1 = ds['x1']
# convolve function
y = convolve([ds['h1'], ds['h2']], [ds['x1'], ds['x2']])
assert_dataobj_equal(y, ds['y'], name=False)
# test prediction with res.h and res.h_scaled
res = boosting(ds['y'], ds['x1'], 0, 1)
y1 = convolve(res.h_scaled, ds['x1'])
x_scaled = ds['x1'] / res.x_scale
y2 = convolve(res.h, x_scaled)
y2 *= res.y_scale
y2 += y1.mean() - y2.mean() # mean can't be reconstructed
assert_dataobj_equal(y1, y2, decimal=12)
# reconstruction
res = boosting(x1, y, -1, 0, debug=True)
x1r = convolve(res.h_scaled, y)
assert correlation_coefficient(res.y_pred, x1r) > .999
assert correlation_coefficient(x1r[0.9:], x1[0.9:]) == approx(res.r, abs=1e-3)
# test NaN checks (modifies data)
ds['x2'].x[1, 50] = np.nan
with pytest.raises(ValueError):
boosting(ds['y'], ds['x2'], 0, .5)
with pytest.raises(ValueError):
boosting(ds['y'], ds['x2'], 0, .5, False)
ds['x2'].x[1, :] = 1
with catch_warnings():
filterwarnings('ignore', category=RuntimeWarning)
with pytest.raises(ValueError):
boosting(ds['y'], ds['x2'], 0, .5)
ds['y'].x[50] = np.nan
with pytest.raises(ValueError):
boosting(ds['y'], ds['x1'], 0, .5)
with pytest.raises(ValueError):
boosting(ds['y'], ds['x1'], 0, .5, False)
def test_boosting(n_workers):
"Test boosting NDVars"
ds = datasets._get_continuous(ynd=True)
configure(n_workers=n_workers)
y = ds['y']
ynd = ds['ynd']
x1 = ds['x1']
x2 = ds['x2']
y_mean = y.mean()
x2_mean = x2.mean('time')
# test values from running function, not verified independently
res = boosting(y, x1 * 2000, 0, 1, scale_data=False, mindelta=0.0025)
assert repr(
res) == '<boosting y ~ x1, 0 - 1, scale_data=False, mindelta=0.0025>'
assert res.r == approx(0.75, abs=0.001)
assert res.y_mean is None
assert res.h.info['unit'] == 'V'
assert res.h_scaled.info['unit'] == 'V'
with pytest.raises(NotImplementedError):
res.proportion_explained
res = boosting(y, x1, 0, 1)
assert repr(res) == '<boosting y ~ x1, 0 - 1>'
assert res.r == approx(0.83, abs=0.001)
assert res.y_mean == y_mean
assert res.y_scale == y.std()
assert res.x_mean == x1.mean()
assert res.x_scale == x1.std()
assert res.h.name == 'x1'
assert res.h.info['unit'] == 'normalized'
assert res.h_scaled.name == 'x1'
assert res.h_scaled.info['unit'] == 'V'
assert res.proportion_explained == approx(0.506, abs=0.001)
# inplace
res_ip = boosting(y.copy(), x1.copy(), 0, 1, 'inplace')
assert_res_equal(res_ip, res)
# persistence
res_p = pickle.loads(pickle.dumps(res, pickle.HIGHEST_PROTOCOL))
assert_res_equal(res_p, res)
res = boosting(y, x2, 0, 1)
assert res.r == approx(0.601, abs=0.001)
assert res.proportion_explained == approx(0.273, abs=0.001)
res = boosting(y, x2, 0, 1, error='l1')
assert res.r == approx(0.553, abs=0.001)
assert res.y_mean == y.mean()
assert res.y_scale == (y - y_mean).abs().mean()
assert_array_equal(res.x_mean.x, x2_mean)
assert_array_equal(res.x_scale, (x2 - x2_mean).abs().mean('time'))
assert res.proportion_explained == approx(0.123, abs=0.001)
# 2 predictors
res = boosting(y, [x1, x2], 0, 1)
assert res.r == approx(0.947, abs=0.001)
# selective stopping
res = boosting(y, [x1, x2], 0, 1, selective_stopping=1)
assert res.r == approx(0.967, abs=0.001)
res = boosting(y, [x1, x2], 0, 1, selective_stopping=2)
assert res.r == approx(0.992, abs=0.001)
# prefit
res_full = boosting(y, [x1, x2], 0, 1)
prefit = boosting(y, x1, 0, 1)
res = boosting(y, [x1, x2], 0, 1, prefit=prefit)
assert correlation_coefficient(res.h, res_full.h[1]) == approx(0.984, 1e-3)
prefit = boosting(y, x2, 0, 1)
res = boosting(y, [x1, x2], 0, 1, prefit=prefit)
assert correlation_coefficient(res.h, res_full.h[0]) == approx(0.995, 1e-3)
# ynd
res_full = boosting(ynd, [x1, x2], 0, 1)
prefit = boosting(ynd, x1, 0, 1)
res = boosting(ynd, [x1, x2], 0, 1, prefit=prefit)
assert correlation_coefficient(res.h, res_full.h[1]) == approx(0.978, 1e-3)
prefit = boosting(ynd, x2, 0, 1)
res = boosting(ynd, [x1, x2], 0, 1, prefit=prefit)
assert correlation_coefficient(res.h, res_full.h[0]) == approx(0.997, 1e-3)