Merge pull request #1829 from pypeit/numpy_v2

Adds support for `numpy>=2.0.0`

doc/help/run_pypeit.rst

@@ -4,7 +4,7 @@
     usage: run_pypeit [-h] [-v VERBOSITY] [-r REDUX_PATH] [-m] [-s] [-o] [-c]
                       pypeit_file
     
-    ##  [1;37;42mPypeIt : The Python Spectroscopic Data Reduction Pipeline v1.16.1.dev84+g643dd5acc[0m
+    ##  [1;37;42mPypeIt : The Python Spectroscopic Data Reduction Pipeline v1.16.1.dev97+g2ab5988a9[0m
     ##  
     ##  Available spectrographs include:
     ##   bok_bc, gemini_flamingos1, gemini_flamingos2, gemini_gmos_north_e2v,

doc/releases/1.16.1dev.rst

@@ -13,6 +13,8 @@ Installation Changes
 Dependency Changes
 ------------------
 
+- Support added for numpy>=2.0.0; numpy<=2.0.0 should still be supported
+
 Functionality/Performance Improvements and Additions
 ----------------------------------------------------
 

presentations/py/users.py

@@ -0,0 +1,80 @@
+from matplotlib import pyplot, rc, dates
+import matplotlib.dates as mdates
+import matplotlib as mpl
+mpl.rcParams['font.family'] = 'stixgeneral'
+
+import numpy
+from IPython import embed
+
+def set_fontsize(ax, fsz):
+    """
+    Set the fontsize throughout an Axis
+
+    Args:
+        ax (Matplotlib Axis):
+        fsz (float): Font size
+
+    Returns:
+
+    """
+    for item in ([ax.title, ax.xaxis.label, ax.yaxis.label] +
+                 ax.get_xticklabels() + ax.get_yticklabels()):
+        item.set_fontsize(fsz)
+
+user_dates = ["2021-03-11", "2022-04-29", "2022-11-07", "2022-12-06", "2023-06-08", "2023-06-29", "2023-07-11", "2023-09-03", "2023-10-13", "2023-12-01", "2023-12-15", "2024-02-22", "2024-03-21", "2024-04-09", "2024-05-02", "2024-05-19", "2024-06-06", "2024-06-10"]
+user_dates = numpy.array([numpy.datetime64(date) for date in user_dates])
+user_number = numpy.array([125, 293, 390, 394, 477, 487, 506, 518, 531, 544, 551, 568, 579, 588, 596, 603, 616, 620])
+
+user_pred_dates = numpy.array([numpy.datetime64(date)
+                            for date in ["2024-06-10", "2024-12-31", "2025-12-31", "2026-12-31",
+                                         "2027-12-31"]])
+user_pred_num = numpy.array([620, 620+0.5*160, 620+1.5*160, 620+2.5*160, 620+3.5*160])
+
+
+cite_dates = ["2020-12-31", "2021-12-31", "2022-12-31", "2023-12-31", "2024-06-10"]
+cite_dates = numpy.array([numpy.datetime64(date) for date in cite_dates])
+cite_ref = numpy.cumsum([7, 24, 31, 56, 53])
+cite_all = numpy.cumsum([8, 25, 33, 68, 81])
+
+cite_pred_dates = numpy.array([numpy.datetime64(date)
+                            for date in ["2024-06-10", "2024-12-31", "2025-12-31", "2026-12-31", "2027-12-31"]])
+cite_pred_all = numpy.cumsum([8, 25, 33, 68, 81, numpy.sqrt(1.5)*81, 1.5*68, 1.5**2*68, 1.5**3*68])
+cite_pred_all = cite_pred_all[cite_all.size-1:]
+
+rc('font', size=14)
+
+w,h = pyplot.figaspect(1)
+fig = pyplot.figure(figsize=(1.9*w,1.5*h))
+
+ax = fig.add_axes([0.2, 0.2, 0.75, 0.75])
+ax.plot(user_dates, user_number, ls='-', color='k', label='Slack Users')
+ax.plot(user_pred_dates, user_pred_num, ls=':', color='k')
+ax.set_ylim([0,1400])
+ax.set_ylabel("Cumulative Usage Metric")
+ax.set_xlabel("Date")
+ax.xaxis.set_major_locator(dates.MonthLocator(bymonth=[1,7]))
+fig.autofmt_xdate()
+
+#axt = ax.twinx()
+#ax.plot(cite_dates, cite_ref, ls='--', color='0.5', label='All Cite')
+ax.plot(cite_dates, cite_all, ls='-', color='C0', label='Citations')
+ax.plot(cite_pred_dates, cite_pred_all, ls=':', color='C0')
+#axt.set_ylim([0,250])
+
+#ax.scatter(user_dates, user_number, marker='.', lw=0, s=200, color='k')
+#fig.canvas.print_figure('pypeit_users.pdf', bbox_inches='tight')
+
+ax.legend()
+
+ax.xaxis.set_major_locator(mdates.YearLocator())
+
+set_fontsize(ax, 16)
+
+
+outfile = "pypeit_users.png"
+pyplot.savefig(outfile, dpi=300)
+print(f"Saved: {outfile}")
+
+#pyplot.show()
+#fig.clear()
+#pyplot.close(fig)

