Transform PHMSA company data

docs/release_notes.rst

@@ -18,6 +18,13 @@ EIA 176
 * Extracted these interim tables up through the latest 2023 data release. See
   :issue:`4002` and :pr:`4004`.
 
+PHMSA
+~~~~~
+* Add a transformed table containing annual operator data from PHMSA natural gas
+  distributors. This is a subset of the overall distributor data, focusing on
+  company-level attributes. Thanks to :user:`seeess1` for all of your work on this! See
+  :issue:`3770` and :pr:`4005`.
+
 Bug Fixes
 ^^^^^^^^^
 

notebooks/work-in-progress/eia861-transform.ipynb

@@ -1438,7 +1438,7 @@
      "traceback": [
       "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
       "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
-      "\u001b[0;32m/var/folders/tf/l271ymp92vvbty6j01j580xm0000gn/T/ipykernel_27389/914883076.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0;31m# Prep raw data for comparison\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mraw_dfs_dict\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0meia861_raw_dfs\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcopy\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      3\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mdf_name\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdf\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mraw_dfs_dict\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mitems\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      5\u001b[0m     \u001b[0mdf\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpudl\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mhelpers\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfix_eia_na\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdf\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/var/folders/tf/l271ymp92vvbty6j01j580xm0000gn/T/ipykernel_27389/914883076.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0;31m# Prep raw data for comparison\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mraw_dfs_dict\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0meia861_raw_dfs\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcopy\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      3\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mdf_name\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdf\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mraw_dfs_dict\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mitems\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      5\u001b[0m     \u001b[0mdf\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpudl\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mhelpers\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstandardize_na_values\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdf\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
       "\u001b[0;31mNameError\u001b[0m: name 'eia861_raw_dfs' is not defined"
      ]
     }
@@ -1448,7 +1448,7 @@
     "raw_dfs_dict = eia861_raw_dfs.copy()\n",
     "\n",
     "for df_name, df in raw_dfs_dict.items():\n",
-    "    df = pudl.helpers.fix_eia_na(df)\n",
+    "    df = pudl.helpers.standardize_na_values(df)\n",
     "    df = pudl.helpers.convert_to_date(df)\n",
     "    raw_dfs_dict[df_name] = df\n",
     "    \n",