def mapper(self, dataTable):
dataTable = dataTable.subTable() # ensure that the results of this calculation do not get propagated
self.metadata["ClusteringModel"].calculate(dataTable, performanceTable=self.performanceTable)
data = dataTable.score.data
mask = dataTable.score.mask
stringToValue = dataTable.score.fieldType.stringToValue
for index, cluster in enumerate(self.clusters):
clusterName = cluster.get("id", "%d" % (index + 1))
value = stringToValue(clusterName)
selection = NP(data == value)
if mask is not None:
NP("logical_and", selection, NP(mask == defs.VALID), selection)
denominator = selection.sum()
numer = dict((fieldName, 0.0) for fieldName in self.fieldNames)
denom = dict((fieldName, 0.0) for fieldName in self.fieldNames)
for fieldName in self.fieldNames:
numer[fieldName] += dataTable.fields[fieldName].data[selection].sum()
denom[fieldName] += denominator
self.emit(clusterName, {"numer": numer, "denom": denom})
def pointsToSmoothCurve(xarray, yarray, samples, smoothingScale, loop):
"""Fit a smooth line through a set of given numeric points
with a characteristic smoothing scale.
This is a non-parametric locally linear fit, used to plot data
as a smooth line.
@type xarray: 1d Numpy array of numbers
@param xarray: Array of x values.
@type yarray: 1d Numpy array of numbers
@param yarray: Array of y values.
@type samples: 1d Numpy array of numbers
@param samples: Locations at which to fit the C{xarray} and C{yarray} with best-fit positions and derivatives.
@type smoothingScale: number
@param smoothingScale: Standard deviation of the Gaussian kernel used to smooth the locally linear fit.
@type loop: bool
@param loop: If False, disconnect the end of the fitted curve from the beginning.
@rtype: 4-tuple of 1d Numpy arrays
@return: C{xlist}, C{ylist}, C{dxlist}, C{dylist} appropriate for C{formatPathdata}.
"""
ylist = []
dylist = []
for sample in samples:
weights = NP(
NP(
NP(
"exp",
NP(
NP(-0.5 * NP("power", NP(xarray - sample), 2)) /
NP(smoothingScale * smoothingScale))) /
smoothingScale) / (math.sqrt(2.0 * math.pi)))
sum1 = weights.sum()
sumx = NP(weights * xarray).sum()
sumxx = NP(weights * NP(xarray * xarray)).sum()
sumy = NP(weights * yarray).sum()
sumxy = NP(weights * NP(xarray * yarray)).sum()
delta = (sum1 * sumxx) - (sumx * sumx)
intercept = ((sumxx * sumy) - (sumx * sumxy)) / delta
slope = ((sum1 * sumxy) - (sumx * sumy)) / delta
ylist.append(intercept + (sample * slope))
dylist.append(slope)
xlist = samples
ylist = NP("array", ylist, dtype=NP.dtype(float))
dxlist = NP((NP("roll", xlist, -1) - NP("roll", xlist, 1)) / 2.0)
dylist = NP("array", dylist, dtype=NP.dtype(float)) * dxlist
if not loop:
dxlist[0] = 0.0
dxlist[-1] = 0.0
dylist[0] = 0.0
dylist[-1] = 0.0
return xlist, ylist, dxlist, dylist
def pointsToSmoothCurve(xarray, yarray, samples, smoothingScale, loop):
"""Fit a smooth line through a set of given numeric points
with a characteristic smoothing scale.
This is a non-parametric locally linear fit, used to plot data
as a smooth line.
@type xarray: 1d Numpy array of numbers
@param xarray: Array of x values.
@type yarray: 1d Numpy array of numbers
@param yarray: Array of y values.
@type samples: 1d Numpy array of numbers
@param samples: Locations at which to fit the C{xarray} and C{yarray} with best-fit positions and derivatives.
@type smoothingScale: number
@param smoothingScale: Standard deviation of the Gaussian kernel used to smooth the locally linear fit.
@type loop: bool
@param loop: If False, disconnect the end of the fitted curve from the beginning.
@rtype: 4-tuple of 1d Numpy arrays
@return: C{xlist}, C{ylist}, C{dxlist}, C{dylist} appropriate for C{formatPathdata}.
"""
ylist = []
dylist = []
for sample in samples:
weights = NP(NP(NP("exp", NP(NP(-0.5 * NP("power", NP(xarray - sample), 2)) / NP(smoothingScale * smoothingScale))) / smoothingScale) / (math.sqrt(2.0*math.pi)))
sum1 = weights.sum()
sumx = NP(weights * xarray).sum()
sumxx = NP(weights * NP(xarray * xarray)).sum()
sumy = NP(weights * yarray).sum()
sumxy = NP(weights * NP(xarray * yarray)).sum()
delta = (sum1 * sumxx) - (sumx * sumx)
intercept = ((sumxx * sumy) - (sumx * sumxy)) / delta
slope = ((sum1 * sumxy) - (sumx * sumy)) / delta
ylist.append(intercept + (sample * slope))
dylist.append(slope)
xlist = samples
ylist = NP("array", ylist, dtype=NP.dtype(float))
dxlist = NP((NP("roll", xlist, -1) - NP("roll", xlist, 1)) / 2.0)
dylist = NP("array", dylist, dtype=NP.dtype(float)) * dxlist
if not loop:
dxlist[0] = 0.0
dxlist[-1] = 0.0
dylist[0] = 0.0
dylist[-1] = 0.0
return xlist, ylist, dxlist, dylist
