j40-cejst-2/data/data-pipeline/data_pipeline/ipython/explore_eamlis.ipynb
Travis Newby a27ca46b1d
Update dependencies to fix safety check failures (#2142)
* Update dependencies

Update dependencies causing safety check to fail

* Remove nb_black from jupyter notebooks

Because of the build issue on M1 macs, nb_black was removed as a dev dependency. This change removes the lines referencing nb_black (%load_ext lab_black) from all jupyter notebooks.
2023-02-02 16:43:59 -06:00

2432 lines
88 KiB
Text
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "24085186-3472-43d3-8b87-b5191c4f6ca6",
"metadata": {},
"outputs": [],
"source": [
"import geopandas as gpd\n",
"import pandas as pd\n",
"import numpy as np\n",
"import os\n",
"import sys\n",
"\n",
"module_path = os.path.abspath(os.path.join(\"../..\"))\n",
"if module_path not in sys.path:\n",
" sys.path.append(module_path)\n",
"\n",
"from data_pipeline.config import settings\n",
"from data_pipeline.etl.base import ExtractTransformLoad\n",
"from data_pipeline.etl.sources.census.etl import CensusETL\n",
"from data_pipeline.etl.sources.geo_utils import add_tracts_for_geometries\n",
"from data_pipeline.utils import unzip_file_from_url"
]
},
{
"cell_type": "markdown",
"id": "dbecd665-1c8a-40fe-a7fc-684ecf73f991",
"metadata": {},
"source": [
"# Grab the data"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "f451ea70-917c-45f9-adf9-9306436b955d",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"2022-08-16 11:50:57,573 [data_pipeline.utils] INFO Downloading https://justice40-data.s3.amazonaws.com/data-sources/eAMLIS export of all data.tsv.zip\n",
"2022-08-16 11:50:57,857 [data_pipeline.utils] INFO Extracting /home/matt/active/justice40-tool/data/data-pipeline/data_pipeline/data/tmp/abandoned_mine_lands/downloaded-af59fffe-aec2-48b4-a57f-716b8dc7e0a3.zip\n"
]
}
],
"source": [
"tmp_path = ExtractTransformLoad.DATA_PATH / \"tmp\" / \"abandoned_mine_lands\"\n",
"# Create directory if it doesn't exist\n",
"tmp_path.mkdir(parents=True, exist_ok=True)\n",
"\n",
"eamlis_path_in_s3 = (\n",
" settings.AWS_JUSTICE40_DATASOURCES_URL\n",
" + \"/eAMLIS export of all data.tsv.zip\"\n",
")\n",
"\n",
"unzip_file_from_url(\n",
" file_url=eamlis_path_in_s3,\n",
" download_path=tmp_path,\n",
" unzipped_file_path=tmp_path,\n",
")\n",
"\n",
"eamlis_path = tmp_path / \"eAMLIS export of all data.tsv\""
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "5cee0a59-4f69-4678-a7ab-877e57d06f1b",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'/home/matt/active/justice40-tool/data/data-pipeline/data_pipeline/data/tmp/abandoned_mine_lands/eAMLIS export of all data.tsv'"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"str(eamlis_path)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "5b8119d8-315b-4e87-b286-3767158d63ab",
"metadata": {},
"outputs": [],
"source": [
"df = pd.read_csv(eamlis_path, sep=\"\\t\", low_memory=False)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "4fbac263-5868-4fbc-bcb7-168ef479af53",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(57149, 42)"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"gdf = gpd.GeoDataFrame(\n",
" df,\n",
" geometry=gpd.points_from_xy(\n",
" x=df[\"Longitude\"],\n",
" y=df[\"Latitude\"],\n",
" ),\n",
" crs=\"epsg:4326\",\n",
")\n",
"gdf.shape"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "3b176f62-2d13-4bd2-9211-0ac7c2807146",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(3977, 42)"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"gdf.drop_duplicates(subset=[\"geometry\"], inplace=True, keep=\"last\")\n",
"gdf.shape"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "a0116c52-58f5-48a6-aa9e-c49873ebafa7",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"2022-08-16 11:51:28,795 [data_pipeline.etl.sources.geo_utils] DEBUG Appending tract data to dataframe\n",
"2022-08-16 11:51:28,796 [data_pipeline.etl.sources.geo_utils] INFO Loading tract geometry data from census ETL\n",
"2022-08-16 11:51:28,796 [data_pipeline.etl.sources.geo_utils] DEBUG Loading existing tract geojson\n",
"/home/matt/.cache/pypoetry/virtualenvs/justice40-data-pipeline-IwBjhw-4-py3.10/lib/python3.10/site-packages/IPython/core/interactiveshell.py:3553: FutureWarning: The `op` parameter is deprecated and will be removed in a future release. Please use the `predicate` parameter instead.\n",
" exec(code_obj, self.user_global_ns, self.user_ns)\n"
]
}
],
"source": [
"gdf_tracts = add_tracts_for_geometries(gdf)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "2a18ba4d-274b-4640-a83c-02ae1d02837c",
"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>AMLIS Key</th>\n",
" <th>State/Tribe</th>\n",
" <th>County</th>\n",
" <th>Congressional District</th>\n",
" <th>Quadrangle Name</th>\n",
" <th>Watershed</th>\n",
" <th>HUC Code</th>\n",
" <th>FIPS Code</th>\n",
" <th>Latitude</th>\n",
" <th>Longitude</th>\n",
" <th>...</th>\n",
" <th>Funded GPRA Acres</th>\n",
" <th>Funded Metric Units</th>\n",
" <th>Completed Standard Units</th>\n",
" <th>Completed Costs</th>\n",
" <th>Completed GPRA Acres</th>\n",
" <th>Completed Metric Units</th>\n",
" <th>Unnamed: 40</th>\n",
" <th>geometry</th>\n",
" <th>index_right</th>\n",
" <th>GEOID10_TRACT</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" </tbody>\n",
"</table>\n",
"<p>0 rows × 44 columns</p>\n",
"</div>"
],
"text/plain": [
"Empty GeoDataFrame\n",
"Columns: [AMLIS Key, State/Tribe, County, Congressional District, Quadrangle Name, Watershed, HUC Code, FIPS Code, Latitude, Longitude, Funding Source / Program, Problem Area Name, Problem Area Number, Planning Unit Name, Planning Unit Number, Problem Priority, Problem Type, Mining Type, Ore Types, Date Prepared, Date Revised, Private Owner %, State Owner %, Other Federal Owner %, Park Service Owner %, Forest Service Owner %, Indian Owner %, BLM Owner %, Unfunded Standard Units, Unfunded Costs, Unfunded GPRA Acres, Unfunded Metric Units, Funded Standard Units, Funded Costs, Funded GPRA Acres, Funded Metric Units, Completed Standard Units, Completed Costs, Completed GPRA Acres, Completed Metric Units, Unnamed: 40, geometry, index_right, GEOID10_TRACT]\n",
"Index: []\n",
"\n",
"[0 rows x 44 columns]"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"gdf_tracts[gdf_tracts.GEOID10_TRACT.isna()]"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "e9aaa563-4c11-46b0-a64d-6ce053412e9c",
"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>AMLIS Key</th>\n",
" <th>State/Tribe</th>\n",
" <th>County</th>\n",
" <th>Congressional District</th>\n",
" <th>Quadrangle Name</th>\n",
" <th>Watershed</th>\n",
" <th>HUC Code</th>\n",
" <th>FIPS Code</th>\n",
" <th>Latitude</th>\n",
" <th>Longitude</th>\n",
" <th>...</th>\n",
" <th>Funded GPRA Acres</th>\n",
" <th>Funded Metric Units</th>\n",
" <th>Completed Standard Units</th>\n",
" <th>Completed Costs</th>\n",
" <th>Completed GPRA Acres</th>\n",
" <th>Completed Metric Units</th>\n",
" <th>Unnamed: 40</th>\n",
" <th>geometry</th>\n",
" <th>index_right</th>\n",
