arvi 0.2.4__tar.gz → 0.2.6__tar.gz

{arvi-0.2.4/arvi.egg-info → arvi-0.2.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: arvi
-Version: 0.2.4
+Version: 0.2.6
 Summary: The Automated RV Inspector
 Author-email: João Faria <joao.faria@unige.ch>
 License: MIT

{arvi-0.2.4 → arvi-0.2.6}/arvi/dace_wrapper.py

@@ -7,7 +7,7 @@ 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):
@@ -86,6 +86,11 @@ 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]):
@@ -164,19 +169,19 @@ def get_observations_from_instrument(star, instrument, user=None, main_id=None,
             dictionary with data from DACE
     """
     Spectroscopy = load_spectroscopy(user)
-
     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('simbad 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():
@@ -187,11 +192,16 @@ def get_observations_from_instrument(star, instrument, user=None, main_id=None,
         except TypeError:
             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)):
+        filters = {
+            "ins_name": {"contains": instrument},
+            "obj_id_daceid": {"contains": [dace_id]}
+        }
     with all_logging_disabled():
         result = Spectroscopy.query_database(filters=filters)
     
@@ -302,12 +312,14 @@ 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 +343,53 @@ 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):
+        key = 0
+        key -= 2 if val == '3.5' 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)
+        # )
+        # 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 +423,7 @@ 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
         ]   
@@ -506,7 +541,7 @@ def do_download_filetype(type, raw_files, output_directory, clobber=False, user=
     # 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?

{arvi-0.2.4 → arvi-0.2.6}/arvi/gaia_wrapper.py

@@ -3,8 +3,6 @@ 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')
 
@@ -78,6 +76,8 @@ 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:

{arvi-0.2.4 → arvi-0.2.6}/arvi/instrument_specific.py

@@ -5,7 +5,7 @@ from .setup_logger import setup_logger
 from .utils import ESPRESSO_ADC_issues, ESPRESSO_cryostat_issues
 
 
-# HARPS started operations in October 1st, 2003
+# HARPS started operations on October 1st, 2003
 # https://www.eso.org/sci/facilities/lasilla/instruments/harps/news.html
 HARPS_start = 52913
 
@@ -21,6 +21,11 @@ HARPS_technical_intervention = 57170
 # when the instrument was handed back to Science Operations.
 HARPS_technical_intervention_range = (57161, 57176)
 
+
+# ESPRESSO started operations on October 1st, 2018
+# see Pepe et al. (2021, A&A 645, A96)
+ESPRESSO_start = 58392
+
 # ESPRESSO fiber link upgrade (1 July 2019)
 ESPRESSO_technical_intervention = 58665
 
@@ -102,18 +107,11 @@ def divide_HARPS(self):
     
 
 def check(self, instrument):
-    logger = setup_logger()
-    instruments = self._check_instrument(instrument)
-    if instruments is None:
-        if self.verbose:
-            logger.error(f"HARPS_fiber_commissioning: no data from {instrument}")
-        return None
-    return instruments
-
+    return self._check_instrument(instrument)
 
 # HARPS commissioning
 def HARPS_commissioning(self, mask=True, plot=True):
-    """ Identify and optionally mask points during HARPS commissioning (HARPS).
+    """ Identify and optionally mask points during HARPS commissioning.
 
     Args:
         mask (bool, optional):
@@ -175,6 +173,38 @@ def HARPS_fiber_commissioning(self, mask=True, plot=True):
     return affected
 
