def testSplit(self):
# Single segment.
all_time = np.concatenate([np.arange(0, 1, 0.1), np.arange(1.5, 2, 0.1)])
all_flux = np.ones(15)
# Gap width 0.5.
split_time, split_flux = util.split(all_time, all_flux, gap_width=0.5)
self.assertLen(split_time, 2)
self.assertLen(split_flux, 2)
self.assertSequenceAlmostEqual(np.arange(0, 1, 0.1), split_time[0])
self.assertSequenceAlmostEqual(np.ones(10), split_flux[0])
self.assertSequenceAlmostEqual(np.arange(1.5, 2, 0.1), split_time[1])
self.assertSequenceAlmostEqual(np.ones(5), split_flux[1])
# Multi segment.
all_time = [
np.concatenate([
np.arange(0, 1, 0.1),
np.arange(1.5, 2, 0.1),
np.arange(3, 4, 0.1)
]),
np.arange(4, 5, 0.1)
]
all_flux = [np.ones(25), np.ones(10)]
self.assertEqual(len(all_time), 2)
self.assertEqual(len(all_time[0]), 25)
self.assertEqual(len(all_time[1]), 10)
self.assertEqual(len(all_flux), 2)
self.assertEqual(len(all_flux[0]), 25)
self.assertEqual(len(all_flux[1]), 10)
# Gap width 0.5.
split_time, split_flux = util.split(all_time, all_flux, gap_width=0.5)
self.assertLen(split_time, 4)
self.assertLen(split_flux, 4)
self.assertSequenceAlmostEqual(np.arange(0, 1, 0.1), split_time[0])
self.assertSequenceAlmostEqual(np.ones(10), split_flux[0])
self.assertSequenceAlmostEqual(np.arange(1.5, 2, 0.1), split_time[1])
self.assertSequenceAlmostEqual(np.ones(5), split_flux[1])
self.assertSequenceAlmostEqual(np.arange(3, 4, 0.1), split_time[2])
self.assertSequenceAlmostEqual(np.ones(10), split_flux[2])
self.assertSequenceAlmostEqual(np.arange(4, 5, 0.1), split_time[3])
self.assertSequenceAlmostEqual(np.ones(10), split_flux[3])
# Gap width 1.0.
split_time, split_flux = util.split(all_time, all_flux, gap_width=1)
self.assertLen(split_time, 3)
self.assertLen(split_flux, 3)
self.assertSequenceAlmostEqual([
0., 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.5, 1.6, 1.7, 1.8, 1.9
], split_time[0])
self.assertSequenceAlmostEqual(np.ones(15), split_flux[0])
self.assertSequenceAlmostEqual(np.arange(3, 4, 0.1), split_time[1])
self.assertSequenceAlmostEqual(np.ones(10), split_flux[1])
self.assertSequenceAlmostEqual(np.arange(4, 5, 0.1), split_time[2])
self.assertSequenceAlmostEqual(np.ones(10), split_flux[2])
def read_and_process_light_curve(kepid, kepler_data_dir, max_gap_width=0.75):
"""Reads a light curve, fits a B-spline and divides the curve by the spline.
Args:
kepid: Kepler id of the target star.
kepler_data_dir: Base directory containing Kepler data. See
kepler_io.kepler_filenames().
max_gap_width: Gap size (in days) above which the light curve is split for
the fitting of B-splines.
Returns:
time: 1D NumPy array; the time values of the light curve.
flux: 1D NumPy array; the normalized flux values of the light curve.
Raises:
IOError: If the light curve files for this Kepler ID cannot be found.
ValueError: If the spline could not be fit.
"""
# Read the Kepler light curve.
file_names = kepler_io.kepler_filenames(kepler_data_dir, kepid)
if not file_names:
raise IOError("Failed to find .fits files in %s for Kepler ID %s" %
(kepler_data_dir, kepid))
all_time, all_flux = kepler_io.read_kepler_light_curve(file_names)
# Split on gaps.
all_time, all_flux = util.split(all_time, all_flux, gap_width=max_gap_width)
# Logarithmically sample candidate break point spacings between 0.5 and 20
# days.
bkspaces = np.logspace(np.log10(0.5), np.log10(20), num=20)
# Generate spline.
spline = kepler_spline.choose_kepler_spline(
all_time, all_flux, bkspaces, penalty_coeff=1.0, verbose=False)[0]
if spline is None:
raise ValueError("Failed to fit spline with Kepler ID %s", kepid)
# Concatenate the piecewise light curve and spline.
time = np.concatenate(all_time)
flux = np.concatenate(all_flux)
spline = np.concatenate(spline)