" <th>GEOID10_TRACT</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>AK000001</td>\n",
" <td>AK</td>\n",
" <td>MATANUSKA-SUSITNA</td>\n",
" <td>1.0</td>\n",
" <td>ANCHORAGE C-8</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>02170</td>\n",
" <td>61.6</td>\n",
" <td>-149.8</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>900.00</td>\n",
" <td>33200.0</td>\n",
" <td>12.86</td>\n",
" <td>274.30</td>\n",
" <td>NaN</td>\n",
" <td>POINT (-149.80000 61.60000)</td>\n",
" <td>9900</td>\n",
" <td>02170000401</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>AK000003</td>\n",
" <td>AK</td>\n",
" <td>VALDEZ-CORDOVA</td>\n",
" <td>1.0</td>\n",
" <td>Valdez C-1</td>\n",
" <td>19050003</td>\n",
" <td>NaN</td>\n",
" <td>02-26</td>\n",
" <td>61.6</td>\n",
" <td>-144.0</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.34</td>\n",
" <td>9200.0</td>\n",
" <td>0.03</td>\n",
" <td>0.34</td>\n",
" <td>NaN</td>\n",
" <td>POINT (-144.00000 61.60000)</td>\n",
" <td>9918</td>\n",
" <td>02261000100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100</th>\n",
" <td>AK000080</td>\n",
" <td>AK</td>\n",
" <td>VALDEZ-CORDOVA CENSU</td>\n",
" <td>1.0</td>\n",
" <td>MCCARTHY C-5</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>02261</td>\n",
" <td>61.5</td>\n",
" <td>-142.8</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>4.00</td>\n",
" <td>9924.0</td>\n",
" <td>0.40</td>\n",
" <td>4.00</td>\n",
" <td>NaN</td>\n",
" <td>POINT (-142.80000 61.50000)</td>\n",
" <td>9918</td>\n",
" <td>02261000100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>113</th>\n",
" <td>AK000096</td>\n",
" <td>AK</td>\n",
" <td>VALDEZ-CORDOVA</td>\n",
" <td>1.0</td>\n",
" <td>MCCARTHY C-6</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>Alaska</td>\n",
" <td>61.6</td>\n",
" <td>-142.8</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>2.00</td>\n",
" <td>29729.0</td>\n",
" <td>0.20</td>\n",
" <td>2.00</td>\n",
" <td>NaN</td>\n",
" <td>POINT (-142.80000 61.60000)</td>\n",
" <td>9918</td>\n",
" <td>02261000100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>AK000006</td>\n",
" <td>AK</td>\n",
" <td>MATANUSKA-SUSITNA</td>\n",
" <td>1.0</td>\n",
" <td>ANCHORAGE C-6</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>Alaska</td>\n",
" <td>61.7</td>\n",
" <td>-149.0</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>3.00</td>\n",
" <td>9225.0</td>\n",
" <td>0.30</td>\n",
" <td>3.00</td>\n",
" <td>NaN</td>\n",
" <td>POINT (-149.00000 61.70000)</td>\n",
" <td>9938</td>\n",
" <td>02170000200</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 44 columns</p>\n",
"</div>"
],
"text/plain": [
" AMLIS Key State/Tribe County Congressional District \\\n",
"2 AK000001 AK MATANUSKA-SUSITNA 1.0 \n",
"6 AK000003 AK VALDEZ-CORDOVA 1.0 \n",
"100 AK000080 AK VALDEZ-CORDOVA CENSU 1.0 \n",
"113 AK000096 AK VALDEZ-CORDOVA 1.0 \n",
"12 AK000006 AK MATANUSKA-SUSITNA 1.0 \n",
"\n",
" Quadrangle Name Watershed HUC Code FIPS Code Latitude Longitude ... \\\n",
"2 ANCHORAGE C-8 NaN NaN 02170 61.6 -149.8 ... \n",
"6 Valdez C-1 19050003 NaN 02-26 61.6 -144.0 ... \n",
"100 MCCARTHY C-5 NaN NaN 02261 61.5 -142.8 ... \n",
"113 MCCARTHY C-6 NaN NaN Alaska 61.6 -142.8 ... \n",
"12 ANCHORAGE C-6 NaN NaN Alaska 61.7 -149.0 ... \n",
"\n",
" Funded GPRA Acres Funded Metric Units Completed Standard Units \\\n",
"2 0.0 0.0 900.00 \n",
"6 0.0 0.0 0.34 \n",
"100 0.0 0.0 4.00 \n",
"113 0.0 0.0 2.00 \n",
"12 0.0 0.0 3.00 \n",
"\n",
" Completed Costs Completed GPRA Acres Completed Metric Units Unnamed: 40 \\\n",
"2 33200.0 12.86 274.30 NaN \n",
"6 9200.0 0.03 0.34 NaN \n",
"100 9924.0 0.40 4.00 NaN \n",
"113 29729.0 0.20 2.00 NaN \n",
"12 9225.0 0.30 3.00 NaN \n",
"\n",
" geometry index_right GEOID10_TRACT \n",
"2 POINT (-149.80000 61.60000) 9900 02170000401 \n",
"6 POINT (-144.00000 61.60000) 9918 02261000100 \n",
"100 POINT (-142.80000 61.50000) 9918 02261000100 \n",
"113 POINT (-142.80000 61.60000) 9918 02261000100 \n",
"12 POINT (-149.00000 61.70000) 9938 02170000200 \n",
"\n",
"[5 rows x 44 columns]"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"gdf_tracts.head()"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "901f8c2f-b27a-4223-ad73-71daf51f6bd6",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(2034, 44)"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"gdf_tracts.drop_duplicates(\"GEOID10_TRACT\").shape"
]
},
{
"cell_type": "code",
"execution_count": 24,
"id": "65bfb3e7-d562-4d59-a2ef-f59d385a7c23",
"metadata": {},
"outputs": [],
"source": [
"census_tracts = gpd.read_file(CensusETL.NATIONAL_TRACT_JSON_PATH)"
]
},
{
"cell_type": "code",
"execution_count": 26,
"id": "6b7011aa-49e8-4cf8-877f-b3b36805c18e",
"metadata": {},
"outputs": [],
"source": [
"census_tracts.set_index(\"GEOID10\", drop=False, inplace=True)"
]
},
{
"cell_type": "code",
"execution_count": 54,
"id": "4334eb8e-c8eb-486a-a4e0-a455f18c038c",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(3976, 44)"
]
},
"execution_count": 54,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"gdf_tracts.shape"
]
},
{
"cell_type": "code",
"execution_count": 59,
"id": "cbc84001-bb43-46dc-bc6a-306f0e169a20",
"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>AMLIS Key</th>\n",
" <th>State/Tribe</th>\n",
" <th>County</th>\n",
" <th>Congressional District</th>\n",
" <th>Quadrangle Name</th>\n",
" <th>Watershed</th>\n",
" <th>HUC Code</th>\n",
" <th>FIPS Code</th>\n",
" <th>Latitude</th>\n",
" <th>Longitude</th>\n",
" <th>...</th>\n",
" <th>Funded GPRA Acres</th>\n",
" <th>Funded Metric Units</th>\n",
" <th>Completed Standard Units</th>\n",
" <th>Completed Costs</th>\n",
" <th>Completed GPRA Acres</th>\n",
" <th>Completed Metric Units</th>\n",
" <th>Unnamed: 40</th>\n",
" <th>geometry</th>\n",
" <th>index_right</th>\n",
" <th>GEOID10_TRACT</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>100</th>\n",
" <td>AK000080</td>\n",
" <td>AK</td>\n",
" <td>VALDEZ-CORDOVA CENSU</td>\n",
" <td>1.0</td>\n",
" <td>MCCARTHY C-5</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>02261</td>\n",
" <td>61.5</td>\n",
" <td>-142.8</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>4.0</td>\n",
" <td>9924.0</td>\n",
" <td>0.4</td>\n",
" <td>4.0</td>\n",
" <td>NaN</td>\n",
" <td>POINT (-142.80000 61.50000)</td>\n",
" <td>9918</td>\n",
" <td>02261000100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>113</th>\n",
" <td>AK000096</td>\n",
" <td>AK</td>\n",
" <td>VALDEZ-CORDOVA</td>\n",
" <td>1.0</td>\n",
" <td>MCCARTHY C-6</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>Alaska</td>\n",
" <td>61.6</td>\n",
" <td>-142.8</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>2.0</td>\n",
" <td>29729.0</td>\n",
" <td>0.2</td>\n",
" <td>2.0</td>\n",
" <td>NaN</td>\n",
" <td>POINT (-142.80000 61.60000)</td>\n",
" <td>9918</td>\n",
" <td>02261000100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>30</th>\n",
" <td>AK000015</td>\n",
" <td>AK</td>\n",
" <td>MATANUSKA-SUSITNA</td>\n",
" <td>1.0</td>\n",
