def getSurrogate(paramRanges,paramKDE,srcParam,srcEpoch,nSamples=100):
import sys
sys.path.append('/home/ehab/MyFiles/Softex/spacePy/spacepy-0.1.5')
import spacepy.toolbox as tb
epoch=[]
pbase=[]
ppstd=[]
pmstd=[]
for j in range(len(srcParam)):
for i in range(len(paramRanges)):
if paramKDE[i] != []:
if srcParam[j] >= paramRanges[i][0] and srcParam[j] <= paramRanges[i][1]:
mad = tb.medAbsDev(paramKDE[i].resample(nSamples)[0])
ppstd.extend([srcParam[j] - mad])
pmstd.extend([srcParam[j] + mad])
epoch.extend([srcEpoch[j]])
pbase.extend([srcParam[j]])
return ppstd, pbase, pmstd, epoch
def test_medAbsDev(self):
"""medAbsDev should return a known range for given random input"""
data = numpy.random.normal(0, 1, 100000)
real_ans = 0.7
ans = tb.medAbsDev(data)
self.assertAlmostEqual(ans, real_ans, places=1)
def sea(self, **kwargs):
"""Method called to perform superposed epoch analysis on data in object.
Uses object attributes obj.data, obj.times, obj.epochs, obj.delta,
obj.window, all of which must be available on instantiation.
Other Parameters
================
storedata : boolean
saves matrix of epoch windows as obj.datacube (default = False)
quartiles : list
calculates the quartiles as the upper and lower bounds (and is default);
ci : float
will find the bootstrapped confidence intervals of ci_quan at the ci percent level (default=95)
mad : float
will use +/- the median absolute deviation for the bounds;
ci_quan : string
can be set to 'median' (default) or 'mean'
Notes
=====
A basic plot can be raised with :meth:`plot`
"""
#check this hasn't already been done
#TODO: find out why doing two .sea() calls back-to-back fails 2nd time
if hasattr(self, 'semedian') or hasattr(self, 'semean'):
return None
#check defaults
defaults = {
'storedata': True,
'quartiles': True,
'ci': False,
'mad': False,
'ci_quan': 'median'
}
for default in defaults:
if default not in kwargs:
kwargs[default] = defaults[default]
#ensure all input is np array
delt = float(self.delta)
if isinstance(self.data, np.ndarray):
y = self.data
else:
y = np.asarray(self.data, dtype=float)
if kwargs['ci']:
kwargs['quartiles'], kwargs['mad'] = False, False
if kwargs['mad']:
kwargs['quartiles'], kwargs['ci'] = False, False
time, t_epoch = self._timeepoch(delt)
#build SEA matrix and perform analysis
wind = int(self.window)
m = int(2 * wind + 1)
n = len(t_epoch)
y_sea = np.zeros((n, m), dtype=float)
blankslice = np.zeros([m], dtype=float)
for i in range(n):
dif = np.abs(time - t_epoch[i])
j = np.where(dif == np.min(dif))
stpt = j[0][0] - wind
enpt = j[0][0] + wind + 1
sea_slice = blankslice.copy()
if stpt < 0: #fix for bad epochs not correctly moved to badepochs attr #TODO: make badepochs robust or do all checking here
sea_slice[0:abs(stpt)] = np.NaN
sea_slice[abs(stpt):] = y[0:enpt]
elif enpt >= len(y):
tmpslice = y[stpt:]
sea_slice[:len(tmpslice)] = tmpslice
sea_slice[len(tmpslice):] = np.NaN
else:
sea_slice = y[stpt:enpt]
y_sea[i, 0:] = sea_slice
#find SEA mean, median and percentiles - exclude NaNs (or badval)
try:
badval = kwargs['badval']
except KeyError:
badval = np.nan
y_sea_m = ma.masked_where(np.isnan(y_sea), y_sea)
else:
y_sea_m = ma.masked_values(y_sea, badval)
self.semean = [np.mean(y_sea_m[:, i].compressed()) for i in range(m)]
self.semedian = [
np.median(y_sea_m[:, i].compressed()) for i in range(m)
]
self.semean, self.semedian = np.array(self.semean), np.array(
self.semedian)
self.bound_low = np.zeros((m, 1))
self.bound_high = np.zeros((m, 1))
if kwargs['quartiles']:
from matplotlib.mlab import prctile
for i in range(m):
dum = np.sort(y_sea_m[:, i].compressed())
qul = prctile(dum, p=(25, 75))
self.bound_low[i], self.bound_high[i] = qul[0], qul[1]
self.bound_type = 'quartiles'
elif kwargs['ci']: #bootstrapped confidence intervals (95%)
funcdict = {'mean': np.mean, 'median': np.median}
try:
if isinstance(kwargs['ci'], bool):
raise ValueError #fall through to default case
else:
ci_level = float(kwargs['ci'])
except ValueError:
ci_level = 95
from spacepy.poppy import boots_ci
if hasattr(kwargs['ci_quan'], "__call__"): #ci_quan is a function
ci_func = kwargs['ci_quan']
else:
ci_func = funcdict[kwargs['ci_quan']]
for i in range(m):
dum = np.sort(y_sea_m[:, i].compressed())
self.bound_low[i], self.bound_high[i] = \
boots_ci(dum, 800, ci_level, ci_func)
self.bound_type = 'ci'
elif kwargs['mad']: #median absolute deviation
for i in range(m):
dum = np.sort(y_sea_m[:, i].compressed())
spread_mad = tb.medAbsDev(dum)
self.bound_low[i] = self.semedian[i] - spread_mad
self.bound_high[i] = self.semedian[i] + spread_mad
self.bound_type = 'mad'
self.x = np.linspace(-1.*self.window*self.delta, self.window*self.delta, \
len(self.semedian))
if kwargs['storedata']:
self.datacube = y_sea_m
if self.verbose:
print('sea(): datacube added as new attribute')
if self.verbose:
print('Superposed epoch analysis complete')
def test_medAbsDev(self):
"""medAbsDev should return a known range for given random input"""
data = numpy.random.normal(0, 1, 100000)
real_ans = 0.7
ans = tb.medAbsDev(data)
self.assertAlmostEqual(ans, real_ans, places=1)
def sea(self, **kwargs):
"""Method called to perform superposed epoch analysis on data in object.
