Inheritance diagram for Overtraining:

Public Member Functions
	__init__ (self, figure=None, dpi=None)

	add (self, data, column, train_mask, test_mask, signal_mask, bckgrd_mask, weight_column=None)

	finish (self)

	add_subplot (self, gridspecs)

	save (self, filename)

	set_plot_options (self, plot_kwargs={ 'linestyle':''})

	set_errorbar_options (self, errorbar_kwargs={ 'fmt':'.', 'elinewidth':3, 'alpha':1})
	Overrides default errorbar options for datapoint errorbars.

	set_errorband_options (self, errorband_kwargs={ 'alpha':0.5})

	set_fill_options (self, fill_kwargs=None)

	setAxisLimits (self, factor=0.0)

	scale_limits (self)

Public Attributes
	dpi = dpi
	set default dpi

	plot_kwargs = None
	create figure

	errorbar_kwargs = None
	Default keyword arguments for errorbar function.

	errorband_kwargs = None
	Default keyword arguments for errorband function.

	fill_kwargs = None
	Default keyword arguments for fill_between function.

	prop_cycler = itertools.cycle(plt.rcParams["axes.prop_cycle"])
	Property cycler used to give plots unique colors.

Static Public Attributes
	axis_d1 = None
	Axis which shows the difference between training and test signal.

	axis_d2 = None
	Axis which shows the difference between training and test background.

list	plots = None
	Plots added to the axis so far.

list	labels = None
	Labels of the plots added so far.

	xmin = None
	Minimum x value.

	xmax = None
	Maximum x value.

	ymin = None
	Minimum y value.

	ymax = None
	Maximum y value.

float	yscale = 0.0
	create figure

float	xscale = 0.0
	create figure

	figure = None
	figure which is used to draw

	axis = None
	Main axis which is used to draw.

Protected Member Functions
	_plot_datapoints (self, axis, x, y, xerr=None, yerr=None)

Detailed Description

Create TMVA-like overtraining control plot for a classification training

Definition at line 1171 of file plotting.py.

Constructor & Destructor Documentation

◆ init()

__init__	(	self,
		figure = None,
		dpi = None )

Creates a new figure if None is given, sets the default plot parameters
@param figure default draw figure which is used
@param dpi dpi for the matplotlib figure, if None default is used

Definition at line 1185 of file plotting.py.

    def __init__(self, figure=None, dpi=None):
        """
        Creates a new figure if None is given, sets the default plot parameters
        @param figure default draw figure which is used
        @param dpi dpi for the matplotlib figure, if None default is used
        """
        
        self.dpi = dpi
        if figure is None:
            
            self.figure = matplotlib.figure.Figure(figsize=(12, 8), dpi=self.dpi)
        else:
            self.figure = figure
 
        gs = matplotlib.gridspec.GridSpec(5, 1)
        
        self.axis = self.figure.add_subplot(gs[:3, :])
        
        self.axis_d1 = self.figure.add_subplot(gs[3, :], sharex=self.axis)
        
        self.axis_d2 = self.figure.add_subplot(gs[4, :], sharex=self.axis)
 
        super().__init__(self.figure, self.axis)
 

Member Function Documentation

◆ _plot_datapoints()

_plot_datapoints	(	self,
		axis,
		x,
		y,
		xerr = None,
		yerr = None )

protectedinherited

Plot the given datapoints, with plot, errorbar and make a errorband with fill_between
@param x coordinates of the data points
@param y coordinates of the data points
@param xerr symmetric error on x data points
@param yerr symmetric error on y data points

Definition at line 184 of file plotting.py.

    def _plot_datapoints(self, axis, x, y, xerr=None, yerr=None):
        """
        Plot the given datapoints, with plot, errorbar and make a errorband with fill_between
        @param x coordinates of the data points
        @param y coordinates of the data points
        @param xerr symmetric error on x data points
        @param yerr symmetric error on y data points
        """
        p = e = f = None
        plot_kwargs = copy.copy(self.plot_kwargs)
        errorbar_kwargs = copy.copy(self.errorbar_kwargs)
        errorband_kwargs = copy.copy(self.errorband_kwargs)
        fill_kwargs = copy.copy(self.fill_kwargs)
 
        if plot_kwargs is None or 'color' not in plot_kwargs:
            color = next(self.prop_cycler)
            color = color['color']
            plot_kwargs['color'] = color
        else:
            color = plot_kwargs['color']
        color = matplotlib.colors.ColorConverter().to_rgb(color)
        patch = matplotlib.patches.Patch(color=color, alpha=0.5)
        patch.get_color = patch.get_facecolor
        patches = [patch]
 
        if plot_kwargs is not None:
            p, = axis.plot(x, y, rasterized=True, **plot_kwargs)
            patches.append(p)
 
        if errorbar_kwargs is not None and (xerr is not None or yerr is not None):
            if 'color' not in errorbar_kwargs:
                errorbar_kwargs['color'] = color
            if 'ecolor' not in errorbar_kwargs:
                errorbar_kwargs['ecolor'] = [0.5 * x for x in color]
 
