xradio 0.0.56__py3-none-any.whl → 0.0.58__py3-none-any.whl

xradio/measurement_set/_utils/_msv2/_tables/read.py

@@ -46,16 +46,20 @@ def convert_casacore_time(
     rawtimes: np.ndarray, convert_to_datetime: bool = True
 ) -> np.ndarray:
     """
-    Read time columns to datetime format
-    pandas datetimes are referenced against a 0 of 1970-01-01
-    CASA's modified julian day reference time is (of course) 1858-11-17
+    Convert data from casacore time columns to a different format, either:
+    a) pandas style datetime,
+    b) simply seconds from 1970-01-01 00:00:00 UTC (as used in the Unix scale of
+       astropy).
+
+    Pandas datetimes and Unix times are referenced against a 0 of 1970-01-01.
+    CASA's (casacore) modified julian day reference time is (of course) 1858-11-17.
 
     This requires a correction of 3506716800 seconds which is hardcoded to save time
 
     Parameters
     ----------
     rawtimes : np.ndarray
-        times in casacore ref
+        time values wrt casacore reference
     convert_to_datetime : bool (Default value = True)
         whether to produce pandas style datetime
 
@@ -351,70 +355,6 @@ def add_units_measures(
     return mvars
 
 
-def make_freq_attrs(spw_xds: xr.Dataset, spw_id: int) -> Dict[str, Any]:
-    """
-    Grab the units/measure metainfo for the xds.freq dimension of a
-    parttion from the SPECTRAL_WINDOW subtable CTDS attributes.
-
-    Has to read xds_spw.meas_freq_ref and use it as index in the CTDS
-    'VarRefCol' attrs of CHAN_FREQ and REF_FREQUENCY to give a
-    reference frame to xds_spw.ref_frequency and xds_spw.chan_freq
-    (then the ref frame from the second will be pulled to
-    xds.freq.attrs)
-
-    Parameters
-    ----------
-    spw_xds : xr.Dataset
-        (metainfo) SPECTRAL_WINDOW xds
-    spw_id : int
-        SPW id of a partition
-
-    Returns
-    -------
-    Dict[str, Any]
-        attributes (units/measure) for the freq dim of a partition
-    """
-    fallback_TabRefTypes = [
-        "REST",
-        "LSRK",
-        "LSRD",
-        "BARY",
-        "GEO",
-        "TOPO",
-        "GALACTO",
-        "LGROUP",
-        "CMB",
-    ]
-
-    ctds_cols = spw_xds.attrs["other"]["msv2"]["ctds_attrs"]["column_descriptions"]
-    cfreq = ctds_cols["CHAN_FREQ"]
-
-    cf_attrs = spw_xds.data_vars["CHAN_FREQ"].attrs
-    if "MEASINFO" in cfreq["keywords"] and "VarRefCol" in cfreq["keywords"]["MEASINFO"]:
-        fattrs = cfreq["keywords"]["MEASINFO"]
-        var_ref_col = fattrs["VarRefCol"]
-        # This should point to the SPW/MEAS_FREQ_REF col
-        meas_freq_ref_idx = spw_xds.data_vars[var_ref_col].values[spw_id]
-
-        if "TabRefCodes" not in fattrs or "TabRefTypes" not in fattrs:
-            # Datasets like vla/ic2233_1.ms say "VarRefCol" but "TabRefTypes" is missing
-            ref_frame = fallback_TabRefTypes[meas_freq_ref_idx]
-        else:
-            ref_type_code = fattrs["TabRefCodes"][meas_freq_ref_idx]
-            ref_frame = fattrs["TabRefTypes"][ref_type_code]
-
-        cf_attrs["measure"] = {
-            "type": fattrs["type"],
-            "ref_frame": ref_frame,
-        }
-
-        # Also set the 'VarRefCol' for CHAN_FREQ and REF_FREQUENCEY
-        spw_xds.data_vars["CHAN_FREQ"].attrs.update(cf_attrs)
-        spw_xds.data_vars["REF_FREQUENCY"].attrs.update(cf_attrs)
-
-    return cf_attrs
-
-
 def redimension_ms_subtable(xds: xr.Dataset, subt_name: str) -> xr.Dataset:
     """
     Expand a MeasurementSet subtable xds from single dimension (row)
@@ -551,8 +491,8 @@ def load_generic_table(
     tname : str
         (sub)table name, for example 'SOURCE' for myms.ms/SOURCE
     timecols : Union[List[str], None] (Default value = None)
-        column names to convert to numpy datetime format.
-        leaves times as their original casacore format.
+        Names of time column(s), to convert from casacore times to 1970-01-01 scale
+        An empty list leaves times as their original casacore format.
     ignore : Union[List[str], None] (Default value = None)
         list of column names to ignore and not try to read.
     rename_ids : Dict[str, str] (Default value = None)
@@ -748,7 +688,7 @@ def load_generic_cols(
     tb_tool : tables.table
         table to load the columns
     timecols : Union[List[str], None]
-        columns names to convert to datetime format
+        column names to convert from casacore time format
     ignore : Union[List[str], None]
         list of column names to skip and not try to load.
 
@@ -828,7 +768,7 @@ def load_fixed_size_cols(
     tb_tool : tables.table
         table to red the columns
     timecols : Union[List[str], None]
-        columns names to convert to datetime format
+        column names to convert from casacore time format
     ignore : Union[List[str], None]
         list of column names to skip and not try to load.
 
@@ -923,7 +863,8 @@ def raw_col_data_to_coords_vars(
     data: np.ndarray :
         column data
     timecols: Union[List[str], None]
-        columns to be treated as TIME-related
+        columns to be treated as TIME-related (they are coordinate, need conversion from
+        casacore time format.
 
     Returns
     -------
@@ -953,7 +894,7 @@ def raw_col_data_to_coords_vars(
             data = convert_mjd_time(data).astype("float64") / 1e9
         else:
             try:
-                data = convert_casacore_time(data)
+                data = convert_casacore_time(data, False)
             except pd.errors.OutOfBoundsDatetime as exc:
                 if inpath.endswith("WEATHER"):
                     # intentionally not callling logging.exception
@@ -993,7 +934,7 @@ def raw_col_data_to_coords_vars(
 
 def get_pad_value_in_tablerow_column(trows: tables.tablerow, col: str) -> object:
     """
-    Gets the pad value for the type of a column (IMPORTANTLY) as froun in the
+    Gets the pad value for the type of a column (IMPORTANTLY) as found in the
     the type specified in the row / column value dict returned by tablerow.
     This can differ from the type of the column as given in the casacore
     column descriptions. See https://github.com/casangi/xradio/issues/242.
@@ -1195,7 +1136,7 @@ def read_col_chunk(
     np.ndarray
     """
     # TODO: consider calling load_col_chunk() from inside the withs
-    # for read_delayed_pointing_table and read_expanded_main_table
+    # for read_expanded_main_table
     with open_table_ro(infile) as mtable:
         with open_query(mtable, ts_taql) as query:
             if (len(cshape) == 2) or (col == "UVW"):  # all the scalars and UVW