def _selectMax(self, dataTable, functionTable, performanceTable,
segmentation):
"""Used by C{calculateScore}."""
performanceTable.begin("Segmentation max")
scoresData = NP("empty", len(dataTable), dtype=NP.dtype(object))
filled = NP("zeros", len(dataTable), dtype=NP.dtype(bool))
unfilled = NP("ones", len(dataTable), dtype=NP.dtype(bool))
newOutputData = []
for segment in segmentation.childrenOfTag("Segment", iterator=True):
performanceTable.pause("Segmentation max")
selection = segment.childOfClass(PmmlPredicate).evaluate(
dataTable, functionTable, performanceTable)
performanceTable.unpause("Segmentation max")
if not selection.any():
continue
subTable = dataTable.subTable(selection)
subModel = segment.childOfClass(PmmlModel)
performanceTable.pause("Segmentation max")
subModel.calculate(subTable, functionTable, performanceTable)
performanceTable.unpause("Segmentation max")
if subTable.score.fieldType.dataType in ("string", "boolean",
"object"):
raise defs.PmmlValidationError(
"Segmentation with multipleModelMethod=\"max\" cannot be applied to models that produce dataType \"%s\""
% subTable.score.fieldType.dataType)
# ignore invalid in matches (like the built-in "min" Apply function)
if subTable.score.mask is not None:
NP("logical_and", selection,
NP(subTable.score.mask == defs.VALID), selection)
selectionFilled = NP("logical_and", selection, filled)
selectionUnfilled = NP("logical_and", selection, unfilled)
filled_selection = filled[selection]
unfilled_selection = unfilled[selection]
left, right = subTable.score.data[filled_selection], scoresData[
selectionFilled]
condition = NP(left > right)
scoresData[selectionFilled] = NP("where", condition, left, right)
scoresData[selectionUnfilled] = subTable.score.data[
unfilled_selection]
for fieldName, dataColumn in subTable.output.items():
if fieldName not in dataTable.output:
data = NP("empty",
len(dataTable),
dtype=dataColumn.fieldType.dtype)
data[selectionUnfilled] = dataColumn.data
mask = NP(
NP("ones", len(dataTable), dtype=defs.maskType) *
defs.MISSING)
if dataColumn.mask is None:
mask[selectionUnfilled] = defs.VALID
else:
mask[selectionUnfilled] = dataColumn.mask
newDataColumn = DataColumn(dataColumn.fieldType, data,
mask)
newDataColumn._unlock()
dataTable.output[fieldName] = newDataColumn
newOutputData.append(newDataColumn)
else:
newDataColumn = dataTable.output[fieldName]
newDataColumn.data[selectionFilled] = NP(
"where", condition, dataColumn.data[filled_selection],
newDataColumn.data[selectionFilled])
newDataColumn.data[selectionUnfilled] = dataColumn.data[
unfilled_selection]
if dataColumn.mask is None:
newDataColumn.mask[selectionUnfilled] = defs.VALID
else:
newDataColumn.mask[selectionUnfilled] = dataColumn.mask
filled += selectionUnfilled
unfilled -= selectionUnfilled
for newDataColumn in newOutputData:
if not newDataColumn.mask.any():
newDataColumn._mask = None
newDataColumn._lock()
if filled.all():
scoresMask = None
else:
scoresMask = NP(NP("logical_not", filled) * defs.MISSING)
scores = DataColumn(self.scoreType, scoresData, scoresMask)
performanceTable.end("Segmentation max")
return {None: scores}
def _selectMax(self, dataTable, functionTable, performanceTable, segmentation):
"""Used by C{calculateScore}."""
