def features_to_exponential(header, row, limits):
if len(header) != 2:
return None
if 'mean' not in header:
return None
mean = float(row[header.index('mean')])
# Is it one-sided?
if mean > limits[0] and limits[0] + (mean - limits[0]) * 3 < limits[1]:
# positive exponential
return SplineModelConditional.make_single(limits[0], limits[1], [limits[0] / (mean - limits[0]), -1/(mean - limits[0])]).rescale()
if mean < limits[1] or limits[1] - (limits[1] - mean) * 3 > limits[0]:
# negative exponential
return SplineModelConditional.make_single(limits[0], limits[1], [-limits[1] / (limits[1] - mean), 1/(limits[1] - mean)]).rescale()
else:
return None
def features_to_exponential(header, row, limits):
if len(header) != 2:
return None
if 'mean' not in header:
return None
mean = float(row[header.index('mean')])
# Is it one-sided?
if mean > limits[0] and limits[0] + (mean - limits[0]) * 3 < limits[1]:
# positive exponential
return SplineModelConditional.make_single(
limits[0], limits[1],
[limits[0] / (mean - limits[0]), -1 /
(mean - limits[0])]).rescale()
if mean < limits[1] or limits[1] - (limits[1] - mean) * 3 > limits[0]:
# negative exponential
return SplineModelConditional.make_single(
limits[0], limits[1],
[-limits[1] / (limits[1] - mean), 1 /
(limits[1] - mean)]).rescale()
else:
return None
def features_to_gaussian(header, row, limits):
# Does this look like a mean-variance feature file?
if len(header) == 3:
mean = None
if 'mean' in header:
mean = float(row[header.index('mean')])
if 'mode' in header:
mean = float(row[header.index('mode')])
if .5 in header:
mean = float(row[header.index(.5)])
if mean is None:
return None
if 'var' in header:
var = float(row[header.index('var')])
elif 'sdev' in header:
var = float(row[header.index('sdev')]) * float(row[header.index('sdev')])
else:
return None
if np.isnan(var) or var == 0:
return SplineModelConditional.make_single(mean, mean, [])
# This might be uniform
if mean - 2*var < limits[0] or mean + 2*var > limits[1]:
return None
return SplineModelConditional.make_gaussian(limits[0], limits[1], mean, var)
elif len(header) == 4:
# Does this look like a mean and evenly spaced p-values?
header = header[1:] # Make a copy of the list
row = row[1:]
mean = None
if 'mean' in header:
mean = float(row.pop(header.index('mean')))
header.remove('mean')
elif 'mode' in header:
mean = float(row.pop(header.index('mode')))
header.remove('mode')
elif .5 in header:
mean = float(row.pop(header.index(.5)))
header.remove(.5)
else:
return None
# Check that the two other values are evenly spaced p-values
row = map(float, row[0:2])
if np.all(np.isnan(row)):
return SplineModelConditional.make_single(mean, mean, [])
if header[1] == 1 - header[0] and abs(row[1] - mean - (mean - row[0])) < abs(row[1] - row[0]) / 1000.0:
lowp = min(header)
lowv = np.array(row)[np.array(header) == lowp][0]
if lowv == mean:
return SplineModelConditional.make_single(mean, mean, [])
lowerbound = 1e-4 * (mean - lowv)
upperbound = np.sqrt((mean - lowv) / lowp)
sdev = brentq(lambda sdev: norm.cdf(lowv, mean, sdev) - lowp, lowerbound, upperbound)
if float(limits[0]) < mean - 3*sdev and float(limits[1]) > mean + 3*sdev:
return SplineModelConditional.make_gaussian(limits[0], limits[1], mean, sdev*sdev)
else:
return None
else:
# Heuristic best curve: known tails, fit to mean
lowp = min(header)
lowv = np.array(row)[np.array(header) == lowp][0]
lowerbound = 1e-4 * (mean - lowv)
upperbound = np.log((mean - lowv) / lowp)
low_sdev = brentq(lambda sdev: norm.cdf(lowv, mean, sdev) - lowp, lowerbound, upperbound)
if float(limits[0]) > mean - 3*low_sdev:
return None
low_segment = SplineModelConditional.make_gaussian(float(limits[0]), lowv, mean, low_sdev*low_sdev)
highp = max(header)
highv = np.array(row)[np.array(header) == highp][0]
lowerbound = 1e-4 * (highv - mean)
upperbound = np.log((highv - mean) / (1 - highp))
high_scale = brentq(lambda scale: .5 + expon.cdf(highv, mean, scale) / 2 - highp, lowerbound, upperbound)
if float(limits[1]) < mean + 3*high_scale:
return None
# Construct exponential, starting at mean, with full cdf of .5
high_segment = SplineModelConditional.make_single(highv, float(limits[1]), [np.log(1/high_scale) + np.log(.5) + mean / high_scale, -1 / high_scale])
sevenys = np.linspace(lowv, highv, 7)
ys = np.append(sevenys[0:2], [mean, sevenys[-2], sevenys[-1]])
lps0 = norm.logpdf(ys[0:2], mean, low_sdev)
lps1 = expon.logpdf([ys[-2], ys[-1]], mean, high_scale) + np.log(.5)
#bounds = [norm.logpdf(mean, mean, low_sdev), norm.logpdf(mean, mean, high_sdev)]
result = minimize(lambda lpmean: FeaturesInterpreter.skew_gaussian_evaluate(ys, np.append(np.append(lps0, [lpmean]), lps1), low_segment, high_segment, mean, lowp, highp), .5, method='Nelder-Mead')
print np.append(np.append(lps0, result.x), lps1)
return FeaturesInterpreter.skew_gaussian_construct(ys, np.append(np.append(lps0, result.x), lps1), low_segment, high_segment)
def features_to_uniform(header, row, limits):
if len(header) != 1:
return None
return SplineModelConditional.make_single(limits[0], limits[1], [1/(limits[1] - limits[0])])
def features_to_uniform(header, row, limits):
if len(header) != 1:
return None
return SplineModelConditional.make_single(
limits[0], limits[1], [1 / (limits[1] - limits[0])])
def features_to_gaussian(header, row, limits):
