dlpy.model.DataSpec

class dlpy.model.DataSpec(type_, layer, data=None, data_layer=None, nominals=None, numeric_nominal_parms=None, loss_scale_factor=None)

Data spec parameters.

Parameters

type_string

Specifies the type of the input data in the data spec. Valid Values: NUMERICNOMINAL, NUMNOM, TEXT, IMAGE, OBJECTDETECTION

layerstring

Specifies the name of the layer to data spec.

datalist, optional

Specifies the name of the columns/variables as the data, this might be input or output based on layer type.

data_layerstring, optional

Specifies the name of the input layer that binds to the output layer.

nominalslist, optional

Specifies the nominal input variables to use in the analysis.

numeric_nominal_parmsDataSpecNumNomOpts, optional

Specifies the parameters for the numeric nominal data spec inputs.

loss_scale_factordouble, optional

Specifies the value to scale the loss for a given task layer. This option only affects the task layers.

Returns

DataSpec

A dictionary of data spec parameters.

__init__(type_, layer, data=None, data_layer=None, nominals=None, numeric_nominal_parms=None, loss_scale_factor=None)

Initialize self. See help(type(self)) for accurate signature.

Methods

__init__(type_, layer[, data, data_layer, …])	Initialize self.
clear()
get(k[,d])
items()
keys()
pop(k[,d])	If key is not found, d is returned if given, otherwise KeyError is raised.
popitem()	as a 2-tuple; but raise KeyError if D is empty.
setdefault(k[,d])
update([E, ]**F)	If E present and has a .keys() method, does: for k in E: D[k] = E[k] If E present and lacks .keys() method, does: for (k, v) in E: D[k] = v In either case, this is followed by: for k, v in F.items(): D[k] = v
values()