def detect_spikes_time_slice_diffs(array,
zalph=5.,
time_axis=-1,
slice_axis=-2,
output_fname=None,
title=None):
""" Detect spiked slices using the time slice difference as a criterion.
Parameters
----------
array: array (mandatory)
array where the time is the last dimension.
zalph: float (optional default 5)
cut off for the sum of square.
time_axis: int (optional, default -1)
axis of the input array that varies over time. The default is the last
axis.
slice_axis: int (optional default -2)
axis of the array that varies over image slice. The default is the last
non-time axis.
output_fname: str (optional default None)
the output file name where the image that represents the detected
spikes is saved.
Returns
-------
slices_to_correct : dict
the timepoints where spikes are detected as keys and the corresponding
spiked slices.
spikes: array (T-1, S)
all the detected spikes.
"""
# Reshape the input array: roll time and slice axis
logger.info("Input array shape is '%s'", array.shape)
array = format_time_serie(array, time_axis, slice_axis)
logger.info(
"Reshape array shape is '%s' when time axis is '%s' and slice "
"axis is '%s'", array.shape, time_axis, slice_axis)
# Time-point to time-point differences over and slices
logger.info("Computing time-point to time-point differences over "
"slices...")
smd2 = time_slice_diffs(array)
logger.info(
"Metric smd2 shape is '%s', ie. (number of timepoints - 1, "
"number of slices).", smd2.shape)
# Detect spikes from quared difference
spikes, meds, mads = spikes_from_slice_diff(smd2, zalph)
# Filter the spikes to preserve outliers only
final_spikes = final_detection(spikes)
# Find which timepoints and which slices are affected
times_to_correct = np.where(final_spikes.sum(axis=1) > 0)[0]
slices_to_correct = {}
for timepoint in times_to_correct:
slices_to_correct[timepoint] = np.where(
final_spikes[timepoint, :] > 0)[0]
# Information message
logger.info("Total number of outliers found: '%s'.", spikes.sum())
logger.info("Total number of slices to be corrected: '%s'.",
slices_to_correct)
# Display detected spikes
if output_fname is not None:
display_spikes(array, smd2, spikes, meds, mads, zalph, output_fname,
title)
return slices_to_correct, spikes
def detect_spikes_time_slice_vals(array, time_axis=-1, slice_axis=-2, sigma=2,
output_fname=None):
""" Detect spiked slices using the time slice values as a criterion.
Parameters
----------
array: array (mandatory)
array where the time is the last dimension.
time_axis: int (optional, default -1)
axis of the input array that varies over time. The default is the last
axis.
slice_axis: int (optional default -2)
axis of the array that varies over image slice. The default is the last
non-time axis.
sigma: float (optional default 3)
cut off for the sum of square.
output_fname: str (optional default None)
the output file name where the image that represents the detected
spikes is saved.
Returns
-------
slices_to_correct : dict
the timepoints where spikes are detected as keys and the corresponding
spiked slices.
"""
# Reshape the input array: roll time and slice axis
logger.info("Input array shape is '%s'", array.shape)
array = format_time_serie(array, time_axis, slice_axis)
logger.info("Reshape array shape is '%s' when time axis is '%s' and slice "
"axis is '%s'", array.shape, time_axis, slice_axis)
# Go through all time-points
gaussians = []
for timepoint in range(array.shape[0]):
# Go through all slices and compute the mutual information to the
# the referecne first slice
reference_slice = array[timepoint, 0]
mi_values = []
for sliceid in range(array.shape[1]):
# Compute the mutual information between slices
mi_values.append(mutual_information(
reference_slice, array[timepoint, sliceid], bins=256))
# Remove the mi corresponding to MI(X, X) = H(X)
mi_values = np.asarray(mi_values[1:])
# Make the assumption of a gaussian distribution
mean = np.mean(mi_values)
std = np.std(mi_values)
# Reject slice to far from the distribution +/-n sigma
lower_bound = mean - sigma * std
upper_bound = mean + sigma * std
# Store the result
gaussians.append({
"dist": mi_values,
"mean": mean,
"bounds": (lower_bound, upper_bound),
"outliers": []
})
print np.where(mi_values < lower_bound)
print np.where(mi_values > upper_bound)
# Display nicely the slice distributions
if output_fname is not None:
display_slice_distributions(gaussians, 18, output_fname)
def detect_spikes_time_slice_vals(array,
time_axis=-1,
slice_axis=-2,
sigma=2,
output_fname=None):
""" Detect spiked slices using the time slice values as a criterion.
