arvi 0.2.4__tar.gz → 0.3.0__tar.gz

{arvi-0.2.4 → arvi-0.3.0}/.github/workflows/docs-gh-pages.yml

@@ -26,13 +26,13 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         
       - name: Setup Pages
         uses: actions/configure-pages@v5
 
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: "3.10"
   

{arvi-0.2.4 → arvi-0.3.0}/.github/workflows/install.yml

@@ -16,9 +16,9 @@ jobs:
         python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
 
     steps:
-    - uses: actions/checkout@v4
+    - uses: actions/checkout@v6
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v5
+      uses: actions/setup-python@v6
       with:
         python-version: ${{ matrix.python-version }}
 

{arvi-0.2.4 → arvi-0.3.0}/.github/workflows/python-publish.yml

@@ -22,9 +22,9 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-    - uses: actions/checkout@v4
+    - uses: actions/checkout@v6
     - name: Set up Python
-      uses: actions/setup-python@v5
+      uses: actions/setup-python@v6
       with:
         python-version: '3.x'
     - name: Install dependencies
@@ -34,7 +34,7 @@ jobs:
     - name: Build package
       run: python -m build
     - name: Publish package
-      uses: pypa/gh-action-pypi-publish@27b31702a0e7fc50959f5ad993c78deac1bdfc29
+      uses: pypa/gh-action-pypi-publish@ed0c53931b1dc9bd32cbe73a98c7f6766f8a527e
       with:
         user: __token__
         password: ${{ secrets.PYPI_API_TOKEN }}

{arvi-0.2.4/arvi.egg-info → arvi-0.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: arvi
-Version: 0.2.4
+Version: 0.3.0
 Summary: The Automated RV Inspector
 Author-email: João Faria <joao.faria@unige.ch>
 License: MIT

{arvi-0.2.4 → arvi-0.3.0}/arvi/__init__.py

@@ -20,6 +20,7 @@ def __getattr__(name: str):
     if name in (
         '_ipython_canary_method_should_not_exist_',
         '_ipython_display_',
+        '__custom_documentations__',
         '_repr_mimebundle_',
         '__wrapped__'
     ):

{arvi-0.2.4 → arvi-0.3.0}/arvi/dace_wrapper.py

@@ -2,15 +2,15 @@ import os
 import sys
 import tarfile
 import collections
-from functools import lru_cache
+from functools import lru_cache, partial
 from itertools import islice
 import numpy as np
 
 from .setup_logger import setup_logger
-from .utils import create_directory, all_logging_disabled, stdout_disabled, tqdm
+from .utils import create_directory, all_logging_disabled, stdout_disabled, timer, tqdm
 
 
-def load_spectroscopy(user=None):
+def load_spectroscopy(user=None, verbose=True):
     logger = setup_logger()
     with all_logging_disabled():
         from dace_query.spectroscopy import SpectroscopyClass, Spectroscopy as default_Spectroscopy
@@ -19,7 +19,8 @@ def load_spectroscopy(user=None):
     from .config import config
     # requesting as public
     if config.request_as_public:
-        logger.warning('requesting DACE data as public')
+        if verbose:
+            logger.warning('requesting DACE data as public')
         with all_logging_disabled():
             dace = DaceClass(dace_rc_config_path='none')
         return SpectroscopyClass(dace_instance=dace)
@@ -86,11 +87,16 @@ def get_arrays(result, latest_pipeline=True, ESPRESSO_mode='HR11', NIRPS_mode='H
                 i = [i for i, pipe in enumerate(pipelines) if ESPRESSO_mode in pipe][0]
                 pipelines = [pipelines[i]]
 
