Container for information returned by RegressionFeatures.constructFeatures.
Parallel to featureNames.
Parallel to featureNames. This is the sequence of functions that extract data from the input value.
Parallel to featureFunctions.
Parallel to featureFunctions.
A threshold dictating how many missing features to allow before making the prediction fail.
A threshold dictating how many missing features to allow before making the prediction fail. None means the threshold is ∞. If, when mapping featureFunctions over the input, the resulting sequence contains more than numMissingThreshold values that are empty Iterable values, then the Features.missingOk value returned by constructFeatures will be false; otherwise, it will be true.
Extract the features from the raw data by mapping featureFunctions over the input.
Extract the features from the raw data by mapping featureFunctions over the input. If numMissingThreshold is not None and the number of resulting empty Iterables exceeds the numMissingThreshold value, then the resulting Features.missingOk value is false; otherwise, it will be true. If Features.missingOk is false, then go back and check all feature functions for missing values and add findings to the Features.missing map. This Features.missing is a mapping from the feature specification to the list of variable names whose associated values are missing from the input.
raw input data of the model input type.
a Features instance with the following: 1 the transformed input vector 1 the map of bad features to the missing values in the raw data that were needed to compute the feature 1 whether the amount of missing data is acceptable to still continue
A helper trait for sparse regression models with String keys. This trait exposes the constructFeatures method which applies the featureFunctions to the input data and keeps track of missing features.