|AHELP for CIAO 4.3 Sherpa v1||
Create a confidence plot of fit statistic vs. parameter value.
int_proj(par, [id, otherids=None, replot=False, fast=True, min=None, max=None, nloop=20, delv=None, fac=1, log=False, overplot=False, numcores])
The int_proj command creates a confidence plot of fit statistic as a function of parameter value, with dashed lines indicating the best fit statistic and best fit parameter value. The parameter value is varied on the computed grid until the fit statistic is increased by delta_S, which is a function of sigma (e.g., delta_S = 1 if the statistic is chi-square and fac = 1).
int_proj differs from int_unc ("ahelp int_unc") in that all other thawed parameters are allowed to float to new best-fit values, instead of being fixed to the initial best-fit values. This makes the plot created by int_proj a more accurate rendering of the projected shape of statistical hypersurface, but the computation is slower.
The computationally intensive projection function is parallelized to make use of multi-core systems (i.e., laptops or desktops with 2 or 4 cores) to provide significant improvements in efficiency compared to previous releases of Sherpa; the 'numcores' argument may be used to specify how the cores should be used when projection is run.
- par - source model parameter
- id, otherids - the id(s) of the dataset(s) to use; by default, uses all datasets; otherids=None
- replot - should the cached arrays be used in the plot? False (default)=do the calculation, True=redisplay the existing values
- fast - if True (the default), the method is automatically switched to a faster option to reduce the time per fit as projection visits many points in parameter space and performs a fit at each one. Chi-squared, Cash, and Cstat fits are switched to Levenberg-Marquardt (LMDIF). When the projection is done, the method is switched back to the original value.
- min - minimum grid boundary; default=None, which calculates the value from the covariance. This is always a linear quantity, regardless of the log setting.
- max - maximum grid boundary; default=None, which calculates the value from the covariance. This is always a linear quantity, regardless of the log setting.
- nloop - bin size for calculating the step size (delv); default=20
- delv - step size; default=None, which calculates the value using the min, max, and nloop values
- fac - the number of sigma (i.e., the change in statistic) for the plot; default=1
- log - use log space for the grid interval? default=False
- overplot - should the new plot be overlaid in the plotting window? False (default)=clear the window, True=overplot on any existing plots
- numcores - number of cores to use in parallelization; default is to use all cores available (2 or 4)
The calculated values, such as the grid min and max, can be retrieved with get_int_proj ("ahelp get_int_proj").
The plot is displayed in a ChIPS plotting window. If there is no plotting window open, one is created. If a plotting window exists, the overplot parameter value determines whether the new plot is overlaid on any existing plots in the window or if the window is cleared before the plot is drawn.
ChIPS commands may be used within Sherpa to modify plot characteristics and create hardcopies; refer to the ChIPS website for information.
sherpa> int_proj(p1.gamma, id=1)
Run int_proj on the parameter p1.gamma from dataset 1.
sherpa> int_proj(const.c0, id="bkg")
Run int_proj for the parameter const.c0 in the dataset "bkg".
sherpa> int_proj(p1.gamma, 1, [2,3])
int_proj is run for parameter p1.gamma for datasets 1, 2, and 3.
sherpa> int_proj(p1.gamma, min=2.0, max=2.5)
Manually set the grid limits to 2.0 (lower bound) and 2.5 (upper bound) before running int_proj for p1.gamma.
sherpa> int_proj(src1.c2, log=True)
Use a log grid when running int_proj on the parameter src1.c2.
sherpa> int_proj(p1.gamma, overplot=True)
Run int_proj on p1.gamma, overlaying the results on any existing plot.
The plot produced by the function int_proj() now includes dashed lines indicating the best fit statistic and best fit parameter value. The int_proj()function has a new argument 'numcores' to specify how many cores on a user's system should be utilized when the computationally intensive projection function is run.
See the bugs pages on the Sherpa website for an up-to-date listing of known bugs.