pz-rail-astro-tools 1.0.5__tar.gz → 1.0.6__tar.gz

{pz_rail_astro_tools-1.0.5 → pz_rail_astro_tools-1.0.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pz-rail-astro-tools
-Version: 1.0.5
+Version: 1.0.6
 Author-email: "LSST Dark Energy Science Collaboration (DESC)" <lsst-desc-rail-admin@slac.stanford.edu>
 License: MIT License
         

{pz_rail_astro_tools-1.0.5 → pz_rail_astro_tools-1.0.6}/src/pz_rail_astro_tools.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pz-rail-astro-tools
-Version: 1.0.5
+Version: 1.0.6
 Author-email: "LSST Dark Energy Science Collaboration (DESC)" <lsst-desc-rail-admin@slac.stanford.edu>
 License: MIT License
         

{pz_rail_astro_tools-1.0.5 → pz_rail_astro_tools-1.0.6}/src/pz_rail_astro_tools.egg-info/SOURCES.txt

@@ -22,7 +22,6 @@ src/pz_rail_astro_tools.egg-info/requires.txt
 src/pz_rail_astro_tools.egg-info/top_level.txt
 src/rail/astro_tools/__init__.py
 src/rail/astro_tools/_version.py
-src/rail/creation/degraders/bl_demo.ipynb
 src/rail/creation/degraders/grid_selection.py
 src/rail/creation/degraders/observing_condition_degrader.py
 src/rail/creation/degraders/photometric_errors.py

{pz_rail_astro_tools-1.0.5 → pz_rail_astro_tools-1.0.6}/src/rail/astro_tools/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '1.0.5'
-__version_tuple__ = version_tuple = (1, 0, 5)
+__version__ = version = '1.0.6'
+__version_tuple__ = version_tuple = (1, 0, 6)

{pz_rail_astro_tools-1.0.5 → pz_rail_astro_tools-1.0.6}/src/rail/creation/degraders/unrec_bl_model.py

@@ -2,6 +2,7 @@
 
 from ceci.config import StageParameter as Param
 from rail.creation.degrader import Degrader
+from rail.core.data import PqHandle
 import numpy as np, pandas as pd
 import FoFCatalogMatching
 
@@ -27,6 +28,46 @@ class UnrecBlModel(Degrader):
                           b=Param(str, 'semi_minor', msg='semi minor axis column name'),
                           theta=Param(str, 'orientation', msg='orientation angle column name'))
 
+    outputs = [("output", PqHandle), ("compInd", PqHandle)]
+
+    def __call__(self, sample, seed: int = None):
+        """The main interface method for ``Degrader``.
+
+        Applies degradation.
+
+        This will attach the sample to this `Degrader` (for introspection and
+        provenance tracking).
+
+        Then it will call the run() and finalize() methods, which need to be
+        implemented by the sub-classes.
+
+        The run() method will need to register the data that it creates to this
+        Estimator by using ``self.add_data('output', output_data)``.
+
+        Finally, this will return a PqHandle providing access to that output
+        data.
+
+        Parameters
+        ----------
+        sample : table-like
+            The sample to be degraded
+        seed : int, default=None
+            An integer to set the numpy random seed
+
+        Returns
+        -------
+        output_data : PqHandle
+            A handle giving access to a table with degraded sample
+        """
+        if seed is not None:
+            self.config.seed = seed
+
+        self.set_data("input", sample)
+        self.run()
+        self.finalize()
+
+        return {'output':self.get_handle("output"), 'compInd':self.get_handle("compInd")}
+
     def __match_bl__(self, data):
 
         """Group sources with friends of friends"""
@@ -43,7 +84,7 @@ class UnrecBlModel(Degrader):
         ## adding the group id as the last column to data
         matchData = pd.merge(data, results, left_index=True, right_index=True)
 
-        return matchData
+        return matchData, results
 
     def __merge_bl__(self, data):
 
@@ -53,30 +94,25 @@ class UnrecBlModel(Degrader):
         unique_id = np.unique(group_id)
 
         ra_label, dec_label = self.config.ra_label, self.config.dec_label
-
-        cols = list(data.columns)
-        ra_ind = cols.index(ra_label)
-        dec_ind = cols.index(dec_label)
-        bands_ind = {b:cols.index(b) for b in self.config.bands}
+        cols = [ra_label, dec_label] + [b for b in self.config.bands] + ['group_id']
 
         N_rows = len(unique_id)
         N_cols = len(cols)
 
         mergeData = np.zeros((N_rows, N_cols))
-        
         for i, id in enumerate(unique_id):
 
             this_group = data.query(f'group_id=={id}')
 
