arvi 0.2.1__py3-none-any.whl → 0.2.3__py3-none-any.whl

arvi/__init__.py

@@ -1,22 +1,22 @@
-__all__ = ['RV']
+__all__ = ['RV', 'config', 'simbad', 'gaia']
 
 from importlib.metadata import version, PackageNotFoundError
-
-from .config import config
-from .timeseries import RV
-
 try:
     __version__ = version("arvi")
 except PackageNotFoundError:
     # package is not installed
     pass
 
-## OLD
-# # the __getattr__ function is always called twice, so we need this
-# # to only build and return the RV object on the second time
-# _ran_once = False
+from .config import config
+from .simbad_wrapper import simbad
+from .gaia_wrapper import gaia
+
+from .timeseries import RV
 
 def __getattr__(name: str):
+    if not config.fancy_import:
+        raise AttributeError
+    
     if name in (
         '_ipython_canary_method_should_not_exist_',
         '_ipython_display_',
@@ -29,15 +29,5 @@ def __getattr__(name: str):
         globals()[name] = RV(name)
         return globals()[name]
     except ValueError as e:
-        raise ImportError(e) from None
-        # raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
-
-    ## OLD
-    # # can't do it any other way :(
-    # global _ran_once
+        raise AttributeError(e)
 
-    # if _ran_once:
-    #     _ran_once = False
-    #     return RV(name)
-    # else:
-    #     _ran_once = True

arvi/binning.py

@@ -1,6 +1,6 @@
 import numpy as np
 
-from .setup_logger import logger
+from .setup_logger import setup_logger
 
 ###############################################################################
 # the following is mostly a copy of the scipy implementation of
@@ -390,6 +390,7 @@ def binRV(time, rv, err=None, stat='wmean', tstat='wmean', estat='addquad',
 
 
 def bin_ccf_mask(time, ccf_mask):
+    logger = setup_logger()
     indices = binRV(time, None, binning_indices=True)
     indices = np.r_[indices, time.size]
     bmask = []

arvi/config.py

@@ -31,6 +31,8 @@ class config:
         'check_internet': False,
         # make all DACE requests without using a .dacerc file
         'request_as_public': False,
+        # enable from arvi import star_name
+        'fancy_import': True,
         # debug
         'debug': False,
     }
@@ -43,10 +45,16 @@ class config:
             # return {'return_self': 'help!'}
             return {}
 
-        if self.__user_config.has_option('config', name):
-            self.__conf[name] = self.__user_config.get('config', name)
+        try:
+            if self.__user_config.has_option('config', name):
+                value = self.__user_config.get('config', name)
+                value = True if value == 'True' else value
+                value = False if value == 'False' else value
+                self.__conf[name] = value
 
-        return self.__conf[name]
+            return self.__conf[name]
+        except KeyError:
+            raise KeyError(f"unknown config option '{name}'")
 
     def __setattr__(self, name, value):
         if name in config.__setters:
@@ -54,7 +62,7 @@ class config:
         else:
             if 'config' not in self.__user_config:
                 self.__user_config.add_section('config')
-            self.__user_config.set('config', name, value)
+            self.__user_config.set('config', name, str(value))
             save_config(self.__user_config)
             # raise NameError(f"unknown configuration name '{name}'")
 

arvi/dace_wrapper.py

@@ -5,13 +5,17 @@ import collections
 from functools import lru_cache
 from itertools import islice
 import numpy as np
-from dace_query import DaceClass
-from dace_query.spectroscopy import SpectroscopyClass, Spectroscopy as default_Spectroscopy
-from .setup_logger import logger
+
+from .setup_logger import setup_logger
 from .utils import create_directory, all_logging_disabled, stdout_disabled, tqdm
 
 
-def load_spectroscopy(user=None) -> SpectroscopyClass:
+def load_spectroscopy(user=None):
+    logger = setup_logger()
+    with all_logging_disabled():
+        from dace_query.spectroscopy import SpectroscopyClass, Spectroscopy as default_Spectroscopy
+        from dace_query import DaceClass
+
     from .config import config
     # requesting as public
     if config.request_as_public:
@@ -39,10 +43,13 @@ def load_spectroscopy(user=None) -> SpectroscopyClass:
         logger.info(f'using credentials for user {user} in ~/.dacerc')
         return SpectroscopyClass(dace_instance=dace)
     # default
+    if not os.path.exists(os.path.expanduser('~/.dacerc')):
+        logger.warning('requesting DACE data as public (no .dacerc file found)')
     return default_Spectroscopy
 