# In rare cases the piecewise spline contains NaNs in places the spline could
# not be fit. We can't normalize those points if the spline isn't defined
# there. Instead we just remove them.
finite_i = np.isfinite(spline)
if not np.all(finite_i):
tf.logging.warn("Incomplete spline with Kepler ID %s", kepid)
time = time[finite_i]
flux = flux[finite_i]
spline = spline[finite_i]
# "Flatten" the light curve (remove low-frequency variability) by dividing by
# the spline.
flux /= spline
return time, flux
def testSplit(self):
all_time = [
np.concatenate([
np.arange(0, 1, 0.1),
np.arange(1.5, 2, 0.1),
np.arange(3, 4, 0.1)
])
]
all_flux = [np.array([1] * 25)]
# Gap width 0.5.
split_time, split_flux = util.split(all_time, all_flux, gap_width=0.5)
self.assertLen(split_time, 3)
self.assertLen(split_flux, 3)
self.assertSequenceAlmostEqual(
[0., 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9], split_time[0])
self.assertSequenceAlmostEqual([1, 1, 1, 1, 1, 1, 1, 1, 1, 1],
split_flux[0])
self.assertSequenceAlmostEqual([1.5, 1.6, 1.7, 1.8, 1.9],
split_time[1])
self.assertSequenceAlmostEqual([1, 1, 1, 1, 1], split_flux[1])
self.assertSequenceAlmostEqual(
[3., 3.1, 3.2, 3.3, 3.4, 3.5, 3.6, 3.7, 3.8, 3.9], split_time[2])
self.assertSequenceAlmostEqual([1, 1, 1, 1, 1, 1, 1, 1, 1, 1],
split_flux[2])
# Gap width 1.0.
split_time, split_flux = util.split(all_time, all_flux, gap_width=1)
self.assertLen(split_time, 2)
self.assertLen(split_flux, 2)
self.assertSequenceAlmostEqual([
0., 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.5, 1.6, 1.7,
1.8, 1.9
], split_time[0])
self.assertSequenceAlmostEqual(
[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], split_flux[0])
self.assertSequenceAlmostEqual(
[3., 3.1, 3.2, 3.3, 3.4, 3.5, 3.6, 3.7, 3.8, 3.9], split_time[1])
self.assertSequenceAlmostEqual([1, 1, 1, 1, 1, 1, 1, 1, 1, 1],
split_flux[1])
def testSplit(self):
all_time = [
np.concatenate([
np.arange(0, 1, 0.1),
np.arange(1.5, 2, 0.1),
np.arange(3, 4, 0.1)
])
]
all_flux = [np.array([1] * 25)]
# Gap width 0.5.
split_time, split_flux = util.split(all_time, all_flux, gap_width=0.5)
self.assertLen(split_time, 3)
self.assertLen(split_flux, 3)
self.assertSequenceAlmostEqual(
[0., 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9], split_time[0])
self.assertSequenceAlmostEqual([1, 1, 1, 1, 1, 1, 1, 1, 1, 1],
split_flux[0])
self.assertSequenceAlmostEqual([1.5, 1.6, 1.7, 1.8, 1.9], split_time[1])
self.assertSequenceAlmostEqual([1, 1, 1, 1, 1], split_flux[1])
self.assertSequenceAlmostEqual(
[3., 3.1, 3.2, 3.3, 3.4, 3.5, 3.6, 3.7, 3.8, 3.9], split_time[2])
self.assertSequenceAlmostEqual([1, 1, 1, 1, 1, 1, 1, 1, 1, 1],
split_flux[2])
# Gap width 1.0.
split_time, split_flux = util.split(all_time, all_flux, gap_width=1)
self.assertLen(split_time, 2)
self.assertLen(split_flux, 2)
self.assertSequenceAlmostEqual([
0., 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.5, 1.6, 1.7, 1.8, 1.9
], split_time[0])
self.assertSequenceAlmostEqual(
[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], split_flux[0])
self.assertSequenceAlmostEqual(
[3., 3.1, 3.2, 3.3, 3.4, 3.5, 3.6, 3.7, 3.8, 3.9], split_time[1])
self.assertSequenceAlmostEqual([1, 1, 1, 1, 1, 1, 1, 1, 1, 1],
split_flux[1])
def process_light_curve(all_time, all_flux):
"""Removes low-frequency variability from a light curve.
Args:
all_time: A list of numpy arrays; the time values of the raw light curve.
all_flux: A list of numpy arrays corresponding to the time arrays in
all_time.
Returns:
time: 1D NumPy array; the time values of the light curve.
flux: 1D NumPy array; the normalized flux values of the light curve.
