Transform a dataset into parameter estimates for a general linear model.
This is a univariate measure were the model is fitted independently to each input feature.
The GLM design matrix is created from two different source: a) sample attributes of the input dataset, and b) common regressors stored in the mapper itself upon instantiation. The order of the design matrix columns is as follows: First regressors from the dataset in the order in which their names were specified, then additional regressors stored in the mapper – appended in their given order, and, lastly, a potential constant column.
The nature of the values returned with the mapped dataset depends on the implementation details and parameter settings of the actual GLMMapper subclass. Most commonly, however, is a mapped dataset that has the same number of features as the input, and each sample contains the parameter estimates corresponding to a design matrix column.
This is a base class, thus is not supposed to be used directly by users which should use specific implementations suchas NiPyGLMMapper and StatsmodelsGLMMapper.
Notes
Available conditional attributes:
(Conditional attributes enabled by default suffixed with +)
Methods
forward(data) | Map data from input to output space. |
forward1(data) | Wrapper method to map single samples. |
generate(ds) | Yield processing results. |
get_postproc() | Returns the post-processing node or None. |
get_space() | Query the processing space name of this node. |
reset() | |
reverse(data) | Reverse-map data from output back into input space. |
reverse1(data) | Wrapper method to map single samples. |
set_postproc(node) | Assigns a post-processing node |
set_space(name) | Set the processing space name of this node. |
train(ds) | The default implementation calls _pretrain(), _train(), and finally _posttrain(). |
untrain() | Reverts changes in the state of this node caused by previous training |
Parameters : | regs : list
add_regs : tuple, optional
add_constant : bool, optional
return_design : bool, optional
return_model : bool, optional
enable_ca : None or list of str
disable_ca : None or list of str
auto_train : bool
force_train : bool
space : str, optional
pass_attr : str, list of str|tuple, optional
postproc : Node instance, optional
descr : str
|
---|
Methods
forward(data) | Map data from input to output space. |
forward1(data) | Wrapper method to map single samples. |
generate(ds) | Yield processing results. |
get_postproc() | Returns the post-processing node or None. |
get_space() | Query the processing space name of this node. |
reset() | |
reverse(data) | Reverse-map data from output back into input space. |
reverse1(data) | Wrapper method to map single samples. |
set_postproc(node) | Assigns a post-processing node |
set_space(name) | Set the processing space name of this node. |
train(ds) | The default implementation calls _pretrain(), _train(), and finally _posttrain(). |
untrain() | Reverts changes in the state of this node caused by previous training |