Histograms Class Reference

Public Member Functions
def	__init__ (self, data, column, masks=dict(), weight_column=None, bins=100, equal_frequency=True, range_in_std=None)
def	get_hist (self, name=None)
def	get_summed_hist (self, names)
def	get_efficiency (self, signal_names)
def	get_true_positives (self, signal_names)
def	get_false_positives (self, bckgrd_names)
def	get_purity (self, signal_names, bckgrd_names)
def	get_signal_to_noise (self, signal_names, bckgrd_names)
def	get_purity_per_bin (self, signal_names, bckgrd_names)

Static Public Attributes
	hist = None
	Histogram of the full data.
	bins = None
	Binning.
	bin_centers = None
	Bin centers.
	bin_widths = None
	Bin widths.
	hists = None
	Dictionary of histograms for the given masks.

Detailed Description

Extracts information from a pandas.DataFrame and stores it
in a binned format.
Therefore the size independent from the size of the pandas.DataFrame.
Used by the plotting routines below.

Definition at line 42 of file histogram.py.

Constructor & Destructor Documentation

__init__()

def __init__	(		self,
			data,
			column,
			masks = dict(),
			weight_column = None,
			bins = 100,
			equal_frequency = True,
			range_in_std = None
	)

Creates a common binning of the given column of the given pandas.Dataframe,
and stores for each given mask the histogram of the column
@param data pandas.DataFrame  like object containing column and weight_column
@param column string identifiying the column in the pandas.DataFrame which is binned.
@param masks dictionary of names and boolean arrays, which select the data
             used for the creation of histograms with these names
@param weight_column identifiying the column in the pandas.DataFrame which is used as weight
@param bins use given bins instead of default 100
@param equal_frequency perform an equal_frequency binning
@param range_in_std show only the data in a windows around +- range_in_std * standard_deviation around the mean

Definition at line 61 of file histogram.py.

    def __init__(self, data, column, masks=dict(), weight_column=None, bins=100, equal_frequency=True, range_in_std=None):
        """
        Creates a common binning of the given column of the given pandas.Dataframe,
        and stores for each given mask the histogram of the column
        @param data pandas.DataFrame  like object containing column and weight_column
        @param column string identifiying the column in the pandas.DataFrame which is binned.
        @param masks dictionary of names and boolean arrays, which select the data
                     used for the creation of histograms with these names
        @param weight_column identifiying the column in the pandas.DataFrame which is used as weight
        @param bins use given bins instead of default 100
        @param equal_frequency perform an equal_frequency binning
        @param range_in_std show only the data in a windows around +- range_in_std * standard_deviation around the mean
        """
        isfinite = numpy.isfinite(data[column])
        if range_in_std is not None:
            mean, std = weighted_mean_and_std(data[column][isfinite],
                                              None if weight_column is None else data[weight_column][isfinite])
            # Everything outside mean +- range_in_std * std is considered infinite
            isfinite = isfinite & (data[column] > (mean - range_in_std * std)) & (data[column] < (mean + range_in_std * std))
 
        if equal_frequency:
            if data[column][isfinite].size > 0:
                bins = numpy.unique(numpy.percentile(data[column][isfinite], q=range(bins + 1)))
            else:
                print('Empty Array')
                bins = [1]
            # If all values are unique, we make at least one bin
            if len(bins) == 1:
                bins = numpy.array([bins[0]-1, bins[0]+1])
 
        self.hist, self.bins = numpy.histogram(data[column][isfinite], bins=bins,
                                               weights=None if weight_column is None else data[weight_column])
        self.bin_centers = (self.bins + numpy.roll(self.bins, 1))[1:] / 2.0
        # Subtract a small number from the bin width, otherwise the errorband plot is unstable.
        self.bin_widths = (self.bins - numpy.roll(self.bins, 1))[1:] - 0.00001
        self.hists = dict()
        for name, mask in masks.items():
            self.hists[name] = numpy.histogram(data[column][mask & isfinite], bins=self.bins,
                                               weights=None if weight_column is None else data[weight_column][mask & isfinite])[0]
 

Member Function Documentation

get_efficiency()

def get_efficiency	(		self,
			signal_names
	)

Return the cumulative efficiency in each bin of the sum of the histograms with the given names.
@param  signal_names of the histograms
@return numpy.array with hist data, numpy.array with corresponding binomial errors

Definition at line 122 of file histogram.py.

get_false_positives()

def get_false_positives	(		self,
			bckgrd_names
	)

Return the cumulative false positives in each bin of the sum of the histograms with the given names.
@param names names of the histograms
@return numpy.array with hist data, numpy.array with corresponding binomial errors

Definition at line 149 of file histogram.py.

get_hist()

def get_hist	(		self,
			name = None
	)

Return histogram with the given name. If none returns histogram of the full data.
@param name name of the histogram
@return numpy.array with hist data, numpy.array with corresponding poisson errors

Definition at line 101 of file histogram.py.

get_purity()

def get_purity	(		self,
			signal_names,
			bckgrd_names
	)

Return the cumulative purity in each bin of the sum of the histograms with the given names.
@param names names of the histograms
@return numpy.array with hist data, numpy.array with corresponding binomial errors

Definition at line 160 of file histogram.py.

get_purity_per_bin()

def get_purity_per_bin	(		self,
			signal_names,
			bckgrd_names
	)

Return the purity in each bin of the sum of the histograms with the given names.
@param names names of the histograms
@return numpy.array with hist data, numpy.array with corresponding binomial errors

Definition at line 190 of file histogram.py.

get_signal_to_noise()

def get_signal_to_noise	(		self,
			signal_names,
			bckgrd_names
	)

Return the cumulative signal to noise ratio in each bin of the sum of the histograms with the given names.
@param names names of the histograms
@return numpy.array with hist data, numpy.array with corresponding binomial errors

Definition at line 175 of file histogram.py.

get_summed_hist()

def get_summed_hist	(		self,
			names
	)

Return the sum of histograms with the given names.
@param names names of the histograms
@return numpy.array with hist data, numpy.array with corresponding poisson errors

Definition at line 111 of file histogram.py.

get_true_positives()

def get_true_positives	(		self,
			signal_names
	)

Return the cumulative true positives in each bin of the sum of the histograms with the given names.
@param names names of the histograms
@return numpy.array with hist data, numpy.array with corresponding binomial errors

Definition at line 138 of file histogram.py.

---

The documentation for this class was generated from the following file:

• mva/scripts/basf2_mva_evaluation/histogram.py