             ## take the average position for the blended source
-            mergeData[i, ra_ind] = this_group[ra_label].mean()
-            mergeData[i, dec_ind] = this_group[dec_label].mean()
+            mergeData[i, cols.index(ra_label)] = this_group[ra_label].mean()
+            mergeData[i, cols.index(dec_label)] = this_group[dec_label].mean()
 
             ## sum up the fluxes into the blended source
             for b in self.config.bands:
-                  mergeData[i, bands_ind[b]] = -2.5*np.log10(np.sum(10**(-this_group[b]/2.5)))
+                  mergeData[i, cols.index(b)] = -2.5*np.log10(np.sum(10**(-this_group[b]/2.5)))
 
-        mergeData[:,-1] = unique_id
+        mergeData[:,cols.index('group_id')] = unique_id
         mergeData_df = pd.DataFrame(data=mergeData, columns=cols)
         mergeData_df['group_id'] = mergeData_df['group_id'].astype(int)
 
@@ -89,10 +125,12 @@ class UnrecBlModel(Degrader):
         data = self.get_data("input")
 
         # Match for close-by objects
-        matchData = self.__match_bl__(data)
+        matchData, compInd = self.__match_bl__(data)
 
         # Merge matched objects into unrec-bl
         blData = self.__merge_bl__(matchData)
 
-        # Return the new catalog
+        # Return the new catalog and component index in original catalog
         self.add_data("output", blData)
+        self.add_data("compInd", compInd)
+

{pz_rail_astro_tools-1.0.5 → pz_rail_astro_tools-1.0.6}/tests/astro_tools/test_degraders.py

@@ -83,7 +83,7 @@ def data_for_bl():
     DS.__class__.allow_overwrite = True
 
     # generate random normal data
-    columns=['ra', 'dec', 'redshift', 'u', 'g', 'r', 'i', 'z', 'y']
+    columns=['ra', 'dec', 'u', 'g', 'r', 'i', 'z', 'y']
     rng = np.random.default_rng(0)
     x = rng.normal(loc=23, scale=3, size=(1000, len(columns)))
 
@@ -91,9 +91,6 @@ def data_for_bl():
     x[:, 0] = np.random.uniform(low=0, high=0.02, size=1000)
     x[:, 1] = np.random.uniform(low=0, high=0.02, size=1000)
 
-    # replace redshifts with reasonable values
-    x[:, 2] = np.linspace(0, 2, x.shape[0])
-
     # return data in handle wrapping a pandas DataFrame
     df = pd.DataFrame(x, columns=columns)
     return DS.add_data("data_for_bl", df, TableHandle, path="dummy_for_bl.pd")
@@ -423,12 +420,19 @@ def test_EucliErrorModel(data):
 
 def test_BLModel(data_for_bl):
     # Setup the stage
-    degrader = UnrecBlModel.make_stage()
+
+    degrader = UnrecBlModel.make_stage(name='unrec_bl_model', ra_label='ra', dec_label='dec', linking_lengths=1.0, bands='ugrizy', seed=1234)
 
     # Apply the degrader and get the data out
-    degraded_data = degrader(data_for_bl).data
+    outputs = degrader(data_for_bl)
+    degraded_data = outputs['output'].data
+    truth_components = outputs['compInd'].data
 
     # Check output data has less rows than input data
     assert degraded_data.shape[0] < data_for_bl.data.shape[0]
 
+    # Check components has the same rows as input data
+    assert truth_components.shape[0] == data_for_bl.data.shape[0]
+
     os.remove(degrader.get_output(degrader.get_aliased_tag("output"), final_name=True))
+    os.remove(degrader.get_output(degrader.get_aliased_tag("compInd"), final_name=True))

