def _count(process, region):
"""Computes the weighted event count of a process in a region.
Args:
process: The process whose events should be counted
region: The region whose weighting/selection should be applied
Returns:
The weighted event count in the region.
"""
# Compute weighted selection
selection, weight = region.selection_weight()
# Compute the weighted selection properties
required_properties = set()
required_properties.update(properties(selection))
required_properties.update(properties(weight))
# Load data
data = process.load(required_properties)
# Apply selection if specified
if selection != '':
data = data[data.eval(normalized(selection))]
# Compute the weighted or unweighted count
if weight != '':
return data.eval(normalized(weight)).sum()
else:
return len(data)
def __init__(self, selection):
"""Initializes a new instance of the Filter class.
Args:
selection: The selection expression to apply to the process data
"""
self._selection = normalized(selection)
def __init__(self, selection):
"""Initializes a new instance of the Filter class.
Args:
selection: The selection expression to apply to the process data
"""
self._selection = normalized(selection)
def __init__(self, weight):
"""Initializes a new instance of the Reweighted class.
Args:
weight: The weight expression to incorporate into the region
"""
# Store the weight
self._weight = normalized(weight)
def __init__(self, weight):
"""Initializes a new instance of the Reweighted class.
Args:
weight: The weight expression to incorporate into the region
"""
# Store the weight
self._weight = normalized(weight)
def _histogram(process, region, expressions, binnings, load_hints = None):
"""Generates a ROOT histogram of a distribution a process in a region.
Args:
process: The process whose events should be histogrammed
region: The region whose weighting/selection should be applied
expressions: A tuple of expression strings
binnings: A tuple of Binning instances
distribution: The distribution to histogram
load_hints: If provided, this argument will hint to _histogram that it
should load additional properties when loading data and that it
should use the _caching_loader. This facilitates cached loading of
data across multiple calls to _histogram with the same process.
This is particularly useful for parallelized histogramming, where
the jobs are grouped by process.
Returns:
A ROOT histogram, of the TH1F, TH2F, or TH3F variety.
"""
# Compute weighted selection
selection, weight = region.selection_weight()
# Expand binnings to edge lists
edges = tuple((b.edges() for b in binnings))
# Load data
if load_hints is not None:
# If load_hints have been provided, just use those with the
# _caching_loader
data = _caching_loader(process, load_hints)
else:
# Otherwise manually create the set of necessary properties
# NOTE: All we need to do are region and expression properties - patch
# properties are handled internally by the process
required_properties = set()
# Add those properties necessary to evaluate region selection/weight
required_properties.update(properties(selection))
required_properties.update(properties(weight))
# Add in those properties necessary to evaluate expressions
required_properties.update(*(properties(e) for e in expressions))
# Load data
data = process.load(required_properties)
# Apply selection if specified
if selection != '':
data = data[data.eval(normalized(selection))]
# Evaluate each variable expression, converting the resultant Pandas Series
# to a NumPy array
# HACK: TH1::FillN only supports 64-bit floating point values, so convert
# things. Would be nice to find a better approach.
samples = tuple((data.eval(normalized(e)).values.astype(numpy.float64)
for e
in expressions))
# Evaluate weights, converting the resultant Pandas Series to a NumPy array
# HACK: TH1::FillN only supports 64-bit floating point values, so convert
# things. Would be nice to find a better approach.
if weight != '':
weights = data.eval(normalized(weight)).values.astype(numpy.float64)
else:
weights = nullptr
# Create a unique name and title for the histogram
name = title = uuid4().hex
# Create a histogram based on dimensionality
# NOTE: When specifying explicit bin edges, you aren't passing a length
# argument, you are passing an nbins argument, which is length - 1, hence
# the code below. If you pass length for n bins, then you'll get garbage
# for the last bin's upper edge and things go nuts in ROOT.
dimensionality = len(expressions)
count = len(data)
if dimensionality == 1:
# Create a one-dimensional histogram
result = TH1F(name, title,
len(edges[0]) - 1, edges[0])
# Fill the histogram
# HACK: TH1::FillN will die if N == 0
if count > 0:
result.FillN(count, samples[0], weights)
elif dimensionality == 2:
# Create a two-dimensional histogram
result = TH2F(name, title,
len(edges[0]) - 1, edges[0],
len(edges[1]) - 1, edges[1])
# Fill the histogram
# HACK: TH1::FillN will die if N == 0
if count > 0:
result.FillN(count, samples[0], samples[1], weights)
elif dimensionality == 3:
# Create a three-dimensional histogram
result = TH3F(name, title,
len(edges[0]) - 1, edges[0],
len(edges[1]) - 1, edges[1],
len(edges[2]) - 1, edges[2])
# HACK: TH3 doesn't have a FillN method, so we have to do things the
# slow way.
# TODO: We may want to put a warning about this slowness
if weights == nullptr:
weights = numpy.ones(count, dtype = numpy.float64)
for x, y, z, w in zip(samples[0], samples[1], samples[2], weights):
result.Fill(x, y, z, w)
else:
raise ValueError('ROOT can only histograms 1 - 3 dimensions')
# All done
return result
def _histogram(process, region, expressions, binnings, load_hints=None):
"""Generates a ROOT histogram of a distribution a process in a region.
