lumicks.pylake.GaussianMixtureModel¶

class GaussianMixtureModel(data, n_states, init_method, n_init, tol, max_iter)¶

A wrapper around scikit-learn’s GMM.

This model accepts a 1D array as training data. The state parameters are sorted according to state mean in order to facilitate comparison of models with different number of states or trained on different datasets. As the current implementation is designed to specifically handle 1D data, model parameters are also returned as 1D arrays (np.squeeze() is applied to the results) so that users do not have to be concerned with the shape of the output results.

Parameters:

data : array-like: Data object used for model training.
n_states : int: The number of Gaussian components in the model.
init_method : ‘kmeans’ or ‘random’: The method used to initialize parameters.
n_init : int: The number of initializations to perform.
tol : float: The tolerance for training convergence.
max_iter : int: The maximum number of iterations to perform.

__init__(data, n_states, init_method, n_init, tol, max_iter)¶: Initialize self. See help(type(self)) for accurate signature.

Methods

`__init__`(data, n_states, init_method, …)	Initialize self.
`from_channel`(slc, n_states[, init_method, …])	Initialize a model from channel data.
`hist`(trace[, n_bins, plot_kwargs, hist_kwargs])	Plot a histogram of the data overlaid with the model PDF.
`label`(trace)	Label channel trace data as states.
`pdf`(x)	Probability Distribution Function (states as rows).
`plot`(trace[, trace_kwargs, label_kwargs])	Plot a time trace with each data point labeled with the state assignment.

Attributes

`aic`	Akaike Information Criterion.
`bic`	Bayesian Information Criterion.
`exit_flag`	Model optimization information.
`means`	Model state means.
`std`	Model state standard deviations.
`variances`	Model state variances.
`weights`	Model state weights.

classmethod from_channel(slc, n_states, init_method='kmeans', n_init=1, tol=0.001, max_iter=100)¶

Initialize a model from channel data.

Parameters:	slc : Slice Channel data used for model training. n_states : int The number of Gaussian components in the model. init_method : ‘kmeans’ or ‘random’ The method used to initialize parameters. n_init : int The number of initializations to perform. tol : float The tolerance for training convergence. max_iter : int The maximum number of iterations to perform.

hist(trace, n_bins=100, plot_kwargs={}, hist_kwargs={})¶

Plot a histogram of the data overlaid with the model PDF.

Parameters:	trace : Slice-like Data object to histogram. n_bins : int Number of histogram bins. plot_kwargs : dict Plotting keyword arguments passed to the PDF line plot. hist_kwargs : dict Plotting keyword arguments passed to the histogram plot.

label(trace)¶: Label channel trace data as states.

pdf(x)¶: Probability Distribution Function (states as rows).

plot(trace, trace_kwargs={}, label_kwargs={})¶

Plot a time trace with each data point labeled with the state assignment.

Parameters:	trace : Slice-like Data object to histogram. trace_kwargs : dict Plotting keyword arguments passed to the data line plot. label_kwargs : dict Plotting keyword arguments passed to the state labels plot.

aic¶: Akaike Information Criterion.

bic¶: Bayesian Information Criterion.

exit_flag¶: Model optimization information.

means¶: Model state means.

std¶: Model state standard deviations.

variances¶: Model state variances.

weights¶: Model state weights.