HiddenMarkovModel¶

lumicks.pylake.HiddenMarkovModel

class HiddenMarkovModel(data, n_states, *, tol=0.001, max_iter=250, initial_guess=None)¶

A Hidden Markov Model describing hidden state occupancy and state transitions of observed time series data (force, fluorescence, etc.)

A detailed description of the model properties and training algorithms can be found in [1].

Warning

This is early access alpha functionality. While usable, this has not yet been tested in a large number of different scenarios. The API can still be subject to change without any prior deprecation notice! If you use this functionality keep a close eye on the changelog for any changes that may affect your analysis.

Parameters:

data (numpy.ndarray | Slice) – Data array used for model training.
n_states (int) – The number of hidden states in the model.
tol (float) – The tolerance for training convergence.
max_iter (int) – The maximum number of iterations to perform.
initial_guess (HiddenMarkovModel | GaussianMixtureModel | None) – Initial guess for the observation model parameters.

References

emission_path(trace)¶

Calculate the emission path for a given data trace.

Parameters:: trace (Slice) – Channel data to determine path.
Returns:: emission_path – Estimated emission path
Return type:: Slice

extract_dwell_times(trace, *, exclude_ambiguous_dwells=True)¶

Calculate lists of dwelltimes for each state in a time-ordered state path array.

Parameters:

trace (Slice) – Channel data to be analyzed.
exclude_ambiguous_dwells (bool) – Determines whether to exclude dwelltimes which are not exactly determined. If True, the first and last dwells are not used in the analysis, since the exact start/stop times of these events are not definitively known.

Returns:

Dictionary of all dwell times (in seconds) for each state. Keys are state labels.

Return type:

dict

hist(trace, n_bins=100, plot_kwargs=None, hist_kwargs=None)¶

Plot a histogram of the trace data overlaid with the model state path.

Parameters:

trace (Slice) – Data object to histogram.
n_bins (int) – Number of histogram bins.
plot_kwargs (Optional[dict]) – Plotting keyword arguments passed to the state path line plot.
hist_kwargs (Optional[dict]) – Plotting keyword arguments passed to the histogram plot.

plot(trace, *, trace_kwargs=None, label_kwargs=None)¶

Plot a histogram of the trace data with data points classified in states.

Parameters:

trace (Slice) – Data object to histogram.
trace_kwargs (Optional[dict]) – Plotting keyword arguments passed to the data line plot.
label_kwargs (Optional[dict]) – Plotting keyword arguments passed to the state labels plot.

plot_path(trace, *, trace_kwargs=None, path_kwargs=None)¶

Plot a histogram of the trace data overlaid with the model path.

Parameters:

trace (Slice) – Data object to histogram.
trace_kwargs (Optional[dict]) – Plotting keyword arguments passed to the data line plot.
path_kwargs (Optional[dict]) – Plotting keyword arguments passed to the path line plot.

state_path(trace)¶

Calculate the state path for a given data trace.

Parameters:: trace (Slice) – Channel data to determine path.
Returns:: state_path – Estimated state path
Return type:: Slice

property fit_info: PopulationFitInfo¶: Information about the model training exit conditions.

property initial_state_probability: ndarray¶: Model initial state probability.

property means: ndarray¶: Model state means.

property std: ndarray¶: Model state standard deviations.

property transition_matrix: ndarray¶

Model state transition matrix.

Element i, j gives the probability of transitioning from state i at time point t to state j at time point t+1.

property variances: ndarray¶: Model state variances.