[pre-commit.ci] pre-commit autoupdate

.pre-commit-config.yaml

@@ -1,7 +1,7 @@
 repos:
 - repo: https://github.com/astral-sh/ruff-pre-commit
   # Ruff version.
-  rev: v0.8.3
+  rev: v0.9.3
   hooks:
     # Run the linter.
     - id: ruff

arrakis/imager.py

@@ -110,12 +110,12 @@ def merge_imagesets(image_sets: List[Optional[ImageSet]]) -> ImageSet:
     prefix = image_sets[0].prefix
 
     for image_set in image_sets:
-        assert (
-            image_set.ms.name == ms.name
-        ), f"{image_set.ms.name=} does not match {ms.name=}"
-        assert (
-            image_set.prefix == prefix
-        ), f"{image_set.prefix=} does not match {prefix=}"
+        assert image_set.ms.name == ms.name, (
+            f"{image_set.ms.name=} does not match {ms.name=}"
+        )
+        assert image_set.prefix == prefix, (
+            f"{image_set.prefix=} does not match {prefix=}"
+        )
 
     image_lists = {}
     aux_lists = {}
@@ -936,9 +936,9 @@ def main(
     logger.info(f"Searching {msdir} for MS matching {ms_glob_pattern}.")
     mslist = sorted(msdir.glob(ms_glob_pattern))
 
-    assert (
-        (len(mslist) > 0) & (len(mslist) == num_beams)
-    ), f"Incorrect number of MS files found: {len(mslist)} / {num_beams} - glob pattern: {ms_glob_pattern}"
+    assert (len(mslist) > 0) & (len(mslist) == num_beams), (
+        f"Incorrect number of MS files found: {len(mslist)} / {num_beams} - glob pattern: {ms_glob_pattern}"
+    )
 
     logger.info(f"Will image {len(mslist)} MS files in {msdir} to {out_dir}")
     cleans = []

arrakis/linmos.py

@@ -79,9 +79,9 @@ def find_images(
     image_list: List[Path] = []
     for bm in list(set(field_beams["beam_list"])):  # Ensure list of beams is unique!
         imfile = Path(field_beams[f"{stoke.lower()}_beam{bm}_image_file"])
-        assert (
-            imfile.parent.name == src_name
-        ), f"Looking in wrong directory! '{imfile.parent.name}'"
+        assert imfile.parent.name == src_name, (
+            f"Looking in wrong directory! '{imfile.parent.name}'"
+        )
         new_imfile = datadir.resolve() / imfile
         image_list.append(new_imfile)
     image_list = sorted(image_list)
@@ -92,19 +92,19 @@ def find_images(
     weight_list: List[Path] = []
     for bm in list(set(field_beams["beam_list"])):  # Ensure list of beams is unique!
         wgtsfile = Path(field_beams[f"{stoke.lower()}_beam{bm}_weight_file"])
-        assert (
-            wgtsfile.parent.name == src_name
-        ), f"Looking in wrong directory! '{wgtsfile.parent.name}'"
+        assert wgtsfile.parent.name == src_name, (
+            f"Looking in wrong directory! '{wgtsfile.parent.name}'"
+        )
         new_wgtsfile = datadir.resolve() / wgtsfile
         weight_list.append(new_wgtsfile)
     weight_list = sorted(weight_list)
 
     assert len(image_list) == len(weight_list), "Unequal number of weights and images"
 
     for im, wt in zip(image_list, weight_list):
-        assert (
-            im.parent.name == wt.parent.name
-        ), "Image and weight are in different areas!"
+        assert im.parent.name == wt.parent.name, (
+            "Image and weight are in different areas!"
+        )
 
     return ImagePaths(image_list, weight_list)
 
