spine.constants.columns

Canonical SPINE tensor column conventions.

This module defines the fixed column layouts used throughout SPINE for sparse input tensors, cluster labels, coordinate labels, and PPN targets/predictions. These are not physics categories; they are schema conventions for tensors.

Design notes

Single columns are represented as enum.IntEnum members for readable access such as SparseTensorCol.X or ClusterLabelCol.PARTICLE.
Multi-column selectors are represented as plain tuples so they can be used directly with NumPy and PyTorch indexing without introducing a numerical dependency in the constants package.
Backward-compatible aliases such as BATCH_COL and COORD_COLS are kept at module scope so existing code can migrate incrementally.

Classes

`ClusterLabelCol`(value)	Columns of the canonical cluster label tensor layout.
`CoordLabelCol`(value)	Columns of the canonical coordinate-label tensor layout.
`PPNLabelCol`(value)	Columns of the canonical PPN label tensor layout.
`PPNPredCol`(value)	Columns of the canonical PPN prediction tensor layout.
`SparseTensorCol`(value)	Columns of the canonical sparse tensor layout.

class spine.constants.columns.SparseTensorCol(value)[source]

Columns of the canonical sparse tensor layout.

Attributes:

denominator: the denominator of a rational number in lowest terms
imag: the imaginary part of a complex number
numerator: the numerator of a rational number in lowest terms
real: the real part of a complex number

Methods

`as_integer_ratio`(/)	Return integer ratio.
`bit_count`(/)	Number of ones in the binary representation of the absolute value of self.
`bit_length`(/)	Number of bits necessary to represent self in binary.
`conjugate`	Returns self, the complex conjugate of any int.
`from_bytes`(/, bytes[, byteorder, signed])	Return the integer represented by the given array of bytes.
`to_bytes`(/[, length, byteorder, signed])	Return an array of bytes representing an integer.

BATCH = 0

X = 1

Y = 2

Z = 3

VALUE = 4

class spine.constants.columns.ClusterLabelCol(value)[source]

Columns of the canonical cluster label tensor layout.

Attributes:

denominator: the denominator of a rational number in lowest terms
imag: the imaginary part of a complex number
numerator: the numerator of a rational number in lowest terms
real: the real part of a complex number

Methods

`as_integer_ratio`(/)	Return integer ratio.
`bit_count`(/)	Number of ones in the binary representation of the absolute value of self.
`bit_length`(/)	Number of bits necessary to represent self in binary.
`conjugate`	Returns self, the complex conjugate of any int.
`from_bytes`(/, bytes[, byteorder, signed])	Return the integer represented by the given array of bytes.
`to_bytes`(/[, length, byteorder, signed])	Return an array of bytes representing an integer.

BATCH = 0

X = 1

Y = 2

Z = 3

VALUE = 4

CLUSTER = 5

PARTICLE = 6

GROUP = 7

ANCESTOR = 8

INTERACTION = 9

NU = 10

PID = 11

GROUP_PRIMARY = 12

INTER_PRIMARY = 13

VTX_X = 14

VTX_Y = 15

VTX_Z = 16

MOMENTUM = 17

SHAPE = 18

class spine.constants.columns.CoordLabelCol(value)[source]

Columns of the canonical coordinate-label tensor layout.

Attributes:

denominator: the denominator of a rational number in lowest terms
imag: the imaginary part of a complex number
numerator: the numerator of a rational number in lowest terms
real: the real part of a complex number

Methods

`as_integer_ratio`(/)	Return integer ratio.
`bit_count`(/)	Number of ones in the binary representation of the absolute value of self.
`bit_length`(/)	Number of bits necessary to represent self in binary.
`conjugate`	Returns self, the complex conjugate of any int.
`from_bytes`(/, bytes[, byteorder, signed])	Return the integer represented by the given array of bytes.
`to_bytes`(/[, length, byteorder, signed])	Return an array of bytes representing an integer.

BATCH = 0

START_X = 1

START_Y = 2

START_Z = 3

END_X = 4

END_Y = 5

END_Z = 6

TIME = 7

SHAPE = 8

class spine.constants.columns.PPNLabelCol(value)[source]

Columns of the canonical PPN label tensor layout.

Attributes:

denominator: the denominator of a rational number in lowest terms
imag: the imaginary part of a complex number
numerator: the numerator of a rational number in lowest terms
real: the real part of a complex number

Methods

`as_integer_ratio`(/)	Return integer ratio.
`bit_count`(/)	Number of ones in the binary representation of the absolute value of self.
`bit_length`(/)	Number of bits necessary to represent self in binary.
`conjugate`	Returns self, the complex conjugate of any int.
`from_bytes`(/, bytes[, byteorder, signed])	Return the integer represented by the given array of bytes.
`to_bytes`(/[, length, byteorder, signed])	Return an array of bytes representing an integer.

BATCH = 0

X = 1

Y = 2

Z = 3

TYPE = 4

PARTICLE = 5

ENDPOINT = 6

class spine.constants.columns.PPNPredCol(value)[source]

Columns of the canonical PPN prediction tensor layout.

Attributes:

denominator: the denominator of a rational number in lowest terms
imag: the imaginary part of a complex number
numerator: the numerator of a rational number in lowest terms
real: the real part of a complex number

Methods

`as_integer_ratio`(/)	Return integer ratio.
`bit_count`(/)	Number of ones in the binary representation of the absolute value of self.
`bit_length`(/)	Number of bits necessary to represent self in binary.
`conjugate`	Returns self, the complex conjugate of any int.
`from_bytes`(/, bytes[, byteorder, signed])	Return the integer represented by the given array of bytes.
`to_bytes`(/[, length, byteorder, signed])	Return an array of bytes representing an integer.

RAW_DX = 0

RAW_DY = 1

RAW_DZ = 2

RAW_TYPE_0 = 3

RAW_TYPE_1 = 4

RAW_TYPE_2 = 5

RAW_TYPE_3 = 6

RAW_TYPE_4 = 7

RAW_POS_0 = 8

RAW_POS_1 = 9

SCORE_NEG = 4

SCORE_POS = 5

OCCUPANCY = 6

CLASS_0 = 7

CLASS_1 = 8

CLASS_2 = 9

CLASS_3 = 10

CLASS_4 = 11

SHAPE = 12

END_NEG = 13

END_POS = 14