"""
# Split on gaps.
all_time, all_flux = util.split(all_time, all_flux, gap_width=0.75)
# Fit a piecewise-cubic spline with default arguments.
spline = kepler_spline.fit_kepler_spline(all_time, all_flux,
verbose=False)[0]
# Concatenate the piecewise light curve and spline.
time = np.concatenate(all_time)
flux = np.concatenate(all_flux)
spline = np.concatenate(spline)
# In rare cases the piecewise spline contains NaNs in places the spline could
# not be fit. We can't normalize those points if the spline isn't defined
# there. Instead we just remove them.
finite_i = np.isfinite(spline)
if not np.all(finite_i):
time = time[finite_i]
flux = flux[finite_i]
spline = spline[finite_i]
# "Flatten" the light curve (remove low-frequency variability) by dividing by
# the spline.
flux /= spline
return time, flux
def process_light_curve(all_time, all_flux):
"""Removes low-frequency variability from a light curve.
Args:
all_time: A list of numpy arrays; the time values of the raw light curve.
all_flux: A list of numpy arrays corresponding to the time arrays in
all_time.
Returns:
time: 1D NumPy array; the time values of the light curve.
flux: 1D NumPy array; the normalized flux values of the light curve.
"""
# Split on gaps.
all_time, all_flux = util.split(all_time, all_flux, gap_width=0.75)
# Fit a piecewise-cubic spline with default arguments.
spline = kepler_spline.fit_kepler_spline(all_time, all_flux, verbose=False)[0]
# Concatenate the piecewise light curve and spline.
time = np.concatenate(all_time)
flux = np.concatenate(all_flux)
spline = np.concatenate(spline)
# In rare cases the piecewise spline contains NaNs in places the spline could
# not be fit. We can't normalize those points if the spline isn't defined
# there. Instead we just remove them.
finite_i = np.isfinite(spline)
if not np.all(finite_i):
time = time[finite_i]
flux = flux[finite_i]
spline = spline[finite_i]
# "Flatten" the light curve (remove low-frequency variability) by dividing by
# the spline.
flux /= spline
return time, flux
def read_and_process_light_curve(kepid, kepler_data_dir, campaign, max_gap_width=0.75):
"""Reads a light curve, fits a B-spline and divides the curve by the spline.
Args:
kepid: Kepler id of the target star.
kepler_data_dir: Base directory containing Kepler data. See
kepler_io.kepler_filenames().
campaign: K2 campaign where data was taken.
max_gap_width: Gap size (in days) above which the light curve is split for
the fitting of B-splines.
Returns:
time: 1D NumPy array; the time values of the light curve.
flux: 1D NumPy array; the normalized flux values of the light curve.
Raises:
IOError: If the light curve files for this Kepler ID cannot be found.
ValueError: If the spline could not be fit.
"""
# Read the Kepler light curve.
file_names = kepler_io.kepler_filenames(kepler_data_dir, kepid, campaign)
if not file_names:
print(campaign)
raise IOError("Failed to find .idl file in %s for EPIC ID %s" %
(kepler_data_dir, kepid))
all_time, all_flux = kepler_io.read_kepler_light_curve(file_names)
# Split on gaps.
all_time, all_flux = util.split(all_time, all_flux, gap_width=max_gap_width)
# Logarithmically sample candidate break point spacings between 0.5 and 20
# days.
bkspaces = np.logspace(np.log10(0.5), np.log10(20), num=20)
# Generate spline.
spline = kepler_spline.choose_kepler_spline(
all_time, all_flux, bkspaces, penalty_coeff=1.0, verbose=False)[0]
if spline is None:
raise ValueError("Failed to fit spline with Kepler ID %s", kepid)
# Concatenate the piecewise light curve and spline.
time = np.concatenate(all_time)
flux = np.concatenate(all_flux)
spline = np.concatenate(spline)
# In rare cases the piecewise spline contains NaNs in places the spline could
# not be fit. We can't normalize those points if the spline isn't defined
# there. Instead we just remove them.
finite_i = np.isfinite(spline)
if not np.all(finite_i):
tf.logging.warn("Incomplete spline with Kepler ID %s", kepid)
time = time[finite_i]
flux = flux[finite_i]
spline = spline[finite_i]
# "Flatten" the light curve (remove low-frequency variability) by dividing by
# the spline.
flux /= spline
#Remove points where the thrusters are on
#using s.data.moving
#Remove points where the xcenter is off
#using.s.data.xc
#Remove points where the background flux is off
#using s.data.medians
#Let's remove upward outliers?