" <td>ANCHORAGE D-4</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>02170</td>\n",
" <td>61.7</td>\n",
" <td>-148.2</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>7.0</td>\n",
" <td>4100.0</td>\n",
" <td>0.7</td>\n",
" <td>7.0</td>\n",
" <td>NaN</td>\n",
" <td>POINT (-148.20000 61.70000)</td>\n",
" <td>9938</td>\n",
" <td>02170000200</td>\n",
" </tr>\n",
" <tr>\n",
" <th>45</th>\n",
" <td>AK000040</td>\n",
" <td>AK</td>\n",
" <td>MATANUSKA-SUSITNA</td>\n",
" <td>1.0</td>\n",
" <td>ANCHORAGE C-6</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>02170</td>\n",
" <td>61.7</td>\n",
" <td>-148.8</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>20284.0</td>\n",
" <td>0.1</td>\n",
" <td>1.0</td>\n",
" <td>NaN</td>\n",
" <td>POINT (-148.80000 61.70000)</td>\n",
" <td>9938</td>\n",
" <td>02170000200</td>\n",
" </tr>\n",
" <tr>\n",
" <th>117</th>\n",
" <td>AK000099</td>\n",
" <td>AK</td>\n",
" <td>MATANUSKA-SUSITNA</td>\n",
" <td>1.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>02170</td>\n",
" <td>61.7</td>\n",
" <td>-148.4</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>POINT (-148.40000 61.70000)</td>\n",
" <td>9938</td>\n",
" <td>02170000200</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>57095</th>\n",
" <td>WY176742</td>\n",
" <td>WY</td>\n",
" <td>Campbell County</td>\n",
" <td>1.0</td>\n",
" <td>Little Thunder Reservoir</td>\n",
" <td>UPPER CHEYENNE</td>\n",
" <td>10120103.0</td>\n",
" <td>56005</td>\n",
" <td>43.7</td>\n",
" <td>-105.4</td>\n",
" <td>...</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>8.6</td>\n",
" <td>1407322.0</td>\n",
" <td>8.6</td>\n",
" <td>8.6</td>\n",
" <td>NaN</td>\n",
" <td>POINT (-105.40000 43.70000)</td>\n",
" <td>28394</td>\n",
" <td>56005000100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>56861</th>\n",
" <td>WY082926</td>\n",
" <td>WY</td>\n",
" <td>PLATTE</td>\n",
" <td>1.0</td>\n",
" <td>Guernsey Reservoir</td>\n",
" <td>GLENDO RESERVOIR</td>\n",
" <td>10180008.0</td>\n",
" <td>56031</td>\n",
" <td>42.3</td>\n",
" <td>-104.7</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>293122.0</td>\n",
" <td>1.0</td>\n",
" <td>0.4</td>\n",
" <td>NaN</td>\n",
" <td>POINT (-104.70000 42.30000)</td>\n",
" <td>28402</td>\n",
" <td>56031959100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>56864</th>\n",
" <td>WY086744</td>\n",
" <td>WY</td>\n",
" <td>PLATTE</td>\n",
" <td>1.0</td>\n",
" <td>HELL GAP</td>\n",
" <td>GLENDO RESERVOIR</td>\n",
" <td>10180008.0</td>\n",
" <td>56031</td>\n",
" <td>42.4</td>\n",
" <td>-104.7</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>18848.0</td>\n",
" <td>0.1</td>\n",
" <td>1.0</td>\n",
" <td>NaN</td>\n",
" <td>POINT (-104.70000 42.40000)</td>\n",
" <td>28402</td>\n",
" <td>56031959100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>56930</th>\n",
" <td>WY102624</td>\n",
" <td>WY</td>\n",
" <td>FREMONT</td>\n",
" <td>1.0</td>\n",
" <td>Lookout Butte</td>\n",
" <td>LOWER WIND</td>\n",
" <td>10080005.0</td>\n",
" <td>56013</td>\n",
" <td>43.3</td>\n",
" <td>-108.7</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>POINT (-108.70000 43.30000)</td>\n",
" <td>28442</td>\n",
" <td>56013940201</td>\n",
" </tr>\n",
" <tr>\n",
" <th>57021</th>\n",
" <td>WY132533</td>\n",
" <td>WY</td>\n",
" <td>FREMONT</td>\n",
" <td>1.0</td>\n",
" <td>Eagle Point</td>\n",
" <td>LOWER WIND</td>\n",
" <td>10080005.0</td>\n",
" <td>56013</td>\n",
" <td>43.4</td>\n",
" <td>-108.7</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>POINT (-108.70000 43.40000)</td>\n",
" <td>28442</td>\n",
" <td>56013940201</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1942 rows × 44 columns</p>\n",
"</div>"
],
"text/plain": [
" AMLIS Key State/Tribe County Congressional District \\\n",
"100 AK000080 AK VALDEZ-CORDOVA CENSU 1.0 \n",
"113 AK000096 AK VALDEZ-CORDOVA 1.0 \n",
"30 AK000015 AK MATANUSKA-SUSITNA 1.0 \n",
"45 AK000040 AK MATANUSKA-SUSITNA 1.0 \n",
"117 AK000099 AK MATANUSKA-SUSITNA 1.0 \n",
"... ... ... ... ... \n",
"57095 WY176742 WY Campbell County 1.0 \n",
"56861 WY082926 WY PLATTE 1.0 \n",
"56864 WY086744 WY PLATTE 1.0 \n",
"56930 WY102624 WY FREMONT 1.0 \n",
"57021 WY132533 WY FREMONT 1.0 \n",
"\n",
" Quadrangle Name Watershed HUC Code FIPS Code \\\n",
"100 MCCARTHY C-5 NaN NaN 02261 \n",
"113 MCCARTHY C-6 NaN NaN Alaska \n",
"30 ANCHORAGE D-4 NaN NaN 02170 \n",
"45 ANCHORAGE C-6 NaN NaN 02170 \n",
"117 NaN NaN NaN 02170 \n",
"... ... ... ... ... \n",
"57095 Little Thunder Reservoir UPPER CHEYENNE 10120103.0 56005 \n",
"56861 Guernsey Reservoir GLENDO RESERVOIR 10180008.0 56031 \n",
"56864 HELL GAP GLENDO RESERVOIR 10180008.0 56031 \n",
"56930 Lookout Butte LOWER WIND 10080005.0 56013 \n",
"57021 Eagle Point LOWER WIND 10080005.0 56013 \n",
"\n",
" Latitude Longitude ... Funded GPRA Acres Funded Metric Units \\\n",
"100 61.5 -142.8 ... 0.0 0.0 \n",
"113 61.6 -142.8 ... 0.0 0.0 \n",
"30 61.7 -148.2 ... 0.0 0.0 \n",
"45 61.7 -148.8 ... 0.0 0.0 \n",
"117 61.7 -148.4 ... 0.0 0.0 \n",
"... ... ... ... ... ... \n",
"57095 43.7 -105.4 ... 3.0 3.0 \n",
"56861 42.3 -104.7 ... 0.0 0.0 \n",
"56864 42.4 -104.7 ... 0.0 0.0 \n",
"56930 43.3 -108.7 ... 0.0 0.0 \n",
"57021 43.4 -108.7 ... 0.0 0.0 \n",
"\n",
" Completed Standard Units Completed Costs Completed GPRA Acres \\\n",
"100 4.0 9924.0 0.4 \n",
"113 2.0 29729.0 0.2 \n",
"30 7.0 4100.0 0.7 \n",
"45 1.0 20284.0 0.1 \n",
"117 0.0 0.0 0.0 \n",
"... ... ... ... \n",
"57095 8.6 1407322.0 8.6 \n",
"56861 1.0 293122.0 1.0 \n",
"56864 1.0 18848.0 0.1 \n",
"56930 0.0 0.0 0.0 \n",
"57021 0.0 0.0 0.0 \n",
"\n",
" Completed Metric Units Unnamed: 40 geometry \\\n",
"100 4.0 NaN POINT (-142.80000 61.50000) \n",
"113 2.0 NaN POINT (-142.80000 61.60000) \n",
"30 7.0 NaN POINT (-148.20000 61.70000) \n",
"45 1.0 NaN POINT (-148.80000 61.70000) \n",
"117 0.0 NaN POINT (-148.40000 61.70000) \n",
"... ... ... ... \n",
"57095 8.6 NaN POINT (-105.40000 43.70000) \n",
"56861 0.4 NaN POINT (-104.70000 42.30000) \n",
"56864 1.0 NaN POINT (-104.70000 42.40000) \n",
"56930 0.0 NaN POINT (-108.70000 43.30000) \n",
"57021 0.0 NaN POINT (-108.70000 43.40000) \n",
"\n",
" index_right GEOID10_TRACT \n",
"100 9918 02261000100 \n",
"113 9918 02261000100 \n",
"30 9938 02170000200 \n",
"45 9938 02170000200 \n",
"117 9938 02170000200 \n",
"... ... ... \n",
"57095 28394 56005000100 \n",
"56861 28402 56031959100 \n",
"56864 28402 56031959100 \n",
"56930 28442 56013940201 \n",
"57021 28442 56013940201 \n",
"\n",
"[1942 rows x 44 columns]"
]
},
"execution_count": 59,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"gdf_tracts[gdf_tracts.GEOID10_TRACT.duplicated()]"
]
},
{
"cell_type": "markdown",
"id": "bdf572df-8a20-4711-812c-376887de8d30",
"metadata": {},
"source": [
"# Assemble test data"
]
},
{
"cell_type": "markdown",
"id": "c6820da8-d61d-4da7-870a-d1e648152ae2",
"metadata": {},
"source": [
"## Get some test tracts"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "78cf15fc-a9a6-41bc-ab90-9c94a32e0fcd",
"metadata": {},
"outputs": [],
"source": [
"example_geoids = pd.read_csv(\n",
