Create simple SQL view assets

devtools/output-table-conversion-test.ipynb

@@ -0,0 +1,287 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "f786051b-2aa0-44e0-bfd7-fe6827b6e1a3",
+   "metadata": {},
+   "source": [
+    "# Purpose\n",
+    "We are in the process of converting some functions in `pudl.output` to be SQL views. This notebook allows us to compare the outputs of the old python functions with the SQL view."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "ec08c060-ba49-4466-81a0-315a45993928",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "assert os.environ.get(\"DAGSTER_HOME\"), (\n",
+    "    \"The DAGSTER_HOME env var is not set so dagster won't be able to find the assets.\"\n",
+    "    \"Set the DAGSTER_HOME env var in this notebook or kill the jupyter server and set\"\n",
+    "    \" the DAGSTER_HOME env var in your terminal and relaunch jupyter.\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "5ce7f88e-c7b9-4963-a0e4-72ccbcb1f70e",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "pudl_settings is being deprecated in favor of environment variables variables PUDL_OUTPUT and PUDL_INPUT. For more info see: https://catalystcoop-pudl.readthedocs.io/en/dev/dev/dev_setup.html\n",
+      "pudl_settings is being deprecated in favor of environment variables PUDL_OUTPUT and PUDL_INPUT. For more info see: https://catalystcoop-pudl.readthedocs.io/en/dev/dev/dev_setup.html\n",
+      "sqlite and parquet directories are no longer being used. Make sure there is a single directory named 'output' at the root of your workspace. For more info see: https://catalystcoop-pudl.readthedocs.io/en/dev/dev/dev_setup.html\n",
+      "pudl_settings is being deprecated in favor of environment variables variables PUDL_OUTPUT and PUDL_INPUT. For more info see: https://catalystcoop-pudl.readthedocs.io/en/dev/dev/dev_setup.html\n",
+      "pudl_settings is being deprecated in favor of environment variables PUDL_OUTPUT and PUDL_INPUT. For more info see: https://catalystcoop-pudl.readthedocs.io/en/dev/dev/dev_setup.html\n",
+      "sqlite and parquet directories are no longer being used. Make sure there is a single directory named 'output' at the root of your workspace. For more info see: https://catalystcoop-pudl.readthedocs.io/en/dev/dev/dev_setup.html\n"
+     ]
+    }
+   ],
+   "source": [
+    "from pudl.workspace.setup import get_defaults\n",
+    "import sqlalchemy as sa\n",
+    "import pandas as pd\n",
+    "\n",
+    "# TODO: This should be replaced with get_defaults()\n",
+    "engine = sa.create_engine(f\"sqlite:///{os.environ['PUDL_OUTPUT']}pudl.sqlite\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d5f6b021-26cf-4804-929f-0e4975751bd1",
+   "metadata": {},
+   "source": [
+    "## Compare output of old python function with SQL view"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "5c705a39-0517-4c7b-a1b0-ca8a12daec53",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 34.1 ms, sys: 3.71 ms, total: 37.8 ms\n",
+      "Wall time: 53.8 ms\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "view_name = \"denorm_plants_utils_ferc1\"\n",
+    "\n",
+    "with engine.connect() as con:\n",
+    "    view_df = pd.read_sql_table(view_name, con)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "633999af-d881-424b-af8c-64fc837982cd",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>utility_id_ferc1</th>\n",
+       "      <th>plant_name_ferc1</th>\n",
+       "      <th>plant_id_pudl</th>\n",
+       "      <th>utility_name_ferc1</th>\n",
+       "      <th>utility_id_pudl</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>206</td>\n",
+       "      <td>*dolet hills (3)</td>\n",
+       "      <td>1</td>\n",
+       "      <td>Southwestern Electric Power Company</td>\n",
+       "      <td>301</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>206</td>\n",
+       "      <td>*flint creek (1)</td>\n",
+       "      <td>2</td>\n",
+       "      <td>Southwestern Electric Power Company</td>\n",
+       "      <td>301</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>206</td>\n",
+       "      <td>*pirkey (2)</td>\n",
+       "      <td>3</td>\n",
+       "      <td>Southwestern Electric Power Company</td>\n",
