KShape¶

class mesmerize.plotting.KShapeWidget(parent=None)[source]¶

Bases: PyQt5.QtWidgets.QMainWindow, mesmerize.plotting.widgets.base.BasePlotWidget

User-end KShape widget

sig_output_changed¶: Emits output Transmission containing cluster labels

drop_opts = None¶: Unused by this plot widget

property input_arrays¶

The input arrays for clustering

Returns: 2D array, shape is [num_samples, padded_peak_curve_length]
Return type: np.ndarray

property ks¶: tslearn KShape object

property n_clusters¶

Number of clusters

Return type: int

property train_data¶

The training data for clustering

Returns: Training data as a 2D array, shape is [n_samples, padded_curve_length]
Return type: np.ndarray

property y_pred¶

Predicted cluster labels after the model converges

Returns: 1D array of cluster labels that correspond to the input_data
Return type: np.ndarray

property cluster_centers¶

Cluster centroids

Returns: 2D array, shape is [n_clusters, centroid_array]
Return type: np.ndarray

property cluster_means¶

The cluster means

Returns: 2D array, shape is [cluster_label, mean_array]
Return type: np.ndarray

property params¶

Parameters dict.

Return type: dict

set_input(transmission: mesmerize.analysis.data_types.Transmission)[source]¶

Set the input Transmission for the widget

Parameters: transmission – Input Transmission

pad_input_data(a: numpy.ndarray, method: str = 'random') → numpy.ndarray[source]¶

Pad all the input arrays so that are of the same length. The length is determined by the largest input array. The padding value for each input array is the minimum value in that array.

Padding for each input array is either done after the array’s last index to fill up to the length of the largest input array (method ‘fill-size’) or the padding is randomly flanked to the input array (method ‘random) for easier visualization.

Parameters

a – 1D array of input arrays where each element is a sample array
method – ‘fill-size’ or ‘random’

Returns

2D array of the padded arrays in the rows

start_process(*args, **kwargs)[source]¶: Start the the KShape clustering in a QProcess

property transmission¶

The input transmission

Return type: Transmission

class mesmerize.plotting.widgets.kshape.widget.KShapeMeansPlot(parent)[source]¶

Bases: mesmerize.pyqtgraphCore.widgets.MatplotlibWidget.MatplotlibWidget

Means plots grouped by cluster membership

axs¶: array of axis objects used for drawing the means plots, shape is [nrows, ncols]

set_plots(input_arrays: numpy.ndarray, n_clusters: int, y_pred: numpy.ndarray, xzero_pos: str, error_band)[source]¶

Set the subplots

Parameters

input_arrays – padded input arrays (2D), shape is [num_samples, padded_peak_curve_length]
n_clusters – number of clusters
y_pred – cluster predictions (labels)
xzero_pos – set the zero position as the ‘zero’ position of the input array or the ‘maxima’ of the input array
error_band – Type of error band to show, one of either ‘ci’ or ‘std’

class mesmerize.plotting.widgets.kshape.widget.KShapePlot(parent)[source]¶

Bases: PyQt5.QtWidgets.QDockWidget

Curves plots, showing a sample of individual curves from a single cluster

ax¶: The Axes object for this plot

plot¶: MatplotlibWidget() instance