" \"../tests/sources/example/data/extract.csv\", dtype=\"object\"\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "c0129782-bc75-4cb5-b53f-4a99d4473aa6",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(15, 2)"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"example_geoids.shape"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "2647d12f-3eab-4cbc-a656-a514a2c06084",
"metadata": {},
"outputs": [],
"source": [
"tract_df = gdf_tracts"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "7ac85550-c8b9-4978-869b-1a233f89a1b2",
"metadata": {},
"outputs": [],
"source": [
"merged_exaple_data = pd.merge(\n",
" example_geoids[\"GEOID10_TRACT\"],\n",
" tract_df,\n",
" on=\"GEOID10_TRACT\",\n",
" how=\"left\",\n",
" indicator=True,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "e3e36b6f-8edc-4459-9703-83b790778ce6",
"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>GEOID10_TRACT</th>\n",
" <th>AMLIS Key</th>\n",
" <th>State/Tribe</th>\n",
" <th>County</th>\n",
" <th>Congressional District</th>\n",
" <th>Quadrangle Name</th>\n",
" <th>Watershed</th>\n",
" <th>HUC Code</th>\n",
" <th>FIPS Code</th>\n",
" <th>Latitude</th>\n",
" <th>...</th>\n",
" <th>Funded GPRA Acres</th>\n",
" <th>Funded Metric Units</th>\n",
" <th>Completed Standard Units</th>\n",
" <th>Completed Costs</th>\n",
" <th>Completed GPRA Acres</th>\n",
" <th>Completed Metric Units</th>\n",
" <th>Unnamed: 40</th>\n",
" <th>geometry</th>\n",
" <th>index_right</th>\n",
" <th>_merge</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>06027000800</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>None</td>\n",
" <td>NaN</td>\n",
" <td>left_only</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>06069000802</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>None</td>\n",
" <td>NaN</td>\n",
" <td>left_only</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>06061021322</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>None</td>\n",
" <td>NaN</td>\n",
" <td>left_only</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>15001021010</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>None</td>\n",
" <td>NaN</td>\n",
" <td>left_only</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>15001021101</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>None</td>\n",
" <td>NaN</td>\n",
" <td>left_only</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>15007040603</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>None</td>\n",
" <td>NaN</td>\n",
" <td>left_only</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>15007040700</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>None</td>\n",
" <td>NaN</td>\n",
" <td>left_only</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>15009030100</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>None</td>\n",
" <td>NaN</td>\n",
" <td>left_only</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>15009030201</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>None</td>\n",
" <td>NaN</td>\n",
" <td>left_only</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>15001021402</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>None</td>\n",
" <td>NaN</td>\n",
" <td>left_only</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>15001021800</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>None</td>\n",
" <td>NaN</td>\n",
" <td>left_only</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>15009030402</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>None</td>\n",
" <td>NaN</td>\n",
" <td>left_only</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>15009030800</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>None</td>\n",
" <td>NaN</td>\n",
" <td>left_only</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>15003010201</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>None</td>\n",
" <td>NaN</td>\n",
" <td>left_only</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>15007040604</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>None</td>\n",
" <td>NaN</td>\n",
" <td>left_only</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>15 rows × 45 columns</p>\n",
"</div>"
],
"text/plain": [
" GEOID10_TRACT AMLIS Key State/Tribe County Congressional District \\\n",
"0 06027000800 NaN NaN NaN NaN \n",
"1 06069000802 NaN NaN NaN NaN \n",
"2 06061021322 NaN NaN NaN NaN \n",
"3 15001021010 NaN NaN NaN NaN \n",
"4 15001021101 NaN NaN NaN NaN \n",
"5 15007040603 NaN NaN NaN NaN \n",
"6 15007040700 NaN NaN NaN NaN \n",
"7 15009030100 NaN NaN NaN NaN \n",
"8 15009030201 NaN NaN NaN NaN \n",
"9 15001021402 NaN NaN NaN NaN \n",
"10 15001021800 NaN NaN NaN NaN \n",
"11 15009030402 NaN NaN NaN NaN \n",
"12 15009030800 NaN NaN NaN NaN \n",
"13 15003010201 NaN NaN NaN NaN \n",
"14 15007040604 NaN NaN NaN NaN \n",
"\n",
" Quadrangle Name Watershed HUC Code FIPS Code Latitude ... \\\n",
"0 NaN NaN NaN NaN NaN ... \n",
"1 NaN NaN NaN NaN NaN ... \n",
"2 NaN NaN NaN NaN NaN ... \n",
"3 NaN NaN NaN NaN NaN ... \n",
"4 NaN NaN NaN NaN NaN ... \n",
"5 NaN NaN NaN NaN NaN ... \n",
"6 NaN NaN NaN NaN NaN ... \n",
"7 NaN NaN NaN NaN NaN ... \n",
"8 NaN NaN NaN NaN NaN ... \n",
"9 NaN NaN NaN NaN NaN ... \n",
"10 NaN NaN NaN NaN NaN ... \n",
"11 NaN NaN NaN NaN NaN ... \n",
"12 NaN NaN NaN NaN NaN ... \n",
"13 NaN NaN NaN NaN NaN ... \n",
"14 NaN NaN NaN NaN NaN ... \n",
"\n",
" Funded GPRA Acres Funded Metric Units Completed Standard Units \\\n",
"0 NaN NaN NaN \n",
"1 NaN NaN NaN \n",
"2 NaN NaN NaN \n",
"3 NaN NaN NaN \n",
"4 NaN NaN NaN \n",
"5 NaN NaN NaN \n",
"6 NaN NaN NaN \n",
"7 NaN NaN NaN \n",
"8 NaN NaN NaN \n",
"9 NaN NaN NaN \n",
"10 NaN NaN NaN \n",
"11 NaN NaN NaN \n",
"12 NaN NaN NaN \n",
"13 NaN NaN NaN \n",
"14 NaN NaN NaN \n",
"\n",
" Completed Costs Completed GPRA Acres Completed Metric Units Unnamed: 40 \\\n",
"0 NaN NaN NaN NaN \n",
"1 NaN NaN NaN NaN \n",
"2 NaN NaN NaN NaN \n",
"3 NaN NaN NaN NaN \n",
"4 NaN NaN NaN NaN \n",
"5 NaN NaN NaN NaN \n",
"6 NaN NaN NaN NaN \n",
"7 NaN NaN NaN NaN \n",
"8 NaN NaN NaN NaN \n",
"9 NaN NaN NaN NaN \n",
"10 NaN NaN NaN NaN \n",
"11 NaN NaN NaN NaN \n",
"12 NaN NaN NaN NaN \n",
"13 NaN NaN NaN NaN \n",
"14 NaN NaN NaN NaN \n",
"\n",
" geometry index_right _merge \n",
"0 None NaN left_only \n",
"1 None NaN left_only \n",
"2 None NaN left_only \n",
"3 None NaN left_only \n",
"4 None NaN left_only \n",
"5 None NaN left_only \n",
"6 None NaN left_only \n",
"7 None NaN left_only \n",
"8 None NaN left_only \n",
"9 None NaN left_only \n",
"10 None NaN left_only \n",
"11 None NaN left_only \n",
"12 None NaN left_only \n",
"13 None NaN left_only \n",
"14 None NaN left_only \n",
"\n",
"[15 rows x 45 columns]"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"merged_exaple_data[merged_exaple_data[\"_merge\"] == \"left_only\"]"
]
},
{
"cell_type": "code",
"execution_count": 22,
"id": "76f66b32-ce2e-4ad1-93f2-eb566be2e04f",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'AMLIS Key': 'AK000001',\n",
" 'State/Tribe': 'AK',\n",
" 'County': 'MATANUSKA-SUSITNA',\n",