pz_rail_astro_tools-1.0.5/src/rail/creation/degraders/bl_demo.ipynb

@@ -1,206 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "2610a0f0-0c71-4401-896f-734442bcd66d",
-   "metadata": {},
-   "source": [
-    "## Blending Degrader demo\n",
-    "\n",
-    "author: Shuang Liang\n",
-    "\n",
-    "This notebook demonstrate the use of `rail.creation.degradation.unrec_bl_model`, which uses Friends of Friends to finds sources close to each other and merge them into unrecognized blends"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "f7a6adc3-68e8-4a1d-842f-bfb0960a1c4a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from rail.creation.degraders.unrec_bl_model import UnrecBlModel\n",
-    "\n",
-    "from rail.core.data import PqHandle\n",
-    "from rail.core.stage import RailStage\n",
-    "\n",
-    "import matplotlib.pyplot as plt\n",
-    "import pandas as pd, numpy as np"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "6912a740-31ea-4987-b06d-81ff17cd895a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "DS = RailStage.data_store\n",
-    "DS.__class__.allow_overwrite = True\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "a282c2ed-141b-4507-8254-dc8fbc9864dc",
-   "metadata": {},
-   "source": [
-    "### Create a random catalog with ugrizy+YJHF bands as the the true input"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "1078bc2a-fc54-41c3-bd30-6c447bb971d4",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "data = np.random.normal(23, 3, size = (1000,12))\n",
-    "data[:, 0] = np.random.uniform(low=0, high=0.03, size=1000)\n",
-    "data[:, 1] = np.random.uniform(low=0, high=0.03, size=1000)\n",
-    "\n",
-    "data_df = pd.DataFrame(data=data,    # values\n",
-    "            columns=['ra', 'dec', 'u', 'g', 'r', 'i', 'z', 'y', 'Y', 'J', 'H', 'F'])\n",
-    "\n",
-    "data_truth = DS.add_data('input', data_df, PqHandle)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "33c99a4d-8375-4003-9a9a-70fa85a3eb82",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "#data_df.to_parquet('bl_test.pq')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "a5636721-a734-4746-bd93-8101bc558b6e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "plt.scatter(data_truth.data['ra'], data_truth.data['dec'], s=5)\n",
-    "plt.xlabel(\"Ra [Deg]\", fontsize=14)\n",
-    "plt.ylabel(\"Dec [Deg]\", fontsize=14)\n",
-    "plt.show()\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "1da27deb-d167-4f38-8c59-f270184d6ab3",
-   "metadata": {},
-   "source": [
-    "### The blending model"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "a07f72a0-e24c-4844-90f0-d5a49ac4362b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "## radius cut is in arcsecs\n",
-    "blModel = UnrecBlModel.make_stage(name='unrec_bl_model', ra_label='ra', dec_label='dec', linking_lengths=1.0, \\\n",
-    "                                  bands='ugrizyYJHF')\n",
-    "blModel.get_config_dict()\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "e5f4862a-0621-46d4-8901-7e84b461c424",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "samples_w_bl = blModel(data_truth)\n",
-    "samples_w_bl()\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "bc5158dd-f474-4731-b847-b4a7358656b9",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "fig, ax = plt.subplots(figsize=(6, 5), dpi=100)\n",
-    "\n",
-    "ax.scatter(data_truth.data['ra'],   data_truth.data['dec'],   s=10, facecolors='none', edgecolors='b', label='Original')\n",
-    "ax.scatter(samples_w_bl.data['ra'], samples_w_bl.data['dec'], s=5, c='r', label='w. Unrec-BL')\n",
-    "\n",
-    "ax.legend(loc=2, fontsize=12)\n",
-    "ax.set_xlabel(\"Ra [Deg]\", fontsize=14)\n",
-    "ax.set_ylabel(\"Dec [Deg]\", fontsize=14)\n",
-    "\n",
-    "plt.show()\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "268b3d37-b7fd-4ac1-8457-2104a87c9e6d",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "b = 'r'\n",
-    "plt.hist(data_truth.data[b], bins=np.linspace(10, 30, 20), label='Original')\n",
-    "plt.hist(samples_w_bl.data[b], bins=np.linspace(10, 30, 20),  fill=False, label='w. Unrec-BL')\n",
-    "\n",
-    "plt.xlabel(fr'Magnitude ${b}$', fontsize=14)\n",
-    "plt.legend(fontsize=12)\n",
-    "plt.show()\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "a1d51c15-1e04-4b22-9abb-9b267965dbeb",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "flux = 10**(-(data_truth.data[b]-28.10)/2.5)       # r band zp for lsst is 28.10\n",
-    "flux_bl = 10**(-(samples_w_bl.data[b]-28.10)/2.5)\n",
-    "\n",
-    "plt.hist(flux, bins=np.linspace(0, 10000, 40), label='Original')\n",
-    "plt.hist(flux_bl, bins=np.linspace(0, 10000, 40), fill=False, label='w. Unrec-BL')\n",
-    "\n",
-    "plt.xlabel(fr'Flux ${b}$', fontsize=14)\n",
-    "plt.yscale('log')\n",
-    "plt.legend(fontsize=12)\n",
-    "plt.show()\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "da2b37c8-4667-4ad2-ad09-b1c68d2612b8",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.12.3"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}