Parameters
----------
array: array (mandatory)
array where the time is the last dimension.
time_axis: int (optional, default -1)
axis of the input array that varies over time. The default is the last
axis.
slice_axis: int (optional default -2)
axis of the array that varies over image slice. The default is the last
non-time axis.
sigma: float (optional default 3)
cut off for the sum of square.
output_fname: str (optional default None)
the output file name where the image that represents the detected
spikes is saved.
Returns
-------
slices_to_correct : dict
the timepoints where spikes are detected as keys and the corresponding
spiked slices.
"""
# Reshape the input array: roll time and slice axis
logger.info("Input array shape is '%s'", array.shape)
array = format_time_serie(array, time_axis, slice_axis)
logger.info(
"Reshape array shape is '%s' when time axis is '%s' and slice "
"axis is '%s'", array.shape, time_axis, slice_axis)
# Go through all time-points
gaussians = []
for timepoint in range(array.shape[0]):
# Go through all slices and compute the mutual information to the
# the referecne first slice
reference_slice = array[timepoint, 0]
mi_values = []
for sliceid in range(array.shape[1]):
# Compute the mutual information between slices
mi_values.append(
mutual_information(reference_slice,
array[timepoint, sliceid],
bins=256))
# Remove the mi corresponding to MI(X, X) = H(X)
mi_values = np.asarray(mi_values[1:])
# Make the assumption of a gaussian distribution
mean = np.mean(mi_values)
std = np.std(mi_values)
# Reject slice to far from the distribution +/-n sigma
lower_bound = mean - sigma * std
upper_bound = mean + sigma * std
# Store the result
gaussians.append({
"dist": mi_values,
"mean": mean,
"bounds": (lower_bound, upper_bound),
"outliers": []
})
print np.where(mi_values < lower_bound)
print np.where(mi_values > upper_bound)
# Display nicely the slice distributions
if output_fname is not None:
display_slice_distributions(gaussians, 18, output_fname)
def detect_spikes_time_slice_diffs(array, zalph=5., time_axis=-1,
slice_axis=-2, output_fname=None,
title=None):
""" Detect spiked slices using the time slice difference as a criterion.
Parameters
----------
array: array (mandatory)
array where the time is the last dimension.
zalph: float (optional default 5)
cut off for the sum of square.
time_axis: int (optional, default -1)
axis of the input array that varies over time. The default is the last
axis.
slice_axis: int (optional default -2)
axis of the array that varies over image slice. The default is the last
non-time axis.
output_fname: str (optional default None)
the output file name where the image that represents the detected
spikes is saved.
Returns
-------
slices_to_correct : dict
the timepoints where spikes are detected as keys and the corresponding
spiked slices.
spikes: array (T-1, S)
all the detected spikes.
"""
# Reshape the input array: roll time and slice axis
logger.info("Input array shape is '%s'", array.shape)
array = format_time_serie(array, time_axis, slice_axis)
logger.info("Reshape array shape is '%s' when time axis is '%s' and slice "
"axis is '%s'", array.shape, time_axis, slice_axis)
# Time-point to time-point differences over and slices
logger.info("Computing time-point to time-point differences over "
"slices...")
smd2 = time_slice_diffs(array)
logger.info("Metric smd2 shape is '%s', ie. (number of timepoints - 1, "
"number of slices).", smd2.shape)
# Detect spikes from quared difference
spikes = spikes_from_slice_diff(smd2, zalph)
# Filter the spikes to preserve outliers only
final_spikes = final_detection(spikes)
# Find which timepoints and which slices are affected
times_to_correct = np.where(final_spikes.sum(axis=1) > 0)[0]
slices_to_correct = {}
for timepoint in times_to_correct:
slices_to_correct[timepoint] = np.where(
final_spikes[timepoint, :] > 0)[0]
# Information message
logger.info("Total number of outliers found: '%s'.", spikes.sum())
logger.info("Total number of slices to be corrected: '%s'.",
slices_to_correct)
# Display detected spikes
if output_fname is not None:
display_spikes(array, smd2, spikes, output_fname, title)
return slices_to_correct, spikes