" 'Congressional District': 1.0,\n",
" 'Quadrangle Name': 'ANCHORAGE C-8',\n",
" 'Watershed': nan,\n",
" 'HUC Code': nan,\n",
" 'FIPS Code': '02170',\n",
" 'Latitude': 61.6,\n",
" 'Longitude': -149.8,\n",
" 'Funding Source / Program': 'FRA',\n",
" 'Problem Area Name': 'EAST HOUSTON MINE',\n",
" 'Problem Area Number': 1,\n",
" 'Planning Unit Name': 'HOUSTON',\n",
" 'Planning Unit Number': '1',\n",
" 'Problem Priority': '1',\n",
" 'Problem Type': 'VO',\n",
" 'Mining Type': 'S',\n",
" 'Ore Types': nan,\n",
" 'Date Prepared': '12/3/1986 12:00:00 AM',\n",
" 'Date Revised': '4/23/2014 6:40:28 PM',\n",
" 'Private Owner %': 0.0,\n",
" 'State Owner %': 0.0,\n",
" 'Other Federal Owner %': 0.0,\n",
" 'Park Service Owner %': 0.0,\n",
" 'Forest Service Owner %': 0.0,\n",
" 'Indian Owner %': 0.0,\n",
" 'BLM Owner %': 0.0,\n",
" 'Unfunded Standard Units': 0.0,\n",
" 'Unfunded Costs': 0.0,\n",
" 'Unfunded GPRA Acres': 0.0,\n",
" 'Unfunded Metric Units': 0.0,\n",
" 'Funded Standard Units': 0.0,\n",
" 'Funded Costs': 0.0,\n",
" 'Funded GPRA Acres': 0.0,\n",
" 'Funded Metric Units': 0.0,\n",
" 'Completed Standard Units': 2.0,\n",
" 'Completed Costs': 10000.0,\n",
" 'Completed GPRA Acres': 0.2,\n",
" 'Completed Metric Units': 2.0,\n",
" 'Unnamed: 40': nan,\n",
" 'geometry': <shapely.geometry.point.Point at 0x7f858be68850>}"
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dict(df.iloc[0])"
]
},
{
"cell_type": "code",
"execution_count": 21,
"id": "3caf8290-8248-44e5-8f3b-c67c54e834de",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Index(['AMLIS Key', 'BLM Owner %', 'Completed Costs', 'Completed GPRA Acres',\n",
" 'Completed Metric Units', 'Completed Standard Units',\n",
" 'Congressional District', 'County', 'Date Prepared', 'Date Revised',\n",
" 'FIPS Code', 'Forest Service Owner %', 'Funded Costs',\n",
" 'Funded GPRA Acres', 'Funded Metric Units', 'Funded Standard Units',\n",
" 'Funding Source / Program', 'HUC Code', 'Indian Owner %', 'Latitude',\n",
" 'Longitude', 'Mining Type', 'Ore Types', 'Other Federal Owner %',\n",
" 'Park Service Owner %', 'Planning Unit Name', 'Planning Unit Number',\n",
" 'Private Owner %', 'Problem Area Name', 'Problem Area Number',\n",
" 'Problem Priority', 'Problem Type', 'Quadrangle Name', 'State Owner %',\n",
" 'State/Tribe', 'Unfunded Costs', 'Unfunded GPRA Acres',\n",
" 'Unfunded Metric Units', 'Unfunded Standard Units', 'Unnamed: 40',\n",
" 'Watershed', '_merge', 'geometry', 'index_right'],\n",
" dtype='object')"
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"merged_exaple_data.columns.difference([\"GEOID10_TRACT\"])"
]
},
{
"cell_type": "code",
"execution_count": 36,
"id": "2f0cd691-069e-4367-8f42-e77efd649e77",
"metadata": {},
"outputs": [],
"source": [
"def generate_fake_eamlis_row(tract: str, state: str) -> dict:\n",
" generate_fake_eamlis_row._row_id += 1\n",
" centroid = census_tracts.loc[tract].geometry.centroid\n",
" return {\n",
" \"AMLIS Key\": f\"{state}{str(generate_fake_eamlis_row._row_id).zfill(6)}\",\n",
" \"State/Tribe\": state,\n",
" \"County\": \"MATANUSKA-SUSITNA\",\n",
" \"Congressional District\": 1.0,\n",
" \"Quadrangle Name\": \"ANCHORAGE C-8\",\n",
" \"Watershed\": np.nan,\n",
" \"HUC Code\": np.nan,\n",
" \"FIPS Code\": \"02170\",\n",
" \"Latitude\": centroid.y,\n",
" \"Longitude\": centroid.x,\n",
" \"Funding Source / Program\": \"FRA\",\n",
" \"Problem Area Name\": \"EAST HOUSTON MINE\",\n",
" \"Problem Area Number\": 1,\n",
" \"Planning Unit Name\": \"HOUSTON\",\n",
" \"Planning Unit Number\": \"1\",\n",
" \"Problem Priority\": \"1\",\n",
" \"Problem Type\": \"VO\",\n",
" \"Mining Type\": \"S\",\n",
" \"Ore Types\": np.nan,\n",
" \"Date Prepared\": \"12/3/1986 12:00:00 AM\",\n",
" \"Date Revised\": \"4/23/2014 6:40:28 PM\",\n",
" \"Private Owner %\": 0.0,\n",
" \"State Owner %\": 0.0,\n",
" \"Other Federal Owner %\": 0.0,\n",
" \"Park Service Owner %\": 0.0,\n",
" \"Forest Service Owner %\": 0.0,\n",
" \"Indian Owner %\": 0.0,\n",
" \"BLM Owner %\": 0.0,\n",
" \"Unfunded Standard Units\": 0.0,\n",
" \"Unfunded Costs\": 0.0,\n",
" \"Unfunded GPRA Acres\": 0.0,\n",
" \"Unfunded Metric Units\": 0.0,\n",
" \"Funded Standard Units\": 0.0,\n",
" \"Funded Costs\": 0.0,\n",
" \"Funded GPRA Acres\": 0.0,\n",
" \"Funded Metric Units\": 0.0,\n",
" \"Completed Standard Units\": 2.0,\n",
" \"Completed Costs\": 10000.0,\n",
" \"Completed GPRA Acres\": 0.2,\n",
" \"Completed Metric Units\": 2.0,\n",
" \"Unnamed: 40\": np.nan,\n",
" }\n",
"\n",
"\n",
"generate_fake_eamlis_row._row_id = 0"
]
},
{
"cell_type": "code",
"execution_count": 37,
"id": "6ab61dda-8642-4706-9b67-b03ed27713fd",
"metadata": {},
"outputs": [],
"source": [
"rows = []\n",
"for tract in merged_exaple_data[\n",
" merged_exaple_data[\"_merge\"] == \"left_only\"\n",
"].GEOID10_TRACT:\n",
" state = \"HI\"\n",
" if tract.startswith(\"06\"):\n",
" state = \"CA\"\n",
" rows.append(generate_fake_eamlis_row(tract, state))"
]
},
{
"cell_type": "code",
"execution_count": 42,
"id": "93714c4d-3e1d-49c1-9bac-4e553e0bae08",
"metadata": {},
"outputs": [],
"source": [
"pd.DataFrame(rows).to_csv(\n",
" \"/home/matt/active/justice40-tool/data/data-pipeline/data_pipeline/tests/sources/eamlis/data/eAMLIS export of all data.tsv.zip\",\n",
" index=False,\n",
" sep=\"\\t\",\n",
")"
]
},
{
"cell_type": "markdown",
"id": "776d4dab-4067-4d36-9ce3-d7c7094ea8c6",
"metadata": {},
"source": [
"## Get the points for the geolocation mock"
]
},
{
"cell_type": "code",
"execution_count": 47,
"id": "a630a0f8-e922-4eb3-9937-6c4b590fd527",
"metadata": {},
"outputs": [],
"source": [
"lookup_table = {}\n",
"for tract in merged_exaple_data[\n",
" merged_exaple_data[\"_merge\"] == \"left_only\"\n",
"].GEOID10_TRACT:\n",
" centroid = census_tracts.loc[tract].geometry.centroid\n",
" lookup_table[(centroid.x, centroid.y)] = tract"
]
},
{
"cell_type": "code",
"execution_count": 51,
"id": "d828b2e0-424e-4040-b167-da46734bcf4d",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[{'AMLIS Key': 'CA000001',\n",
" 'State/Tribe': 'CA',\n",
" 'County': 'MATANUSKA-SUSITNA',\n",
" 'Congressional District': 1.0,\n",
" 'Quadrangle Name': 'ANCHORAGE C-8',\n",
" 'Watershed': nan,\n",
" 'HUC Code': nan,\n",
" 'FIPS Code': '02170',\n",
" 'Latitude': 36.25161281807095,\n",
" 'Longitude': -117.11772856883819,\n",
" 'Funding Source / Program': 'FRA',\n",
" 'Problem Area Name': 'EAST HOUSTON MINE',\n",
" 'Problem Area Number': 1,\n",
" 'Planning Unit Name': 'HOUSTON',\n",
" 'Planning Unit Number': '1',\n",
" 'Problem Priority': '1',\n",
" 'Problem Type': 'VO',\n",
" 'Mining Type': 'S',\n",
" 'Ore Types': nan,\n",
" 'Date Prepared': '12/3/1986 12:00:00 AM',\n",
" 'Date Revised': '4/23/2014 6:40:28 PM',\n",
" 'Private Owner %': 0.0,\n",
" 'State Owner %': 0.0,\n",
" 'Other Federal Owner %': 0.0,\n",
" 'Park Service Owner %': 0.0,\n",
" 'Forest Service Owner %': 0.0,\n",
" 'Indian Owner %': 0.0,\n",
" 'BLM Owner %': 0.0,\n",
" 'Unfunded Standard Units': 0.0,\n",
" 'Unfunded Costs': 0.0,\n",
" 'Unfunded GPRA Acres': 0.0,\n",
