Download IGRINS data from Google Drive

IGRINS stores all of its data on Google Drive. Here we show how to programmatically fetch that data with Python.

from muler.igrins import IGRINSSpectrum
import requests
%matplotlib inline
%config InlineBackend.figure_format='retina'

---------------------------------------------------------------------------
ModuleNotFoundError                       Traceback (most recent call last)
Cell In[1], line 1
----> 1 from muler.igrins import IGRINSSpectrum
      2 import requests
      3 get_ipython().run_line_magic('matplotlib', 'inline')

File ~/checkouts/readthedocs.org/user_builds/muler/envs/latest/lib/python3.8/site-packages/muler/igrins.py:15
     13 import json
     14 from matplotlib import pyplot as plt
---> 15 from muler.echelle import EchelleSpectrum, EchelleSpectrumList
     16 from muler.utilities import Slit, concatenate_orders, resample_list, roll_along_axis, edge_normalize, isolate_and_normalize_hi_order, round_to_multiple, photometry
     17 from astropy.time import Time

File ~/checkouts/readthedocs.org/user_builds/muler/envs/latest/lib/python3.8/site-packages/muler/echelle.py:31
     29 from scipy.ndimage import median_filter, gaussian_filter1d
     30 import specutils
---> 31 from muler.utilities import apply_numpy_mask, is_list, resample_list
     34 # from barycorrpy import get_BC_vel
     35 from astropy.coordinates import SkyCoord, EarthLocation

File ~/checkouts/readthedocs.org/user_builds/muler/envs/latest/lib/python3.8/site-packages/muler/utilities.py:15
     13 from astropy.convolution import convolve, Gaussian1DKernel
     14 from scipy.ndimage import binary_dilation
---> 15 from astroquery.simbad import Simbad
     16 Simbad.add_votable_fields('V', 'B', 'J', 'H', 'K', 'parallax')
     17 LinInterpResampler = LinearInterpolatedResampler()

ModuleNotFoundError: No module named 'astroquery'

For now, you need the filename and Google Drive ID for a spectrum. Eventually this information may come from an observation Log provided by the IGRINS team. At the moment, I just retrieved this information by navigating to the Google Drive website.

These data are already public on the muler_example_date repo, but I uploaded them to a public Google Drive for the purpose of this demo. Eventually the entire IGRINS archive will be in a public Google Drive like this.

download_dictionary = {'SDCH_20201202_0059.spec_a0v.fits':'1tBY0NCcTnnCkvXXvFNOiqd4e10S6W2RB',
                       'SDCH_20201202_0059.sn.fits':'1NlIUWPxiN_nkZ83JsTzXby_5ihSSZ34o'}

We need two files because the IGRINS pipeline houses the uncertainty values in a separate file from the flux values.

def download_file(filename, file_id):
    """Download the file from Google Drive"""
    URL = "https://docs.google.com/uc?export=download"
    session = requests.Session()
    response = session.get(URL, params = { 'id' : file_id }, stream = True)
    if response.status_code == 200: # Successfully found the file on Google Drive
        CHUNK_SIZE = 32768

        with open(filename, "wb") as f:
            for chunk in response.iter_content(CHUNK_SIZE):
                if chunk: # filter out keep-alive new chunks
                    f.write(chunk)
        print("Downloaded {}".format(filename))

for key, value in download_dictionary.items():
    download_file(key, value)

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[4], line 2
      1 for key, value in download_dictionary.items():
----> 2     download_file(key, value)

Cell In[3], line 4, in download_file(filename, file_id)
      2 """Download the file from Google Drive"""
      3 URL = "https://docs.google.com/uc?export=download"
----> 4 session = requests.Session()
      5 response = session.get(URL, params = { 'id' : file_id }, stream = True)
      6 if response.status_code == 200: # Successfully found the file on Google Drive

NameError: name 'requests' is not defined

Hooray, we downloaded the files! They are saved in the local directory.

We can simply read them in by handing-in the filename:

spectrum = IGRINSSpectrum(file='SDCH_20201202_0059.spec_a0v.fits', order=11).normalize()

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[5], line 1
----> 1 spectrum = IGRINSSpectrum(file='SDCH_20201202_0059.spec_a0v.fits', order=11).normalize()

NameError: name 'IGRINSSpectrum' is not defined

spectrum = spectrum.trim_edges().remove_nans()
spectrum.plot();

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[6], line 1
----> 1 spectrum = spectrum.trim_edges().remove_nans()
      2 spectrum.plot();

NameError: name 'spectrum' is not defined

Great, we fetched the spectrum from Google Drive, did some light post-processing, and plotted it!