pypeit/cache.py

@@ -63,13 +63,22 @@
 def git_branch():
     """
     Return the name/hash of the currently checked out branch
-
+    
     Returns:
-        :obj:`str`: Branch name or hash
+        :obj:`str`: Branch name or hash. Defaults to "develop" if PypeIt is not currently in a repository
+        or pygit2 is inot installed.
+    
     """
-    if Repository is None:
+    if Repository is not None:
+        try:
+            repo = Repository(resources.files('pypeit'))
+        except Exception as e:
+            # PypeIt not in a git repo
+            repo = None
+
+    if Repository is None or repo is None:
         return 'develop' if '.dev' in __version__ else __version__
-    repo = Repository(resources.files('pypeit'))
+
     return str(repo.head.target) if repo.head_is_detached else str(repo.head.shorthand)
 
 

pypeit/core/findobj_skymask.py

@@ -66,57 +66,68 @@ def create_skymask(sobjs, thismask, slit_left, slit_righ, box_rad_pix=None, trim
         global sky subtraction (True means the pixel is usable for sky
         subtraction, False means it should be masked when subtracting sky).
     """
+    # Number of objects
     nobj = len(sobjs)
-    ximg, _ = pixels.ximg_and_edgemask(slit_left, slit_righ, thismask, trim_edg=trim_edg)
-    # How many pixels wide is the slit at each Y?
-    xsize = slit_righ - slit_left
-    #nsamp = np.ceil(np.median(xsize)) # JFH Changed 07-07-19
-    nsamp = np.ceil(xsize.max())
+    if nobj == 0:
+        msgs.info('No objects were detected. The entire slit will be used for sky subtraction.')
+        return thismask[thismask]
 