" 'Unfunded Metric Units': 0.0,\n",
" 'Funded Standard Units': 0.0,\n",
" 'Funded Costs': 0.0,\n",
" 'Funded GPRA Acres': 0.0,\n",
" 'Funded Metric Units': 0.0,\n",
" 'Completed Standard Units': 2.0,\n",
" 'Completed Costs': 10000.0,\n",
" 'Completed GPRA Acres': 0.2,\n",
" 'Completed Metric Units': 2.0,\n",
" 'Unnamed: 40': nan},\n",
" {'AMLIS Key': 'CA000002',\n",
" 'State/Tribe': 'CA',\n",
" 'County': 'MATANUSKA-SUSITNA',\n",
" 'Congressional District': 1.0,\n",
" 'Quadrangle Name': 'ANCHORAGE C-8',\n",
" 'Watershed': nan,\n",
" 'HUC Code': nan,\n",
" 'FIPS Code': '02170',\n",
" 'Latitude': 36.5498780497345,\n",
" 'Longitude': -121.0070599015156,\n",
" 'Funding Source / Program': 'FRA',\n",
" 'Problem Area Name': 'EAST HOUSTON MINE',\n",
" 'Problem Area Number': 1,\n",
" 'Planning Unit Name': 'HOUSTON',\n",
" 'Planning Unit Number': '1',\n",
" 'Problem Priority': '1',\n",
" 'Problem Type': 'VO',\n",
" 'Mining Type': 'S',\n",
" 'Ore Types': nan,\n",
" 'Date Prepared': '12/3/1986 12:00:00 AM',\n",
" 'Date Revised': '4/23/2014 6:40:28 PM',\n",
" 'Private Owner %': 0.0,\n",
" 'State Owner %': 0.0,\n",
" 'Other Federal Owner %': 0.0,\n",
" 'Park Service Owner %': 0.0,\n",
" 'Forest Service Owner %': 0.0,\n",
" 'Indian Owner %': 0.0,\n",
" 'BLM Owner %': 0.0,\n",
" 'Unfunded Standard Units': 0.0,\n",
" 'Unfunded Costs': 0.0,\n",
" 'Unfunded GPRA Acres': 0.0,\n",
" 'Unfunded Metric Units': 0.0,\n",
" 'Funded Standard Units': 0.0,\n",
" 'Funded Costs': 0.0,\n",
" 'Funded GPRA Acres': 0.0,\n",
" 'Funded Metric Units': 0.0,\n",
" 'Completed Standard Units': 2.0,\n",
" 'Completed Costs': 10000.0,\n",
" 'Completed GPRA Acres': 0.2,\n",
" 'Completed Metric Units': 2.0,\n",
" 'Unnamed: 40': nan},\n",
" {'AMLIS Key': 'CA000003',\n",
" 'State/Tribe': 'CA',\n",
" 'County': 'MATANUSKA-SUSITNA',\n",
" 'Congressional District': 1.0,\n",
" 'Quadrangle Name': 'ANCHORAGE C-8',\n",
" 'Watershed': nan,\n",
" 'HUC Code': nan,\n",
" 'FIPS Code': '02170',\n",
" 'Latitude': 38.84602113669345,\n",
" 'Longitude': -121.40564726784282,\n",
" 'Funding Source / Program': 'FRA',\n",
" 'Problem Area Name': 'EAST HOUSTON MINE',\n",
" 'Problem Area Number': 1,\n",
" 'Planning Unit Name': 'HOUSTON',\n",
" 'Planning Unit Number': '1',\n",
" 'Problem Priority': '1',\n",
" 'Problem Type': 'VO',\n",
" 'Mining Type': 'S',\n",
" 'Ore Types': nan,\n",
" 'Date Prepared': '12/3/1986 12:00:00 AM',\n",
" 'Date Revised': '4/23/2014 6:40:28 PM',\n",
" 'Private Owner %': 0.0,\n",
" 'State Owner %': 0.0,\n",
" 'Other Federal Owner %': 0.0,\n",
" 'Park Service Owner %': 0.0,\n",
" 'Forest Service Owner %': 0.0,\n",
" 'Indian Owner %': 0.0,\n",
" 'BLM Owner %': 0.0,\n",
" 'Unfunded Standard Units': 0.0,\n",
" 'Unfunded Costs': 0.0,\n",
" 'Unfunded GPRA Acres': 0.0,\n",
" 'Unfunded Metric Units': 0.0,\n",
" 'Funded Standard Units': 0.0,\n",
" 'Funded Costs': 0.0,\n",
" 'Funded GPRA Acres': 0.0,\n",
" 'Funded Metric Units': 0.0,\n",
" 'Completed Standard Units': 2.0,\n",
" 'Completed Costs': 10000.0,\n",
" 'Completed GPRA Acres': 0.2,\n",
" 'Completed Metric Units': 2.0,\n",
" 'Unnamed: 40': nan},\n",
" {'AMLIS Key': 'HI000004',\n",
" 'State/Tribe': 'HI',\n",
" 'County': 'MATANUSKA-SUSITNA',\n",
" 'Congressional District': 1.0,\n",
" 'Quadrangle Name': 'ANCHORAGE C-8',\n",
" 'Watershed': nan,\n",
" 'HUC Code': nan,\n",
" 'FIPS Code': '02170',\n",
" 'Latitude': 19.49784370888389,\n",
" 'Longitude': -155.10321769858746,\n",
" 'Funding Source / Program': 'FRA',\n",
" 'Problem Area Name': 'EAST HOUSTON MINE',\n",
" 'Problem Area Number': 1,\n",
" 'Planning Unit Name': 'HOUSTON',\n",
" 'Planning Unit Number': '1',\n",
" 'Problem Priority': '1',\n",
" 'Problem Type': 'VO',\n",
" 'Mining Type': 'S',\n",
" 'Ore Types': nan,\n",
" 'Date Prepared': '12/3/1986 12:00:00 AM',\n",
" 'Date Revised': '4/23/2014 6:40:28 PM',\n",
" 'Private Owner %': 0.0,\n",
" 'State Owner %': 0.0,\n",
" 'Other Federal Owner %': 0.0,\n",
" 'Park Service Owner %': 0.0,\n",
" 'Forest Service Owner %': 0.0,\n",
" 'Indian Owner %': 0.0,\n",
" 'BLM Owner %': 0.0,\n",
" 'Unfunded Standard Units': 0.0,\n",
" 'Unfunded Costs': 0.0,\n",
" 'Unfunded GPRA Acres': 0.0,\n",
" 'Unfunded Metric Units': 0.0,\n",
" 'Funded Standard Units': 0.0,\n",
" 'Funded Costs': 0.0,\n",
" 'Funded GPRA Acres': 0.0,\n",
" 'Funded Metric Units': 0.0,\n",
" 'Completed Standard Units': 2.0,\n",
" 'Completed Costs': 10000.0,\n",
" 'Completed GPRA Acres': 0.2,\n",
" 'Completed Metric Units': 2.0,\n",
" 'Unnamed: 40': nan},\n",
" {'AMLIS Key': 'HI000005',\n",
" 'State/Tribe': 'HI',\n",
" 'County': 'MATANUSKA-SUSITNA',\n",
" 'Congressional District': 1.0,\n",
" 'Quadrangle Name': 'ANCHORAGE C-8',\n",
" 'Watershed': nan,\n",
" 'HUC Code': nan,\n",
" 'FIPS Code': '02170',\n",
" 'Latitude': 19.446650238354696,\n",
" 'Longitude': -154.89548634140738,\n",
" 'Funding Source / Program': 'FRA',\n",
" 'Problem Area Name': 'EAST HOUSTON MINE',\n",
" 'Problem Area Number': 1,\n",
" 'Planning Unit Name': 'HOUSTON',\n",
" 'Planning Unit Number': '1',\n",
" 'Problem Priority': '1',\n",
" 'Problem Type': 'VO',\n",
" 'Mining Type': 'S',\n",
" 'Ore Types': nan,\n",
" 'Date Prepared': '12/3/1986 12:00:00 AM',\n",
" 'Date Revised': '4/23/2014 6:40:28 PM',\n",
" 'Private Owner %': 0.0,\n",
" 'State Owner %': 0.0,\n",
" 'Other Federal Owner %': 0.0,\n",
" 'Park Service Owner %': 0.0,\n",
" 'Forest Service Owner %': 0.0,\n",
" 'Indian Owner %': 0.0,\n",
" 'BLM Owner %': 0.0,\n",
" 'Unfunded Standard Units': 0.0,\n",
" 'Unfunded Costs': 0.0,\n",
" 'Unfunded GPRA Acres': 0.0,\n",
" 'Unfunded Metric Units': 0.0,\n",
" 'Funded Standard Units': 0.0,\n",
" 'Funded Costs': 0.0,\n",
" 'Funded GPRA Acres': 0.0,\n",
" 'Funded Metric Units': 0.0,\n",
" 'Completed Standard Units': 2.0,\n",
" 'Completed Costs': 10000.0,\n",
" 'Completed GPRA Acres': 0.2,\n",
" 'Completed Metric Units': 2.0,\n",
" 'Unnamed: 40': nan},\n",
" {'AMLIS Key': 'HI000006',\n",
" 'State/Tribe': 'HI',\n",
" 'County': 'MATANUSKA-SUSITNA',\n",
" 'Congressional District': 1.0,\n",
" 'Quadrangle Name': 'ANCHORAGE C-8',\n",
" 'Watershed': nan,\n",
" 'HUC Code': nan,\n",
" 'FIPS Code': '02170',\n",
" 'Latitude': 21.904412260968197,\n",
" 'Longitude': -159.43665201302525,\n",
" 'Funding Source / Program': 'FRA',\n",
" 'Problem Area Name': 'EAST HOUSTON MINE',\n",
" 'Problem Area Number': 1,\n",
" 'Planning Unit Name': 'HOUSTON',\n",
" 'Planning Unit Number': '1',\n",
" 'Problem Priority': '1',\n",
" 'Problem Type': 'VO',\n",
" 'Mining Type': 'S',\n",
" 'Ore Types': nan,\n",
" 'Date Prepared': '12/3/1986 12:00:00 AM',\n",
" 'Date Revised': '4/23/2014 6:40:28 PM',\n",
" 'Private Owner %': 0.0,\n",
" 'State Owner %': 0.0,\n",
" 'Other Federal Owner %': 0.0,\n",
" 'Park Service Owner %': 0.0,\n",
" 'Forest Service Owner %': 0.0,\n",
" 'Indian Owner %': 0.0,\n",
" 'BLM Owner %': 0.0,\n",
" 'Unfunded Standard Units': 0.0,\n",
" 'Unfunded Costs': 0.0,\n",
" 'Unfunded GPRA Acres': 0.0,\n",
" 'Unfunded Metric Units': 0.0,\n",
" 'Funded Standard Units': 0.0,\n",
" 'Funded Costs': 0.0,\n",