+        # select NIRPS mode
+        if 'NIRPS' in inst:
+            if any(this_mode := [p for p in pipelines if NIRPS_mode in p]):
+                pipelines = this_mode
+
         if latest_pipeline:
             npipe = len(pipelines)
             if 'NIRPS' in inst and any(['LBL' in p for p in pipelines]):
                 # TODO: correctly load both CCF and LBL
-                pipelines = [pipelines[1]]
+                pipelines = [pipelines[0]]
             if 'HARPS' in inst and npipe > 1 and pipelines[1] == pipelines[0] + '-EGGS':
                 pipelines = pipelines[:2]
             else:
@@ -163,20 +169,20 @@ def get_observations_from_instrument(star, instrument, user=None, main_id=None,
         dict:
             dictionary with data from DACE
     """
-    Spectroscopy = load_spectroscopy(user)
-
+    Spectroscopy = load_spectroscopy(user, verbose)
     found_dace_id = False
-    try:
-        dace_id = get_dace_id(star, verbose=verbose, raise_error=True)
-        found_dace_id = True
-    except ValueError as e:
-        if main_id is not None:
-            try:
-                dace_id = get_dace_id(main_id, verbose=verbose, raise_error=True)
-                found_dace_id = True
-            except ValueError:
-                pass
-    
+    with timer('dace_id query'):
+        try:
+            dace_id = get_dace_id(star, verbose=verbose, raise_error=True)
+            found_dace_id = True
+        except ValueError as e:
+            if main_id is not None:
+                try:
+                    dace_id = get_dace_id(main_id, verbose=verbose, raise_error=True)
+                    found_dace_id = True
+                except ValueError:
+                    pass
+
     if not found_dace_id:
         try:
             with all_logging_disabled():
@@ -188,10 +194,16 @@ def get_observations_from_instrument(star, instrument, user=None, main_id=None,
             msg = f'no {instrument} observations for {star}'
             raise ValueError(msg) from None
 
-    filters = {
-        "ins_name": {"contains": [instrument]},
-        "obj_id_daceid": {"contains": [dace_id]}
-    }
+    if (isinstance(instrument, str)):
+        filters = {
+            "ins_name": {"contains": [instrument]},
+            "obj_id_daceid": {"contains": [dace_id]}
+        }
+    elif (isinstance(instrument, (list, tuple, np.ndarray))):
+        filters = {
+            "ins_name": {"contains": instrument},
+            "obj_id_daceid": {"contains": [dace_id]}
+        }
     with all_logging_disabled():
         result = Spectroscopy.query_database(filters=filters)
     
@@ -202,63 +214,96 @@ def get_observations_from_instrument(star, instrument, user=None, main_id=None,
 
     for inst in np.unique(result['ins_name']):
         mask1 = result['ins_name'] == inst
-        r[inst] = {}
+        r[str(inst)] = {}
 
-        for pipe in np.unique(result['ins_drs_version'][mask1]):
-            mask2 = mask1 & (result['ins_drs_version'] == pipe)
-            r[inst][pipe] = {}
+        key2 = 'ins_drs_version'
+        n_key2 = len(np.unique(result[key2][mask1]))
+        if len(np.unique(result['pub_bibcode'][mask1])) >= n_key2:
+            key2 = 'pub_bibcode'
+
+        for pipe in np.unique(result[key2][mask1]):
+            mask2 = mask1 & (result[key2] == pipe)
+            r[str(inst)][str(pipe)] = {}
 
             for ins_mode in np.unique(result['ins_mode'][mask2]):
                 mask3 = mask2 & (result['ins_mode'] == ins_mode)
                 _nan = np.full(mask3.sum(), np.nan)
 
