Computation functions¶

histogram_blas_log_spec_edges¶

Compute a histogram with bins of constant width in log space, as determined from specified bin edges.

Parameters:

Name	Type	Description	Default
`user_bools`	`UserBools`	Contains the relevant boolean information used to compute the histogram.	required
`user_input`	`UserInput`	Contains the relevant numerical input information used to compute the histogram.	required

Returns:

Type	Description
`DArr \| None`	Bin counts for the histogram with constant-width bins in log space. None if the input array 'my_data' does not have any entries or if the specified 'my_bin_edges' or 'my_data' are None.

Raises:

Type	Description
`NotImplementedError`	If both empirical_probability and empirical_density are True. This is undefined behavior.

histogram_blas_spec_width¶

Individual function to be used to compute a constant-width histogram of a data set with a specified bin width.

Parameters:

Name	Type	Description	Default
`user_bools`	`UserBools`	Contains the relevant boolean information used to compute the histogram.	required
`user_input`	`UserInput`	Contains the relevant numerical input information used to compute the histogram.	required

Returns:

Type	Description
`DArr \| None`	Bin counts for the constant-width histogram. None if the input array 'my_data' does not have any entries or if the specified 'my_bw' or 'my_data' is None.

Raises:

Type	Description
`NotImplementedError`	If both empirical_probability and empirical_density are True. This is undefined behavior.

hogg_jackknife_likelihood_blas¶

Define how the jackknife likelihood is computed for the Hogg (2008) (constant) bin width selection procedure, using a BLAS-empowered implementation for a constant-width histogram.

Notes

Will select a constant bin width!

Parameters:

Name	Type	Description	Default
`user_bools`	`UserBools`	Contains boolean information to compute the histogram.	required
`hogg_bools`	`UserHoggBools`	Contains additional boolean information to compute the histogram.	required
`hogg_input`	`UserHoggInput`	Contains the necessary numerical input values to compute the histogram.	required

Returns:

Name	Type	Description
`hist_counts`	`DArr \| None`	The count or empirical probability or empirical density histogram that has maximized the jackknife likelihood.
`hist_edges`	`DArr \| None`	The bin edges of the histogram whose counts have maximized the jackknife likelihood.
`max_bin_width`	`DVar \| None`	The bin width for the jackknife likelihood is maximized.
`binning_params`	`dict \| None`	Contains the binning parameters, if requested ('return_binning_parameters' == True) and if the optimization was performed, otherwise, None.

hogg_jackknife_likelihood_blas_log¶

Define how the jackknife likelihood is computed for the Hogg (2008) (constant) bin width selection procedure, using a BLAS-empowered implementation for a constant-width-in-log-space histogram.

Notes

Will select a constant bin width!

Parameters:

Name	Type	Description	Default
`user_bools`	`UserBools`	Contains boolean information to compute the histogram.	required
`hogg_bools`	`UserHoggBools`	Contains additional boolean information to compute the histogram.	required
`hogg_input`	`UserHoggInput`	Contains the necessary numerical input values to compute the histogram.	required

Returns:

Name	Type	Description
`hist_counts`	`DArr \| None`	The count or empirical probability or empirical density histogram that has maximized the jackknife likelihood.
`hist_edges`	`DArr \| None`	The bin edges of the histogram whose counts have maximized the jackknife likelihood.
`max_bin_widths`	`DArr \| None`	The bin width array for which the jackknife likelihood is maximized.
`binning_params`	`dict \| None`	Contains the binning parameters, if requested ('return_binning_parameters' == True) and if the optimization was performed, otherwise, None.