 @lru_cache()
 def get_dace_id(star, verbose=True):
+    logger = setup_logger()
     filters = {"obj_id_catname": {"equal": [star]}}
     try:
         with all_logging_disabled():
@@ -54,6 +61,7 @@ def get_dace_id(star, verbose=True):
         raise ValueError from None
 
 def get_arrays(result, latest_pipeline=True, ESPRESSO_mode='HR11', NIRPS_mode='HE', verbose=True):
+    logger = setup_logger()
     arrays = []
     instruments = [str(i) for i in result.keys()]
 
@@ -153,6 +161,7 @@ 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)
@@ -254,8 +263,10 @@ def get_observations_from_instrument(star, instrument, user=None, main_id=None,
     return r
 
 def get_observations(star, instrument=None, user=None, main_id=None, verbose=True):
+    logger = setup_logger()
     if instrument is None:
         Spectroscopy = load_spectroscopy(user)
+
         try:
             with stdout_disabled(), all_logging_disabled():
                 result = Spectroscopy.get_timeseries(target=star,
@@ -438,6 +449,7 @@ def extract_fits(output_directory, filename=None):
 
 
 def do_symlink_filetype(type, raw_files, output_directory, clobber=False, top_level=None, verbose=True):
+    logger = setup_logger()
     terminations = {
         'CCF': '_CCF_A.fits',
         'S1D': '_S1D_A.fits',
@@ -483,6 +495,7 @@ def do_symlink_filetype(type, raw_files, output_directory, clobber=False, top_le
 def do_download_filetype(type, raw_files, output_directory, clobber=False, user=None,
                          verbose=True, chunk_size=20, parallel_limit=30):
     """ Download CCFs / S1Ds / S2Ds from DACE """
+    logger = setup_logger()
     raw_files = np.atleast_1d(raw_files)
 
     create_directory(output_directory)

arvi/exofop_wrapper.py

@@ -0,0 +1,62 @@
+import csv
+import requests
+import time
+import importlib.resources as resources
+import numpy as np
+
+from .setup_logger import setup_logger
+
+def get_toi_list(verbose=True):
+    logger = setup_logger()
+    toi_list = resources.files('arvi') / 'data' / 'exofop_toi_list.csv'
+    now = time.time()
+    download = not toi_list.exists() or toi_list.stat().st_mtime < now - 48 * 60 * 60
+    if download:
+        if verbose:
+            logger.info('Downloading exofop TOI list (can take a while)...')
+        r = requests.get('https://exofop.ipac.caltech.edu/tess/download_toi.php?sort=toi&output=csv')
+        with open(toi_list, 'wb') as f:
+            f.write(r.content)
+    return toi_list
+
+class exofop:
+    def __init__(self, star: str, verbose=True, _debug=False):
+        self.star = star
+        self.verbose = verbose
+        
+        toi_list = get_toi_list(verbose=verbose)
+        tsv = ('|'.join(i) for i in csv.reader(open(toi_list, encoding='utf8')))
+        self.data = np.genfromtxt(tsv, delimiter='|', 
+                                  names=True, encoding='utf8', dtype=None)
+
+
+        try:
+            if self.star.startswith('TIC'):
+                self.tic = self.star
+                w = self.data['TIC_ID'] == int(self.star[3:])
+                self.toi = 'TOI-' + str(int(self.data['TOI'][w][0]))
+            else:
+                toi = self.star.replace('TOI-', '')
+                toi = toi if toi.endswith('.01') else toi + '.01'
+                toi_float = float(toi)
+                if toi_float not in self.data['TOI']:
+                    raise ValueError
+                w = self.data['TOI'] == toi_float
+                self.tic = 'TIC' + str(int(self.data['TIC_ID'][w][0]))
+                self.toi = self.star
+        except ValueError:
+            raise ValueError(f'{self.star} not found in exofop TOI list')
+        else:
+            self.ra = str(self.data['RA'][w][0])
+            self.dec = str(self.data['Dec'][w][0])
+
+            self.epoch = float(self.data['Epoch_BJD'][w][0])
+            self.period = float(self.data['Period_days'][w][0])
+            if self.period == 0.0:
+                self.period = np.nan
+            self.duration = float(self.data['Duration_hours'][w][0])
+            self.depth = float(self.data['Depth_ppm'][w][0])
+
+        
+    def __repr__(self):
+        return f'{self.star} (TIC={self.tic}, epoch={self.epoch:.3f}, period={self.period:.3f})'

arvi/extra_data.py

@@ -3,8 +3,7 @@ from glob import glob
 import json
 
 from numpy import full
-from .setup_logger import logger
-from . import timeseries
+from .setup_logger import setup_logger
 
 refs = {
     'HD86226': 'Teske et al. 2020 (AJ, 160, 2)'
@@ -12,16 +11,21 @@ refs = {
 
 def get_extra_data(star, instrument=None, path=None, verbose=True,
                    check_for_kms=True):
+    from . import timeseries
+    logger = setup_logger()
     if path is None:
         path = os.path.dirname(__file__)
         path = os.path.join(path, 'data', 'extra')
+        metadata = json.load(open(os.path.join(path, 'metadata.json'), 'r'))
+        # print(metadata)
+    else:
+        metadata = {}
 