-                r[inst][pipe][ins_mode] = {
-                    'texp': result['texp'][mask3],
-                    'bispan': result['spectro_ccf_bispan'][mask3],
-                    'bispan_err': result['spectro_ccf_bispan_err'][mask3],
-                    'drift_noise': result['spectro_cal_drift_noise'][mask3],
-                    'rjd': result['obj_date_bjd'][mask3],
-                    'cal_therror': _nan,
-                    'fwhm': result['spectro_ccf_fwhm'][mask3],
-                    'fwhm_err': result['spectro_ccf_fwhm_err'][mask3],
-                    'rv': result['spectro_ccf_rv'][mask3],
-                    'rv_err': result['spectro_ccf_rv_err'][mask3],
-                    'berv': result['spectro_cal_berv'][mask3],
-                    'ccf_noise': _nan,
-                    'rhk': result['spectro_analysis_rhk'][mask3],
-                    'rhk_err': result['spectro_analysis_rhk_err'][mask3],
-                    'contrast': result['spectro_ccf_contrast'][mask3],
-                    'contrast_err': result['spectro_ccf_contrast_err'][mask3],
-                    'cal_thfile': result['spectro_cal_thfile'][mask3],
-                    'spectroFluxSn50': result['spectro_flux_sn50'][mask3],
-                    'protm08': result['spectro_analysis_protm08'][mask3],
-                    'protm08_err': result['spectro_analysis_protm08_err'][mask3],
-                    'caindex': result['spectro_analysis_ca'][mask3],
-                    'caindex_err': result['spectro_analysis_ca_err'][mask3],
-                    'pub_reference': result['pub_ref'][mask3],
-                    'drs_qc': result['spectro_drs_qc'][mask3],
-                    'haindex': result['spectro_analysis_halpha'][mask3],
-                    'haindex_err': result['spectro_analysis_halpha_err'][mask3],
-                    'protn84': result['spectro_analysis_protn84'][mask3],
-                    'protn84_err': result['spectro_analysis_protn84_err'][mask3],
-                    'naindex': result['spectro_analysis_na'][mask3],
-                    'naindex_err': result['spectro_analysis_na_err'][mask3],
-                    'snca2': _nan,
-                    'mask': result['spectro_ccf_mask'][mask3],
-                    'public': result['public'][mask3],
-                    'spectroFluxSn20': result['spectro_flux_sn20'][mask3],
-                    'sindex': result['spectro_analysis_smw'][mask3],
-                    'sindex_err': result['spectro_analysis_smw_err'][mask3],
-                    'drift_used': _nan,
-                    'ccf_asym': result['spectro_ccf_asym'][mask3],
-                    'ccf_asym_err': result['spectro_ccf_asym_err'][mask3],
-                    'date_night': result['date_night'][mask3],
-                    'raw_file': result['file_rootpath'][mask3],
-                    'prog_id': result['prog_id'][mask3],
-                    'th_ar': result['th_ar'][mask3],
-                    'th_ar1': result['th_ar1'][mask3],
-                    'th_ar2': result['th_ar2'][mask3],
+                translations = {
+                    'obj_date_bjd': 'rjd',
+                    'spectro_drs_qc': 'drs_qc',
+                    'spectro_cal_berv_mx': 'bervmax',
+                    'pub_ref': 'pub_reference',
+                    'file_rootpath': 'raw_file',
+                    'spectro_ccf_asym': 'ccf_asym',
+                    'spectro_ccf_asym_err': 'ccf_asym_err',
                 }
+                new_result = {}
+                for key in result.keys():
+                    if key in translations:
+                        new_key = translations[key]
+                    else:
+                        new_key = key
+                        new_key = new_key.replace('spectro_ccf_', '')
+                        new_key = new_key.replace('spectro_cal_', '')
+                        new_key = new_key.replace('spectro_analysis_', '')
+                    new_result[new_key] = result[key][mask3]
+
+                new_result['ccf_noise'] = np.sqrt(
+                    np.square(result['spectro_ccf_rv_err'][mask3]) - np.square(result['spectro_cal_drift_noise'][mask3])
+                )
+
+                r[str(inst)][str(pipe)][str(ins_mode)] = new_result
+
+                # r[str(inst)][str(pipe)][str(ins_mode)] = {
+                #     'texp': result['texp'][mask3],
+                #     'bispan': result['spectro_ccf_bispan'][mask3],
+                #     'bispan_err': result['spectro_ccf_bispan_err'][mask3],
+                #     'drift_noise': result['spectro_cal_drift_noise'][mask3],
+                #     'rjd': result['obj_date_bjd'][mask3],
+                #     'cal_therror': _nan,
+                #     'fwhm': result['spectro_ccf_fwhm'][mask3],
+                #     'fwhm_err': result['spectro_ccf_fwhm_err'][mask3],
+                #     'rv': result['spectro_ccf_rv'][mask3],
+                #     'rv_err': result['spectro_ccf_rv_err'][mask3],
+                #     'berv': result['spectro_cal_berv'][mask3],
+                #     'ccf_noise': np.sqrt(
+                #         np.square(result['spectro_ccf_rv_err'][mask3]) - np.square(result['spectro_cal_drift_noise'][mask3])
+                #     ),
+                #     'rhk': result['spectro_analysis_rhk'][mask3],
+                #     'rhk_err': result['spectro_analysis_rhk_err'][mask3],
+                #     'contrast': result['spectro_ccf_contrast'][mask3],
+                #     'contrast_err': result['spectro_ccf_contrast_err'][mask3],
+                #     'cal_thfile': result['spectro_cal_thfile'][mask3],
+                #     'spectroFluxSn50': result['spectro_flux_sn50'][mask3],
+                #     'protm08': result['spectro_analysis_protm08'][mask3],
+                #     'protm08_err': result['spectro_analysis_protm08_err'][mask3],
+                #     'caindex': result['spectro_analysis_ca'][mask3],
+                #     'caindex_err': result['spectro_analysis_ca_err'][mask3],
+                #     'pub_reference': result['pub_ref'][mask3],
+                #     'drs_qc': result['spectro_drs_qc'][mask3],
+                #     'haindex': result['spectro_analysis_halpha'][mask3],
+                #     'haindex_err': result['spectro_analysis_halpha_err'][mask3],
+                #     'protn84': result['spectro_analysis_protn84'][mask3],
+                #     'protn84_err': result['spectro_analysis_protn84_err'][mask3],
+                #     'naindex': result['spectro_analysis_na'][mask3],
+                #     'naindex_err': result['spectro_analysis_na_err'][mask3],
+                #     'snca2': _nan,
+                #     'mask': result['spectro_ccf_mask'][mask3],
+                #     'public': result['public'][mask3],
+                #     'spectroFluxSn20': result['spectro_flux_sn20'][mask3],
+                #     'sindex': result['spectro_analysis_smw'][mask3],
+                #     'sindex_err': result['spectro_analysis_smw_err'][mask3],
+                #     'drift_used': _nan,
+                #     'ccf_asym': result['spectro_ccf_asym'][mask3],
+                #     'ccf_asym_err': result['spectro_ccf_asym_err'][mask3],
+                #     'date_night': result['date_night'][mask3],
+                #     'raw_file': result['file_rootpath'][mask3],
+                #     'prog_id': result['prog_id'][mask3],
+                #     'th_ar': result['th_ar'][mask3],
+                #     'th_ar1': result['th_ar1'][mask3],
+                #     'th_ar2': result['th_ar2'][mask3],
+                # }
     