deviation = flux - np.median(flux)
is_upward_outlier = np.logical_not(robust_mean.robust_mean(deviation, cut=3)[2])
np.logical_and(is_upward_outlier, deviation > 0, out=is_upward_outlier)
flux = flux[~is_upward_outlier]
time = time[~is_upward_outlier]
return time, flux
def testSplit(self):
# Single segment.
all_time = np.concatenate(
[np.arange(0, 1, 0.1),
np.arange(1.5, 2, 0.1)])
all_flux = np.ones(15)
# Gap width 0.5.
split_time, split_flux = util.split(all_time, all_flux, gap_width=0.5)
self.assertLen(split_time, 2)
self.assertLen(split_flux, 2)
self.assertSequenceAlmostEqual(np.arange(0, 1, 0.1), split_time[0])
self.assertSequenceAlmostEqual(np.ones(10), split_flux[0])
self.assertSequenceAlmostEqual(np.arange(1.5, 2, 0.1), split_time[1])
self.assertSequenceAlmostEqual(np.ones(5), split_flux[1])
# Multi segment.
all_time = [
np.concatenate([
np.arange(0, 1, 0.1),
np.arange(1.5, 2, 0.1),
np.arange(3, 4, 0.1)
]),
np.arange(4, 5, 0.1)
]
all_flux = [np.ones(25), np.ones(10)]
self.assertEqual(len(all_time), 2)
self.assertEqual(len(all_time[0]), 25)
self.assertEqual(len(all_time[1]), 10)
self.assertEqual(len(all_flux), 2)
self.assertEqual(len(all_flux[0]), 25)
self.assertEqual(len(all_flux[1]), 10)
# Gap width 0.5.
split_time, split_flux = util.split(all_time, all_flux, gap_width=0.5)
self.assertLen(split_time, 4)
self.assertLen(split_flux, 4)
self.assertSequenceAlmostEqual(np.arange(0, 1, 0.1), split_time[0])
self.assertSequenceAlmostEqual(np.ones(10), split_flux[0])
self.assertSequenceAlmostEqual(np.arange(1.5, 2, 0.1), split_time[1])
self.assertSequenceAlmostEqual(np.ones(5), split_flux[1])
self.assertSequenceAlmostEqual(np.arange(3, 4, 0.1), split_time[2])
self.assertSequenceAlmostEqual(np.ones(10), split_flux[2])
self.assertSequenceAlmostEqual(np.arange(4, 5, 0.1), split_time[3])
self.assertSequenceAlmostEqual(np.ones(10), split_flux[3])
# Gap width 1.0.
split_time, split_flux = util.split(all_time, all_flux, gap_width=1)
self.assertLen(split_time, 3)
self.assertLen(split_flux, 3)
self.assertSequenceAlmostEqual([
0., 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.5, 1.6, 1.7,
1.8, 1.9
], split_time[0])
self.assertSequenceAlmostEqual(np.ones(15), split_flux[0])
self.assertSequenceAlmostEqual(np.arange(3, 4, 0.1), split_time[1])
self.assertSequenceAlmostEqual(np.ones(10), split_flux[1])
self.assertSequenceAlmostEqual(np.arange(4, 5, 0.1), split_time[2])
self.assertSequenceAlmostEqual(np.ones(10), split_flux[2])
def read_and_process_light_curve(kepid, kepler_data_dir, max_gap_width=0.75):
"""Reads a light curve, fits a B-spline and divides the curve by the spline.
Args:
kepid: Kepler id of the target star.
kepler_data_dir: Base directory containing Kepler data. See
kepler_io.kepler_filenames().
max_gap_width: Gap size (in days) above which the light curve is split for
the fitting of B-splines.
Returns:
time: 1D NumPy array; the time values of the light curve.
flux: 1D NumPy array; the normalized flux values of the light curve.
Raises:
IOError: If the light curve files for this Kepler ID cannot be found.
ValueError: If the spline could not be fit.
"""
# Read the Kepler light curve.
file_names = kepler_io.kepler_filenames(kepler_data_dir, kepid)
if not file_names:
raise IOError("Failed to find .fits files in %s for Kepler ID %s" %
(kepler_data_dir, kepid))
all_time, all_flux = kepler_io.read_kepler_light_curve(file_names)
# Split on gaps.
all_time, all_flux = util.split(all_time,
all_flux,
gap_width=max_gap_width)
# Logarithmically sample candidate break point spacings between 0.5 and 20
# days.
bkspaces = np.logspace(np.log10(0.5), np.log10(20), num=20)
# Generate spline.
spline = kepler_spline.choose_kepler_spline(all_time,
all_flux,
bkspaces,
penalty_coeff=1.0,
verbose=False)[0]
if spline is None:
raise ValueError("Failed to fit spline with Kepler ID %s", kepid)
# Concatenate the piecewise light curve and spline.
time = np.concatenate(all_time)
flux = np.concatenate(all_flux)
spline = np.concatenate(spline)
# In rare cases the piecewise spline contains NaNs in places the spline could
# not be fit. We can't normalize those points if the spline isn't defined
# there. Instead we just remove them.
finite_i = np.isfinite(spline)
if not np.all(finite_i):
tf.logging.warn("Incomplete spline with Kepler ID %s", kepid)
time = time[finite_i]
flux = flux[finite_i]
spline = spline[finite_i]
# "Flatten" the light curve (remove low-frequency variability) by dividing by
# the spline.
flux /= spline
return time, flux