" 'Funded GPRA Acres': 0.0,\n",
" 'Funded Metric Units': 0.0,\n",
" 'Completed Standard Units': 2.0,\n",
" 'Completed Costs': 10000.0,\n",
" 'Completed GPRA Acres': 0.2,\n",
" 'Completed Metric Units': 2.0,\n",
" 'Unnamed: 40': nan},\n",
" {'AMLIS Key': 'HI000007',\n",
" 'State/Tribe': 'HI',\n",
" 'County': 'MATANUSKA-SUSITNA',\n",
" 'Congressional District': 1.0,\n",
" 'Quadrangle Name': 'ANCHORAGE C-8',\n",
" 'Watershed': nan,\n",
" 'HUC Code': nan,\n",
" 'FIPS Code': '02170',\n",
" 'Latitude': 21.94208315793464,\n",
" 'Longitude': -159.52362041178708,\n",
" 'Funding Source / Program': 'FRA',\n",
" 'Problem Area Name': 'EAST HOUSTON MINE',\n",
" 'Problem Area Number': 1,\n",
" 'Planning Unit Name': 'HOUSTON',\n",
" 'Planning Unit Number': '1',\n",
" 'Problem Priority': '1',\n",
" 'Problem Type': 'VO',\n",
" 'Mining Type': 'S',\n",
" 'Ore Types': nan,\n",
" 'Date Prepared': '12/3/1986 12:00:00 AM',\n",
" 'Date Revised': '4/23/2014 6:40:28 PM',\n",
" 'Private Owner %': 0.0,\n",
" 'State Owner %': 0.0,\n",
" 'Other Federal Owner %': 0.0,\n",
" 'Park Service Owner %': 0.0,\n",
" 'Forest Service Owner %': 0.0,\n",
" 'Indian Owner %': 0.0,\n",
" 'BLM Owner %': 0.0,\n",
" 'Unfunded Standard Units': 0.0,\n",
" 'Unfunded Costs': 0.0,\n",
" 'Unfunded GPRA Acres': 0.0,\n",
" 'Unfunded Metric Units': 0.0,\n",
" 'Funded Standard Units': 0.0,\n",
" 'Funded Costs': 0.0,\n",
" 'Funded GPRA Acres': 0.0,\n",
" 'Funded Metric Units': 0.0,\n",
" 'Completed Standard Units': 2.0,\n",
" 'Completed Costs': 10000.0,\n",
" 'Completed GPRA Acres': 0.2,\n",
" 'Completed Metric Units': 2.0,\n",
" 'Unnamed: 40': nan},\n",
" {'AMLIS Key': 'HI000008',\n",
" 'State/Tribe': 'HI',\n",
" 'County': 'MATANUSKA-SUSITNA',\n",
" 'Congressional District': 1.0,\n",
" 'Quadrangle Name': 'ANCHORAGE C-8',\n",
" 'Watershed': nan,\n",
" 'HUC Code': nan,\n",
" 'FIPS Code': '02170',\n",
" 'Latitude': 20.72796381691298,\n",
" 'Longitude': -156.14177664396527,\n",
" 'Funding Source / Program': 'FRA',\n",
" 'Problem Area Name': 'EAST HOUSTON MINE',\n",
" 'Problem Area Number': 1,\n",
" 'Planning Unit Name': 'HOUSTON',\n",
" 'Planning Unit Number': '1',\n",
" 'Problem Priority': '1',\n",
" 'Problem Type': 'VO',\n",
" 'Mining Type': 'S',\n",
" 'Ore Types': nan,\n",
" 'Date Prepared': '12/3/1986 12:00:00 AM',\n",
" 'Date Revised': '4/23/2014 6:40:28 PM',\n",
" 'Private Owner %': 0.0,\n",
" 'State Owner %': 0.0,\n",
" 'Other Federal Owner %': 0.0,\n",
" 'Park Service Owner %': 0.0,\n",
" 'Forest Service Owner %': 0.0,\n",
" 'Indian Owner %': 0.0,\n",
" 'BLM Owner %': 0.0,\n",
" 'Unfunded Standard Units': 0.0,\n",
" 'Unfunded Costs': 0.0,\n",
" 'Unfunded GPRA Acres': 0.0,\n",
" 'Unfunded Metric Units': 0.0,\n",
" 'Funded Standard Units': 0.0,\n",
" 'Funded Costs': 0.0,\n",
" 'Funded GPRA Acres': 0.0,\n",
" 'Funded Metric Units': 0.0,\n",
" 'Completed Standard Units': 2.0,\n",
" 'Completed Costs': 10000.0,\n",
" 'Completed GPRA Acres': 0.2,\n",
" 'Completed Metric Units': 2.0,\n",
" 'Unnamed: 40': nan},\n",
" {'AMLIS Key': 'HI000009',\n",
" 'State/Tribe': 'HI',\n",
" 'County': 'MATANUSKA-SUSITNA',\n",
" 'Congressional District': 1.0,\n",
" 'Quadrangle Name': 'ANCHORAGE C-8',\n",
" 'Watershed': nan,\n",
" 'HUC Code': nan,\n",
" 'FIPS Code': '02170',\n",
" 'Latitude': 20.86486713282688,\n",
" 'Longitude': -156.2497797752935,\n",
" 'Funding Source / Program': 'FRA',\n",
" 'Problem Area Name': 'EAST HOUSTON MINE',\n",
" 'Problem Area Number': 1,\n",
" 'Planning Unit Name': 'HOUSTON',\n",
" 'Planning Unit Number': '1',\n",
" 'Problem Priority': '1',\n",
" 'Problem Type': 'VO',\n",
" 'Mining Type': 'S',\n",
" 'Ore Types': nan,\n",
" 'Date Prepared': '12/3/1986 12:00:00 AM',\n",
" 'Date Revised': '4/23/2014 6:40:28 PM',\n",
" 'Private Owner %': 0.0,\n",
" 'State Owner %': 0.0,\n",
" 'Other Federal Owner %': 0.0,\n",
" 'Park Service Owner %': 0.0,\n",
" 'Forest Service Owner %': 0.0,\n",
" 'Indian Owner %': 0.0,\n",
" 'BLM Owner %': 0.0,\n",
" 'Unfunded Standard Units': 0.0,\n",
" 'Unfunded Costs': 0.0,\n",
" 'Unfunded GPRA Acres': 0.0,\n",
" 'Unfunded Metric Units': 0.0,\n",
" 'Funded Standard Units': 0.0,\n",
" 'Funded Costs': 0.0,\n",
" 'Funded GPRA Acres': 0.0,\n",
" 'Funded Metric Units': 0.0,\n",
" 'Completed Standard Units': 2.0,\n",
" 'Completed Costs': 10000.0,\n",
" 'Completed GPRA Acres': 0.2,\n",
" 'Completed Metric Units': 2.0,\n",
" 'Unnamed: 40': nan},\n",
" {'AMLIS Key': 'HI000010',\n",
" 'State/Tribe': 'HI',\n",
" 'County': 'MATANUSKA-SUSITNA',\n",
" 'Congressional District': 1.0,\n",
" 'Quadrangle Name': 'ANCHORAGE C-8',\n",
" 'Watershed': nan,\n",
" 'HUC Code': nan,\n",
" 'FIPS Code': '02170',\n",
" 'Latitude': 19.516629328900667,\n",
" 'Longitude': -155.91378867633992,\n",
" 'Funding Source / Program': 'FRA',\n",
" 'Problem Area Name': 'EAST HOUSTON MINE',\n",
" 'Problem Area Number': 1,\n",
" 'Planning Unit Name': 'HOUSTON',\n",
" 'Planning Unit Number': '1',\n",
" 'Problem Priority': '1',\n",
" 'Problem Type': 'VO',\n",
" 'Mining Type': 'S',\n",
" 'Ore Types': nan,\n",
" 'Date Prepared': '12/3/1986 12:00:00 AM',\n",
" 'Date Revised': '4/23/2014 6:40:28 PM',\n",
" 'Private Owner %': 0.0,\n",
" 'State Owner %': 0.0,\n",
" 'Other Federal Owner %': 0.0,\n",
" 'Park Service Owner %': 0.0,\n",
" 'Forest Service Owner %': 0.0,\n",
" 'Indian Owner %': 0.0,\n",
" 'BLM Owner %': 0.0,\n",
" 'Unfunded Standard Units': 0.0,\n",
" 'Unfunded Costs': 0.0,\n",
" 'Unfunded GPRA Acres': 0.0,\n",
" 'Unfunded Metric Units': 0.0,\n",
" 'Funded Standard Units': 0.0,\n",
" 'Funded Costs': 0.0,\n",
" 'Funded GPRA Acres': 0.0,\n",
" 'Funded Metric Units': 0.0,\n",
" 'Completed Standard Units': 2.0,\n",
" 'Completed Costs': 10000.0,\n",
" 'Completed GPRA Acres': 0.2,\n",
" 'Completed Metric Units': 2.0,\n",
" 'Unnamed: 40': nan},\n",
" {'AMLIS Key': 'HI000011',\n",
" 'State/Tribe': 'HI',\n",
" 'County': 'MATANUSKA-SUSITNA',\n",
" 'Congressional District': 1.0,\n",
" 'Quadrangle Name': 'ANCHORAGE C-8',\n",
" 'Watershed': nan,\n",
" 'HUC Code': nan,\n",
" 'FIPS Code': '02170',\n",
" 'Latitude': 20.164406070883054,\n",
" 'Longitude': -155.81110884967674,\n",
" 'Funding Source / Program': 'FRA',\n",
" 'Problem Area Name': 'EAST HOUSTON MINE',\n",
" 'Problem Area Number': 1,\n",
" 'Planning Unit Name': 'HOUSTON',\n",
" 'Planning Unit Number': '1',\n",
" 'Problem Priority': '1',\n",
" 'Problem Type': 'VO',\n",
" 'Mining Type': 'S',\n",
" 'Ore Types': nan,\n",
" 'Date Prepared': '12/3/1986 12:00:00 AM',\n",
" 'Date Revised': '4/23/2014 6:40:28 PM',\n",
" 'Private Owner %': 0.0,\n",
" 'State Owner %': 0.0,\n",
" 'Other Federal Owner %': 0.0,\n",
" 'Park Service Owner %': 0.0,\n",
" 'Forest Service Owner %': 0.0,\n",
" 'Indian Owner %': 0.0,\n",
" 'BLM Owner %': 0.0,\n",
" 'Unfunded Standard Units': 0.0,\n",
" 'Unfunded Costs': 0.0,\n",
" 'Unfunded GPRA Acres': 0.0,\n",
" 'Unfunded Metric Units': 0.0,\n",
" 'Funded Standard Units': 0.0,\n",
" 'Funded Costs': 0.0,\n",
" 'Funded GPRA Acres': 0.0,\n",
" 'Funded Metric Units': 0.0,\n",
" 'Completed Standard Units': 2.0,\n",