performanceTable.begin("Segmentation max")
scoresData = NP("empty", len(dataTable), dtype=NP.dtype(object))
filled = NP("zeros", len(dataTable), dtype=NP.dtype(bool))
unfilled = NP("ones", len(dataTable), dtype=NP.dtype(bool))
newOutputData = []
for segment in segmentation.childrenOfTag("Segment", iterator=True):
performanceTable.pause("Segmentation max")
selection = segment.childOfClass(PmmlPredicate).evaluate(dataTable, functionTable, performanceTable)
performanceTable.unpause("Segmentation max")
if not selection.any():
continue
subTable = dataTable.subTable(selection)
subModel = segment.childOfClass(PmmlModel)
performanceTable.pause("Segmentation max")
subModel.calculate(subTable, functionTable, performanceTable)
performanceTable.unpause("Segmentation max")
if subTable.score.fieldType.dataType in ("string", "boolean", "object"):
raise defs.PmmlValidationError("Segmentation with multipleModelMethod=\"max\" cannot be applied to models that produce dataType \"%s\"" % subTable.score.fieldType.dataType)
# ignore invalid in matches (like the built-in "min" Apply function)
if subTable.score.mask is not None:
NP("logical_and", selection, NP(subTable.score.mask == defs.VALID), selection)
selectionFilled = NP("logical_and", selection, filled)
selectionUnfilled = NP("logical_and", selection, unfilled)
filled_selection = filled[selection]
unfilled_selection = unfilled[selection]
left, right = subTable.score.data[filled_selection], scoresData[selectionFilled]
condition = NP(left > right)
scoresData[selectionFilled] = NP("where", condition, left, right)
scoresData[selectionUnfilled] = subTable.score.data[unfilled_selection]
for fieldName, dataColumn in subTable.output.items():
if fieldName not in dataTable.output:
data = NP("empty", len(dataTable), dtype=dataColumn.fieldType.dtype)
data[selectionUnfilled] = dataColumn.data
mask = NP(NP("ones", len(dataTable), dtype=defs.maskType) * defs.MISSING)
if dataColumn.mask is None:
mask[selectionUnfilled] = defs.VALID
else:
mask[selectionUnfilled] = dataColumn.mask
newDataColumn = DataColumn(dataColumn.fieldType, data, mask)
newDataColumn._unlock()
dataTable.output[fieldName] = newDataColumn
newOutputData.append(newDataColumn)
else:
newDataColumn = dataTable.output[fieldName]
newDataColumn.data[selectionFilled] = NP("where", condition, dataColumn.data[filled_selection], newDataColumn.data[selectionFilled])
newDataColumn.data[selectionUnfilled] = dataColumn.data[unfilled_selection]
if dataColumn.mask is None:
newDataColumn.mask[selectionUnfilled] = defs.VALID
else:
newDataColumn.mask[selectionUnfilled] = dataColumn.mask
filled += selectionUnfilled
unfilled -= selectionUnfilled
for newDataColumn in newOutputData:
if not newDataColumn.mask.any():
newDataColumn._mask = None
newDataColumn._lock()
if filled.all():
scoresMask = None
else:
scoresMask = NP(NP("logical_not", filled) * defs.MISSING)
scores = DataColumn(self.scoreType, scoresData, scoresMask)
performanceTable.end("Segmentation max")
return {None: scores}
def _selectFirst(self, dataTable, functionTable, performanceTable,
segmentation):
"""Used by C{calculateScore}."""
performanceTable.begin("Segmentation selectFirst")
scoresData = NP("empty", len(dataTable), dtype=NP.dtype(object))
scoresMask = NP("zeros", len(dataTable), dtype=defs.maskType)
unfilled = NP("ones", len(dataTable), dtype=NP.dtype(bool))
segments = NP("empty", len(dataTable), dtype=NP.dtype(object))
newOutputData = []
for segment in segmentation.childrenOfTag("Segment", iterator=True):
performanceTable.pause("Segmentation selectFirst")
selection = segment.childOfClass(PmmlPredicate).evaluate(
dataTable, functionTable, performanceTable)
performanceTable.unpause("Segmentation selectFirst")
NP("logical_and", selection, unfilled, selection)
if not selection.any():
continue
subTable = dataTable.subTable(selection)
subModel = segment.childOfClass(PmmlModel)
performanceTable.pause("Segmentation selectFirst")
subModel.calculate(subTable, functionTable, performanceTable)
performanceTable.unpause("Segmentation selectFirst")
