pymccrgb.classification module

Utilities for updating classifcation of point clouds

pymccrgb.classification.make_sgd_pipeline(X_train, y_train, **kwargs)

Returns an sklearn Pipeline for SGD classification with an RBF kernel

Parameters:

X_train: array

An n x p array of training examples

y_train: array

An n x 1 array of training labels

n_components: int

The number of RBF components to use (Default: 100)

gamma: float

The gamma/variance parameter of the RBF kernel (Default: 0.01)

alpha: float

The penalty parameter of the SGD/SVM classifier (Default: 0.001)

max_iter: int

The maximum number of iterations to fit the classifier (Default: 100)

n_jobs: int

The number of jobs to use in fitting the classifier (Default: -1, Use all cores)

Any other keyword argument to sklearn.linear_model.SGDClassifier

Returns:

A trained pipeline composed of an RBF transformer and SGD classifier