" 'Completed Costs': 10000.0,\n",
" 'Completed GPRA Acres': 0.2,\n",
" 'Completed Metric Units': 2.0,\n",
" 'Unnamed: 40': nan},\n",
" {'AMLIS Key': 'HI000012',\n",
" 'State/Tribe': 'HI',\n",
" 'County': 'MATANUSKA-SUSITNA',\n",
" 'Congressional District': 1.0,\n",
" 'Quadrangle Name': 'ANCHORAGE C-8',\n",
" 'Watershed': nan,\n",
" 'HUC Code': nan,\n",
" 'FIPS Code': '02170',\n",
" 'Latitude': 20.825369670478306,\n",
" 'Longitude': -156.33064622489087,\n",
" 'Funding Source / Program': 'FRA',\n",
" 'Problem Area Name': 'EAST HOUSTON MINE',\n",
" 'Problem Area Number': 1,\n",
" 'Planning Unit Name': 'HOUSTON',\n",
" 'Planning Unit Number': '1',\n",
" 'Problem Priority': '1',\n",
" 'Problem Type': 'VO',\n",
" 'Mining Type': 'S',\n",
" 'Ore Types': nan,\n",
" 'Date Prepared': '12/3/1986 12:00:00 AM',\n",
" 'Date Revised': '4/23/2014 6:40:28 PM',\n",
" 'Private Owner %': 0.0,\n",
" 'State Owner %': 0.0,\n",
" 'Other Federal Owner %': 0.0,\n",
" 'Park Service Owner %': 0.0,\n",
" 'Forest Service Owner %': 0.0,\n",
" 'Indian Owner %': 0.0,\n",
" 'BLM Owner %': 0.0,\n",
" 'Unfunded Standard Units': 0.0,\n",
" 'Unfunded Costs': 0.0,\n",
" 'Unfunded GPRA Acres': 0.0,\n",
" 'Unfunded Metric Units': 0.0,\n",
" 'Funded Standard Units': 0.0,\n",
" 'Funded Costs': 0.0,\n",
" 'Funded GPRA Acres': 0.0,\n",
" 'Funded Metric Units': 0.0,\n",
" 'Completed Standard Units': 2.0,\n",
" 'Completed Costs': 10000.0,\n",
" 'Completed GPRA Acres': 0.2,\n",
" 'Completed Metric Units': 2.0,\n",
" 'Unnamed: 40': nan},\n",
" {'AMLIS Key': 'HI000013',\n",
" 'State/Tribe': 'HI',\n",
" 'County': 'MATANUSKA-SUSITNA',\n",
" 'Congressional District': 1.0,\n",
" 'Quadrangle Name': 'ANCHORAGE C-8',\n",
" 'Watershed': nan,\n",
" 'HUC Code': nan,\n",
" 'FIPS Code': '02170',\n",
" 'Latitude': 20.9170439162332,\n",
" 'Longitude': -156.54289869319305,\n",
" 'Funding Source / Program': 'FRA',\n",
" 'Problem Area Name': 'EAST HOUSTON MINE',\n",
" 'Problem Area Number': 1,\n",
" 'Planning Unit Name': 'HOUSTON',\n",
" 'Planning Unit Number': '1',\n",
" 'Problem Priority': '1',\n",
" 'Problem Type': 'VO',\n",
" 'Mining Type': 'S',\n",
" 'Ore Types': nan,\n",
" 'Date Prepared': '12/3/1986 12:00:00 AM',\n",
" 'Date Revised': '4/23/2014 6:40:28 PM',\n",
" 'Private Owner %': 0.0,\n",
" 'State Owner %': 0.0,\n",
" 'Other Federal Owner %': 0.0,\n",
" 'Park Service Owner %': 0.0,\n",
" 'Forest Service Owner %': 0.0,\n",
" 'Indian Owner %': 0.0,\n",
" 'BLM Owner %': 0.0,\n",
" 'Unfunded Standard Units': 0.0,\n",
" 'Unfunded Costs': 0.0,\n",
" 'Unfunded GPRA Acres': 0.0,\n",
" 'Unfunded Metric Units': 0.0,\n",
" 'Funded Standard Units': 0.0,\n",
" 'Funded Costs': 0.0,\n",
" 'Funded GPRA Acres': 0.0,\n",
" 'Funded Metric Units': 0.0,\n",
" 'Completed Standard Units': 2.0,\n",
" 'Completed Costs': 10000.0,\n",
" 'Completed GPRA Acres': 0.2,\n",
" 'Completed Metric Units': 2.0,\n",
" 'Unnamed: 40': nan},\n",
" {'AMLIS Key': 'HI000014',\n",
" 'State/Tribe': 'HI',\n",
" 'County': 'MATANUSKA-SUSITNA',\n",
" 'Congressional District': 1.0,\n",
" 'Quadrangle Name': 'ANCHORAGE C-8',\n",
" 'Watershed': nan,\n",
" 'HUC Code': nan,\n",
" 'FIPS Code': '02170',\n",
" 'Latitude': 21.556464980367483,\n",
" 'Longitude': -157.89225964427064,\n",
" 'Funding Source / Program': 'FRA',\n",
" 'Problem Area Name': 'EAST HOUSTON MINE',\n",
" 'Problem Area Number': 1,\n",
" 'Planning Unit Name': 'HOUSTON',\n",
" 'Planning Unit Number': '1',\n",
" 'Problem Priority': '1',\n",
" 'Problem Type': 'VO',\n",
" 'Mining Type': 'S',\n",
" 'Ore Types': nan,\n",
" 'Date Prepared': '12/3/1986 12:00:00 AM',\n",
" 'Date Revised': '4/23/2014 6:40:28 PM',\n",
" 'Private Owner %': 0.0,\n",
" 'State Owner %': 0.0,\n",
" 'Other Federal Owner %': 0.0,\n",
" 'Park Service Owner %': 0.0,\n",
" 'Forest Service Owner %': 0.0,\n",
" 'Indian Owner %': 0.0,\n",
" 'BLM Owner %': 0.0,\n",
" 'Unfunded Standard Units': 0.0,\n",
" 'Unfunded Costs': 0.0,\n",
" 'Unfunded GPRA Acres': 0.0,\n",
" 'Unfunded Metric Units': 0.0,\n",
" 'Funded Standard Units': 0.0,\n",
" 'Funded Costs': 0.0,\n",
" 'Funded GPRA Acres': 0.0,\n",
" 'Funded Metric Units': 0.0,\n",
" 'Completed Standard Units': 2.0,\n",
" 'Completed Costs': 10000.0,\n",
" 'Completed GPRA Acres': 0.2,\n",
" 'Completed Metric Units': 2.0,\n",
" 'Unnamed: 40': nan},\n",
" {'AMLIS Key': 'HI000015',\n",
" 'State/Tribe': 'HI',\n",
" 'County': 'MATANUSKA-SUSITNA',\n",
" 'Congressional District': 1.0,\n",
" 'Quadrangle Name': 'ANCHORAGE C-8',\n",
" 'Watershed': nan,\n",
" 'HUC Code': nan,\n",
" 'FIPS Code': '02170',\n",
" 'Latitude': 21.90754283544759,\n",
" 'Longitude': -159.48416846823164,\n",
" 'Funding Source / Program': 'FRA',\n",
" 'Problem Area Name': 'EAST HOUSTON MINE',\n",
" 'Problem Area Number': 1,\n",
" 'Planning Unit Name': 'HOUSTON',\n",
" 'Planning Unit Number': '1',\n",
" 'Problem Priority': '1',\n",
" 'Problem Type': 'VO',\n",
" 'Mining Type': 'S',\n",
" 'Ore Types': nan,\n",
" 'Date Prepared': '12/3/1986 12:00:00 AM',\n",
" 'Date Revised': '4/23/2014 6:40:28 PM',\n",
" 'Private Owner %': 0.0,\n",
" 'State Owner %': 0.0,\n",
" 'Other Federal Owner %': 0.0,\n",
" 'Park Service Owner %': 0.0,\n",
" 'Forest Service Owner %': 0.0,\n",
" 'Indian Owner %': 0.0,\n",
" 'BLM Owner %': 0.0,\n",
" 'Unfunded Standard Units': 0.0,\n",
" 'Unfunded Costs': 0.0,\n",
" 'Unfunded GPRA Acres': 0.0,\n",
" 'Unfunded Metric Units': 0.0,\n",
" 'Funded Standard Units': 0.0,\n",
" 'Funded Costs': 0.0,\n",
" 'Funded GPRA Acres': 0.0,\n",
" 'Funded Metric Units': 0.0,\n",
" 'Completed Standard Units': 2.0,\n",
" 'Completed Costs': 10000.0,\n",
" 'Completed GPRA Acres': 0.2,\n",
" 'Completed Metric Units': 2.0,\n",
" 'Unnamed: 40': nan}]"
]
},
"execution_count": 51,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"rows"
]
},
{
"cell_type": "code",
"execution_count": 48,
"id": "d6b1d835-deb2-4bbd-b33e-460ba94cf192",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{(-117.11772856883819, 36.25161281807095): '06027000800',\n",
" (-121.0070599015156, 36.5498780497345): '06069000802',\n",
" (-121.40564726784282, 38.84602113669345): '06061021322',\n",
" (-155.10321769858746, 19.49784370888389): '15001021010',\n",
" (-154.89548634140738, 19.446650238354696): '15001021101',\n",
" (-159.43665201302525, 21.904412260968197): '15007040603',\n",
" (-159.52362041178708, 21.94208315793464): '15007040700',\n",
" (-156.14177664396527, 20.72796381691298): '15009030100',\n",
" (-156.2497797752935, 20.86486713282688): '15009030201',\n",
" (-155.91378867633992, 19.516629328900667): '15001021402',\n",
" (-155.81110884967674, 20.164406070883054): '15001021800',\n",
" (-156.33064622489087, 20.825369670478306): '15009030402',\n",
" (-156.54289869319305, 20.9170439162332): '15009030800',\n",
" (-157.89225964427064, 21.556464980367483): '15003010201',\n",
" (-159.48416846823164, 21.90754283544759): '15007040604'}"
]
},
"execution_count": 48,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"lookup_table"
]
}
],
"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
}