Uses object attributes obj.data, obj.times, obj.epochs, obj.delta,
obj.window, all of which must be available on instantiation.
Other Parameters
================
storedata : boolean
saves matrix of epoch windows as obj.datacube (default = False)
quartiles : list
calculates the quartiles as the upper and lower bounds (and is default);
ci : float
will find the bootstrapped confidence intervals of ci_quan at the ci percent level (default=95)
mad : float
will use +/- the median absolute deviation for the bounds;
ci_quan : string
can be set to 'median' (default) or 'mean'
Notes
=====
A basic plot can be raised with :meth:`plot`
"""
#check this hasn't already been done
#TODO: find out why doing two .sea() calls back-to-back fails 2nd time
if hasattr(self, 'semedian') or hasattr(self, 'semean'):
return None
#check defaults
defaults = {'storedata': True, 'quartiles': True, 'ci': False,
'mad': False, 'ci_quan': 'median'}
for default in defaults:
if default not in kwargs:
kwargs[default] = defaults[default]
#ensure all input is np array
delt = float(self.delta)
if isinstance(self.data, np.ndarray):
y = self.data
else:
y = np.asarray(self.data, dtype=float)
if kwargs['ci']:
kwargs['quartiles'], kwargs['mad'] = False, False
if kwargs['mad']:
kwargs['quartiles'], kwargs['ci'] = False, False
time, t_epoch = self._timeepoch(delt)
#build SEA matrix and perform analysis
wind = int(self.window)
m = int(2*wind + 1)
n = len(t_epoch)
y_sea = np.zeros((n,m), dtype=float)
blankslice = np.zeros([m], dtype=float)
for i in range(n):
dif = np.abs(time-t_epoch[i])
j = np.where(dif == np.min(dif))
stpt = j[0][0]-wind
enpt = j[0][0]+wind+1
sea_slice = blankslice.copy()
if stpt < 0: #fix for bad epochs not correctly moved to badepochs attr #TODO: make badepochs robust or do all checking here
sea_slice[0:abs(stpt)] = np.NaN
sea_slice[abs(stpt):] = y[0:enpt]
elif enpt >= len(y):
tmpslice = y[stpt:]
sea_slice[:len(tmpslice)] = tmpslice
sea_slice[len(tmpslice):] = np.NaN
else:
sea_slice = y[stpt:enpt]
y_sea[i,0:] = sea_slice
#find SEA mean, median and percentiles - exclude NaNs (or badval)
try:
badval = kwargs['badval']
except KeyError:
badval = np.nan
y_sea_m = ma.masked_where(np.isnan(y_sea), y_sea)
else:
y_sea_m = ma.masked_values(y_sea, badval)
self.semean = [np.mean(y_sea_m[:,i].compressed()) for i in range(m)]
self.semedian = [np.median(y_sea_m[:,i].compressed()) for i in range(m)]
self.semean, self.semedian = np.array(self.semean), np.array(self.semedian)
self.bound_low = np.zeros((m,1))
self.bound_high = np.zeros((m,1))
if kwargs['quartiles']:
for i in range(m):
dum = np.sort(y_sea_m[:,i].compressed())
qul = np.percentile(dum, (25,75))
self.bound_low[i], self.bound_high[i] = qul[0], qul[1]
self.bound_type = 'quartiles'
elif kwargs['ci']: #bootstrapped confidence intervals (95%)
funcdict = {'mean': np.mean,
'median': np.median}
try:
if isinstance(kwargs['ci'], bool):
raise ValueError #fall through to default case
else:
ci_level = float(kwargs['ci'])
except ValueError:
ci_level = 95
from spacepy.poppy import boots_ci
if hasattr(kwargs['ci_quan'], "__call__"): #ci_quan is a function
ci_func = kwargs['ci_quan']
else:
ci_func = funcdict[kwargs['ci_quan']]
for i in range(m):
dum = np.sort(y_sea_m[:,i].compressed())
self.bound_low[i], self.bound_high[i] = \
boots_ci(dum, 800, ci_level, ci_func)
self.bound_type = 'ci'
elif kwargs['mad']: #median absolute deviation
for i in range(m):
dum = np.sort(y_sea_m[:,i].compressed())
spread_mad = tb.medAbsDev(dum)
self.bound_low[i] = self.semedian[i]-spread_mad
self.bound_high[i] = self.semedian[i]+spread_mad
self.bound_type = 'mad'
self.x = np.linspace(-1.*self.window*self.delta, self.window*self.delta, \
len(self.semedian))
if kwargs['storedata']:
self.datacube = y_sea_m
if self.verbose:
print('sea(): datacube added as new attribute')
if self.verbose:
print('Superposed epoch analysis complete')