            # fully mask nan values.
            # Needed until https://github.com/matplotlib/matplotlib/pull/23333 makes it into the externals.
            # TODO: remove in release 8.
            if not isinstance(xerr, (numpy.ndarray, list)):
                xerr = xerr*numpy.ones(len(x))
            if not isinstance(yerr, (numpy.ndarray, list)):
                yerr = yerr*numpy.ones(len(y))
            mask = numpy.logical_and.reduce([numpy.isfinite(v) for v in [x, y, xerr, yerr]])
 
            e = axis.errorbar(
                x[mask], y[mask], xerr=numpy.where(
                    xerr[mask] < 0, 0.0, xerr[mask]), yerr=numpy.where(
                    yerr[mask] < 0, 0.0, yerr[mask]), rasterized=True, **errorbar_kwargs)
            patches.append(e)
 
        if errorband_kwargs is not None and yerr is not None:
            if 'color' not in errorband_kwargs:
                errorband_kwargs['color'] = color
            if xerr is not None:
                # Ensure that xerr and yerr are iterable numpy arrays
                xerr = x + xerr - x
                yerr = y + yerr - y
                for _x, _y, _xe, _ye in zip(x, y, xerr, yerr):
                    axis.add_patch(matplotlib.patches.Rectangle((_x - _xe, _y - _ye), 2 * _xe, 2 * _ye, rasterized=True,
                                                                **errorband_kwargs))
            else:
                f = axis.fill_between(x, y - yerr, y + yerr, interpolate=True, rasterized=True, **errorband_kwargs)
 
        if fill_kwargs is not None:
            # to fill the last bin of a histogram
            x = numpy.append(x, x[-1]+2*xerr[-1])
            y = numpy.append(y, y[-1])
            xerr = numpy.append(xerr, xerr[-1])
 
            axis.fill_between(x-xerr, y, 0, rasterized=True, **fill_kwargs)
 
        return (tuple(patches), p, e, f)
 

◆ add()

add	(	self,
		data,
		column,
		train_mask,
		test_mask,
		signal_mask,
		bckgrd_mask,
		weight_column = None )

Add a new overtraining plot, I recommend to draw only one overtraining plot at the time,
otherwise there are too many curves in the plot to recognize anything in the plot.
@param data pandas.DataFrame containing all data
@param column which is used to calculate distribution histogram
@param train_mask boolean numpy.array defining which events are training events
@param test_mask boolean numpy.array defining which events are test events
@param signal_mask boolean numpy.array defining which events are signal events
@param bckgrd_mask boolean numpy.array defining which events are background events
@param weight_column column in data containing the weights for each event

Reimplemented from Plotter.

Definition at line 1209 of file plotting.py.

    def add(self, data, column, train_mask, test_mask, signal_mask, bckgrd_mask, weight_column=None):
        """
        Add a new overtraining plot, I recommend to draw only one overtraining plot at the time,
        otherwise there are too many curves in the plot to recognize anything in the plot.
        @param data pandas.DataFrame containing all data
        @param column which is used to calculate distribution histogram
        @param train_mask boolean numpy.array defining which events are training events
        @param test_mask boolean numpy.array defining which events are test events
        @param signal_mask boolean numpy.array defining which events are signal events
        @param bckgrd_mask boolean numpy.array defining which events are background events
        @param weight_column column in data containing the weights for each event
        """
        distribution = Distribution(self.figure, self.axis, normed_to_all_entries=True)
        self.axis.set_yscale('log')
 
        distribution.set_plot_options(self.plot_kwargs)
        distribution.set_errorbar_options(self.errorbar_kwargs)
        distribution.set_errorband_options(self.errorband_kwargs)
        distribution.add(data, column, test_mask & signal_mask, weight_column)
        distribution.add(data, column, test_mask & bckgrd_mask, weight_column)
 
