AnaCal ingestion

examples/anacal/config.yml

@@ -0,0 +1,79 @@
+global:
+    chunk_rows: 100000
+    sparse: true  # Generate sparse maps - faster if using small areas
+    pixelization: healpix
+    nside: 512
+
+TXIngestAnacal:
+    # DP1-v3 AnaCal outputs for the a360 cluster field (per-tract).
+    butler_config_file: /global/cfs/cdirs/lsst/production/gen3/rubin/DP1/repo/butler.yaml
+    collections: "u/xiangchl/dp1-v3/a360_anacal2"
+
+    # a360 sits in the "Low Ecliptic Latitude Field" (LELF).  DP1_TRACTS["LELF"]
+    # contains the two live tracts 10463, 10464 (plus four never-processed).
+    select_field: "LELF"
+    cosmology_tracts_only: False
+
+    # Merged catalog carries band-combined shape moments under the "fpfs1_*"
+    # prefix and Gaussian-aperture fluxes at scale "gauss2".  Per-band
+    # columns are survey-prefixed as ``lsst_{band}_...`` (v3 schema) and
+    # carry pre-computed magnitudes + dmag/dg responses, so no
+    # nanojansky→mag conversion happens inside the ingest.  a360 was
+    # measured on griz only (no u/y coadds).
+    prefix: "fpfs1"
+    scale: "gauss2"
+    bands: "griz"
+
+TXSourceSelectorAnaCal:
+    # AnaCal shear-response step size for selection bias correction — must
+    # match the δγ used to build the on-disk photo-z distortions
+    # (zmode_{1p,1m,2p,2m}) in xlens' photoZPipe (currently ±0.01 in
+    # DISTORTIONS).
+    delta_gamma: 0.01
+
+    # mask_value threshold — sources with mask_value >= this get dropped.
+    # AnaCal reports a bit-packed flag; 1 means "any bit set" (strictest).
+    mask_threshold: 40
+
+    # AnaCal S/N cut (flux / flux_err).  Default in code is 5.0.
+    s2n_cut: 5.0
+
+    # Band-combined size cut (m00 + m20) / m00 > T_cut on fpfs1 moments.
+    # Default 0.1.
+    T_cut: 0.1
+
+    # Band-combined shape magnitude cut |e| < emax (selector applies
+    # esq < emax**2 on the ``esq`` column).
+    emax: 0.5
+
+    # Per-band AB mag upper bounds (uses pre-computed mag_{b} from v3
+    # ingest). Default 50 is above the xlens smooth-truncation cap
+    # (mag=40) so no cut is applied; set per band to gate on brightness.
+    g_hi_cut: 50.0
+    r_hi_cut: 50.0
+    i_hi_cut: 50.0
+    z_hi_cut: 50.0
+
+    # Bands available in the a360 ingest.
+    bands: [g, r, i, z]
+
+    # 5 tomographic bins — will need edited to fit your science n(z).
+    source_zbin_edges: [0.3, 0.6, 0.9, 1.2, 1.5, 2.0]
+
+    # ``input_pz: true`` reads ``mean_z`` from the shear catalog and skips the
+    # random-forest classifier.  TXIngestAnacal exposes ``mean_z`` (from
+    # ``zmode_0`` in the merged catalog) plus the four shifted variants
+    # ``mean_z_{1p,1m,2p,2m}`` (from ``zmode_{1p,1m,2p,2m}``) — the selector
+    # consumes the baseline column for tomographic binning and the four
+    # variants for the selection response computation.
+    # If ``input_pz: false``, a shear_tomography_classifier pickle +
+    # spectroscopic_catalog are required (see pipeline.yml inputs).
+    input_pz: true
+    true_z: false
+    verbose: True
+    chunk_rows: 100000
+
+TXShearCalibration:
+    shear_catalog_type: anacal
+    subtract_mean_shear: true
+    chunk_rows: 100000

