{
 "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: 1990 block group parts to 2010 tracts\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": "2020-08-19T22:07:22.191149Z",
     "start_time": "2020-08-19T22:07:22.064267Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2020-08-19T18:07:22-04:00\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": "2020-08-19T22:07:22.478158Z",
     "start_time": "2020-08-19T22:07:22.193759Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "watermark 2.0.2\n",
      "numpy      1.19.1\n",
      "pandas     1.1.0\n",
      "nhgisxwalk 0.0.9\n",
      "\n"
     ]
    }
   ],
   "source": [
    "import nhgisxwalk\n",
    "import inspect\n",
    "import numpy\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": "2020-08-19T22:07:22.498507Z",
     "start_time": "2020-08-19T22:07:22.480973Z"
    }
   },
   "outputs": [],
   "source": [
    "source_year, target_year = \"1990\", \"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": "2020-08-19T22:07:22.571834Z",
     "start_time": "2020-08-19T22:07:22.500302Z"
    }
   },
   "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>GJOIN1990</th>\n",
       "      <th>GJOIN2010</th>\n",
       "      <th>WEIGHT</th>\n",
       "      <th>PAREA_VIA_BLK00</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>G10000100401101</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>G10000100401102</td>\n",
       "      <td>G10000100401001001</td>\n",
       "      <td>0.921750</td>\n",
       "      <td>0.976774</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>G10000100401102</td>\n",
       "      <td>G10000100401001002</td>\n",
       "      <td>0.078219</td>\n",
       "      <td>0.023215</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>G10000100401102</td>\n",
       "      <td>G10000100401001003</td>\n",
       "      <td>0.000031</td>\n",
       "      <td>0.000012</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>G10000100401103</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": [
       "         GJOIN1990           GJOIN2010    WEIGHT  PAREA_VIA_BLK00\n",
       "0  G10000100401101  G10000100401001000  1.000000         1.000000\n",
       "1  G10000100401102  G10000100401001001  0.921750         0.976774\n",
       "2  G10000100401102  G10000100401001002  0.078219         0.023215\n",
       "3  G10000100401102  G10000100401001003  0.000031         0.000012\n",
       "4  G10000100401103  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": [
    "### Set the base (source) summary file name"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-08-19T22:07:22.591531Z",
     "start_time": "2020-08-19T22:07:22.573773Z"
    }
   },
   "outputs": [],
   "source": [
    "base_source_name = \"%s_block.csv.zip\" % source_year\n",
    "base_source_file = \"%s%s\" % (subset_data_dir, base_source_name)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Source supplementary summary data (special case for 1990)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-08-19T22:07:22.609948Z",
     "start_time": "2020-08-19T22:07:22.592899Z"
    }
   },
   "outputs": [],
   "source": [
    "supp_source_name = \"%s_blck_grp_598.csv.zip\" % source_year\n",
    "supp_source_file = \"%s%s\" % (subset_data_dir, supp_source_name)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Convenience code shorthand/lookup"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-08-19T22:07:22.629510Z",
     "start_time": "2020-08-19T22:07:22.611398Z"
    }
   },
   "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": 8,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-08-19T22:07:22.649827Z",
     "start_time": "2020-08-19T22:07:22.632253Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'block': 'blk',\n",
       " 'block group part': 'bgp',\n",
       " 'block group': 'bg',\n",
       " 'tract': 'tr',\n",
       " 'county': 'co'}"
      ]
     },
     "execution_count": 8,
     "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": 9,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-08-19T22:07:22.670875Z",
     "start_time": "2020-08-19T22:07:22.651614Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'Persons': {'Persons': 'Universe',\n",
       "  'NP1': 'Source code',\n",
       "  'ET1': 'NHGIS code',\n",
       "  'Total': 'ET1001'},\n",
       " 'Families': {'Families': 'Universe',\n",
       "  'NP2': 'Source code',\n",
       "  'EUD': 'NHGIS code',\n",
       "  'Total': 'EUD001'},\n",
       " 'Households': {'Households': 'Universe',\n",
       "  'NP3': 'Source code',\n",
       "  'EUO': 'NHGIS code',\n",
       "  'Total': 'EUO001'},\n",
       " 'Housing Units': {'Housing Units': 'Universe',\n",
       "  'NH1': 'Source code',\n",
       "  'ESA': 'NHGIS code',\n",
       "  'Total': 'ESA001'}}"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "nhgisxwalk.desc_code_1990"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-08-19T22:07:22.691725Z",