-    # Objmask
+    # Compute the object mask
     skymask_objsnr = np.copy(thismask)
-    if nobj == 0:
-        msgs.info('No objects were detected. The entire slit will be used to determine the sky subtraction.')
-    else:
-        # Compute some inputs for the object mask
-        xtmp = (np.arange(nsamp) + 0.5)/nsamp
-        # threshold for object finding
-        for iobj in range(nobj):
-            # this will skip also sobjs with THRESHOLD=0, because are the same that have smash_snr=0.
-            if (sobjs[iobj].smash_snr != 0.) and (sobjs[iobj].smash_snr != None):
-                qobj = np.zeros_like(xtmp)
-                sep = np.abs(xtmp-sobjs[iobj].SPAT_FRACPOS)
-                sep_inc = sobjs[iobj].maskwidth/nsamp
-                close = sep <= sep_inc
-                # This is an analytical SNR profile with a Gaussian shape.
-                # JFH modified to use SNR here instead of smash peakflux. I believe that the 2.77 is supposed to be
-                # 2.355**2/2, i.e. the argument of a gaussian with sigma = FWHM/2.35
-                qobj[close] = sobjs[iobj].smash_snr * \
-                               np.exp(np.fmax(-2.77*(sep[close]*nsamp)**2/sobjs[iobj].FWHM**2, -9.0))
-                skymask_objsnr[thismask] &= np.interp(ximg[thismask], xtmp, qobj) < skymask_snr_thresh
-    # FWHM
+    # Create an image with pixel values equal to the fraction of the spatial
+    # position along the slit, ranging from 0 -> 1
+    ximg, _ = pixels.ximg_and_edgemask(slit_left, slit_righ, thismask, trim_edg=trim_edg)
+    # Maximum spatial width rounded up
+    nsamp = np.ceil(np.amax(slit_righ - slit_left))
+    # Fractional position within the maximum spatial width
+    xtmp = (np.arange(nsamp) + 0.5)/nsamp
+    # threshold for object finding
+    for iobj in range(nobj):
+        # this will skip also sobjs with THRESHOLD=0, because are the same that have smash_snr=0.
+        if sobjs[iobj].smash_snr is None or sobjs[iobj].smash_snr <= 0.:
+            continue
+        # Select pixels within the defined width of the object
+        sep = np.absolute(xtmp-sobjs[iobj].SPAT_FRACPOS)
+        sep_inc = sobjs[iobj].maskwidth/nsamp
+        close = sep <= sep_inc
+        # This is an analytical SNR profile with a Gaussian shape.
+        # JFH modified to use SNR here instead of smash peakflux. I believe that
+        # the 2.77 is supposed to be 2.355**2/2, i.e. the argument of a gaussian
+        # with sigma = FWHM/2.35
+        qobj = np.zeros_like(xtmp)
+        qobj[close] = sobjs[iobj].smash_snr * \
+                        np.exp(np.fmax(-2.77*(sep[close]*nsamp)**2/sobjs[iobj].FWHM**2, -9.0))
+        skymask_objsnr[thismask] &= np.interp(ximg[thismask], xtmp, qobj) < skymask_snr_thresh
+
+    # Compute the FWHM mask
     skymask_fwhm = np.copy(thismask)
-    if nobj > 0:
-        nspec, nspat = thismask.shape
-        # spatial position everywhere along image
-        spat_img = np.outer(np.ones(nspec, dtype=int),np.arange(nspat, dtype=int))
-        # Boxcar radius?
-        if box_rad_pix is not None:
-            msgs.info("Using boxcar radius for masking")
-        # Loop me
-        for iobj in range(nobj):
-            # Create a mask for the pixels that will contribute to the object
-            skymask_radius = box_rad_pix if box_rad_pix is not None else sobjs[iobj].FWHM
-            msgs.info(f"Masking around object {iobj+1} within a radius = {skymask_radius} pixels")
-            slit_img = np.outer(sobjs[iobj].TRACE_SPAT, np.ones(nspat))  # central trace replicated spatially
-            objmask_now = thismask & (spat_img > (slit_img - skymask_radius)) & (spat_img < (slit_img + skymask_radius))
-            skymask_fwhm &= np.invert(objmask_now)
-
-        # Check that we have not performed too much masking
-        if (np.sum(skymask_fwhm)/np.sum(thismask) < 0.10):
-            msgs.warn('More than 90% of  usable area on this slit would be masked and not used by global sky subtraction. '
-                      'Something is probably wrong with object finding for this slit. Not masking object for global sky subtraction.')
-            skymask_fwhm = np.copy(thismask)
+    nspec, nspat = thismask.shape
+    # spatial position everywhere along image
+#    spat_img = np.outer(np.ones(nspec, dtype=int),np.arange(nspat, dtype=int))
+    spat_img = np.tile(np.arange(nspat, dtype=int), (nspec,1))
+    # Boxcar radius?
+    if box_rad_pix is not None:
+        msgs.info("Using boxcar radius for masking")
+    # Loop me
+    for iobj in range(nobj):
+        # Create a mask for the pixels that will contribute to the object
+        skymask_radius = box_rad_pix if box_rad_pix is not None else sobjs[iobj].FWHM
+        msgs.info(f"Masking around object {iobj+1} within a radius = {skymask_radius} pixels")
+#        slit_img = np.outer(sobjs[iobj].TRACE_SPAT, np.ones(nspat))  # central trace replicated spatially
+        slit_img = np.tile(sobjs[iobj].TRACE_SPAT, (nspat,1)).T
+        objmask_now = thismask \
+                        & (spat_img > slit_img - skymask_radius) \
+                        & (spat_img < slit_img + skymask_radius)
+        skymask_fwhm &= np.logical_not(objmask_now)
+
+    # Check that we have not performed too much masking
+    # TODO: There is this hard-coded check here, and then there is a similar
+    # check in skysub.global_skysub.  Do we need both?
+    if np.sum(skymask_fwhm)/np.sum(thismask) < 0.10:
+        msgs.warn('More than 90% of  usable area on this slit would be masked and not used by '
+                  'global sky subtraction. Something is probably wrong with object finding for '
+                  'this slit. Not masking object for global sky subtraction.')
+        skymask_fwhm = np.copy(thismask)
 