-    metadata = json.load(open(os.path.join(path, 'metadata.json'), 'r'))
-    # print(metadata)
-
-    files = glob(os.path.join(path, star.replace(' ', '') + '*.rdb'))
+    files = glob(os.path.join(path, star + '*.rdb'))
+    files += glob(os.path.join(path, star.replace(' ', '') + '*.rdb'))
     files = [f for f in files if os.path.isfile(f)]
-    files = [f for f in files if not os.path.basename(f).endswith('.zip')]
+    files = [f for f in files if not f.endswith('_actin.rdb')]
+    files = list(set(files))
 
     if len(files) == 0:
         raise FileNotFoundError

arvi/gaia_wrapper.py

@@ -73,7 +73,7 @@ class gaia:
         plx (float): parallax
         radial_velocity (float): radial velocity
     """
-    def __init__(self, star:str, simbad=None):
+    def __init__(self, star:str, simbad=None, _debug=False):
         """
         Args:
             star (str): The name of the star to query simbad
@@ -83,6 +83,8 @@ class gaia:
         if simbad is None:
             from .simbad_wrapper import simbad as Simbad
             simbad = Simbad(star)
+            if _debug:
+                print(simbad)
 
         ra = simbad.ra
         dec = simbad.dec
@@ -95,10 +97,14 @@ class gaia:
         try:
             if star in translate:
                 table = run_query(query=QUERY_ID.format(id=translate[star]))
-            elif hasattr(simbad, 'gaia_id'):
+            elif hasattr(simbad, 'gaia_id') and simbad.gaia_id is not None:
                 table = run_query(query=QUERY_ID.format(id=simbad.gaia_id))
             else:
                 table = run_query(query=QUERY.format(**args))
+            
+            if _debug:
+                print('table:', table)
+
             results = parse_csv(table)[0]
         except IndexError:
             raise ValueError(f'Gaia query for {star} failed')

arvi/instrument_specific.py

@@ -1,7 +1,7 @@
 import os, sys
 import numpy as np
 
-from .setup_logger import logger
+from .setup_logger import setup_logger
 from .utils import ESPRESSO_ADC_issues, ESPRESSO_cryostat_issues
 
 
@@ -27,6 +27,7 @@ ESPRESSO_technical_intervention = 58665
 
 def divide_ESPRESSO(self):
     """ Split ESPRESSO data into separate sub ESP18 and ESP19 subsets """
+    logger = setup_logger()
     if self._check_instrument('ESPRESSO', strict=False) is None:
         return
     if 'ESPRESSO18' in self.instruments and 'ESPRESSO19' in self.instruments:
@@ -64,6 +65,7 @@ def divide_ESPRESSO(self):
 
 def divide_HARPS(self):
     """ Split HARPS data into separate sub HARPS03 and HARPS15 subsets """
+    logger = setup_logger()
     if self._check_instrument('HARPS', strict=False) is None:
         return
     if 'HARPS03' in self.instruments and 'HARPS15' in self.instruments:
@@ -100,6 +102,7 @@ def divide_HARPS(self):
     
 
 def check(self, instrument):
+    logger = setup_logger()
     instruments = self._check_instrument(instrument)
     if instruments is None:
         if self.verbose:
@@ -118,6 +121,7 @@ def HARPS_commissioning(self, mask=True, plot=True):
         plot (bool, optional):
             Whether to plot the masked points.
     """
+    logger = setup_logger()
     if check(self, 'HARPS') is None:
         return
 
@@ -149,6 +153,7 @@ def HARPS_fiber_commissioning(self, mask=True, plot=True):
         plot (bool, optional):
             Whether to plot the masked points.
     """
+    logger = setup_logger()
     if check(self, 'HARPS') is None:
         return
 
