def test_result():
"Test boosting results"
ds = datasets._get_continuous()
# convolve function
y = convolve([ds['h1'], ds['h2']], [ds['x1'], ds['x2']])
y.name = 'y'
assert_dataobj_equal(y, ds['y'])
# 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)
# test NaN checks (modifies data)
ds['x2'].x[1, 50] = np.nan
assert_raises(ValueError, boosting, ds['y'], ds['x2'], 0, .5)
assert_raises(ValueError, boosting, ds['y'], ds['x2'], 0, .5, False)
ds['x2'].x[1, :] = 1
assert_raises(ValueError, boosting, ds['y'], ds['x2'], 0, .5)
ds['y'].x[50] = np.nan
assert_raises(ValueError, boosting, ds['y'], ds['x1'], 0, .5)
assert_raises(ValueError, boosting, ds['y'], ds['x1'], 0, .5, False)
def test_boosting():
"Test boosting NDVars"
ds = datasets._get_continuous()
# test boosting results
yield run_boosting, ds, True
yield run_boosting, ds, False
def test_cwt():
ds = datasets._get_continuous()
# 1d
y = cwt_morlet(ds['x1'], [4, 6, 8])
assert y.ndim == 2
# 2d
y = cwt_morlet(ds['x2'], [4, 6, 8])
assert y.ndim == 3
def test_cwt():
ds = datasets._get_continuous()
# 1d
y = cwt_morlet(ds['x1'], [4, 6, 8])
assert y.ndim == 2
# 2d
y = cwt_morlet(ds['x2'], [4, 6, 8])
assert y.ndim == 3
def test_boosting():
"Test boosting NDVars"
ds = datasets._get_continuous()
# test boosting results
configure(n_workers=0)
yield run_boosting, ds
configure(n_workers=True)
yield run_boosting, ds
def test_cross_correlation():
ds = datasets._get_continuous()
x = ds['x1']
assert cross_correlation(x, x).argmax() == 0
assert cross_correlation(x[2:], x).argmax() == 0
assert cross_correlation(x[:9], x).argmax() == 0
assert cross_correlation(x, x[1:]).argmax() == 0
assert cross_correlation(x, x[:8]).argmax() == 0
assert cross_correlation(x[2:], x[:8]).argmax() == 0
def test_cross_correlation():
ds = datasets._get_continuous()
x = ds['x1']
eq_(cross_correlation(x, x).argmax(), 0)
eq_(cross_correlation(x[2:], x).argmax(), 0)
eq_(cross_correlation(x[:9], x).argmax(), 0)
eq_(cross_correlation(x, x[1:]).argmax(), 0)
eq_(cross_correlation(x, x[:8]).argmax(), 0)
eq_(cross_correlation(x[2:], x[:8]).argmax(), 0)
def test_cross_correlation():
ds = datasets._get_continuous()
x = ds['x1']
eq_(cross_correlation(x, x).argmax(), 0)
eq_(cross_correlation(x[2:], x).argmax(), 0)
eq_(cross_correlation(x[:9], x).argmax(), 0)
eq_(cross_correlation(x, x[1:]).argmax(), 0)
eq_(cross_correlation(x, x[:8]).argmax(), 0)
eq_(cross_correlation(x[2:], x[:8]).argmax(), 0)
def test_boosting(n_workers):
"Test boosting NDVars"
ds = datasets._get_continuous()
configure(n_workers=n_workers)
y = ds['y']
x1 = ds['x1']
x2 = ds['x2']
y_mean = y.mean()
x2_mean = x2.mean()
# 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'
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.info['unit'] == 'normalized'
assert res.h_scaled.info['unit'] == 'V'
# 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)
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 res.x_mean == x2_mean
assert res.x_scale == (x2 - x2_mean).abs().mean()
# 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)
def test_boosting(n_workers):
"Test boosting NDVars"
ds = datasets._get_continuous()
configure(n_workers=n_workers)
y = ds['y']
x1 = ds['x1']
x2 = ds['x2']
y_mean = y.mean()
x2_mean = x2.mean()
# 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'
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.info['unit'] == 'normalized'
assert res.h_scaled.info['unit'] == 'V'
# 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)
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 res.x_mean == x2_mean
assert res.x_scale == (x2 - x2_mean).abs().mean()
# 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)
def test_convolve():
ds = datasets._get_continuous()
h1 = ds['h1']
h2 = ds['h2']
x1 = ds['x1']
xc = convolve(h1, x1)
xc_np = np.convolve(h1.x, x1.x)
assert_array_equal(xc.x, xc_np[:100])
# add dimension through kernel
xc = convolve(h2, x1)
xc_np = np.vstack(
(np.convolve(h2.x[0], x1.x)[:100], np.convolve(h2.x[1], x1.x)[:100]))
assert_array_equal(xc.x, xc_np)
def test_plot_array():
"Test plot.Array"
ds = datasets.get_uts(utsnd=True)
p = plot.Array('utsnd', ds=ds)
p.close()
p = plot.Array('utsnd', 'A%B', ds=ds)
assert p._layout.nax == 4
p.close()
p = plot.Array('utsnd', 'A', sub='B=="b1"', ds=ds)
assert p._layout.nax == 2
p.close()
# Categorial dimension
ds = datasets._get_continuous()
p = plot.Array(ds['x2'], interpolation='none')
assert len(p.figure.axes[0].get_yticks()) == 2
def test_plot_array():
"Test plot.Array"
ds = datasets.get_uts(utsnd=True)
p = plot.Array('utsnd', ds=ds, show=False)
p.close()
p = plot.Array('utsnd', 'A%B', ds=ds, show=False)
eq_(p._layout.nax, 4)
p.close()
p = plot.Array('utsnd', 'A', sub='B=="b1"', ds=ds, show=False)
eq_(p._layout.nax, 2)
p.close()
# Categorial dimension
ds = datasets._get_continuous()
p = plot.Array(ds['x2'], interpolation='none', show=False)
eq_(len(p.figure.axes[0].get_yticks()), 2)
def test_convolve():
# convolve is also tested in test_boosting.py
ds = datasets._get_continuous()
h1 = ds['h1']
h2 = ds['h2']
x1 = ds['x1']
xc = convolve(h1, x1)
xc_np = np.convolve(h1.x, x1.x)
assert_array_equal(xc.x, xc_np[:100])
# add dimension through kernel
xc = convolve(h2, x1)
xc_np = np.vstack((np.convolve(h2.x[0], x1.x)[:100],
np.convolve(h2.x[1], x1.x)[:100]))
assert_array_equal(xc.x, xc_np)
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)