{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# This file is part of the Minnesota Population Center's NHGISXWALK.\n",
    "# For copyright and licensing information, see the NOTICE and LICENSE files\n",
    "# in this project's top-level directory, and also on-line at:\n",
    "#   https://github.com/ipums/nhgisxwalk"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Sample workflow: 2000 block group parts to 2010 block groups\n",
    "\n",
    "## Starting from a subset of 2010 Delaware blocks\n",
    "\n",
    "For further background information see:\n",
    "\n",
    "* **Schroeder, J. P**. 2007. *Target-density weighting interpolation and uncertainty evaluation for temporal analysis of census data*. Geographical Analysis 39 (3):311–335.\n",
    "\n",
    "#### NHGIS [block crosswalks](https://www.nhgis.org/user-resources/geographic-crosswalks)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-08-19T22:07:25.359511Z",
     "start_time": "2020-08-19T22:07:25.243071Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2020-08-19T18:07:25-04:00\n",
      "\n",
      "CPython 3.8.5\n",
      "IPython 7.16.1\n",
      "\n",
      "compiler   : Clang 10.0.1 \n",
      "system     : Darwin\n",
      "release    : 19.6.0\n",
      "machine    : x86_64\n",
      "processor  : i386\n",
      "CPU cores  : 8\n",
      "interpreter: 64bit\n"
     ]
    }
   ],
   "source": [
    "%load_ext watermark\n",
    "%watermark"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-08-19T22:07:25.648513Z",
     "start_time": "2020-08-19T22:07:25.361589Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "watermark 2.0.2\n",
      "pandas     1.1.0\n",
      "nhgisxwalk 0.0.9\n",
      "\n"
     ]
    }
   ],
   "source": [
    "import nhgisxwalk\n",
    "import inspect\n",
    "import pandas\n",
    "\n",
    "%load_ext autoreload\n",
    "%autoreload 2\n",
    "%watermark -w\n",
    "%watermark -iv"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Source and target years for the crosswalk"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-08-19T22:07:25.671220Z",
     "start_time": "2020-08-19T22:07:25.651159Z"
    }
   },
   "outputs": [],
   "source": [
    "source_year, target_year = \"2000\", \"2010\"\n",
    "gj_src, gj_trg = \"GJOIN%s\"%source_year, \"GJOIN%s\"%target_year"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Source-target building base"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-08-19T22:07:25.740179Z",
     "start_time": "2020-08-19T22:07:25.673969Z"
    }
   },
   "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>GJOIN2000</th>\n",
       "      <th>GJOIN2010</th>\n",
       "      <th>WEIGHT</th>\n",
       "      <th>PAREA</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>G10000100401001000</td>\n",
       "      <td>G10000100401001000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>G10000100401001001</td>\n",
       "      <td>G10000100401001001</td>\n",
       "      <td>0.999981</td>\n",
       "      <td>0.999988</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>G10000100401001001</td>\n",
       "      <td>G10000100401001003</td>\n",
       "      <td>0.000019</td>\n",
       "      <td>0.000012</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>G10000100401001002</td>\n",
       "      <td>G10000100401001002</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>G10000100401001003</td>\n",
       "      <td>G10000100401001003</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            GJOIN2000           GJOIN2010    WEIGHT     PAREA\n",
       "0  G10000100401001000  G10000100401001000  1.000000  1.000000\n",
       "1  G10000100401001001  G10000100401001001  0.999981  0.999988\n",
       "2  G10000100401001001  G10000100401001003  0.000019  0.000012\n",
       "3  G10000100401001002  G10000100401001002  1.000000  1.000000\n",
       "4  G10000100401001003  G10000100401001003  1.000000  1.000000"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "subset_data_dir = \"../testing_data_subsets/\"\n",
    "base_xwalk_name = \"nhgis_blk%s_blk%s_gj\" % (source_year, target_year)\n",
    "data_types = nhgisxwalk.str_types([gj_src, gj_trg])\n",
    "from_csv_kws = {\"path\": subset_data_dir, \"archived\": True, \"remove_unpacked\": True}\n",
    "read_csv_kws = {\"dtype\": data_types}\n",
    "base_xwalk = nhgisxwalk.xwalk_df_from_csv(\n",
    "    base_xwalk_name, **from_csv_kws, **read_csv_kws\n",
    ")\n",