@@ -182,6 +187,7 @@ def ADC_issues(self, mask=True, plot=True, check_headers=False):
         check_headers (bool, optional):
             Whether to (double-)check the headers for missing/zero keywords.
     """
+    logger = setup_logger()
     instruments = self._check_instrument('ESPRESSO')
     
     if instruments is None:
@@ -225,6 +231,7 @@ def blue_cryostat_issues(self, mask=True, plot=True):
         mask (bool, optional): Whether to mask out the points.
         plot (bool, optional): Whether to plot the masked points.
     """
+    logger = setup_logger()
     instruments = self._check_instrument('ESPRESSO')
     
     if instruments is None:
@@ -259,6 +266,7 @@ def qc_scired_issues(self, plot=False, **kwargs):
     Args:
         plot (bool, optional): Whether to plot the masked points.
     """
+    logger = setup_logger()
     from .headers import get_headers
 
     instruments = self._check_instrument('ESPRESSO')
@@ -299,38 +307,40 @@ def qc_scired_issues(self, plot=False, **kwargs):
     return affected
 
 
-def known_issues(self, mask=True, plot=False, **kwargs):
-    """ Identify and optionally mask known instrumental issues.
-
-    Args:
-        mask (bool, optional): Whether to mask out the points.
-        plot (bool, optional): Whether to plot the masked points.
-    """
-    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
-
-    try:
-        # return adc | cryostat
-        return np.logical_or.reduce((adc, cryostat, harps_comm, harps_fibers))
-    except UnboundLocalError:
-        return
+class ISSUES:
+    def known_issues(self, mask=True, plot=False, **kwargs):
+        """ Identify and optionally mask known instrumental issues.
+
+        Args:
+            mask (bool, optional): Whether to mask out the points.
+            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
+
+        try:
+            # return adc | cryostat
+            return np.logical_or.reduce((adc, cryostat, harps_comm, harps_fibers))
+        except UnboundLocalError:
+            return

arvi/plots.py

@@ -5,7 +5,7 @@ import numpy as np
 
 from astropy.timeseries import LombScargle
 
-from .setup_logger import logger
+from .setup_logger import setup_logger
 from .config import config
 from .stats import wmean
 
@@ -172,6 +172,7 @@ def plot(self, ax=None, show_masked=False, instrument=None, time_offset=0,
         Figure: the figure
         Axes: the axis
     """
+    logger = setup_logger()
     if self.N == 0:
         if self.verbose:
             logger.error('no data to plot')
@@ -230,13 +231,13 @@ def plot(self, ax=None, show_masked=False, instrument=None, time_offset=0,
                 _label = label
 
         if versus_n:
-            container = ax.errorbar(np.arange(1, s.mtime.size + 1), s.mvrad, s.msvrad,
-                                    label=_label, picker=True, marker=next(markers), zorder=next(zorders),
-                                    **kwargs)
+            x = np.arange(1, s.mtime.size + 1)
         else:
-            container = ax.errorbar(s.mtime - time_offset, s.mvrad, s.msvrad,
-                                    label=_label, picker=True, marker=next(markers), zorder=next(zorders),
-                                    **kwargs)
+            x = s.mtime - time_offset
+
+        container = ax.errorbar(x, s.mvrad, s.msvrad, label=_label, 
+                                picker=True, marker=next(markers), zorder=next(zorders), **kwargs)
+
 
         containers[inst] = list(container)
 
@@ -357,8 +358,6 @@ def plot(self, ax=None, show_masked=False, instrument=None, time_offset=0,
         plt.connect('pick_event', on_pick_point)
 
 
-
-
     if show_histogram:
         axh.legend()
 
@@ -408,6 +407,7 @@ def plot(self, ax=None, show_masked=False, instrument=None, time_offset=0,
 def plot_quantity(self, quantity, ax=None, show_masked=False, instrument=None,
                   time_offset=0, remove_50000=False, tooltips=False, show_legend=True,
                   N_in_label=False, **kwargs):
+    logger = setup_logger()
     if self.N == 0:
         if self.verbose:
             logger.error('no data to plot')
@@ -533,6 +533,7 @@ def gls(self, ax=None, label=None, instrument=None,
             Whether to adjust (subtract) the weighted means of each instrument.
             Default is `config.adjust_means_gls`.
     """
+    logger = setup_logger()
     if self.N == 0:
         if self.verbose:
             logger.error('no data to compute gls')
@@ -585,10 +586,15 @@ def gls(self, ax=None, label=None, instrument=None,
     maximum_frequency = kwargs.pop('maximum_frequency', 1.0)
     minimum_frequency = kwargs.pop('minimum_frequency', None)
     samples_per_peak = kwargs.pop('samples_per_peak', 10)
+    kw = {
+        'maximum_frequency': maximum_frequency,
+        'minimum_frequency': minimum_frequency,
+        'samples_per_peak': samples_per_peak
+    }
+
+    freq, power = gls.autopower(**kw)
 