     # Still have to make the skymask
     # # TODO -- Make sure this is right
@@ -135,8 +146,10 @@ def create_skymask(sobjs, thismask, slit_left, slit_righ, box_rad_pix=None, trim
     # computation from objs_in_slit is not necessarily that reliable and when large amounts of masking are performed
     # on narrow slits/orders, we have problems. We should revisit this after object finding is refactored since
     # maybe then the fwhm estimates will be more robust.
-    if box_rad_pix is None and np.all([sobj.smash_snr is not None for sobj in sobjs]) \
-            and np.all([sobj.smash_snr != 0. for sobj in sobjs]) and not np.all(skymask_objsnr == thismask):
+    if box_rad_pix is None \
+            and np.all([sobj.smash_snr is not None for sobj in sobjs]) \
+            and np.all([sobj.smash_snr != 0. for sobj in sobjs]) \
+            and not np.all(skymask_objsnr == thismask):
         # TODO This is a kludge until we refactor this routine. Basically mask design objects that are not auto-ID
         # always have smash_snr undefined. If there is a hybrid situation of auto-ID and maskdesign, the logic
         # here does not really make sense. Soution would be to compute thershold and smash_snr for all objects.

pypeit/core/flux_calib.py

@@ -411,7 +411,7 @@ def get_standard_spectrum(star_type=None, star_mag=None, ra=None, dec=None):
         # Pull star spectral model from archive
         msgs.info("Getting archival standard spectrum")
         # Grab closest standard within a tolerance
-        std_dict = find_standard_file(ra, dec)
+        std_dict = find_standard_file(ra, dec,to_pkg='symlink')
 
     elif (star_mag is not None) and (star_type is not None):
         ## using vega spectrum

pypeit/core/skysub.py

@@ -136,11 +136,14 @@ def global_skysub(image, ivar, tilts, thismask, slit_left, slit_righ, inmask=Non
         msgs.error("Type of inmask should be bool and is of type: {:}".format(inmask.dtype))
 
     # Sky pixels for fitting
-    gpm = thismask & (ivar > 0.0) & inmask & np.logical_not(edgmask) & np.isfinite(image) & np.isfinite(ivar)
+    gpm = thismask & (ivar > 0.0) & inmask & np.logical_not(edgmask) \
+            & np.isfinite(image) & np.isfinite(ivar)
     bad_pixel_frac = np.sum(thismask & np.logical_not(gpm))/np.sum(thismask)
     if bad_pixel_frac > max_mask_frac:
-        msgs.warn('This slit/order has {:5.3f}% of the pixels masked, which exceeds the threshold of {:f}%. '.format(100.0*bad_pixel_frac, 100.0*max_mask_frac)
-                  + msgs.newline() + 'There is likely a problem with this slit. Giving up on global sky-subtraction.')
+        msgs.warn(f'This slit/order has {100.0*bad_pixel_frac:.3f}% of the pixels masked, which '
+                  f'exceeds the threshold of {100.0*max_mask_frac:.3f}%.'
+                  + msgs.newline() + 'There is likely a problem with this slit. Giving up on '
+                  'global sky-subtraction.')
         return np.zeros(np.sum(thismask))
 
     # Sub arrays

pypeit/core/wavecal/autoid.py

@@ -3189,7 +3189,7 @@ def finalize_fit(self, detections):
             if self._outroot is not None:
                 # Write IDs
                 out_dict = dict(pix=use_tcent, IDs=self._all_patt_dict[str(slit)]['IDs'])
-                jdict = ltu.jsonify(out_dict)
+                jdict = utils.jsonify(out_dict)
                 ltu.savejson(self._outroot + slittxt + '.json', jdict, easy_to_read=True, overwrite=True)
                 msgs.info("Wrote: {:s}".format(self._outroot + slittxt + '.json'))
 

