pasteur.attribute.StratifiedValue

class pasteur.attribute.StratifiedValue(name, head, common=None, ignore_nan=False)

A version of CategoricalValue which uses a Stratification to represent the domain knowledge of the Value.

Each unique value is mapped to a tree with nodes where the child order matters. By traversing the tree in DFS, each leaf is mapped to an integer.

Attributes

domain
height	Returns the maximum height of this value.
ignore_nan
name

Methods

downsample(value, height)	Receives an array named value and downsamples it based on the provided height, by grouping certain values together.
get_domain(height)	Returns the domain of the attribute in the given height.
get_domain_multiple(heights, vals)
get_human_readable()	Returns a list of human readable values for each discrete value.
get_mapping(height)	Returns a numpy array that associates discrete values with groups at the given height.
get_mapping_multiple(heights, common, vals)
get_naive_mapping_multiple(heights, common, vals)
is_ordinal()	Returns whether this value is ordinal, other than for the elements it shares in common with the other attributes.
prefix_rename(prefix)
rename(name[, name_cnt])
replace(**kwargs)
select_height()
upsample(value, height[, deterministic])	Does the opposite of downsample.

property domain

downsample(value, height)

Receives an array named value and downsamples it based on the provided height, by grouping certain values together. The proper implementation is provided by pasteur.hierarchy.

get_domain(height)

Returns the domain of the attribute in the given height.

static get_domain_multiple(heights, vals)

get_human_readable()

Returns a list of human readable values for each discrete value.

Return type:

list[str]

get_mapping(height)

Returns a numpy array that associates discrete values with groups at the given height.

static get_mapping_multiple(heights, common, vals)

Return type:

ndarray

static get_naive_mapping_multiple(heights, common, vals)

property height

Returns the maximum height of this value.

ignore_nan: bool

is_ordinal()

Returns whether this value is ordinal, other than for the elements it shares in common with the other attributes.

Return type:

bool

name: str

prefix_rename(prefix)

Return type:

Value

rename(name, name_cnt=None)

Return type:

Value

replace(**kwargs)

select_height()

Return type:

int

upsample(value, height, deterministic=True)

Does the opposite of downsample. If deterministic is True, for each group at a given height one of its values is chosen arbitrarily to represent all children of the group.

If deterministic is False, the group is sampled based on this Value’s histogram (not implemented in this class; see pasteur.hierarchy).