@@ -185,8 +185,8 @@ def genparset(
 
     first_image = image_paths.images[0].resolve().with_suffix("").as_posix()
     first_weight = image_paths.weights[0].resolve().with_suffix("").as_posix()
-    linmos_image_str = f"{first_image[:first_image.find('beam')]}linmos"
-    linmos_weight_str = f"{first_weight[:first_weight.find('beam')]}linmos"
+    linmos_image_str = f"{first_image[: first_image.find('beam')]}linmos"
+    linmos_weight_str = f"{first_weight[: first_weight.find('beam')]}linmos"
 
     parset_file = os.path.join(parset_dir, f"linmos_{stoke}.in")
     parset = f"""linmos.names            = {image_string}

arrakis/makecat.py

@@ -217,9 +217,9 @@ def is_blended_component(sub_df: pd.DataFrame) -> pd.DataFrame:
     )
     # Sanity check - no single-component sources should be flagged
     assert np.array_equal(is_blended.index.values, cat["cat_id"].data), "Index mismatch"
-    assert not any(
-        cat["is_blended_flag"] & (cat["N_Gaus"] == 1)
-    ), "Single-component sources cannot be flagged as blended."
+    assert not any(cat["is_blended_flag"] & (cat["N_Gaus"] == 1)), (
+        "Single-component sources cannot be flagged as blended."
+    )
     if "index" in cat.colnames:
         cat.remove_column("index")
     return cat
@@ -507,7 +507,7 @@ def sn_func(index, signal=None, noise=None):
                 if "Not enough S/N in the whole set of pixels." not in str(e):
                     raise e
                 logger.warning(
-                    f"Failed with target number of RMs per bin of {target_sn}. Trying again with {target_sn-10}"
+                    f"Failed with target number of RMs per bin of {target_sn}. Trying again with {target_sn - 10}"
                 )
                 target_sn -= 10
         else:
@@ -943,7 +943,7 @@ def main(
     query = {"$and": [{f"beams.{field}": {"$exists": True}}]}
     all_island_ids = sorted(beams_col.distinct("Source_ID", query))
     tock = time.time()
-    logger.info(f"Finished beams collection query - {tock-tick:.2f}s")
+    logger.info(f"Finished beams collection query - {tock - tick:.2f}s")
 
     logger.info("Starting component collection query")
     tick = time.time()
@@ -1023,15 +1023,15 @@ def main(
     # )
     comps_df.set_index("Source_ID", inplace=True)
     tock = time.time()
-    logger.info(f"Finished component collection query - {tock-tick:.2f}s")
+    logger.info(f"Finished component collection query - {tock - tick:.2f}s")
     logger.info(f"Found {len(comps_df)} components to catalogue. ")
 
     logger.info("Starting island collection query")
     tick = time.time()
     islands_df = pd.DataFrame(island_col.find({"Source_ID": {"$in": all_island_ids}}))
     islands_df.set_index("Source_ID", inplace=True)
     tock = time.time()
-    logger.info(f"Finished island collection query - {tock-tick:.2f}s")
+    logger.info(f"Finished island collection query - {tock - tick:.2f}s")
 
     if len(comps_df) == 0:
         logger.error("No components found for this field.")

arrakis/merge_fields.py

@@ -145,7 +145,7 @@ def genparset(
     new_dir: str,
 ) -> str:
     imlist = "[" + ",".join([im.replace(".fits", "") for im in old_ims]) + "]"
-    weightlist = f"[{','.join([im.replace('.fits', '').replace('.image.restored.','.weights.').replace('.ion','') for im in old_ims])}]"
+    weightlist = f"[{','.join([im.replace('.fits', '').replace('.image.restored.', '.weights.').replace('.ion', '') for im in old_ims])}]"
 
     im_outname = os.path.join(new_dir, os.path.basename(old_ims[0])).replace(
         ".fits", ".edge.linmos"
@@ -288,9 +288,9 @@ def main(
 ) -> str:
     logger.debug(f"{fields=}")
 
-    assert (
-        len(fields) == len(field_dirs)
-    ), f"List of fields must be the same length as length of field dirs. {len(fields)=},{len(field_dirs)=}"
+    assert len(fields) == len(field_dirs), (
+        f"List of fields must be the same length as length of field dirs. {len(fields)=},{len(field_dirs)=}"
+    )
 
     field_dict = {
         field: os.path.join(field_dir, "cutouts")

arrakis/rmclean_oncuts.py

@@ -66,9 +66,9 @@ def rmclean1d(
     logger.debug(f"Working on {comp}")
     save_name = field if sbid is None else f"{field}_{sbid}"
 