scoresData[selection] = subTable.score.data
if subTable.score.mask is not None:
scoresMask[selection] = subTable.score.mask
else:
scoresMask[selection] = defs.VALID
segmentName = segment.get("id")
if segmentName is not None:
segments[selection] = segmentName
for fieldName, dataColumn in subTable.output.items():
if fieldName not in dataTable.output:
data = NP("empty",
len(dataTable),
dtype=dataColumn.fieldType.dtype)
data[selection] = dataColumn.data
mask = NP(
NP("ones", len(dataTable), dtype=defs.maskType) *
defs.MISSING)
if dataColumn.mask is None:
mask[selection] = defs.VALID
else:
mask[selection] = dataColumn.mask
newDataColumn = DataColumn(dataColumn.fieldType, data,
mask)
newDataColumn._unlock()
dataTable.output[fieldName] = newDataColumn
newOutputData.append(newDataColumn)
else:
newDataColumn = dataTable.output[fieldName]
newDataColumn.data[selection] = dataColumn.data
if dataColumn.mask is None:
newDataColumn.mask[selection] = defs.VALID
else:
newDataColumn.mask[selection] = dataColumn.mask
unfilled -= selection
if not unfilled.any():
break
for newDataColumn in newOutputData:
if not newDataColumn.mask.any():
newDataColumn._mask = None
newDataColumn._lock()
if not scoresMask.any():
scoresMask = None
scores = DataColumn(self.scoreType, scoresData, scoresMask)
if self.name is None:
performanceTable.end("Segmentation selectFirst")
return {None: scores}
else:
performanceTable.end("Segmentation selectFirst")
return {
None: scores,
"segment": DataColumn(self.scoreTypeSegment, segments, None)
}
def _selectFirst(self, dataTable, functionTable, performanceTable, segmentation):
"""Used by C{calculateScore}."""
performanceTable.begin("Segmentation selectFirst")
scoresData = NP("empty", len(dataTable), dtype=NP.dtype(object))
scoresMask = NP("zeros", len(dataTable), dtype=defs.maskType)
unfilled = NP("ones", len(dataTable), dtype=NP.dtype(bool))
segments = NP("empty", len(dataTable), dtype=NP.dtype(object))
newOutputData = []
for segment in segmentation.childrenOfTag("Segment", iterator=True):
performanceTable.pause("Segmentation selectFirst")
selection = segment.childOfClass(PmmlPredicate).evaluate(dataTable, functionTable, performanceTable)
performanceTable.unpause("Segmentation selectFirst")
NP("logical_and", selection, unfilled, selection)
if not selection.any():
continue
subTable = dataTable.subTable(selection)
subModel = segment.childOfClass(PmmlModel)
performanceTable.pause("Segmentation selectFirst")
subModel.calculate(subTable, functionTable, performanceTable)
performanceTable.unpause("Segmentation selectFirst")
scoresData[selection] = subTable.score.data
if subTable.score.mask is not None:
scoresMask[selection] = subTable.score.mask
else:
scoresMask[selection] = defs.VALID
segmentName = segment.get("id")
if segmentName is not None:
segments[selection] = segmentName
for fieldName, dataColumn in subTable.output.items():
if fieldName not in dataTable.output:
data = NP("empty", len(dataTable), dtype=dataColumn.fieldType.dtype)
data[selection] = dataColumn.data
mask = NP(NP("ones", len(dataTable), dtype=defs.maskType) * defs.MISSING)
if dataColumn.mask is None:
mask[selection] = defs.VALID
else:
mask[selection] = dataColumn.mask
newDataColumn = DataColumn(dataColumn.fieldType, data, mask)
newDataColumn._unlock()
dataTable.output[fieldName] = newDataColumn
newOutputData.append(newDataColumn)
else:
newDataColumn = dataTable.output[fieldName]
newDataColumn.data[selection] = dataColumn.data
if dataColumn.mask is None:
newDataColumn.mask[selection] = defs.VALID
else:
newDataColumn.mask[selection] = dataColumn.mask
unfilled -= selection
if not unfilled.any():
break
for newDataColumn in newOutputData:
if not newDataColumn.mask.any():
newDataColumn._mask = None
newDataColumn._lock()
if not scoresMask.any():
scoresMask = None
scores = DataColumn(self.scoreType, scoresData, scoresMask)
if self.name is None:
performanceTable.end("Segmentation selectFirst")
return {None: scores}
else:
performanceTable.end("Segmentation selectFirst")
return {None: scores, "segment": DataColumn(self.scoreTypeSegment, segments, None)}