     # print(r.keys())    
     # print([r[k].keys() for k in r.keys()])
@@ -268,7 +313,7 @@ def get_observations_from_instrument(star, instrument, user=None, main_id=None,
 def get_observations(star, instrument=None, user=None, main_id=None, verbose=True):
     logger = setup_logger()
     if instrument is None:
-        Spectroscopy = load_spectroscopy(user)
+        Spectroscopy = load_spectroscopy(user, verbose)
 
         try:
             with stdout_disabled(), all_logging_disabled():
@@ -302,12 +347,14 @@ def get_observations(star, instrument=None, user=None, main_id=None, verbose=Tru
             result[inst] = dict(result[inst])
     #
 
-    instruments = list(result.keys())
+    instruments = list(map(str, result.keys()))
 
     if instrument is not None:
         # select only the provided instrument (if it's there)
-        instruments = [inst for inst in instruments if instrument in inst]
-
+        if (isinstance(instrument, str)):
+            instruments = [inst for inst in instruments if instrument in inst]
+        elif (isinstance(instrument, list)):
+            instruments = [inst for inst in instruments if any(i in inst for i in instrument)]
     if len(instruments) == 0:
         if instrument is None:
             msg = f'no observations for {star}'
@@ -331,30 +378,57 @@ def get_observations(star, instrument=None, user=None, main_id=None, verbose=Tru
     #     else:
     #         return -1
 
