sciSOM.Plotting package

Submodules

sciSOM.Plotting.SOM_plots module

sciSOM.Plotting.SOM_plots.SOM_gird_avg_wavefrom_per_cell(input_data, weight_cube, output_img_name='avg_waveform.png', save_fig=False, is_struct_array=True)[source]

Generates image of the average waveform for each cell in the SOM grid.

This function take in a nunr file from NeuroScope and converts it into a useful format to us Then it uses the data in the nunr file to identify which data samples belong to each PE Finally it takes this data and plots it such that we can overlay any data we want.

Parameters:

  • input_data (ndarray) – waveforms (peaks, peaklets)

  • nunr_file_input (str) – text file output from neuroscope

  • grid_x_dim (int) – SOM x-dimension

  • grid_y_dim (int) – SOM y-dimension

  • x_dim_data_cube (int) – x-dimension of the input data cube for the SOM

  • output_img_name (str) – name of file to save the image to + path

  • is_struct_array (bool) – does the data need to be accessed as peaks[‘data’]?

  • weight_cube (ndarray)

  • save_fig (bool)

sciSOM.Plotting.SOM_plots.SOM_location_recall(weight_cube, normalized_data)[source]

Takes the data, the weight cube and the classification map and assignes each data point a label based on their cluster.

Parameters:

  • array_to_fill (np.ndarray) – structured array to fill with the classification

  • data_in_SOM_fmt (np.ndarray) – data to classify in the SOM format

  • weight_cube (ndarray) – SOM weight cube

  • reference_map (np.ndarray) – reference map for the SOM

  • normalized_data (ndarray)

Returns:

array_to_fill – structured array with the SOM classification added

Return type:

ndarray

sciSOM.Plotting.SOM_plots.calculate_density_matrix(weight_cube, dataset)[source]

Calculate density matrix for a given som weight cube and dataset.

This function is not working as intended, need to review it It is not acutally using the information of the u_matrix

Parameters:

  • weight_cube (ndarray) – SOM weight cube

  • dataset (ndarray) – Data in the same form given to the SOM as input for training

Returns:

density_matrix – The density matrix for the given dataset

Return type:

ndarray

sciSOM.Plotting.SOM_plots.calculate_distance_btw_adjacent_prototypes(weight_cube)[source]

Calculate the distance (fences) for each adjacent neuron in an SOM.

(Need to review this function, dont fully remember what is going on in the implementation)

Parameters:

weight_cube (ndarray) – The weight cube for the SOM

Returns:

distance_btw_proto – The distance matrix for neurons in the SOM

Return type:

np.ndarray

sciSOM.Plotting.SOM_plots.display_density_matrix(density_matrix)[source]

Display the density matrix as an image.

Parameters:

density_matrix (ndarray) – The density matrix to display

sciSOM.Plotting.SOM_plots.plot_SOM_gird_neurons(weight_cube)[source]

This function take in a nunr file from NeuroScope and converts it into a useful format to us Then it uses the data in the nunr file to identify which data samples belong to each PE Finally it takes this data and plots it such that we can overlay any data we want.

Return type:

None

Parameters:

weight_cubenp.ndarray

Weight cube after an SOM has been trained

Returns:

: None

type weight_cube:

ndarray

param weight_cube:

sciSOM.Plotting.SOM_plots.plot_mU_matrix(weight_cube, data, set_costum_min_max=False, fence_vmin=None, fence_vmax=None, density_vmin=None, density_vmax=None, log_density=False, fence_on=True)[source]

Plots the mU-matrix; defined here as the data density per cell and the lines between cells representing the distance between adjacent cells.

This implementation mimicks the major aspects of the mU-matrix in NueroScope (refer to [cite figure such as such of mU-matrix paper]).

Complete information on the NeuroScope implementation of the mU-matrix is given in respective NeuroScope documentation, available upon request from [Erzsébet Merényi](erzsebet@rice.edu| [

Prof. Merényi was not consulted on the implementation of sciSOM functions that intend to mimic NeuroScope functionalities of the same name, nor did she have opportunity to inspect proof of faithfulness to the same-name module in NeuroScope or correctness of the corresponding sciSOM code. Therefore, Dr. Merényi and the NeuroScope group take no responsibility for the likeness and the correctness of the functions implemented to mimic (partial) NeuroScope capabilities in sciSOM. Parameters: ——————- weight_cube : np.ndarray

Weight cube after an SOM has been trained

datanp.ndarray

Data used to train the SOM or data to be mapped to the SOM

set_costum_min_maxbool

If True, the user can set the vmin and vmax for fences

fence_vminfloat

Minimum value for the fences

fence_vmaxfloat

Maximum value for the fences

density_vminfloat

Minimum value for the density matrix (not implemented yet)

density_vmaxfloat

Maximum value for the density matrix (not implemented yet)

log_densitybool

If True applies a log to the density matrix calculation

fence_onbool

If False removes fences from mU matrix image

Returns:

: None

type weight_cube:

ndarray

param weight_cube:

type data:

ndarray

param data:

type set_costum_min_max:

bool

param set_costum_min_max:

type fence_vmin:

float

param fence_vmin:

type fence_vmax:

float

param fence_vmax:

type density_vmin:

float

param density_vmin:

type density_vmax:

float

param density_vmax:

type log_density:

bool

param log_density:

type fence_on:

bool

param fence_on:

sciSOM.Plotting.SOM_plots.rise_time_vs_area_SOM_clusters(data, colors, n_rows, n_cols)[source]

Plots the rise time vs area for each cluster in the SOM.

Takes in the data from peaklet level data using the SOM classification and outputs a grid of plots showing each cluster.

Parameters:

  • data (ndarray) – strudtured array with XENONnT data of data type peaks or peaklet

  • colors (Union[list, ndarray]) – list of colors used by the SOM

  • n_rows (int) – number of coulmns in grid with the plots

  • n_cols (int) – number of rows in grid with the plots

Module contents