catname = "I/354"
catalogue_ivoid = f"ivo://CDS.VizieR/{catname}"

# the actual query to the registry
voresource = registry.search(ivoid=catalogue_ivoid)[0]

voresource.describe(verbose=True)

StarHorse2, Gaia EDR3 photo-astrometric distances
Short Name: I/354
IVOA Identifier: ivo://cds.vizier/i/354
Access modes: conesearch, hips#hips-1.0, tap#aux, web
Multi-capabilty service -- use get_service()

We present a catalogue of 362 million stellar parameters, distances, and
extinctions derived from Gaia's Early Data Release (EDR3) cross-matched with
the photometric catalogues of Pan-STARRS1, SkyMapper, 2MASS, and AllWISE. The
higher precision of the Gaia EDR3 data, combined with the broad wavelength
coverage of the additional photometric surveys and the new stellar-density
priors of the StarHorse code, allows us to substantially improve the accuracy
and precision over previous photo-astrometric stellarparameter estimates. At
magnitude G=14 (17), our typical precisions amount to 3% (15%) in distance,
0.13mag (0.15mag) in V-band extinction, and 140K (180K) in effective
temperature. Our results are validated by comparisons with open clusters, as
well as with asteroseismic and spectroscopic measurements, indicating
systematic errors smaller than the nominal uncertainties for the vast majority
of objects. We also provide distance- and extinction-corrected colour-
magnitude diagrams, extinction maps, and extensive stellar density maps that
reveal detailed substructures in the Milky Way and beyond. The new density
maps now probe a much greater volume, extending to regions beyond the Galactic
bar and to Local Group galaxies, with a larger total number density. We
publish our results through an ADQL query interface (gaia.aip.de) as well as
via tables containing approximations of the full posterior distributions. Our
multi-wavelength approach and the deep magnitude limit render our results
useful also beyond the next Gaia release, DR3.

Subjects: I/354
Waveband Coverage:
More info: https://cdsarc.cds.unistra.fr/viz-bin/cat/I/354

# execute a synchronous ADQL query
tap_service = voresource.get_service("tap")

# Function to run a TAP query and return a Dask DataFrame
def query_tap(service, ra_min, ra_max, dec_min, dec_max):
    query = f'''
    SELECT * 
    FROM "{first_table_name}" 
    WHERE ra BETWEEN {ra_min} AND {ra_max}
    AND dec BETWEEN {dec_min} AND {dec_max}
    '''
    tap_records = service.run_sync(query)
    tbl = tap_records.to_table()
    df = tbl.to_pandas()
    return dd.from_pandas(df, npartitions=1)

# Initialize the Dask DataFrame
final_ddf = dd.DataFrame()

# Coordinate limits
ra_min, ra_max = 0, 360
dec_min, dec_max = -30, 90

# Service initialization (replace with actual service initialization)
service = voresource.get_service("tap")

# Perform the queries in chunks and append to the Dask DataFrame
for dec in range(dec_min, dec_max, dec_step):
  
    dec_min_chunk, dec_max_chunk = dec, dec+dec_step
    chunk_ddf = query_tap(service, ra_min, ra_max, dec_min_chunk, dec_max_chunk)
    
    # Concatenate the new chunk with the final Dask DataFrame
    if final_ddf.npartitions == 0:
        final_ddf = chunk_ddf
    else:
        final_ddf = dd.concat([final_ddf, chunk_ddf])

from hipscat_import.catalog.arguments import ImportArguments

args = ImportArguments(
    ra_column="RA_ICRS_StarHorse",
    dec_column="DE_ICRS_StarHorse",
    file_reader="parquet",
    input_file_list=[f"{input_file}"],
    output_artifact_name="StarHorseApril21_output_hips",
    output_path="/nvme/users/atzanida/tmp/",
    resume=False,
)

# load StarHorse table
object_table = lsdb.read_hipscat("/nvme/users/atzanida/tmp/StarHorseApril21_output_hips")

# Load ZTF DR17 ZUBERBCAL sources
ztf_sources = lsdb.read_hipscat("/epyc/data3/hipscat/catalogs/zubercal", 
                               columns=["mjd", "mag", "magerr", "band", 
                                        "flag", "fieldid", "objectid", "rcidin", 
                                       "objra", "objdec", "info"])

def convert_to_nested_frame(df: pd.DataFrame, nested_columns: list[str]):
    """Map a pandas DataFrame to a nested dataframe."""
    
    other_columns = [col for col in df.columns if col not in nested_columns]

    # Since object rows are repeated, we just drop duplicates
    object_df = df[other_columns].groupby(level=0).first()
    nested_frame = npd.NestedFrame(object_df)
    
    return nested_frame.add_nested(df[nested_columns], "lc")
  
  # join hips FGK object table to ZTF sources
  lsdb_joined = object_table.join(
    ztf_sources,
    left_on="ps1_objid_ztf_dr14",
    right_on="objectid",
    suffixes=("", ""))

  # get joined dataframe
  joined_ddf = lsdb_joined._ddf

  # map partitions of jointed dataframe
  ddf = joined_ddf.map_partitions(
    lambda df: convert_to_nested_frame(df, nested_columns=lc_columns),
    meta=convert_to_nested_frame(joined_ddf._meta, nested_columns=lc_columns),
  )

  nested_ddf = NestedFrame.from_dask_dataframe(ddf)

target = 88291272191

# load target photometry
lc = nested_ddf.loc[target].compute().lc