PDF_Distance¶
- class turbustat.statistics.PDF_Distance(img1, img2, min_val1=-inf, min_val2=-inf, do_fit=True, normalization_type=None, nbins=None, weights1=None, weights2=None, bin_min=None, bin_max=None)[source]¶
Bases:
object
Calculate the distance between two arrays using their PDFs.
Note
Pre-computed
PDF
classes cannot be passed toPDF_Distance
as the data need to be normalized and the PDFs should use the same set of histogram bins.- Parameters:
- img1numpy.ndarray or astropy.io.fits.PrimaryHDU or astropy.io.fits.ImageHDU or spectral_cube.Projection or spectral_cube.Slice or SpectralCube
Array (1-3D).
- img2numpy.ndarray or astropy.io.fits.PrimaryHDU or astropy.io.fits.ImageHDU or spectral_cube.Projection or spectral_cube.Slice or SpectralCube
Array (1-3D).
- min_val1float, optional
Minimum value to keep in img1
- min_val2float, optional
Minimum value to keep in img2
- do_fitbool, optional
Enables fitting a lognormal distribution to each data set.
- normalization_type{“normalize”, “normalize_by_mean”}, optional
See
data_normalization
.- nbinsint, optional
Manually set the number of bins to use for creating the PDFs.
- weights1numpy.ndarray or astropy.io.fits.PrimaryHDU or astropy.io.fits.ImageHDU or spectral_cube.Projection or spectral_cube.Slice or SpectralCube, optional
Weights to be used with img1
- weights2numpy.ndarray or astropy.io.fits.PrimaryHDU or astropy.io.fits.ImageHDU or spectral_cube.Projection or spectral_cube.Slice or SpectralCube, optional
Weights to be used with img2
- bin_minfloat, optional
Minimum value to use for the histogram bins after normalization is applied.
- bin_maxfloat, optional
Maximum value to use for the histogram bins after normalization is applied.
Methods Summary
Compute the distance using the Anderson-Darling Test.
Computes the Hellinger Distance between the two PDFs.
Compute the distance using the KS Test.
Compute the combined t-statistic for the difference in the widths of a lognormal distribution.
distance_metric
([statistic, verbose, ...])Calculate the distance.
Methods Documentation
- compute_lognormal_distance()[source]¶
Compute the combined t-statistic for the difference in the widths of a lognormal distribution.
- distance_metric(statistic='all', verbose=False, plot_kwargs1={'color': 'b', 'label': '1', 'marker': 'D'}, plot_kwargs2={'color': 'g', 'label': '2', 'marker': 'o'}, save_name=None)[source]¶
Calculate the distance. NOTE: The data are standardized before comparing to ensure the distance is calculated on the same scales.
- Parameters:
- statistic‘all’, ‘hellinger’, ‘ks’, ‘lognormal’
Which measure of distance to use.
- labelstuple, optional
Sets the labels in the output plot.
- verbosebool, optional
Enables plotting.
- plot_kwargs1dict, optional
Pass kwargs to
plot
fordataset1
.- plot_kwargs2dict, optional
Pass kwargs to
plot
fordataset2
.- save_namestr,optional
Save the figure when a file name is given.