-    assert (
-        comp["rm_outputs_1d"]["field"] == save_name
-    ), f"Field mismatch - expected {save_name} got {comp['rm_outputs_1d']['field']}"
+    assert comp["rm_outputs_1d"]["field"] == save_name, (
+        f"Field mismatch - expected {save_name} got {comp['rm_outputs_1d']['field']}"
+    )
 
     rm1dfiles = comp["rm_outputs_1d"]["rm1dfiles"]
     fdfFile = outdir / f"{rm1dfiles['FDF_dirty']}"
@@ -175,9 +175,9 @@ def rmclean3d(
     prefix = f"{iname}_"
     rm3dfiles = island["rm_outputs_3d"]["rm3dfiles"]
     save_name = field if sbid is None else f"{field}_{sbid}"
-    assert (
-        island["rm_outputs_3d"]["field"] == save_name
-    ), f"Field mismatch - expected {save_name} got {island['rm_outputs_3d']['field']}"
+    assert island["rm_outputs_3d"]["field"] == save_name, (
+        f"Field mismatch - expected {save_name} got {island['rm_outputs_3d']['field']}"
+    )
 
     cleanFDF, ccArr, iterCountArr, residFDF, headtemp = do_RMclean_3D.run_rmclean(
         fitsFDF=(outdir / rm3dfiles["FDF_real_dirty"]).as_posix(),

arrakis/utils/msutils.py

@@ -69,9 +69,9 @@ def field_idx_from_ms(ms: str) -> int:
     """Get the field from MS metadata"""
     with table(f"{ms}/FIELD", readonly=True, ack=False) as field:
         idxs = list(field.SOURCE_ID)
-        assert len(idxs) == 1 or all(
-            [idx == idxs[0] for idx in idxs]
-        ), "More than one field in MS"
+        assert len(idxs) == 1 or all([idx == idxs[0] for idx in idxs]), (
+            "More than one field in MS"
+        )
         idx = idxs[0]
     return idx
 
@@ -766,6 +766,6 @@ def wsclean(
         elif value:
             if "ws_" in key:  # Catch for ws_continue command
                 key.replace("ws_", "")
-            command += f" -{key.replace('_','-')} {value}"
+            command += f" -{key.replace('_', '-')} {value}"
     command += f" {' '.join(mslist)}"
     return command

arrakis/utils/pipeline.py

@@ -92,9 +92,9 @@ def upload_image_as_artifact_task(
     """
     image_type = image_path.suffix.replace(".", "")
     assert image_path.exists(), f"{image_path} does not exist"
-    assert (
-        image_type in SUPPORTED_IMAGE_TYPES
-    ), f"{image_path} has type {image_type}, and is not supported. Supported types are {SUPPORTED_IMAGE_TYPES}"
+    assert image_type in SUPPORTED_IMAGE_TYPES, (
+        f"{image_path} has type {image_type}, and is not supported. Supported types are {SUPPORTED_IMAGE_TYPES}"
+    )
 
     with open(image_path, "rb") as open_image:
         logger.info(f"Encoding {image_path} in base64")

arrakis/validate.py

@@ -288,7 +288,7 @@ def plot_leakage(
             overlay[1].set_axislabel("$b$", color="tab:blue")
             fig.colorbar(im, ax=ax, label="Fraction", shrink=0.7, pad=0.15)
             ax.set_title(
-                f"Stokes {stokes}/I (binned) - absmed: {np.nanmedian(np.abs(data))*100:0.1f}$\pm${np.nanstd(np.abs(data))*100:0.1f}%",
+                f"Stokes {stokes}/I (binned) - absmed: {np.nanmedian(np.abs(data)) * 100:0.1f}$\pm${np.nanstd(np.abs(data)) * 100:0.1f}%",
                 pad=50,
             )
 
