Clean up test data generation (#16)

* Clean up test data generation

* Almanac data generation.

* Linting

pyproject.toml

@@ -29,6 +29,7 @@ dependencies = [
 dev = [
     "asv==0.6.1", # Used to compute performance benchmarks
     "black", # Used for static linting of files
+    "jupyter", # clear notebook result cells
     "pre-commit", # Used to run checks before finalizing a git commit
     "pylint", # Used for static linting of files
     "pytest",

tests/conftest.py

@@ -2,7 +2,10 @@
 
 import pytest
 
-DATA_DIR_NAME = "data"
+ALMANAC_DIR_NAME = "almanac"
+SMALL_SKY_DIR_NAME = "small_sky"
+SMALL_SKY_ORDER1_DIR_NAME = "small_sky_order1"
+
 
 TEST_DIR = os.path.dirname(__file__)
 SMALL_SKY_DIR_NAME = "small_sky"
@@ -49,3 +52,28 @@ def local_data_dir():
 @pytest.fixture
 def small_sky_dir_local(local_data_dir):
     return os.path.join(local_data_dir, SMALL_SKY_DIR_NAME)
+
+
+@pytest.fixture
+def tmp_dir_cloud(example_cloud_path):
+    return os.path.join(example_cloud_path, "tmp")
+
+
+@pytest.fixture
+def test_data_dir_cloud(example_cloud_path):
+    return os.path.join(example_cloud_path, "data")
+
+
+@pytest.fixture
+def almanac_dir_cloud(test_data_dir_cloud):
+    return os.path.join(test_data_dir_cloud, ALMANAC_DIR_NAME)
+
+
+@pytest.fixture
+def small_sky_dir_cloud(test_data_dir_cloud):
+    return os.path.join(test_data_dir_cloud, SMALL_SKY_DIR_NAME)
+
+
+@pytest.fixture
+def small_sky_order1_dir_cloud(test_data_dir_cloud):
+    return os.path.join(test_data_dir_cloud, SMALL_SKY_ORDER1_DIR_NAME)

tests/data/generate_cloud_data.ipynb

@@ -0,0 +1,170 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# CLOUD unit test data\n",
+    "\n",
+    "There are two types of data used in unit tests in this repo: local and cloud. This notebook concerns itself only with the CLOUD versions of test data, so you can re-generate it.\n",
+    "\n",
+    "This also works to initialize data in a new cloud provider, instead of simply copying an existing data set.\n",
+    "\n",
+    "## Object catalog: small sky\n",
+    "\n",
+    "This is the same \"object catalog\" with 131 randomly generated radec values inside the order0-pixel11 healpix pixel that is used in hipscat and LSDB unit test suites."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import hipscat_import.pipeline as runner\n",
+    "from hipscat_import.catalog.arguments import ImportArguments\n",
+    "from hipscat_import.index.arguments import IndexArguments\n",
+    "from hipscat_import.margin_cache.margin_cache_arguments import MarginCacheArguments\n",
+    "import tempfile\n",
+    "from pathlib import Path\n",
+    "import os\n",
+    "\n",
+    "tmp_path = tempfile.TemporaryDirectory()\n",
+    "tmp_dir = tmp_path.name\n",
+    "\n",
+    "storage_options = {\n",
+    "    \"account_key\": os.environ.get(\"ABFS_LINCCDATA_ACCOUNT_KEY\"),\n",
+    "    \"account_name\": os.environ.get(\"ABFS_LINCCDATA_ACCOUNT_NAME\"),\n",
+    "}\n",
+    "storage_options"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### small_sky\n",
+    "\n",
+    "This catalog was generated with the following snippet:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "args = ImportArguments(\n",
+    "    input_path=\"small_sky_parts\",\n",
+    "    highest_healpix_order=1,\n",
+    "    file_reader=\"csv\",\n",
+    "    output_path=\"abfs://hipscat/pytests/data\",\n",
+    "    output_artifact_name=\"small_sky\",\n",
+    "    output_storage_options=storage_options,\n",
+    "    overwrite=True,\n",
+    "    tmp_dir=tmp_dir,\n",
+    "    dask_tmp=tmp_dir,\n",
+    ")\n",
+    "runner.pipeline(args)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### small_sky_order1\n",
+    "\n",
+    "This catalog has the same data points as other small sky catalogs, but is coerced to spreading these data points over partitions at order 1, instead of order 0.\n",
+    "\n",
+    "This means there are 4 leaf partition files, instead of just 1, and so can be useful for confirming reads/writes over multiple leaf partition files.\n",
+    "\n",
+    "NB: Setting `constant_healpix_order` coerces the import pipeline to create leaf partitions at order 1.\n",
+    "\n",
+    "This catalog was generated with the following snippet:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "args = ImportArguments(\n",
+    "    input_path=\"small_sky_parts\",\n",
+    "    file_reader=\"csv\",\n",
+    "    constant_healpix_order=1,\n",
+    "    output_path=\"abfs://hipscat/pytests/data\",\n",
+    "    output_storage_options=storage_options,\n",
+    "    output_artifact_name=\"small_sky_order1\",\n",
+    "    tmp_dir=tmp_dir,\n",
+    "    dask_tmp=tmp_dir,\n",
+    "    overwrite=True,\n",
+    ")\n",
+    "runner.pipeline(args)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Almanac info\n",
+    "\n",
+    "For the above catalogs, create almanac data."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from hipscat.inspection.almanac import Almanac\n",
+    "from hipscat.inspection.almanac_info import AlmanacInfo\n",
+    "\n",
+    "almanac_info = AlmanacInfo.from_catalog_dir(\n",
+    "    \"abfs://hipscat/pytests/data/small_sky\", storage_options=storage_options\n",
+    ")\n",
+    "almanac_info.write_to_file(\n",
+    "    directory=\"abfs://hipscat/pytests/data/almanac\", default_dir=False, storage_options=storage_options\n",
+    ")\n",
+    "\n",
+    "almanac_info = AlmanacInfo.from_catalog_dir(\n",
+    "    \"abfs://hipscat/pytests/data/small_sky_order1\", storage_options=storage_options\n",
+    ")\n",
+    "almanac_info.write_to_file(\n",
+    "    directory=\"abfs://hipscat/pytests/data/almanac\", default_dir=False, storage_options=storage_options\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tmp_path.cleanup()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "hipscatenv",
+   "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": "3.10.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}