Args:
process: The process whose events should be histogrammed
region: The region whose weighting/selection should be applied
expressions: A tuple of expression strings
binnings: A tuple of Binning instances
distribution: The distribution to histogram
load_hints: If provided, this argument will hint to _histogram that it
should load additional properties when loading data and that it
should use the _caching_loader. This facilitates cached loading of
data across multiple calls to _histogram with the same process.
This is particularly useful for parallelized histogramming, where
the jobs are grouped by process.
Returns:
A ROOT histogram, of the TH1F, TH2F, or TH3F variety.
"""
# Compute weighted selection
selection, weight = region.selection_weight()
# Expand binnings to edge lists
edges = tuple((b.edges() for b in binnings))
# Load data
if load_hints is not None:
# If load_hints have been provided, just use those with the
# _caching_loader
data = _caching_loader(process, load_hints)
else:
# Otherwise manually create the set of necessary properties
# NOTE: All we need to do are region and expression properties - patch
# properties are handled internally by the process
required_properties = set()
# Add those properties necessary to evaluate region selection/weight
required_properties.update(properties(selection))
required_properties.update(properties(weight))
# Add in those properties necessary to evaluate expressions
required_properties.update(*(properties(e) for e in expressions))
# Load data
data = process.load(required_properties)
# Apply selection if specified
if selection != '':
data = data[data.eval(normalized(selection))]
# Evaluate each variable expression, converting the resultant Pandas Series
# to a NumPy array
# HACK: TH1::FillN only supports 64-bit floating point values, so convert
# things. Would be nice to find a better approach.
samples = tuple((data.eval(normalized(e)).values.astype(numpy.float64)
for e in expressions))
# Evaluate weights, converting the resultant Pandas Series to a NumPy array
# HACK: TH1::FillN only supports 64-bit floating point values, so convert
# things. Would be nice to find a better approach.
if weight != '':
weights = data.eval(normalized(weight)).values.astype(numpy.float64)
else:
weights = nullptr
# Create a unique name and title for the histogram
name = title = uuid4().hex
# Create a histogram based on dimensionality
# NOTE: When specifying explicit bin edges, you aren't passing a length
# argument, you are passing an nbins argument, which is length - 1, hence
# the code below. If you pass length for n bins, then you'll get garbage
# for the last bin's upper edge and things go nuts in ROOT.
dimensionality = len(expressions)
count = len(data)
if dimensionality == 1:
# Create a one-dimensional histogram
result = TH1F(name, title, len(edges[0]) - 1, edges[0])
# Fill the histogram
# HACK: TH1::FillN will die if N == 0
if count > 0:
result.FillN(count, samples[0], weights)
elif dimensionality == 2:
# Create a two-dimensional histogram
result = TH2F(name, title,
len(edges[0]) - 1, edges[0],
len(edges[1]) - 1, edges[1])
# Fill the histogram
# HACK: TH1::FillN will die if N == 0
if count > 0:
result.FillN(count, samples[0], samples[1], weights)
elif dimensionality == 3:
# Create a three-dimensional histogram
result = TH3F(name, title,
len(edges[0]) - 1, edges[0],
len(edges[1]) - 1, edges[1],
len(edges[2]) - 1, edges[2])
# HACK: TH3 doesn't have a FillN method, so we have to do things the
# slow way.
# TODO: We may want to put a warning about this slowness
if weights == nullptr:
weights = numpy.ones(count, dtype=numpy.float64)
for x, y, z, w in zip(samples[0], samples[1], samples[2], weights):
result.Fill(x, y, z, w)
else:
raise ValueError('ROOT can only histograms 1 - 3 dimensions')
# All done
return result
def test_normalize(self):
# Check that normalization works
self.assertEqual(normalized("!x && y || z"), "~x & y | z")
def test_normalize(self):
# Check that normalization works
self.assertEqual(normalized('!x && y || z'), '~x & y | z')