        distribution.set_plot_options(
            {'color': distribution.plots[0][0][0].get_color(), 'linestyle': '-', 'lw': 4, 'drawstyle': 'steps-mid'})
        distribution.set_fill_options({'color': distribution.plots[0][0][0].get_color(), 'alpha': 0.5, 'step': 'post'})
        distribution.set_errorbar_options(None)
        distribution.set_errorband_options(None)
        distribution.add(data, column, train_mask & signal_mask, weight_column)
        distribution.set_plot_options(
            {'color': distribution.plots[1][0][0].get_color(), 'linestyle': '-', 'lw': 4, 'drawstyle': 'steps-mid'})
        distribution.set_fill_options({'color': distribution.plots[1][0][0].get_color(), 'alpha': 0.5, 'step': 'post'})
        distribution.add(data, column, train_mask & bckgrd_mask, weight_column)
 
        distribution.labels = ['Test-Signal', 'Test-Background', 'Train-Signal', 'Train-Background']
        distribution.finish()
 
        self.plot_kwargs['color'] = distribution.plots[0][0][0].get_color()
        difference_signal = Difference(self.figure, self.axis_d1, shift_to_zero=True, normed=True)
        difference_signal.set_plot_options(self.plot_kwargs)
        difference_signal.set_errorbar_options(self.errorbar_kwargs)
        difference_signal.set_errorband_options(self.errorband_kwargs)
        difference_signal.add(data, column, train_mask & signal_mask, test_mask & signal_mask, weight_column)
        self.axis_d1.set_xlim((difference_signal.xmin, difference_signal.xmax))
        self.axis_d1.set_ylim((difference_signal.ymin, difference_signal.ymax))
        difference_signal.plots = difference_signal.labels = []
        difference_signal.finish(line_color=distribution.plots[0][0][0].get_color())
 
        self.plot_kwargs['color'] = distribution.plots[1][0][0].get_color()
        difference_bckgrd = Difference(self.figure, self.axis_d2, shift_to_zero=True, normed=True)
        difference_bckgrd.set_plot_options(self.plot_kwargs)
        difference_bckgrd.set_errorbar_options(self.errorbar_kwargs)
        difference_bckgrd.set_errorband_options(self.errorband_kwargs)
        difference_bckgrd.add(data, column, train_mask & bckgrd_mask, test_mask & bckgrd_mask, weight_column)
        self.axis_d2.set_xlim((difference_bckgrd.xmin, difference_bckgrd.xmax))
        self.axis_d2.set_ylim((difference_bckgrd.ymin, difference_bckgrd.ymax))
        difference_bckgrd.plots = difference_bckgrd.labels = []
        difference_bckgrd.finish(line_color=distribution.plots[1][0][0].get_color())
 
        try:
            import scipy.stats
            # Kolmogorov smirnov test
            if len(data[column][train_mask & signal_mask]) == 0 or len(data[column][test_mask & signal_mask]) == 0:
                b2.B2WARNING("Cannot calculate kolmogorov smirnov test for signal due to missing data")
            else:
                ks = scipy.stats.ks_2samp(data[column][train_mask & signal_mask], data[column][test_mask & signal_mask])
                props = dict(boxstyle='round', edgecolor='gray', facecolor='white', linewidth=0.1, alpha=0.5)
                self.axis_d1.text(0.1, 0.9, r'signal (train - test) difference $p={:.2f}$'.format(ks[1]),  bbox=props,
                                  verticalalignment='top', horizontalalignment='left', transform=self.axis_d1.transAxes)
            if len(data[column][train_mask & bckgrd_mask]) == 0 or len(data[column][test_mask & bckgrd_mask]) == 0:
                b2.B2WARNING("Cannot calculate kolmogorov smirnov test for background due to missing data")
            else:
                ks = scipy.stats.ks_2samp(data[column][train_mask & bckgrd_mask], data[column][test_mask & bckgrd_mask])
                props = dict(boxstyle='round', edgecolor='gray', facecolor='white', linewidth=0.1, alpha=0.5)
                self.axis_d2.text(0.1, 0.9, r'background (train - test) difference $p={:.2f}$'.format(ks[1]),
                                  bbox=props,
                                  verticalalignment='top', horizontalalignment='left', transform=self.axis_d2.transAxes)
        except ImportError:
            b2.B2WARNING("Cannot calculate kolmogorov smirnov test please install scipy!")
 
        return self
 

◆ add_subplot()

add_subplot	(		self,
			gridspecs )

inherited

Adds a new subplot to the figure, updates all other axes
according to the given gridspec
@param gridspecs gridspecs for all axes including the new one

Definition at line 129 of file plotting.py.

    def add_subplot(self, gridspecs):
        """
        Adds a new subplot to the figure, updates all other axes
        according to the given gridspec
        @param gridspecs gridspecs for all axes including the new one
        """
        for gs, ax in zip(gridspecs[:-1], self.figure.axes):
            ax.set_position(gs.get_position(self.figure))
            ax.set_subplotspec(gs)
        axis = self.figure.add_subplot(gridspecs[-1], sharex=self.axis)
        return axis
 

◆ finish()

finish ( self )

Sets limits, title, axis-labels and legend of the plot

Reimplemented from Plotter.