    "base_xwalk.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Convenience code shorthand/lookup"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-08-19T22:07:25.764562Z",
     "start_time": "2020-08-19T22:07:25.742008Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "def valid_geo_shorthand(shorthand_name=True):\n",
      "    \"\"\"Shorthand lookups for census geographies.\"\"\"\n",
      "    lookup = {\n",
      "        \"blk\": \"block\",\n",
      "        \"bgp\": \"block group part\",\n",
      "        \"bg\": \"block group\",\n",
      "        \"tr\": \"tract\",\n",
      "        \"co\": \"county\",\n",
      "    }\n",
      "    if not shorthand_name:\n",
      "        lookup = {v: k for k, v in lookup.items()}\n",
      "    return lookup\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(inspect.getsource(nhgisxwalk.valid_geo_shorthand))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-08-19T22:07:25.786672Z",
     "start_time": "2020-08-19T22:07:25.766202Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'block': 'blk',\n",
       " 'block group part': 'bgp',\n",
       " 'block group': 'bg',\n",
       " 'tract': 'tr',\n",
       " 'county': 'co'}"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "nhgisxwalk.valid_geo_shorthand(shorthand_name=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Instantiate an `nhgisxwalk.GeoCrossWalk` object\n",
    "##### see [nhgisxwalk.GeoCrossWalk](https://github.com/ipums/nhgisxwalk/blob/92b4fe55de0a9c53d0315dcda8ec121faaf20aef/nhgisxwalk/geocrosswalk.py#L19) for full details"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-08-19T22:07:25.810746Z",
     "start_time": "2020-08-19T22:07:25.788752Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'Persons': {'Persons': 'Universe',\n",
       "  'NP001A': 'Source code',\n",
       "  'FXS': 'NHGIS code',\n",
       "  'Total': 'FXS001'},\n",
       " 'Families': {'Families': 'Universe',\n",
       "  'NP031A': 'Source code',\n",
       "  'F2V': 'NHGIS code',\n",
       "  'Total': 'F2V001'},\n",
       " 'Households': {'Households': 'Universe',\n",
       "  'NP010A': 'Source code',\n",
       "  'FY4': 'NHGIS code',\n",
       "  'Total': 'FY4001'},\n",
       " 'Housing Units': {'Housing Units': 'Universe',\n",
       "  'NH001A': 'Source code',\n",
       "  'FV5': 'NHGIS code',\n",
       "  'Total': 'FV5001'}}"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "nhgisxwalk.desc_code_2000_SF1b"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-08-19T22:07:25.834599Z",
     "start_time": "2020-08-19T22:07:25.814093Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['FXS001', 'F2V001', 'FY4001', 'FV5001']"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "input_vars = [\n",
    "    nhgisxwalk.desc_code_2000_SF1b[\"Persons\"][\"Total\"],\n",
    "    nhgisxwalk.desc_code_2000_SF1b[\"Families\"][\"Total\"],\n",
    "    nhgisxwalk.desc_code_2000_SF1b[\"Households\"][\"Total\"],\n",
    "    nhgisxwalk.desc_code_2000_SF1b[\"Housing Units\"][\"Total\"]\n",
    "]\n",
    "input_vars"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-08-19T22:07:25.856409Z",
     "start_time": "2020-08-19T22:07:25.836915Z"
    }
   },
   "outputs": [],
   "source": [
    "input_var_tags = [\"pop\", \"fam\", \"hh\", \"hu\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-08-19T22:07:26.159122Z",
     "start_time": "2020-08-19T22:07:25.857972Z"
    }
   },
   "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>bgp2000gj</th>\n",
       "      <th>bg2010gj</th>\n",
       "      <th>bg2010ge</th>\n",
       "      <th>wt_pop</th>\n",
       "      <th>wt_fam</th>\n",
       "      <th>wt_hh</th>\n",
       "      <th>wt_hu</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>G10000109044444430042202U1</td>\n",
       "      <td>G10000100422021</td>\n",
       "      <td>100010422021</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>G10000109044461265042201R1</td>\n",
       "      <td>G10000100422011</td>\n",
       "      <td>100010422011</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>G10000109044461265042201U1</td>\n",
       "      <td>G10000100422011</td>\n",
       "      <td>100010422011</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>G10000109044461265042201U2</td>\n",
       "      <td>G10000100422012</td>\n",
       "      <td>100010422012</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>G10000109044461480042202R2</td>\n",
       "      <td>G10000100422022</td>\n",
       "      <td>100010422022</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1220</th>\n",