+       "      <td>301</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>159</td>\n",
+       "      <td>59th st gt-1</td>\n",
+       "      <td>4</td>\n",
+       "      <td>Consolidated Edison Company of New York, Inc.</td>\n",
+       "      <td>79</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>159</td>\n",
+       "      <td>74th st gt 1&amp;2</td>\n",
+       "      <td>5</td>\n",
+       "      <td>Consolidated Edison Company of New York, Inc.</td>\n",
+       "      <td>79</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   utility_id_ferc1  plant_name_ferc1  plant_id_pudl                             utility_name_ferc1  utility_id_pudl\n",
+       "0               206  *dolet hills (3)              1            Southwestern Electric Power Company              301\n",
+       "1               206  *flint creek (1)              2            Southwestern Electric Power Company              301\n",
+       "2               206       *pirkey (2)              3            Southwestern Electric Power Company              301\n",
+       "3               159      59th st gt-1              4  Consolidated Edison Company of New York, Inc.               79\n",
+       "4               159    74th st gt 1&2              5  Consolidated Edison Company of New York, Inc.               79"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "view_df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "af6253bb-e135-4068-8088-4e08c9914054",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "2023-03-23 13:35:06 [ WARNING] catalystcoop.pudl.output.ferc1:56 pudl.output.ferc1.plants_utils_ferc1() will be deprecated in a future version of PUDL. In the future, call the PudlTabl.pu_ferc1() method or pull the plants_utils_ferc1 tabledirectly from the pudl.sqlite database.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Import the old python functions\n",
+    "from pudl.output.ferc1 import plants_utils_ferc1\n",
+    "\n",
+    "old_output_func = plants_utils_ferc1\n",
+    "\n",
+    "old_df = old_output_func(engine)\n",
+    "\n",
+    "# Align pandas index and sort values using all of the columns\n",
+    "key = list(old_df.columns)\n",
+    "old_df = old_df.sort_values(by=key).reset_index(drop=True)\n",
+    "view_df = view_df.sort_values(by=key).reset_index(drop=True)\n",
+    "\n",
+    "pd.testing.assert_frame_equal(old_df, view_df)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "955efc1e-b21f-473e-b3f2-ab2fad89591d",
+   "metadata": {},
+   "source": [
+    "## Make sure we can load the view using the SQLite IO Manager"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "a9d81a2b-9c68-443b-9a56-5563f4cbc920",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 5 entries, 0 to 4\n",
+      "Data columns (total 5 columns):\n",
+      " #   Column              Non-Null Count  Dtype \n",
+      "---  ------              --------------  ----- \n",
+      " 0   utility_id_ferc1    5 non-null      Int64 \n",
+      " 1   plant_name_ferc1    5 non-null      string\n",
+      " 2   plant_id_pudl       5 non-null      Int64 \n",
+      " 3   utility_name_ferc1  5 non-null      string\n",
+      " 4   utility_id_pudl     5 non-null      Int64 \n",
+      "dtypes: Int64(3), string(2)\n",
+      "memory usage: 343.0 bytes\n"
+     ]
+    }
+   ],
+   "source": [
+    "from dagster import AssetKey\n",
+    "\n",
+    "from pudl.etl import defs\n",
+    "\n",
+    "df = defs.load_asset_value(AssetKey(view_name))\n",
+    "\n",
+    "df.head().info()"
+   ]
+  }
+ ],
+ "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": "3.10.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

src/pudl/etl/__init__.py

@@ -8,6 +8,7 @@
     Definitions,
     define_asset_job,
     load_assets_from_modules,
+    load_assets_from_package_module,
 )
 
 import pudl
@@ -45,6 +46,7 @@
     *load_assets_from_modules([pudl.transform.ferc714], group_name="clean_ferc714"),
     *load_assets_from_modules([glue_assets], group_name="glue"),
     *load_assets_from_modules([static_assets], group_name="static"),
+    *load_assets_from_package_module(pudl.output, group_name="outputs"),
 )
 
 default_resources = {