     "start_time": "2020-08-19T22:07:22.672883Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['ET1001', 'EUD001', 'EUO001', 'ESA001']"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "input_vars = [\n",
    "    nhgisxwalk.desc_code_1990[\"Persons\"][\"Total\"],\n",
    "    nhgisxwalk.desc_code_1990[\"Families\"][\"Total\"],\n",
    "    nhgisxwalk.desc_code_1990[\"Households\"][\"Total\"],\n",
    "    nhgisxwalk.desc_code_1990[\"Housing Units\"][\"Total\"]\n",
    "]\n",
    "input_vars"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-08-19T22:07:22.710638Z",
     "start_time": "2020-08-19T22:07:22.692955Z"
    }
   },
   "outputs": [],
   "source": [
    "input_var_tags = [\"pop\", \"fam\", \"hh\", \"hu\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-08-19T22:07:23.149076Z",
     "start_time": "2020-08-19T22:07:22.711943Z"
    }
   },
   "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>bgp1990gj</th>\n",
       "      <th>tr2010gj</th>\n",
       "      <th>tr2010ge</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>G100001090444072500423009999999999921</td>\n",
       "      <td>G1000010043202</td>\n",
       "      <td>10001043202</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>G100001090444444300422009999999999926</td>\n",
       "      <td>G1000010042202</td>\n",
       "      <td>10001042202</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>G100001090444612650422009999999219011</td>\n",
       "      <td>G1000010041200</td>\n",
       "      <td>10001041200</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>G100001090444612650422009999999219011</td>\n",
       "      <td>G1000010042201</td>\n",
       "      <td>10001042201</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>G100001090444612650422009999999219012</td>\n",
       "      <td>G1000010042201</td>\n",
       "      <td>10001042201</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>1058</th>\n",
       "      <td>G100005093552999990515009999999999923</td>\n",
       "      <td>G1000050051500</td>\n",
       "      <td>10005051500</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>1059</th>\n",
       "      <td>G100005093552999990515009999999999924</td>\n",
       "      <td>G1000050051500</td>\n",
       "      <td>10005051500</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>1060</th>\n",
       "      <td>G100005093552999990516009999999999921</td>\n",
       "      <td>G1000050051702</td>\n",
       "      <td>10005051702</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>1061</th>\n",
       "      <td>G340033010610106000204029999999916014</td>\n",
       "      <td>G1000030990100</td>\n",
       "      <td>10003990100</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1062</th>\n",
       "      <td>NaN</td>\n",
       "      <td>G1000050990000</td>\n",
       "      <td>10005990000</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>1063 rows × 7 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                  bgp1990gj        tr2010gj     tr2010ge  \\\n",
       "0     G100001090444072500423009999999999921  G1000010043202  10001043202   \n",
       "1     G100001090444444300422009999999999926  G1000010042202  10001042202   \n",
       "2     G100001090444612650422009999999219011  G1000010041200  10001041200   \n",
       "3     G100001090444612650422009999999219011  G1000010042201  10001042201   \n",
       "4     G100001090444612650422009999999219012  G1000010042201  10001042201   \n",
       "...                                     ...             ...          ...   \n",
       "1058  G100005093552999990515009999999999923  G1000050051500  10005051500   \n",
       "1059  G100005093552999990515009999999999924  G1000050051500  10005051500   \n",
       "1060  G100005093552999990516009999999999921  G1000050051702  10005051702   \n",
       "1061  G340033010610106000204029999999916014  G1000030990100  10003990100   \n",
       "1062                                    NaN  G1000050990000  10005990000   \n",
       "\n",
       "      wt_pop  wt_fam  wt_hh  wt_hu  \n",
       "0        1.0     1.0    1.0    1.0  \n",
       "1        1.0     1.0    1.0    1.0  \n",
       "2        0.0     0.0    0.0    0.0  \n",
       "3        1.0     1.0    1.0    1.0  \n",
       "4        1.0     1.0    1.0    1.0  \n",
       "...      ...     ...    ...    ...  \n",
       "1058     1.0     1.0    1.0    1.0  \n",
       "1059     1.0     1.0    1.0    1.0  \n",
       "1060     1.0     1.0    1.0    1.0  \n",
       "1061     0.0     0.0    0.0    0.0  \n",
       "1062     0.0     0.0    0.0    0.0  \n",
       "\n",
       "[1063 rows x 7 columns]"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "subset_state = \"10\"\n",
    "bgp1990_to_tr2010 = nhgisxwalk.GeoCrossWalk(\n",
    "    base_xwalk,\n",
    "    source_year=source_year,\n",
    "    target_year=target_year,\n",
    "    source_geo=\"bgp\",\n",
    "    target_geo=\"tr\",\n",
    "    base_source_table=base_source_file,\n",
    "    supp_source_table=supp_source_file,\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",
