crispyn.normalizations

Functions

linear_normalization(matrix, types)	Normalize decision matrix using linear normalization method.
minmax_normalization(matrix, types)	Normalize decision matrix using minimum-maximum normalization method.
max_normalization(matrix, types)	Normalize decision matrix using maximum normalization method.
sum_normalization(matrix, types)	Normalize decision matrix using sum normalization method.
vector_normalization(matrix, types)	Normalize decision matrix using vector normalization method.

Module Contents

crispyn.normalizations.linear_normalization(matrix, types)

Normalize decision matrix using linear normalization method.

Parameters

matrixndarray

Decision matrix with m alternatives in rows and n criteria in columns

typesndarray

Criteria types. Profit criteria are represented by 1 and cost by -1.

Returns

ndarray

Normalized decision matrix

Examples

>>> nmatrix = linear_normalization(matrix, types)

crispyn.normalizations.minmax_normalization(matrix, types)

Normalize decision matrix using minimum-maximum normalization method.

Parameters

matrixndarray

Decision matrix with m alternatives in rows and n criteria in columns

typesndarray

Criteria types. Profit criteria are represented by 1 and cost by -1.

Returns

ndarray

Normalized decision matrix

Examples

>>> nmatrix = minmax_normalization(matrix, types)

crispyn.normalizations.max_normalization(matrix, types)

Normalize decision matrix using maximum normalization method.

Parameters

matrixndarray

Decision matrix with m alternatives in rows and n criteria in columns

typesndarray

Criteria types. Profit criteria are represented by 1 and cost by -1.

Returns

ndarray

Normalized decision matrix

Examples

>>> nmatrix = max_normalization(matrix, types)

crispyn.normalizations.sum_normalization(matrix, types)

Normalize decision matrix using sum normalization method.

Parameters

matrixndarray

Decision matrix with m alternatives in rows and n criteria in columns

typesndarray

Criteria types. Profit criteria are represented by 1 and cost by -1.

Returns

ndarray

Normalized decision matrix

Examples

>>> nmatrix = sum_normalization(matrix, types)

crispyn.normalizations.vector_normalization(matrix, types)

Normalize decision matrix using vector normalization method.

Parameters

matrixndarray

Decision matrix with m alternatives in rows and n criteria in columns

typesndarray

Criteria types. Profit criteria are represented by 1 and cost by -1.

Returns

ndarray

Normalized decision matrix

Examples

>>> nmatrix = vector_normalization(matrix, types)