 
+# ESPRESSO commissioning
+def ESPRESSO_commissioning(self, mask=True, plot=True):
+    """ Identify and optionally mask points during ESPRESSO commissioning.
+
+    Args:
+        mask (bool, optional):
+            Whether to mask out the points.
+        plot (bool, optional):
+            Whether to plot the masked points.
+    """
+    logger = setup_logger()
+    if check(self, 'ESPRESSO') is None:
+        return
+
+    affected = self.time < ESPRESSO_start
+    total_affected = affected.sum()
+
+    if self.verbose:
+        n = total_affected
+        logger.info(f"there {'are'[:n^1]}{'is'[n^1:]} {n} frame{'s'[:n^1]} "
+                     "during ESPRESSO commissioning")
+
+    if mask:
+        self.mask[affected] = False
+        self._propagate_mask_changes()
+
+        if plot:
+            self.plot(show_masked=True)
+
+    return affected
+
+
 # ESPRESSO ADC issues
 def ADC_issues(self, mask=True, plot=True, check_headers=False):
     """ Identify and optionally mask points affected by ADC issues (ESPRESSO).
@@ -316,31 +346,25 @@ class ISSUES:
             plot (bool, optional): Whether to plot the masked points.
         """
         logger = setup_logger()
-        try:
-            adc = ADC_issues(self, mask, plot, **kwargs)
-        except IndexError:
-            logger.error('are the data binned? cannot proceed to mask these points...')
-
-        try:
-            cryostat = blue_cryostat_issues(self, mask, plot)
-        except IndexError:
-            logger.error('are the data binned? cannot proceed to mask these points...')
-
-        try:
-            harps_comm = HARPS_commissioning(self, mask, plot)
-        except IndexError:
-            logger.error('are the data binned? cannot proceed to mask these points...')
-
-        try:
-            harps_fibers = HARPS_fiber_commissioning(self, mask, plot)
-        except IndexError:
-            logger.error('are the data binned? cannot proceed to mask these points...')
 
-        # if None in (adc, cryostat, harps_comm, harps_fibers):
-        #     return
+        functions = (
+            ESPRESSO_commissioning,
+            ADC_issues,
+            blue_cryostat_issues,
+            HARPS_commissioning,
+            HARPS_fiber_commissioning
+        )
+        results = []
+
+        for fun in functions:
+            try:
+                results.append(fun(self, mask, plot, **kwargs))
+            except IndexError:
+                logger.error('are the data binned? cannot proceed to mask these points...')
+        
+        results = list(filter(lambda x: x is not None, results))
 
         try:
-            # return adc | cryostat
-            return np.logical_or.reduce((adc, cryostat, harps_comm, harps_fibers))
+            return np.logical_or.reduce(results)
         except UnboundLocalError:
             return

{arvi-0.2.4 → arvi-0.2.6}/arvi/simbad_wrapper.py

@@ -1,6 +1,7 @@
 import os
 import requests
 from dataclasses import dataclass
+from functools import partial
 
 import numpy as np
 
@@ -63,6 +64,23 @@ JOIN ident ON oidref = oid
 WHERE id = '{star}';
 """
 
+HD_GJ_HIP_QUERY = """
+SELECT id2.id
+FROM ident AS id1 JOIN ident AS id2 USING(oidref)
+WHERE id1.id = '{star}' AND id2.id LIKE '{name}%';
+"""
+
+def find_identifier(identifier, star):
+    response = run_query(HD_GJ_HIP_QUERY.format(name=identifier, star=star))
+    if identifier in response:
+        return response.split('"')[1]
+    raise ValueError(f'no {identifier} identifier found for "{star}"')
+
+find_HD = partial(find_identifier, 'HD')
+find_GJ = partial(find_identifier, 'GJ')
+find_HIP = partial(find_identifier, 'HIP')
+
+
 @dataclass
 class Measurements:
     teff: list