Definition at line 1289 of file plotting.py.

    def finish(self):
        """
        Sets limits, title, axis-labels and legend of the plot
        """
        self.axis.set_title("Overtraining Plot")
        self.axis_d1.set_title("")
        self.axis_d2.set_title("")
        matplotlib.artist.setp(self.axis.get_xticklabels(), visible=False)
        matplotlib.artist.setp(self.axis_d1.get_xticklabels(), visible=False)
        self.axis.get_xaxis().set_label_text('')
        self.axis_d1.get_xaxis().set_label_text('')
        self.axis_d2.get_xaxis().set_label_text('Classifier Output')
        return self
 
 

◆ save()

save	(		self,
			filename )

inherited

Save the figure into a file
@param filename of the file

Definition at line 141 of file plotting.py.

    def save(self, filename):
        """
        Save the figure into a file
        @param filename of the file
        """
        b2.B2INFO("Save figure for class " + str(type(self)))
        from matplotlib.backends.backend_agg import FigureCanvasAgg as FigureCanvas
        canvas = FigureCanvas(self.figure)
        canvas.print_figure(filename, dpi=self.dpi, bbox_inches='tight')
        return self
 

◆ scale_limits()

scale_limits ( self )

inherited

Scale limits to increase distance to boundaries

Definition at line 281 of file plotting.py.

    def scale_limits(self):
        """
        Scale limits to increase distance to boundaries
        """
        self.ymin *= 1.0 - math.copysign(self.yscale, self.ymin)
        self.ymax *= 1.0 + math.copysign(self.yscale, self.ymax)
        self.xmin *= 1.0 - math.copysign(self.xscale, self.xmin)
        self.xmax *= 1.0 + math.copysign(self.xscale, self.xmax)
        return self
 
 

◆ set_errorband_options()

set_errorband_options	(		self,
			errorband_kwargs = {'alpha': 0.5} )

inherited

Overrides default errorband options for datapoint errorband
@param errorbar_kwargs keyword arguments for the fill_between function

Definition at line 168 of file plotting.py.

    def set_errorband_options(self, errorband_kwargs={'alpha': 0.5}):
        """
        Overrides default errorband options for datapoint errorband
        @param errorbar_kwargs keyword arguments for the fill_between function
        """
        self.errorband_kwargs = copy.copy(errorband_kwargs)
        return self
 

◆ set_errorbar_options()

set_errorbar_options	(		self,
			errorbar_kwargs = {'fmt': '.', 'elinewidth': 3, 'alpha': 1} )

inherited

Overrides default errorbar options for datapoint errorbars.

Overrides default errorbar options for datapoint errorbars
@param errorbar_kwargs keyword arguments for the errorbar function

Definition at line 160 of file plotting.py.

    def set_errorbar_options(self, errorbar_kwargs={'fmt': '.', 'elinewidth': 3, 'alpha': 1}):
        """
        Overrides default errorbar options for datapoint errorbars
        @param errorbar_kwargs keyword arguments for the errorbar function
        """
        self.errorbar_kwargs = copy.copy(errorbar_kwargs)
        return self
 

◆ set_fill_options()

set_fill_options	(		self,
			fill_kwargs = None )

inherited

Overrides default fill_between options for datapoint errorband
@param fill_kwargs keyword arguments for the fill_between function

Definition at line 176 of file plotting.py.

    def set_fill_options(self, fill_kwargs=None):
        """
        Overrides default fill_between options for datapoint errorband
        @param fill_kwargs keyword arguments for the fill_between function
        """
        self.fill_kwargs = copy.copy(fill_kwargs)
        return self
 

◆ set_plot_options()

set_plot_options	(		self,
			plot_kwargs = {'linestyle': ''} )

inherited

Overrides default plot options for datapoint plot
@param plot_kwargs keyword arguments for the plot function

Definition at line 152 of file plotting.py.

    def set_plot_options(self, plot_kwargs={'linestyle': ''}):
        """
        Overrides default plot options for datapoint plot
        @param plot_kwargs keyword arguments for the plot function
        """
        self.plot_kwargs = copy.copy(plot_kwargs)
        return self
 

◆ setAxisLimits()

setAxisLimits	(		self,
			factor = 0.0 )

inherited

Sets the limits of the axis with an optional expansion factor.

Parameters:
    factor (float): Fraction by which to expand the axis limits beyond the data range.