       "      <td>G10000509355299999051500R4</td>\n",
       "      <td>G10000500515004</td>\n",
       "      <td>100050515004</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1221</th>\n",
       "      <td>G10000509355299999051500U1</td>\n",
       "      <td>G10000500515001</td>\n",
       "      <td>100050515001</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1222</th>\n",
       "      <td>G10000509355299999051500U3</td>\n",
       "      <td>G10000500515003</td>\n",
       "      <td>100050515003</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1223</th>\n",
       "      <td>G10000509355299999051500U4</td>\n",
       "      <td>G10000500515004</td>\n",
       "      <td>100050515004</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1224</th>\n",
       "      <td>G34003301061010600020400U2</td>\n",
       "      <td>G10000309901000</td>\n",
       "      <td>100039901000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1225 rows × 7 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                       bgp2000gj         bg2010gj      bg2010ge  wt_pop  \\\n",
       "0     G10000109044444430042202U1  G10000100422021  100010422021     1.0   \n",
       "1     G10000109044461265042201R1  G10000100422011  100010422011     1.0   \n",
       "2     G10000109044461265042201U1  G10000100422011  100010422011     1.0   \n",
       "3     G10000109044461265042201U2  G10000100422012  100010422012     1.0   \n",
       "4     G10000109044461480042202R2  G10000100422022  100010422022     1.0   \n",
       "...                          ...              ...           ...     ...   \n",
       "1220  G10000509355299999051500R4  G10000500515004  100050515004     1.0   \n",
       "1221  G10000509355299999051500U1  G10000500515001  100050515001     1.0   \n",
       "1222  G10000509355299999051500U3  G10000500515003  100050515003     1.0   \n",
       "1223  G10000509355299999051500U4  G10000500515004  100050515004     1.0   \n",
       "1224  G34003301061010600020400U2  G10000309901000  100039901000     0.0   \n",
       "\n",
       "      wt_fam  wt_hh  wt_hu  \n",
       "0        1.0    1.0    1.0  \n",
       "1        1.0    1.0    1.0  \n",
       "2        1.0    1.0    1.0  \n",
       "3        1.0    1.0    1.0  \n",
       "4        1.0    1.0    1.0  \n",
       "...      ...    ...    ...  \n",
       "1220     1.0    1.0    1.0  \n",
       "1221     1.0    1.0    1.0  \n",
       "1222     1.0    1.0    1.0  \n",
       "1223     1.0    1.0    1.0  \n",
       "1224     0.0    0.0    0.0  \n",
       "\n",
       "[1225 rows x 7 columns]"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "subset_state = \"10\"\n",
    "bgp2000_to_bg2010 = nhgisxwalk.GeoCrossWalk(\n",
    "    base_xwalk,\n",
    "    source_year=source_year,\n",
    "    target_year=target_year,\n",
    "    source_geo=\"bgp\",\n",
    "    target_geo=\"bg\",\n",
    "    base_source_table=subset_data_dir+\"/2000_block.csv.zip\",\n",
    "    input_var=input_vars,\n",
    "    weight_var=input_var_tags,\n",
    "    stfips=subset_state,\n",
    "    keep_base=True,\n",
    "    add_geoid=True\n",
    ")\n",
    "bgp2000_to_bg2010.xwalk"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Prepare a single data product with a `README.txt`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-08-19T22:07:26.181895Z",
     "start_time": "2020-08-19T22:07:26.161187Z"
    }
   },
   "outputs": [],
   "source": [
    "xwalk, xwalk_name = bgp2000_to_bg2010.xwalk, bgp2000_to_bg2010.xwalk_name\n",
    "xwalk_name_base = \"_\".join(xwalk_name.split(\"_\")[:-1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-08-19T22:07:26.218005Z",
     "start_time": "2020-08-19T22:07:26.183262Z"
    }
   },
   "outputs": [],
   "source": [
    "out_data_dir = \"../../crosswalks/\"\n",
    "out_path = \"%s%s%s/%s\" % (out_data_dir, xwalk_name_base, \"_state\", xwalk_name)\n",
    "nhgisxwalk.prepare_data_product(xwalk, xwalk_name, out_path, remove=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Read crosswalk from a `.zip` archive"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-08-19T22:07:26.254819Z",
     "start_time": "2020-08-19T22:07:26.219857Z"
    }
   },
   "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>bgp2000gj</th>\n",
       "      <th>bg2010gj</th>\n",
       "      <th>bg2010ge</th>\n",
       "      <th>wt_pop</th>\n",
       "      <th>wt_fam</th>\n",
       "      <th>wt_hh</th>\n",
       "      <th>wt_hu</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>G10000109044444430042202U1</td>\n",