@@ -384,8 +384,8 @@ def plot_rm(
             ax.legend()
 
             ax.set(
-                xlabel=f"RACS  / {u.rad/u.m**2:latex_inline}",
-                ylabel=f"{label} / {u.rad/u.m**2:latex_inline}",
+                xlabel=f"RACS  / {u.rad / u.m**2:latex_inline}",
+                ylabel=f"{label} / {u.rad / u.m**2:latex_inline}",
                 aspect="equal",
             )
         _ = ax_dict["M"].imshow(

scripts/casda_prepare.py

@@ -536,9 +536,9 @@ def main(
         cubes = find_cubes(data_dir=data_dir)
         # Check if we have a cube for each source
         try:
-            assert len(cubes) == len(
-                set(polcat["source_id"])
-            ), "Number of cubes does not match number of sources"
+            assert len(cubes) == len(set(polcat["source_id"])), (
+                "Number of cubes does not match number of sources"
+            )
         except AssertionError:
             logger.warning(
                 f"Found {len(cubes)} cubes, expected {len(set(polcat['source_id']))}"
@@ -566,9 +566,9 @@ def main(
                 with open(outf, "w") as f:
                     for rid in rem_ids:
                         f.write(f"{rid}\n")
-                assert (
-                    len(cubes) == len(set(polcat["source_id"]))
-                ), f"Number of cubes does not match number of sources -- {len(cubes)=} and {len(set(polcat['source_id']))=}"
+                assert len(cubes) == len(set(polcat["source_id"])), (
+                    f"Number of cubes does not match number of sources -- {len(cubes)=} and {len(set(polcat['source_id']))=}"
+                )
 
         unique_ids, unique_idx = np.unique(polcat["source_id"], return_index=True)
         lookup = {sid: i for sid, i in zip(unique_ids, unique_idx)}
@@ -609,9 +609,9 @@ def my_sorter(x, lookup=lookup, pbar=pbar):
                 cat_ids.append(cat_id)
             in_idx = np.isin(cat_ids, polcat["cat_id"])
             spectra = list(np.array(spectra)[in_idx])
-        assert len(spectra) == len(
-            polcat
-        ), f"{len(spectra)=} and {len(polcat)=}"  # Sanity check
+        assert len(spectra) == len(polcat), (
+            f"{len(spectra)=} and {len(polcat)=}"
+        )  # Sanity check
 
         unique_ids, unique_idx = np.unique(polcat["cat_id"], return_index=True)
         lookup = {sid: i for sid, i in zip(unique_ids, unique_idx)}
@@ -678,9 +678,9 @@ def my_sorter(x, lookup=lookup, pbar=pbar):
             in_idx = np.isin(cat_ids, polcat["cat_id"])
             plots = list(np.array(plots)[in_idx])
 
-        assert (
-            len(plots) == len(polcat) * 3
-        ), f"{len(plots)=} and {len(polcat)=}"  # Sanity check
+        assert len(plots) == len(polcat) * 3, (
+            f"{len(plots)=} and {len(polcat)=}"
+        )  # Sanity check
 
         with tqdm(total=len(plots), desc="Sorting plots", file=TQDM_OUT) as pbar:
 

scripts/compute_leakage.py

@@ -241,7 +241,7 @@ def main(field, datadir, username="admin", password=None):
         ax[0, i].imshow(q, origin="lower", vmin=-lim, vmax=lim, cmap=plt.cm.coolwarm)
         ax[0, i].axis("off")
         ax[0, i].invert_xaxis()
-        ax[0, i].set_title(f"{f/1e6:0.1f}MHz")
+        ax[0, i].set_title(f"{f / 1e6:0.1f}MHz")
         ax[1, i].imshow(
             u,
             origin="lower",

scripts/find_sbid.py

@@ -110,8 +110,8 @@ def main(
     if not cal and not science and not weight:
         logger.info(f"DB info for RACS_{name}:\n")
         for i, row in enumerate(sub_tab):
-            logger.info(f"{space}CAL SBID {i+1}: {row['CAL_SBID']}")
-            logger.info(f"{space}Science SBID {i+1}: {row['SBID']}\n")
+            logger.info(f"{space}CAL SBID {i + 1}: {row['CAL_SBID']}")
+            logger.info(f"{space}Science SBID {i + 1}: {row['SBID']}\n")
 
 
 def cli():