Definition at line 263 of file plotting.py.

    def setAxisLimits(self, factor=0.0):
        """
        Sets the limits of the axis with an optional expansion factor.
 
        Parameters:
            factor (float): Fraction by which to expand the axis limits beyond the data range.
        """
        dx = self.xmax - self.xmin
        dy = self.ymax - self.ymin
        self.axis.set_xlim((self.xmin - factor*dx, self.xmax + factor*dx))
        self.axis.set_ylim((self.ymin - factor*dy, self.ymax + factor*dy))
 

Member Data Documentation

◆ axis

axis = None

staticinherited

Main axis which is used to draw.

divide figure into subplots

Definition at line 75 of file plotting.py.

◆ axis_d1

axis_d1 = None

static

Axis which shows the difference between training and test signal.

define second subplot

Definition at line 1181 of file plotting.py.

◆ axis_d2

axis_d2 = None

static

Axis which shows the difference between training and test background.

define second subplot

define third subplot

Definition at line 1183 of file plotting.py.

◆ dpi

dpi = dpi

inherited

set default dpi

Definition at line 86 of file plotting.py.

◆ errorband_kwargs

errorband_kwargs = None

inherited

Default keyword arguments for errorband function.

Definition at line 117 of file plotting.py.

◆ errorbar_kwargs

errorbar_kwargs = None

inherited

Default keyword arguments for errorbar function.

Definition at line 115 of file plotting.py.

◆ figure

figure = None

staticinherited

figure which is used to draw

Definition at line 73 of file plotting.py.

◆ fill_kwargs

fill_kwargs = None

inherited

Default keyword arguments for fill_between function.

Definition at line 119 of file plotting.py.

◆ labels

list labels = None

staticinherited

Labels of the plots added so far.

divide figure into subplots

create empty list for plots

create empty list for labels

Definition at line 61 of file plotting.py.

◆ plot_kwargs

plot_kwargs = None

inherited

create figure

divide figure into subplots

create empty list for plots

create empty list for labels

set x limits

set y limits

y limit scale

x limit scale

Default keyword arguments for plot function

Definition at line 113 of file plotting.py.

◆ plots

list plots = None

staticinherited

Plots added to the axis so far.

divide figure into subplots

create empty list for plots

Definition at line 59 of file plotting.py.

◆ prop_cycler

prop_cycler = itertools.cycle(plt.rcParams["axes.prop_cycle"])

inherited

Property cycler used to give plots unique colors.

Definition at line 127 of file plotting.py.

◆ xmax

xmax = None

staticinherited

Maximum x value.

divide figure into subplots

create empty list for plots

create empty list for labels

set x limits

Definition at line 65 of file plotting.py.

◆ xmin

xmin = None

staticinherited

Minimum x value.

create figure

divide figure into subplots

create empty list for plots

create empty list for labels

set x limits

Definition at line 63 of file plotting.py.

◆ xscale

float xscale = 0.0

staticinherited

create figure

limit scale

divide figure into subplots

create empty list for plots

create empty list for labels

set x limits

set y limits

y limit scale

x limit scale

Definition at line 71 of file plotting.py.

◆ ymax

ymax = None

staticinherited

Maximum y value.

divide figure into subplots

create empty list for plots

create empty list for labels

set x limits

set y limits

Definition at line 69 of file plotting.py.

◆ ymin

ymin = None

staticinherited

Minimum y value.

create figure

divide figure into subplots

create empty list for plots

create empty list for labels

set x limits

set y limits

Definition at line 67 of file plotting.py.

◆ yscale

float yscale = 0.0

staticinherited

create figure

limit scale

divide figure into subplots

create empty list for plots

create empty list for labels

set x limits

set y limits

y limit scale

Definition at line 70 of file plotting.py.

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

mva/scripts/basf2_mva_evaluation/plotting.py

Public Member Functions

Public Attributes

Static Public Attributes

Protected Member Functions

Detailed Description

Constructor & Destructor Documentation

◆ __init__()

Member Function Documentation

◆ _plot_datapoints()

◆ add()

◆ add_subplot()

◆ finish()

◆ save()

◆ scale_limits()

◆ set_errorband_options()

◆ set_errorbar_options()

◆ set_fill_options()

◆ set_plot_options()

◆ setAxisLimits()

Member Data Documentation

◆ axis

◆ axis_d1

◆ axis_d2

◆ dpi

◆ errorband_kwargs

◆ errorbar_kwargs

◆ figure

◆ fill_kwargs

◆ labels

◆ plot_kwargs

◆ plots

◆ prop_cycler

◆ xmax

◆ xmin

◆ xscale

◆ ymax

◆ ymin

◆ yscale

◆ init()