# Does this look like a mean-variance feature file?
if len(header) == 3:
mean = None
if 'mean' in header:
mean = float(row[header.index('mean')])
if 'mode' in header:
mean = float(row[header.index('mode')])
if .5 in header:
mean = float(row[header.index(.5)])
if mean is None:
return None
if 'var' in header:
var = float(row[header.index('var')])
elif 'sdev' in header:
var = float(row[header.index('sdev')]) * float(
row[header.index('sdev')])
else:
return None
if np.isnan(var) or var == 0:
return SplineModelConditional.make_single(mean, mean, [])
# This might be uniform
if mean - 2 * var < limits[0] or mean + 2 * var > limits[1]:
return None
return SplineModelConditional.make_gaussian(
limits[0], limits[1], mean, var)
elif len(header) == 4:
# Does this look like a mean and evenly spaced p-values?
header = header[1:] # Make a copy of the list
row = row[1:]
mean = None
if 'mean' in header:
mean = float(row.pop(header.index('mean')))
header.remove('mean')
elif 'mode' in header:
mean = float(row.pop(header.index('mode')))
header.remove('mode')
elif .5 in header:
mean = float(row.pop(header.index(.5)))
header.remove(.5)
else:
return None
# Check that the two other values are evenly spaced p-values
row = map(float, row[0:2])
if np.all(np.isnan(row)):
return SplineModelConditional.make_single(mean, mean, [])
if header[1] == 1 - header[0] and abs(row[1] - mean - (
mean - row[0])) < abs(row[1] - row[0]) / 1000.0:
lowp = min(header)
lowv = np.array(row)[np.array(header) == lowp][0]
if lowv == mean:
return SplineModelConditional.make_single(mean, mean, [])
lowerbound = 1e-4 * (mean - lowv)
upperbound = np.sqrt((mean - lowv) / lowp)
sdev = brentq(lambda sdev: norm.cdf(lowv, mean, sdev) - lowp,
lowerbound, upperbound)
if float(limits[0]) < mean - 3 * sdev and float(
limits[1]) > mean + 3 * sdev:
return SplineModelConditional.make_gaussian(
limits[0], limits[1], mean, sdev * sdev)
else:
return None
else:
# Heuristic best curve: known tails, fit to mean
lowp = min(header)
lowv = np.array(row)[np.array(header) == lowp][0]
lowerbound = 1e-4 * (mean - lowv)
upperbound = np.log((mean - lowv) / lowp)
low_sdev = brentq(
lambda sdev: norm.cdf(lowv, mean, sdev) - lowp, lowerbound,
upperbound)
if float(limits[0]) > mean - 3 * low_sdev:
return None
low_segment = SplineModelConditional.make_gaussian(
float(limits[0]), lowv, mean, low_sdev * low_sdev)
highp = max(header)
highv = np.array(row)[np.array(header) == highp][0]
lowerbound = 1e-4 * (highv - mean)
upperbound = np.log((highv - mean) / (1 - highp))
high_scale = brentq(
lambda scale: .5 + expon.cdf(highv, mean, scale) / 2 -
highp, lowerbound, upperbound)
if float(limits[1]) < mean + 3 * high_scale:
return None
# Construct exponential, starting at mean, with full cdf of .5
high_segment = SplineModelConditional.make_single(
highv, float(limits[1]), [
np.log(1 / high_scale) + np.log(.5) +
mean / high_scale, -1 / high_scale
])
sevenys = np.linspace(lowv, highv, 7)
ys = np.append(sevenys[0:2], [mean, sevenys[-2], sevenys[-1]])
lps0 = norm.logpdf(ys[0:2], mean, low_sdev)
lps1 = expon.logpdf([ys[-2], ys[-1]], mean,
high_scale) + np.log(.5)
#bounds = [norm.logpdf(mean, mean, low_sdev), norm.logpdf(mean, mean, high_sdev)]
result = minimize(
lambda lpmean: FeaturesInterpreter.skew_gaussian_evaluate(
ys, np.append(np.append(lps0, [lpmean]), lps1),
low_segment, high_segment, mean, lowp, highp),
.5,
method='Nelder-Mead')
print np.append(np.append(lps0, result.x), lps1)
return FeaturesInterpreter.skew_gaussian_construct(
ys, np.append(np.append(lps0, result.x), lps1),
low_segment, high_segment)