-    # sort pipelines, must be extra careful with HARPS/HARPN pipeline version numbers
-    # got here with the help of DeepSeek
-    from re import match
-    def custom_sort_key(s):
-        s = s[0]
-        # Check for version number pattern (e.g., 3.2.5 or 3.2.5-EGGS)
-        version_match = match(r'^(\d+(?:\.\d+)*)(?:[-\s](.*))?$', s)
-        if version_match:
-            version_parts = list(map(int, version_match.group(1).split('.')))
-            if len(version_parts) == 2:
-                version_parts.insert(1, -1)
-            return (0, 1, version_parts)
-        # Check for scientific reference pattern (e.g., 2004A&A...)
-        year_match = match(r'^(\d{4})', s)
-        if year_match:
-            year = int(year_match.group(1))
-            return (1, year)
-        # For all other strings, sort alphabetically
-        return (2, s)
-
-    # from functools import cmp_to_key
+    # # sort pipelines, must be extra careful with HARPS/HARPN pipeline version numbers
+    # # got here with the help of DeepSeek
+    # # from functools import cmp_to_key
+    # from re import match
+    # def custom_sort_key(s):
+    #     s = s[0]
+    #     # Check for version number pattern (e.g., 3.2.5 or 3.2.5-EGGS)
+    #     version_match = match(r'^(\d+(?:\.\d+)*)(?:[-\s](.*))?$', s)
+    #     if version_match:
+    #         version_parts = list(map(int, version_match.group(1).split('.')))
+    #         if len(version_parts) == 2:
+    #             version_parts.insert(1, -1)
+    #         # if version_match.group(2) and 'LBL' in version_match.group(2):
+    #         #     version_parts.append(-1)
+    #         # else:
+    #         #     version_parts.append(0)
+    #         if version_match.group(2) is None:
+    #             version_parts.append('')
+    #         else:
+    #             version_parts.append(version_match.group(2))
+    #         return (0, 1, version_parts)
+    #     # Check for scientific reference pattern (e.g., 2004A&A...)
+    #     year_match = match(r'^(\d{4})', s)
+    #     if year_match:
+    #         year = int(year_match.group(1))
+    #         return (1, year)
+    #     # For all other strings, sort alphabetically
+    #     return (2, s)
+
+    def custom_key(val, strip_EGGS=False):
+        if strip_EGGS:
+            val = val.replace('-EGGS', '').replace(' EGGS', '')
+        key = 0
+        key -= 1 if '3.5' in val else 0
+        key -= 1 if 'EGGS' in val else 0
+        key -= 1 if ('UHR' in val or 'MR' in val) else 0
+        key -= 1 if 'LBL' in val else 0
+        return str(key) if key != 0 else val
+
     new_result = {}
     for inst in instruments:
-        new_result[inst] = dict(sorted(result[inst].items(), key=custom_sort_key, reverse=True))
+        # new_result[inst] = dict(
+        #     sorted(result[inst].items(), key=custom_sort_key, reverse=True)
+        # )
+        if all(['EGGS' in k for k in result[inst].keys()]):
+            custom_key = partial(custom_key, strip_EGGS=True)
+        # WARNING: not the same as reverse=True (not sure why)
+        sorted_keys = sorted(result[inst].keys(), key=custom_key)[::-1]
+        new_result[inst] = {}
+        for key in sorted_keys:
+            new_result[inst][key] = result[inst][key]
 
     if verbose:
         logger.info('RVs available from')
@@ -388,7 +462,7 @@ def check_existing(output_directory, files, type):
     ]
 
     if type == 'S2D':
-        existing = [
+        existing += [
             f.partition('.fits')[0] for f in os.listdir(output_directory)
             if 'e2ds' in f
         ]   
@@ -500,20 +574,21 @@ def do_download_filetype(type, raw_files, output_directory, clobber=False, user=
     """ Download CCFs / S1Ds / S2Ds from DACE """
     logger = setup_logger()
     raw_files = np.atleast_1d(raw_files)
+    raw_files_original = raw_files.copy()
 
     create_directory(output_directory)
 