arvi-0.2.6/arvi/sophie_wrapper.py

@@ -0,0 +1,111 @@
+from multiprocessing.pool import ThreadPool
+import re
+import requests
+from io import StringIO
+
+import numpy as np
+
+from .setup_logger import setup_logger
+
+URL_CCF = "http://atlas.obs-hp.fr/sophie/sophie.cgi?n=sophiecc&ob=date&a=t&o={target}"
+URL_HEADER = "http://atlas.obs-hp.fr/sophie/sophie.cgi?n=sophiecc&c=i&z=fd&a=t&o=sophie:[ccf,{seq},{mask},0]"
+
+def extract_keyword(keyword, text, raise_error=True):
+    for line in text.splitlines():
+        if keyword in line:
+            value = re.findall(fr'{keyword}\s+([\'\w\d.]+)', line)[0]
+            value = value.replace("'", "")
+            try:
+                return float(value)
+            except ValueError:
+                return value
+    if raise_error:
+        raise KeyError(f'Keyword {keyword} not found')
+
+def query_sophie_archive(star: str, verbose=True):
+    from .timeseries import RV
+    logger = setup_logger()
+
+    resp = requests.get(URL_CCF.format(target=star))
+    if 'leda did not return a position for the name' in resp.text:
+        raise ValueError(f'no SOPHIE observations for {star}')
+
+    data = np.genfromtxt(StringIO(resp.text), dtype=None, usecols=(0, 4),
+                         names=("seq", "mask"))
+    
+    if verbose:
+        logger.info(f'found {len(data)} SOPHIE observations for {star}')
+
+    urls = [URL_HEADER.format(seq=seq, mask=mask) for seq, mask in data]
+    with ThreadPool(8) as pool:
+        responses = pool.map(requests.get, urls)
+
+    bjd, vrad, svrad = [], [], []
+    fwhm, contrast = [], []
+    ccf_mask = []
+    _quantities = []
+    errors = []
+
+    for i, resp in enumerate(responses):
+        if resp.text == '':
+            errors.append(i)
+            continue
+        
+        try:
+            t, v = map(lambda k: extract_keyword(k, resp.text), 
+                       ("OHP DRS BJD", "OHP DRS CCF RV"))
+        except KeyError:
+            errors.append(i)
+            continue
+        else:
+            bjd.append(t)
+            vrad.append(v)
+        
+        try:
+            svrad.append(extract_keyword("OHP DRS CCF ERR", resp.text))
+        except KeyError:
+            try:
+                svrad.append(1e-3 * extract_keyword("OHP DRS DVRMS", resp.text))
+            except KeyError:
+                bjd.pop(-1)
+                vrad.pop(-1)
+                errors.append(i)
+                continue
+
+        fwhm.append(extract_keyword('OHP DRS CCF FWHM', resp.text))
+        _quantities.append('fwhm')
+
+        contrast.append(extract_keyword('OHP DRS CCF CONTRAST', resp.text))
+        _quantities.append('contrast')
+
+        ccf_mask.append(extract_keyword('OHP DRS CCF MASK', resp.text))
+        _quantities.append('ccf_mask')
+
+    if len(errors) > 0:
+        logger.warning(f'Could not retrieve {len(errors)} observation'
+                       f'{"s" if len(errors) > 1 else ""}')
+
+    bjd = np.array(bjd) - 2400000.5
+
+    s = RV.from_arrays(star, bjd, vrad, svrad, 'SOPHIE',
+                       fwhm=fwhm, fwhm_err=2*np.array(svrad),
+                       contrast=contrast, 
+                       ccf_mask=ccf_mask)
+    s.units = 'km/s'
+
+    # strings
+    for q in ['date_night', 'prog_id', 'raw_file', 'pub_reference']:
+        setattr(s, q, np.full(bjd.size, ''))
+        _quantities.append(q)
+
+    s._quantities = np.array(_quantities)
+
+    setattr(s, 'SOPHIE', s)
+    s._child = False
+    s.verbose = False
+    s._build_arrays()
+    s.change_units('m/s')
+    s.verbose = verbose
+
+    return s
+    

{arvi-0.2.4 → arvi-0.2.6}/arvi/timeseries.py

@@ -55,7 +55,7 @@ class RV(ISSUES, REPORTS):
             Information on the target from Simbad
     """
     star: str
-    instrument: str = field(init=True, repr=False, default=None)
+    instrument: Union[str, list] = field(init=True, repr=False, default=None)
     verbose: bool = field(init=True, repr=False, default=True)
     do_maxerror: Union[bool, float] = field(init=True, repr=False, default=False)
     do_secular_acceleration: bool = field(init=True, repr=False, default=True)
@@ -64,19 +64,21 @@ class RV(ISSUES, REPORTS):
     only_latest_pipeline: bool = field(init=True, repr=False, default=True)
     load_extra_data: Union[bool, str] = field(init=True, repr=False, default=False)
     check_drs_qc: bool = field(init=True, repr=False, default=True)
-    user: bool = field(init=True, repr=False, default=None)
+    check_sophie_archive: bool = field(init=True, repr=False, default=False)
+    user: Union[str, None] = field(init=True, repr=False, default=None)
     #
     units = 'm/s'
     _child: bool = field(init=True, repr=False, default=False)
-    _did_secular_acceleration: bool = field(init=False, repr=False, default=False)
-    _did_sigma_clip: bool = field(init=False, repr=False, default=False)
-    _did_adjust_means: bool = field(init=False, repr=False, default=False)
-    _did_simbad_query: bool = field(init=False, repr=False, default=False)
-    _did_gaia_query: bool = field(init=False, repr=False, default=False)
-    _did_toi_query: bool = field(init=False, repr=False, default=False)
-    _raise_on_error: bool = field(init=True, repr=False, default=True)
-    __masked_numbers: bool = field(init=False, repr=False, default=False)
-    # 
+    #
+    _did_secular_acceleration : bool = field(init=False, repr=False, default=False)
+    _did_sigma_clip           : bool = field(init=False, repr=False, default=False)
+    _did_adjust_means         : bool = field(init=False, repr=False, default=False)
+    _did_simbad_query         : bool = field(init=False, repr=False, default=False)
+    _did_gaia_query           : bool = field(init=False, repr=False, default=False)
+    _did_toi_query            : bool = field(init=False, repr=False, default=False)
+    _raise_on_error  : bool = field(init=True, repr=False, default=True)
+    __masked_numbers : bool = field(init=False, repr=False, default=False)
+    #
     _simbad = None
     _gaia = None
     _toi = None
@@ -104,7 +106,7 @@ class RV(ISSUES, REPORTS):
 
