Currently this method works only on data that fits in local memory.
Currently this method works only on data that fits in local memory. Hard limit of up to ~4B bytes of feature data due to max Java array length
Solves multi-class LDA via Eigenvector decomposition
"multi-class Linear Discriminant Analysis" or "Multiple Discriminant Analysis" by C. R. Rao in 1948 (The utilization of multiple measurements in problems of biological classification) http://www.jstor.org/discover/10.2307/2983775?uid=3739560&uid=2&uid=4&uid=3739256&sid=21106766791933
Python implementation reference at: http://sebastianraschka.com/Articles/2014_python_lda.html
to train on.
Input class labels.
A PipelineNode which can be called on new data.
Constructs a pipeline that fits this label estimator to training data and labels, then applies the resultant transformer to the Pipeline input.
Constructs a pipeline that fits this label estimator to training data and labels, then applies the resultant transformer to the Pipeline input.
The training data
The training labels
A pipeline that fits this label estimator and applies the result to inputs.
Constructs a pipeline that fits this label estimator to training data and labels, then applies the resultant transformer to the Pipeline input.
Constructs a pipeline that fits this label estimator to training data and labels, then applies the resultant transformer to the Pipeline input.
The training data
The training labels
A pipeline that fits this label estimator and applies the result to inputs.
Constructs a pipeline that fits this label estimator to training data and labels, then applies the resultant transformer to the Pipeline input.
Constructs a pipeline that fits this label estimator to training data and labels, then applies the resultant transformer to the Pipeline input.
The training data
The training labels
A pipeline that fits this label estimator and applies the result to inputs.
Constructs a pipeline that fits this label estimator to training data and labels, then applies the resultant transformer to the Pipeline input.
Constructs a pipeline that fits this label estimator to training data and labels, then applies the resultant transformer to the Pipeline input.
The training data
The training labels
A pipeline that fits this label estimator and applies the result to inputs.
An Estimator that fits Linear Discriminant Analysis (currently not calculated in a distributed fashion), and returns a transformer that projects into the new space
Solves multi-class LDA via Eigenvector decomposition