-    freq, power = gls.autopower(maximum_frequency=maximum_frequency,
-                                minimum_frequency=minimum_frequency,
-                                samples_per_peak=samples_per_peak)
+    show_peak_fap = kwargs.pop('show_peak_fap', False)
 
     if ax is None:
         fig, ax = plt.subplots(1, 1, constrained_layout=True)
@@ -607,14 +613,22 @@ def gls(self, ax=None, label=None, instrument=None,
         if isinstance(fap, float):
             fap_level = fap
 
-        fap = gls.false_alarm_level(fap_level, method=fap_method)
+        fap = gls.false_alarm_level(fap_level, method=fap_method, **kw)
 
-        if fap > 0.05 and fap_method == 'baluev':
-            logger.warning('FAP is high (>5%), the analytical estimate may be underestimated. Using the bootstrap method instead.')
-            fap = gls.false_alarm_level(fap_level, method='bootstrap')
+        # if fap > 0.05 and fap_method == 'baluev':
+        #     logger.warning('FAP is high (>5%), the analytical estimate may be underestimated. Using the bootstrap method instead.')
+        #     fap = gls.false_alarm_level(fap_level, method='bootstrap')
 
         ax.axhline(fap, color='k', alpha=0.2, zorder=-1)
 
+    if show_peak_fap:
+        peak_per = 1/freq[np.argmax(power)]
+        peak_power = np.max(power)
+        peak_fap = gls.false_alarm_probability(peak_power, method=fap_method, **kw)
+        ax.plot(peak_per, peak_power, 'o', color='r', zorder=1)
+        ax.annotate(f'{peak_per:1.3f} days\nFAP: {peak_fap:1.1e}', (peak_per, peak_power), 
+                    va='top', textcoords='offset points', xytext=(10, 0), zorder=1)
+
     ax.set(xlabel='Period [days]', ylabel='Normalized power', ylim=(0, None))
     ax.minorticks_on()
 
@@ -681,7 +695,7 @@ def gls_quantity(self, quantity, ax=None, instrument=None,
             Whether to adjust (subtract) the weighted means of each instrument.
             Default is `config.adjust_means_gls`.
     """
-
+    logger = setup_logger()
     if not hasattr(self, quantity):
         if self.verbose:
             logger.error(f"cannot find '{quantity}' attribute")
@@ -743,10 +757,17 @@ def gls_quantity(self, quantity, ax=None, instrument=None,
     else:
         fig = ax.figure
 
-    spp = kwargs.get('samples_per_peak', 5)
+    maximum_frequency = kwargs.pop('maximum_frequency', 1.0)
+    minimum_frequency = kwargs.pop('minimum_frequency', None)
+    samples_per_peak = kwargs.pop('samples_per_peak', 10)
+    kw = {
+        'maximum_frequency': maximum_frequency,
+        'minimum_frequency': minimum_frequency,
+        'samples_per_peak': samples_per_peak
+    }
 
     gls = LombScargle(t, y, ye)
-    freq, power = gls.autopower(maximum_frequency=1.0, samples_per_peak=spp)
+    freq, power = gls.autopower(**kw)
 
     ax.semilogx(1/freq, power, picker=picker, **kwargs)
 
@@ -755,11 +776,11 @@ def gls_quantity(self, quantity, ax=None, instrument=None,
         if isinstance(fap, float):
             fap_level = fap
 
-        fap = gls.false_alarm_level(fap_level, method=fap_method)
+        fap = gls.false_alarm_level(fap_level, method=fap_method, **kw)
 
-        if fap > 0.05 and fap_method == 'baluev':
-            logger.warning('FAP is high (>5%), the analytical estimate may be underestimated. Using the bootstrap method instead.')
-            fap = gls.false_alarm_level(fap_level, method='bootstrap')
+        # if fap > 0.05 and fap_method == 'baluev':
+        #     logger.warning('FAP is high (>5%), the analytical estimate may be underestimated. Using the bootstrap method instead.')
+        #     fap = gls.false_alarm_level(fap_level, method='bootstrap', **kw)
 
         ax.axhline(fap, color='k', alpha=0.2, zorder=-1)
 
@@ -794,6 +815,8 @@ def window_function(self, ax1=None, ax2=None, instrument=None, crosshair=False,
         crosshair (bool):
             If True, a crosshair will be drawn on the plot.
     """
+    logger = setup_logger()
+
     if self.N == 0:
         if self.verbose:
             logger.error('no data to compute window function')