    "bgp1990_to_tr2010.xwalk"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-08-10T18:49:59.203300Z",
     "start_time": "2020-08-10T18:49:59.184356Z"
    }
   },
   "source": [
    "### Prepare a single data product with a `README.txt`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-08-19T22:07:23.168951Z",
     "start_time": "2020-08-19T22:07:23.150700Z"
    }
   },
   "outputs": [],
   "source": [
    "xwalk, xwalk_name = bgp1990_to_tr2010.xwalk, bgp1990_to_tr2010.xwalk_name\n",
    "xwalk_name_base = \"_\".join(xwalk_name.split(\"_\")[:-1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-08-19T22:07:23.200102Z",
     "start_time": "2020-08-19T22:07:23.170495Z"
    }
   },
   "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": 15,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-08-19T22:07:23.234234Z",
     "start_time": "2020-08-19T22:07:23.201433Z"
    }
   },
   "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>bgp1990gj</th>\n",
       "      <th>tr2010gj</th>\n",
       "      <th>tr2010ge</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>G100001090444072500423009999999999921</td>\n",
       "      <td>G1000010043202</td>\n",
       "      <td>10001043202</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>G100001090444444300422009999999999926</td>\n",
       "      <td>G1000010042202</td>\n",
       "      <td>10001042202</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>G100001090444612650422009999999219011</td>\n",
       "      <td>G1000010041200</td>\n",
       "      <td>10001041200</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>G100001090444612650422009999999219011</td>\n",
       "      <td>G1000010042201</td>\n",
       "      <td>10001042201</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>G100001090444612650422009999999219012</td>\n",
       "      <td>G1000010042201</td>\n",
       "      <td>10001042201</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>1058</th>\n",
       "      <td>G100005093552999990515009999999999923</td>\n",
       "      <td>G1000050051500</td>\n",
       "      <td>10005051500</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>1059</th>\n",
       "      <td>G100005093552999990515009999999999924</td>\n",
       "      <td>G1000050051500</td>\n",
       "      <td>10005051500</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>1060</th>\n",
       "      <td>G100005093552999990516009999999999921</td>\n",
       "      <td>G1000050051702</td>\n",
       "      <td>10005051702</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>1061</th>\n",
       "      <td>G340033010610106000204029999999916014</td>\n",
       "      <td>G1000030990100</td>\n",
       "      <td>10003990100</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1062</th>\n",
       "      <td>NaN</td>\n",
       "      <td>G1000050990000</td>\n",
       "      <td>10005990000</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>1063 rows × 7 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                  bgp1990gj        tr2010gj     tr2010ge  \\\n",
       "0     G100001090444072500423009999999999921  G1000010043202  10001043202   \n",
       "1     G100001090444444300422009999999999926  G1000010042202  10001042202   \n",
       "2     G100001090444612650422009999999219011  G1000010041200  10001041200   \n",
       "3     G100001090444612650422009999999219011  G1000010042201  10001042201   \n",
       "4     G100001090444612650422009999999219012  G1000010042201  10001042201   \n",
       "...                                     ...             ...          ...   \n",
       "1058  G100005093552999990515009999999999923  G1000050051500  10005051500   \n",
       "1059  G100005093552999990515009999999999924  G1000050051500  10005051500   \n",
       "1060  G100005093552999990516009999999999921  G1000050051702  10005051702   \n",
       "1061  G340033010610106000204029999999916014  G1000030990100  10003990100   \n",
       "1062                                    NaN  G1000050990000  10005990000   \n",
       "\n",
       "      wt_pop  wt_fam  wt_hh  wt_hu  \n",
       "0        1.0     1.0    1.0    1.0  \n",
       "1        1.0     1.0    1.0    1.0  \n",
       "2        0.0     0.0    0.0    0.0  \n",
       "3        1.0     1.0    1.0    1.0  \n",
       "4        1.0     1.0    1.0    1.0  \n",
       "...      ...     ...    ...    ...  \n",
       "1058     1.0     1.0    1.0    1.0  \n",
       "1059     1.0     1.0    1.0    1.0  \n",
       "1060     1.0     1.0    1.0    1.0  \n",
       "1061     0.0     0.0    0.0    0.0  \n",
       "1062     0.0     0.0    0.0    0.0  \n",
       "\n",
       "[1063 rows x 7 columns]"
      ]
     },
     "execution_count": 15,
     "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",
    "bgp1990_to_tr2010_df = nhgisxwalk.xwalk_df_from_csv(\n",
    "    xwalk_name, **from_csv_kws, **read_csv_kws\n",
    ")\n",
    "bgp1990_to_tr2010_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
}