     # check existing files to avoid re-downloading
     if not clobber:
         raw_files = check_existing(output_directory, raw_files, type)
-
+    
     n = raw_files.size
 
     # any file left to download?
     if n == 0:
         if verbose:
             logger.info('no files to download')
-        return
+        return list(map(os.path.basename, raw_files_original))
 
     # avoid an empty chunk
     if chunk_size > n:
@@ -531,7 +606,9 @@ def do_download_filetype(type, raw_files, output_directory, clobber=False, user=
 
     if n < parallel_limit:
         iterator = [raw_files[i:i + chunk_size] for i in range(0, n, chunk_size)]
-        for files in tqdm(iterator, total=len(iterator)):
+        if len(iterator) > 1:
+            iterator = tqdm(iterator, total=len(iterator))
+        for files in iterator:
             download(files, type, output_directory, quiet=False, user=user)
             extract_fits(output_directory)
 
@@ -560,6 +637,7 @@ def do_download_filetype(type, raw_files, output_directory, clobber=False, user=
 
     sys.stdout.flush()
     logger.info('extracted .fits files')
+    return list(map(os.path.basename, raw_files_original))
 
 
 # def do_download_s1d(raw_files, output_directory, clobber=False, verbose=True):

{arvi-0.2.4 → arvi-0.3.0}/arvi/gaia_wrapper.py

@@ -3,15 +3,14 @@ from io import StringIO
 from csv import DictReader
 import requests
 
-from astropy.coordinates import SkyCoord
-
 DATA_PATH = os.path.dirname(__file__)
 DATA_PATH = os.path.join(DATA_PATH, 'data')
 
 QUERY = """
 SELECT TOP 20 gaia_source.designation, gaia_source.source_id,
               gaia_source.ra, gaia_source.dec, 
-              gaia_source.parallax, gaia_source.pmra, gaia_source.pmdec,
+              gaia_source.parallax, gaia_source.parallax_error,
+              gaia_source.pmra, gaia_source.pmdec,
               gaia_source.ruwe, gaia_source.phot_g_mean_mag, gaia_source.bp_rp, 
               gaia_source.radial_velocity, gaia_source.radial_velocity_error
 FROM gaiadr3.gaia_source 
@@ -29,7 +28,8 @@ CONTAINS(
 QUERY_ID = """
 SELECT TOP 20 gaia_source.designation, gaia_source.source_id,
               gaia_source.ra, gaia_source.dec, 
-              gaia_source.parallax, gaia_source.pmra, gaia_source.pmdec,
+              gaia_source.parallax, gaia_source.parallax_error,
+              gaia_source.pmra, gaia_source.pmdec,
               gaia_source.ruwe, gaia_source.phot_g_mean_mag, gaia_source.bp_rp, 
               gaia_source.radial_velocity, gaia_source.radial_velocity_error
 FROM gaiadr3.gaia_source 
@@ -78,6 +78,8 @@ class gaia:
         Args:
             star (str): The name of the star to query simbad
         """
+        from astropy.coordinates import SkyCoord
+
         self.star = star
 
         if simbad is None:
@@ -120,6 +122,7 @@ class gaia:
         self.pmdec = float(results['pmdec'])
         self.coords = SkyCoord(self.ra, self.dec, unit='deg')
         self.plx = float(results['parallax'])
+        self.plx_err = float(results['parallax_error'])
         try:
             self.radial_velocity = float(results['radial_velocity'])
         except ValueError:
@@ -131,5 +134,12 @@ class gaia:
 
         return
 
+    def distance(self):
+        """ Calculate the distance to the star as 1 / parallax [pc] """
+        from astropy import units as u
+        d = (self.plx * u.mas).to(u.parsec, 
+                                  equivalencies=u.equivalencies.parallax())
+        return d
+
     def __repr__(self):
         return f'{self.star} (DR3 id={self.dr3_id})'