pypeit/find_objects.py

@@ -253,28 +253,29 @@ def create_skymask(self, sobjs_obj):
             subtraction.  True = usable for sky subtraction, False = should be
             masked when sky subtracting.
         """
-        # Masking options
-        boxcar_rad_pix = None
-
+        # Instantiate the mask
         skymask = np.ones_like(self.sciImg.image, dtype=bool)
-        gdslits = np.where(np.invert(self.reduce_bpm))[0]
-        if sobjs_obj.nobj > 0:
-            for slit_idx in gdslits:
-                slit_spat = self.slits.spat_id[slit_idx]
-                qa_title ="Generating skymask for slit # {:d}".format(slit_spat)
-                msgs.info(qa_title)
-                thismask = self.slitmask == slit_spat
-                this_sobjs = sobjs_obj.SLITID == slit_spat
-                # Boxcar mask?
-                if self.par['reduce']['skysub']['mask_by_boxcar']:
-                    boxcar_rad_pix = self.par['reduce']['extraction']['boxcar_radius'] / \
-                                     self.get_platescale(slitord_id=self.slits.slitord_id[slit_idx])
-                # Do it
-                skymask[thismask] = findobj_skymask.create_skymask(sobjs_obj[this_sobjs], thismask,
-                                                                   self.slits_left[:,slit_idx],
-                                                                   self.slits_right[:,slit_idx],
-                                                                   box_rad_pix=boxcar_rad_pix,
-                                                                   trim_edg=self.par['reduce']['findobj']['find_trim_edge'])
+        if sobjs_obj.nobj == 0:
+            # No objects found, so entire image contains sky
+            return skymask
+
+        # Build the mask for each slit
+        boxcar_rad_pix = None
+        gdslits = np.where(np.logical_not(self.reduce_bpm))[0]
+        for slit_idx in gdslits:
+            slit_spat = self.slits.spat_id[slit_idx]
+            msgs.info(f'Generating skymask for slit # {slit_spat}')
+            thismask = self.slitmask == slit_spat
+            this_sobjs = sobjs_obj.SLITID == slit_spat
+            # Boxcar mask?
+            if self.par['reduce']['skysub']['mask_by_boxcar']:
+                boxcar_rad_pix = self.par['reduce']['extraction']['boxcar_radius'] / \
+                                    self.get_platescale(slitord_id=self.slits.slitord_id[slit_idx])
+            # Do it
+            skymask[thismask] = findobj_skymask.create_skymask(
+                                    sobjs_obj[this_sobjs], thismask, self.slits_left[:,slit_idx],
+                                    self.slits_right[:,slit_idx], box_rad_pix=boxcar_rad_pix,
+                                    trim_edg=self.par['reduce']['findobj']['find_trim_edge'])
         # Return
         return skymask
 
@@ -592,6 +593,7 @@ def global_skysub(self, skymask=None, bkg_redux_sciimg=None,
                 pos_mask=not self.bkg_redux and not objs_not_masked,
                 max_mask_frac=self.par['reduce']['skysub']['max_mask_frac'],
                 show_fit=show_fit)
+
             # Mask if something went wrong
             if np.sum(global_sky[thismask]) == 0.:
                 msgs.warn("Bad fit to sky.  Rejecting slit: {:d}".format(slit_spat))

pypeit/images/buildimage.py

@@ -157,8 +157,8 @@ def construct_file_name(cls, calib_key, calib_dir=None, basename=None):
 
 
 def buildimage_fromlist(spectrograph, det, frame_par, file_list, bias=None, bpm=None, dark=None,
-                        scattlight=None, flatimages=None, maxiters=5, ignore_saturation=True, slits=None,
-                        mosaic=None, calib_dir=None, setup=None, calib_id=None):
+                        scattlight=None, flatimages=None, maxiters=5, ignore_saturation=True,
+                        slits=None, mosaic=None, calib_dir=None, setup=None, calib_id=None):
     """
     Perform basic image processing on a list of images and combine the results.
 
@@ -249,8 +249,8 @@ def buildimage_fromlist(spectrograph, det, frame_par, file_list, bias=None, bpm=
 
     # Do it
     combineImage = combineimage.CombineImage(spectrograph, det, frame_par['process'], file_list)
-    pypeitImage = combineImage.run(bias=bias, bpm=bpm, dark=dark, flatimages=flatimages, scattlight=scattlight,
-                                   sigma_clip=frame_par['process']['clip'],
+    pypeitImage = combineImage.run(bias=bias, bpm=bpm, dark=dark, flatimages=flatimages,
+                                   scattlight=scattlight, sigma_clip=frame_par['process']['clip'],
                                    sigrej=frame_par['process']['comb_sigrej'],
                                    maxiters=maxiters, ignore_saturation=ignore_saturation,
                                    slits=slits, combine_method=frame_par['process']['combine'],

pypeit/metadata.py

@@ -747,7 +747,7 @@ def unique_configurations(self, force=False, copy=False, rm_none=False):
         ignore_frames, ignore_indx = self.ignore_frames()
         # Find the indices of the frames not to ignore
         indx = np.arange(len(self.table))
-        indx = indx[np.logical_not(np.in1d(indx, ignore_indx))]
+        indx = indx[np.logical_not(np.isin(indx, ignore_indx))]
 
         if len(indx) == 0:
             msgs.error('No frames to use to define configurations!')

pypeit/par/parset.py

@@ -345,7 +345,7 @@ def _data_table_string(data_table, delimeter='print'):
         return '\n'.join(row_string)+'\n'
 
     @staticmethod
-    def _data_string(data, use_repr=True, verbatim=False):
+    def _data_string(data, use_repr=False, verbatim=False):
         """
         Convert a single datum into a string