examples/anacal/ingest.yml

@@ -0,0 +1,28 @@
+# AnaCal ingest — runs TXIngestAnacal only.  Writes the shear catalog
+# into ``data/example/anacal_inputs`` which is then consumed by
+# ``examples/anacal/pipeline.yml``.
+
+stages:
+  - name: TXIngestAnacal
+
+output_dir: data/example/anacal_inputs
+
+launcher:
+    name: mini
+    interval: 1.0
+
+site:
+    name: local
+
+modules: >
+    txpipe
+
+config: examples/anacal/config.yml
+
+inputs:
+    # Butler-mode ingest doesn't read this FITS, but ceci requires every
+    # declared input to have a path — pointed at the DP1-v3 published
+    # per-field catalog to satisfy the graph builder.
+    anacal_catalog: /global/cfs/cdirs/desc-wl/projects/anacal/DP1-v3/catalogs/anacal_catalog_a360.fits
+
+resume: False

examples/anacal/pipeline.yml

@@ -0,0 +1,35 @@
+# AnaCal selector + calibrator pipeline — reads the shear catalog produced
+# by ``examples/anacal/ingest.yml``.
+
+stages:
+  - name: TXSourceSelectorAnaCal
+  - name: TXShearCalibration
+
+output_dir: data/example/output_anacal
+
+launcher:
+    name: mini
+    interval: 1.0
+
+site:
+    name: local
+    max_threads: 2
+
+modules: >
+    txpipe
+
+config: examples/anacal/config.yml
+
+inputs:
+    shear_catalog: data/example/anacal_inputs/shear_catalog.hdf5
+
+    # Selector-side inputs.  With ``input_pz: true`` in config.yml the
+    # selector reads ``mean_z`` from the shear catalog (populated by
+    # TXIngestAnacal from ``zmode_0``), so these two are only exercised
+    # under ``input_pz: false`` (random-forest tomography).  Kept here to
+    # satisfy the ceci graph builder — ceci checks every declared input
+    # has a path, even when the stage doesn't open it.
+    spectroscopic_catalog: /pscratch/sd/x/xiangchl/data/DP1/catalogs/spec_catalog_a360.hdf5
+    shear_tomography_classifier: /pscratch/sd/x/xiangchl/data/DP1/catalogs/shear_tomography_classifier_a360.pkl
+
+resume: False

txpipe/__init__.py

@@ -10,6 +10,7 @@
     TXSourceSelectorMetacal,
     TXSourceSelectorLensfit,
     TXSourceSelectorMetadetect,
+    TXSourceSelectorAnacal,
 )
 from .lens_selector import TXMeanLensSelector
 from .photoz_stack import TXPhotozStack, TXPhotozPlot, TXTruePhotozStack

txpipe/calibrate.py

@@ -181,6 +181,8 @@ def run(self):
                     # therefore, we add dec to split data into these fields.
                     # You can choose not to by setting dec_cut = 90 in the config, for example.
                     d["g1"], d["g2"] = cal.apply(d["g1"], d["g2"], d["dec"], subtract_mean=subtract_mean_shear)
+                elif cat_type == "anacal":
+                    d["g1"], d["g2"] = cal.apply(d["g1"], d["g2"], d["weight"], subtract_mean=subtract_mean_shear)
                 else:
                     d["g1"], d["g2"] = cal.apply(d["g1"], d["g2"], subtract_mean=subtract_mean_shear)
 

txpipe/data_types.py

@@ -108,6 +108,9 @@ def get_primary_catalog_names(self, true_shear=False):
         elif self.catalog_type == "metadetect":
             shear_cols = ["00/g1", "00/g2", "00/ra", "00/dec", "00/weight"]
             rename = {c: c[3:] for c in shear_cols}
+        elif self.catalog_type == "anacal":
+            shear_cols = ["e1", "e2", "ra", "dec", "weight"]
+            rename = {"e1":"g1", "e2":"g2"}
         else:
             shear_cols = ["g1", "g2", "ra", "dec", "weight"]
             rename = {}

txpipe/diagnostics.py

@@ -223,6 +223,8 @@ def run(self):
                 "weight",
             )
             shear_cols += band_variants(bands, "mag", "mag_err", shear_catalog_type="metadetect")
+        elif cat_type == "anacal":
+            raise NameError("anacal does not work with this atm.")
         else:
             shear_cols = [
                 "dec",

txpipe/ingest/__init__.py

@@ -10,4 +10,5 @@
     TXIngestSSIDetectionDESBalrog,
 )
 from .dp1 import TXIngestDataPreview1
+from .anacal import TXIngestAnacal
 from .stage3 import TXIngestDESY3Gold