CutClassifier Class Reference

Inheritance diagram for CutClassifier:

Public Member Functions
def	__init__ (self, cut_direction=1, cut_value=np.nan)
def	cut_direction (self)
def	cut_value (self)
def	clone (self)
def	determine_cut_value (self, estimates, truths)
def	fit (self, estimates, truths)
def	predict (self, estimates)
def	describe (self, estimates, truths)

Public Attributes
	cut_direction_
	cached copy of the cut direction (< or >)
	cut_value_
	cached copy of the cut threshold

Detailed Description

Simple classifier cutting on a single variable

Definition at line 496 of file classification.py.

Constructor & Destructor Documentation

__init__()

def __init__	(		self,
			cut_direction = 1,
			cut_value = np.nan
	)

Constructor

Reimplemented in CutAtBackgroundRejectionClassifier.

Definition at line 500 of file classification.py.

    def __init__(self, cut_direction=1, cut_value=np.nan):
        """Constructor"""
        
        self.cut_direction_ = cut_direction
        
        self.cut_value_ = cut_value
 

Member Function Documentation

clone()

def clone

(

self

)

Return a clone of this object

Definition at line 517 of file classification.py.

    def clone(self):
        """Return a clone of this object"""
        return copy.copy(self)
 

cut_direction()

def cut_direction

(

self

)

Get the value of the cut direction

Definition at line 508 of file classification.py.

    def cut_direction(self):
        """Get the value of the cut direction"""
        return self.cut_direction_
 

cut_value()

def cut_value

(

self

)

Get the value of the cut threshold

Definition at line 513 of file classification.py.

    def cut_value(self):
        """Get the value of the cut threshold"""
        return self.cut_value_
 

describe()

def describe	(		self,
			estimates,
			truths
	)

Describe the cut selection and its efficiency, purity and background rejection

Definition at line 542 of file classification.py.

    def describe(self, estimates, truths):
        """Describe the cut selection and its efficiency, purity and background rejection"""
        if self.cut_direction_ < 0:
            print("Cut accepts >= ", self.cut_value_, 'with')
        else:
            print("Cut accepts <= ", self.cut_value_, 'with')
 
        binary_estimates = self.predict(estimates)
 
        efficiency = scores.efficiency(truths, binary_estimates)
        purity = scores.purity(truths, binary_estimates)
        background_rejection = scores.background_rejection(truths, binary_estimates)
 
        print("efficiency", efficiency)
        print("purity", purity)
        print("background_rejection", background_rejection)
 
 

determine_cut_value()

def determine_cut_value	(		self,
			estimates,
			truths
	)

Get the value of the cut threshold

Reimplemented in CutAtBackgroundRejectionClassifier.

Definition at line 521 of file classification.py.

    def determine_cut_value(self, estimates, truths):
        """Get the value of the cut threshold"""
        return self.cut_value_  # do not change cut value from constructed one
 

fit()

def fit	(		self,
			estimates,
			truths
	)

Fit to determine the cut threshold

Definition at line 525 of file classification.py.

    def fit(self, estimates, truths):
        """Fit to determine the cut threshold"""
        self.cut_value_ = self.determine_cut_value(estimates, truths)
        return self
 

predict()

def predict	(		self,
			estimates
	)

Select estimates that satisfy the cut

Definition at line 530 of file classification.py.

    def predict(self, estimates):
        """Select estimates that satisfy the cut"""
        if self.cut_value_ is None:
            raise ValueError("Cut value not set. Forgot to fit?")
 
        if self.cut_direction_ < 0:
            binary_estimates = estimates >= self.cut_value_
        else:
            binary_estimates = estimates <= self.cut_value_
 
        return binary_estimates
 

Member Data Documentation

cut_direction_

cut_direction_

cached copy of the cut direction (< or >)

Definition at line 503 of file classification.py.

cut_value_

cut_value_

cached copy of the cut threshold

Definition at line 505 of file classification.py.

---

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

• tracking/scripts/tracking/validation/classification.py