         if self._child:
             return None
-    
+
         if self._did_simbad_query:
             return None
 
@@ -288,6 +290,21 @@ class RV(ISSUES, REPORTS):
                 # all other quantities
                 self._build_arrays()
 
+                # self.actin = get_actin_data(self, verbose=self.verbose)
+
+
+        # check for SOPHIE observations
+        cond = not self._child
+        cond = cond and self.instrument is None
+        cond = cond and self.check_sophie_archive
+        if cond:
+            try:
+                from arvi.sophie_wrapper import query_sophie_archive
+                self.__add__(query_sophie_archive(self.star, verbose=self.verbose),
+                             inplace=True)
+            except Exception as e:
+                print(e)
+
         # do clip_maxerror, secular_acceleration, sigmaclip, adjust_means
         if not self._child:
             if self.do_maxerror:
@@ -1376,7 +1393,7 @@ class RV(ISSUES, REPORTS):
             instrument_index = self.obs[index]
             np.array(self.instruments)[instrument_index - 1]
         except IndexError:
-            logger.errors(f'index {index} is out of bounds for N={self.N}')
+            logger.error(f'index {index} is out of bounds for N={self.N}')
             return
 
         if self.verbose:
@@ -1408,7 +1425,7 @@ class RV(ISSUES, REPORTS):
             instrument_index = self.obs[index]
             np.array(self.instruments)[instrument_index - 1]
         except IndexError:
-            logger.errors(f'index {index} is out of bounds for N={self.N}')
+            logger.error(f'index {index} is out of bounds for N={self.N}')
             return
 
         if self.verbose:

{arvi-0.2.4 → arvi-0.2.6}/arvi/utils.py

@@ -79,14 +79,17 @@ def timer(name=None):
     if name is None:
         logger.debug('starting timer')
     else:
-        logger.debug(f'starting timer: {name}')
+        logger.debug(f'{name}: starting timer')
 
     start = time.time()
     try:
         yield
     finally:
         end = time.time()
-        logger.debug(f'elapsed time: {end - start:.2f} seconds')
+        if name is None:
+            logger.debug(f'elapsed time {end - start:.2f} seconds')
+        else:
+            logger.debug(f'{name}: elapsed time {end - start:.2f} seconds')
 
 
 def sanitize_path(path):

{arvi-0.2.4 → arvi-0.2.6/arvi.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: arvi
-Version: 0.2.4
+Version: 0.2.6
 Summary: The Automated RV Inspector
 Author-email: João Faria <joao.faria@unige.ch>
 License: MIT

{arvi-0.2.4 → arvi-0.2.6}/arvi.egg-info/SOURCES.txt

@@ -28,6 +28,7 @@ arvi/programs.py
 arvi/reports.py
 arvi/setup_logger.py
 arvi/simbad_wrapper.py
+arvi/sophie_wrapper.py
 arvi/spectra.py
 arvi/stats.py
 arvi/stellar.py

{arvi-0.2.4 → arvi-0.2.6}/tests/test_create_RV.py

@@ -19,3 +19,10 @@ def test_from_rdb(change_test_dir):
     assert (s.bispan == 0).all()
     assert isnan(s.rhk).all()
 
+
+def test_list_instruments():
+    from arvi import RV, config
+    config.request_as_public = True
+    _ = RV('HD28185', instrument='CORALIE')
+    _ = RV('HD28185', instrument=['CORALIE'])
+    _ = RV('HD28185', instrument=['CORALIE', 'HRS'])