mbi.Dataset

class mbi.Dataset(data: ArrayLike | dict[str, ArrayLike], domain: Domain, weights: ndarray | None = None)[source]

Bases: object

create a Dataset object

Parameters:

data – a numpy array (n x d) or a dictionary of 1d arrays (length n), keyed by attribute.
domain – a domain object
weight – weight for each row

Methods

`__init__`	create a Dataset object
`compress`	Compresses the dataset by mapping domain elements to a smaller domain.
`datavector`	return the database in vector-of-counts form
`decompress`	Decompresses the dataset by reversing the mapping.
`drop`	Returns a new Dataset with the specified columns removed.
`load`	Load data into a dataset object
`project`	project dataset onto a subset of columns
`supports`
`synthetic`	Generate synthetic data conforming to the given domain
`to_dict`

Attributes

`df`
`records`	Returns the number of records (rows) in the dataset.

to_dict() → dict[str, ndarray][source]

property df

static synthetic(domain: Domain, N: int) → Dataset[source]

Generate synthetic data conforming to the given domain

Parameters:

domain – The domain object
N – the number of individuals

static load(path: str, domain: str | Domain) → Dataset[source]

Load data into a dataset object

Parameters:

path – path to csv file
domain – path to json file encoding the domain information

project(cols: int | str | Sequence[str] | Sequence[int]) → Factor[source]: project dataset onto a subset of columns

supports(cols: str | Sequence[str]) → bool[source]

drop(cols: Sequence[str]) → Factor[source]: Returns a new Dataset with the specified columns removed.

property records: int: Returns the number of records (rows) in the dataset.

datavector(flatten: bool = True) → ndarray[tuple[Any, ...], dtype[_ScalarT]][source]: return the database in vector-of-counts form

compress(mapping: dict[str, ndarray]) → Dataset[source]

Compresses the dataset by mapping domain elements to a smaller domain.

Parameters:: mapping – A dictionary where keys are attribute names and values are 1D arrays. mapping[attr][i] gives the new value for original value i.
Returns:: A new Dataset with transformed values and updated domain.

decompress(mapping: dict[str, ndarray]) → Dataset[source]

Decompresses the dataset by reversing the mapping. Since the mapping is surjective, the reverse mapping is one-to-many. We sample uniformly from the possible original values.

Parameters:: mapping – The same mapping dictionary used for compression.
Returns:: A new Dataset with restored domain size and sampled values.