data.Dataset

data.Dataset()

Wrapper around a C++ class that stores all of the non-outcome data used in stochtree. This includes:

1. Features used for partitioning (also referred to as “covariates” in many places in these docs).
2. Basis vectors used to define non-constant leaf models. This is optional but may be included via the add_basis method.
3. Variance weights used to define heteroskedastic or otherwise weighted models. This is optional but may be included via the add_variance_weights method.

Methods

Name	Description
add_covariates	Add covariates to a dataset
add_basis	Add basis matrix to a dataset
update_basis	Update basis matrix in a dataset. Allows users to build an ensemble whose leaves
add_variance_weights	Add variance weights to a dataset
update_variance_weights	Update variance weights in a dataset. Allows users to build an ensemble that depends on
num_observations	Query the number of observations in a dataset
num_covariates	Query the number of covariates (features) in a dataset
num_basis	Query the dimension of the basis vector in a dataset
get_covariates	Return the covariates in a Dataset as a numpy array
get_basis	Return the bases in a Dataset as a numpy array
get_variance_weights	Return the variance weights in a Dataset as a numpy array
has_basis	Whether or not a dataset has a basis vector (for leaf regression)
has_variance_weights	Whether or not a dataset has variance weights
add_auxiliary_dimension	Add an auxiliary data dimension to the dataset
set_auxiliary_data_value	Set a value in the auxiliary data
get_auxiliary_data_value	Get a value from the auxiliary data
get_auxiliary_data_vector	Get an auxiliary data vector as a numpy array

add_covariates

data.Dataset.add_covariates(covariates)

Add covariates to a dataset

Parameters

Name	Type	Description	Default
covariates	np.array	Numpy array of covariates. If data contain categorical, string, time series, or other columns in a dataframe, please first preprocess using the CovariateTransformer.	required

add_basis

data.Dataset.add_basis(basis)

Add basis matrix to a dataset

Parameters

Name	Type	Description	Default
basis	np.array	Numpy array of basis vectors.	required

update_basis

data.Dataset.update_basis(basis)

Update basis matrix in a dataset. Allows users to build an ensemble whose leaves regress on bases that are updated throughout the sampler.

Parameters

Name	Type	Description	Default
basis	np.array	Numpy array of basis vectors.	required

add_variance_weights

data.Dataset.add_variance_weights(variance_weights)

Add variance weights to a dataset

Parameters

Name	Type	Description	Default
variance_weights	np.array	Univariate numpy array of variance weights.	required

update_variance_weights

data.Dataset.update_variance_weights(variance_weights, exponentiate=False)

Update variance weights in a dataset. Allows users to build an ensemble that depends on variance weights that are updated throughout the sampler.

Parameters

Name	Type	Description	Default
variance_weights	np.array	Univariate numpy array of variance weights.	required
exponentiate	bool	Whether to exponentiate the variance weights before storing them in the dataset.	False

num_observations

data.Dataset.num_observations()

Query the number of observations in a dataset

Returns

Name	Type	Description
	int	Number of observations in the dataset

num_covariates

data.Dataset.num_covariates()

Query the number of covariates (features) in a dataset

Returns

Name	Type	Description
	int	Number of covariates in the dataset

num_basis

data.Dataset.num_basis()

Query the dimension of the basis vector in a dataset

Returns

Name	Type	Description
	int	Dimension of the basis vector in the dataset, returning 0 if the dataset does not have a basis

get_covariates

data.Dataset.get_covariates()

Return the covariates in a Dataset as a numpy array

Returns

Name	Type	Description
	np.array	Covariate data

get_basis

data.Dataset.get_basis()

Return the bases in a Dataset as a numpy array

Returns

Name	Type	Description
	np.array	Basis data

get_variance_weights

data.Dataset.get_variance_weights()

Return the variance weights in a Dataset as a numpy array

Returns

Name	Type	Description
	np.array	Variance weights data

has_basis

data.Dataset.has_basis()

Whether or not a dataset has a basis vector (for leaf regression)

Returns

Name	Type	Description
	bool	True if the dataset has a basis, False otherwise

has_variance_weights

data.Dataset.has_variance_weights()

Whether or not a dataset has variance weights

Returns

Name	Type	Description
	bool	True if the dataset has variance weights, False otherwise

add_auxiliary_dimension

data.Dataset.add_auxiliary_dimension(dim_size)

Add an auxiliary data dimension to the dataset

Parameters

Name	Type	Description	Default
dim_size	int	Number of elements in the new auxiliary dimension	required

set_auxiliary_data_value

data.Dataset.set_auxiliary_data_value(dim_idx, element_idx, value)

Set a value in the auxiliary data

Parameters

Name	Type	Description	Default
dim_idx	int	Index of the auxiliary dimension	required
element_idx	int	Index of the element within the dimension	required
value	float	Value to set	required

get_auxiliary_data_value

data.Dataset.get_auxiliary_data_value(dim_idx, element_idx)

Get a value from the auxiliary data

Parameters

Name	Type	Description	Default
dim_idx	int	Index of the auxiliary dimension	required
element_idx	int	Index of the element within the dimension	required

Returns

Name	Type	Description
	float	The auxiliary data value

get_auxiliary_data_vector

data.Dataset.get_auxiliary_data_vector(dim_idx)

Get an auxiliary data vector as a numpy array

Parameters

Name	Type	Description	Default
dim_idx	int	Index of the auxiliary dimension	required

Returns

Name	Type	Description
	np.array	The auxiliary data vector