       "      <td>G10000100422021</td>\n",
       "      <td>100010422021</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>G10000109044461265042201R1</td>\n",
       "      <td>G10000100422011</td>\n",
       "      <td>100010422011</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>G10000109044461265042201U1</td>\n",
       "      <td>G10000100422011</td>\n",
       "      <td>100010422011</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>G10000109044461265042201U2</td>\n",
       "      <td>G10000100422012</td>\n",
       "      <td>100010422012</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>G10000109044461480042202R2</td>\n",
       "      <td>G10000100422022</td>\n",
       "      <td>100010422022</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1220</th>\n",
       "      <td>G10000509355299999051500R4</td>\n",
       "      <td>G10000500515004</td>\n",
       "      <td>100050515004</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1221</th>\n",
       "      <td>G10000509355299999051500U1</td>\n",
       "      <td>G10000500515001</td>\n",
       "      <td>100050515001</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1222</th>\n",
       "      <td>G10000509355299999051500U3</td>\n",
       "      <td>G10000500515003</td>\n",
       "      <td>100050515003</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1223</th>\n",
       "      <td>G10000509355299999051500U4</td>\n",
       "      <td>G10000500515004</td>\n",
       "      <td>100050515004</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1224</th>\n",
       "      <td>G34003301061010600020400U2</td>\n",
       "      <td>G10000309901000</td>\n",
       "      <td>100039901000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1225 rows × 7 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                       bgp2000gj         bg2010gj      bg2010ge  wt_pop  \\\n",
       "0     G10000109044444430042202U1  G10000100422021  100010422021     1.0   \n",
       "1     G10000109044461265042201R1  G10000100422011  100010422011     1.0   \n",
       "2     G10000109044461265042201U1  G10000100422011  100010422011     1.0   \n",
       "3     G10000109044461265042201U2  G10000100422012  100010422012     1.0   \n",
       "4     G10000109044461480042202R2  G10000100422022  100010422022     1.0   \n",
       "...                          ...              ...           ...     ...   \n",
       "1220  G10000509355299999051500R4  G10000500515004  100050515004     1.0   \n",
       "1221  G10000509355299999051500U1  G10000500515001  100050515001     1.0   \n",
       "1222  G10000509355299999051500U3  G10000500515003  100050515003     1.0   \n",
       "1223  G10000509355299999051500U4  G10000500515004  100050515004     1.0   \n",
       "1224  G34003301061010600020400U2  G10000309901000  100039901000     0.0   \n",
       "\n",
       "      wt_fam  wt_hh  wt_hu  \n",
       "0        1.0    1.0    1.0  \n",
       "1        1.0    1.0    1.0  \n",
       "2        1.0    1.0    1.0  \n",
       "3        1.0    1.0    1.0  \n",
       "4        1.0    1.0    1.0  \n",
       "...      ...    ...    ...  \n",
       "1220     1.0    1.0    1.0  \n",
       "1221     1.0    1.0    1.0  \n",
       "1222     1.0    1.0    1.0  \n",
       "1223     1.0    1.0    1.0  \n",
       "1224     0.0    0.0    0.0  \n",
       "\n",
       "[1225 rows x 7 columns]"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "in_path = \"%s%s%s\" % (out_data_dir, xwalk_name_base, \"_state/\")\n",
    "id_cols = [c for c in xwalk.columns if not c.startswith(\"wt\")]\n",
    "data_types = nhgisxwalk.str_types(id_cols)\n",
    "from_csv_kws = {\"path\": in_path, \"archived\": True, \"remove_unpacked\": True}\n",
    "read_csv_kws = {\"dtype\": data_types}\n",
    "bgp2000_to_bg2010_df = nhgisxwalk.xwalk_df_from_csv(\n",
    "    xwalk_name, **from_csv_kws, **read_csv_kws\n",
    ")\n",
    "bgp2000_to_bg2010_df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "-----------------------------------------------"
   ]
  }
 ],
 "metadata": {
  "_draft": {
   "nbviewer_url": "https://gist.github.com/9f47e4ec2cc37bce83acf20abfca69d2"
  },
  "gist": {
   "data": {
    "description": "sample-workflow.ipynb",
    "public": true
   },
   "id": "9f47e4ec2cc37bce83acf20abfca69d2"
  },
  "kernelspec": {
   "display_name": "Python [conda env:nhgis] *",
   "language": "python",
   "name": "conda-env-nhgis-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}