{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Sample workflow: 1990 block group parts to 2010 counties\n",
    "\n",
    "## Starting from a subset of 2010 Delaware blocks\n",
    "\n",
    "For further background information see:\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": "2020-06-22T00:09:36.595166Z",
     "start_time": "2020-06-22T00:09:36.562841Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2020-06-21T20:09:36-04:00\n",
      "\n",
      "CPython 3.7.6\n",
      "IPython 7.15.0\n",
      "\n",
      "compiler   : Clang 9.0.1 \n",
      "system     : Darwin\n",
      "release    : 19.5.0\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": "2020-06-22T00:09:37.352276Z",
     "start_time": "2020-06-22T00:09:37.073590Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "watermark 2.0.2\n",
      "nhgisxwalk 0.0.5\n",
      "numpy      1.18.5\n",
      "pandas     1.0.4\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": "2020-06-22T00:09:38.160877Z",
     "start_time": "2020-06-22T00:09:38.130399Z"
    }
   },
   "outputs": [],
   "source": [
    "source_year, target_year = \"1990\", \"2010\""
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Source-target building base"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-06-22T00:09:38.965841Z",
     "start_time": "2020-06-22T00:09:38.874865Z"
    }
   },
   "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>NaN</td>\n",
       "      <td>G10000100432021078</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>NaN</td>\n",
       "      <td>G10000100432023014</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>NaN</td>\n",
       "      <td>G10000100432023015</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>NaN</td>\n",
       "      <td>G10000109900000011</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>NaN</td>\n",
       "      <td>G10000109900000012</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  GJOIN1990           GJOIN2010  WEIGHT  PAREA_VIA_BLK00\n",
       "0       NaN  G10000100432021078     0.0              0.0\n",
       "1       NaN  G10000100432023014     0.0              0.0\n",
       "2       NaN  G10000100432023015     0.0              0.0\n",
       "3       NaN  G10000109900000011     0.0              0.0\n",
       "4       NaN  G10000109900000012     0.0              0.0"
      ]
     },
     "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.csv.zip\" % (source_year, target_year)\n",
    "base_xwalk_file = subset_data_dir + base_xwalk_name\n",
    "data_types = nhgisxwalk.str_types([\"GJOIN%s\"%source_year, \"GJOIN%s\"%target_year])\n",
    "base_xwalk = pandas.read_csv(base_xwalk_file, index_col=0, dtype=data_types)\n",
    "base_xwalk.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Source supplementary summary data (special case for 1990)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-06-22T00:09:40.983368Z",
     "start_time": "2020-06-22T00:09:40.953058Z"
    }
   },
   "outputs": [],
   "source": [
    "supp_source_name = \"%s_blck_grp_598_103.csv.zip\" % source_year\n",
    "supp_source_file = subset_data_dir + supp_source_name"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Convenience code shorthand/lookup"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-06-22T00:09:41.794199Z",
     "start_time": "2020-06-22T00:09:41.761857Z"
    }
   },
   "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",
      "        \"bkg\": \"block group\",\n",
      "        \"trt\": \"tract\",\n",
      "        \"cty\": \"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": 7,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-06-22T00:09:42.534098Z",
     "start_time": "2020-06-22T00:09:42.502108Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'block': 'blk',\n",
       " 'block group part': 'bgp',\n",
       " 'block group': 'bkg',\n",
       " 'tract': 'trt',\n",
       " 'county': 'cty'}"
      ]
     },
     "execution_count": 7,
     "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/jGaboardi/nhgisxwalk/blob/92b4fe55de0a9c53d0315dcda8ec121faaf20aef/nhgisxwalk/geocrosswalk.py#L19) for full details"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-06-22T00:09:43.218813Z",
     "start_time": "2020-06-22T00:09:43.185876Z"
    }
   },
   "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": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "nhgisxwalk.desc_code_1990"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-06-22T00:09:43.651933Z",
     "start_time": "2020-06-22T00:09:43.617962Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['ET1001', 'EUD001', 'EUO001', 'ESA001']"
      ]
     },
     "execution_count": 9,
     "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": 10,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-06-22T00:09:44.595756Z",
     "start_time": "2020-06-22T00:09:44.565838Z"
    }
   },
   "outputs": [],
   "source": [
    "input_var_tags = [\"pop\", \"fam\", \"hh\", \"hu\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-06-22T00:09:46.260049Z",
     "start_time": "2020-06-22T00:09:45.799249Z"
    }
   },
   "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>cty2010gj</th>\n",
       "      <th>cty2010ge</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>G1000010</td>\n",
       "      <td>10001</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>G1000010</td>\n",
       "      <td>10001</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>G1000010</td>\n",
       "      <td>10001</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>G100001090444612650422009999999219012</td>\n",
       "      <td>G1000010</td>\n",
       "      <td>10001</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>G100001090444614800422009999999999924</td>\n",
       "      <td>G1000010</td>\n",
       "      <td>10001</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>772</th>\n",
       "      <td>G100005093552999990515009999999999922</td>\n",
       "      <td>G1000050</td>\n",
       "      <td>10005</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>773</th>\n",
       "      <td>G100005093552999990515009999999999923</td>\n",
       "      <td>G1000050</td>\n",
       "      <td>10005</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>774</th>\n",
       "      <td>G100005093552999990515009999999999924</td>\n",
       "      <td>G1000050</td>\n",
       "      <td>10005</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>775</th>\n",
       "      <td>G100005093552999990516009999999999921</td>\n",
       "      <td>G1000050</td>\n",
       "      <td>10005</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>776</th>\n",
       "      <td>G340033010610106000204029999999916014</td>\n",
       "      <td>G1000030</td>\n",
       "      <td>10003</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>777 rows × 7 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                 bgp1990gj cty2010gj cty2010ge  wt_pop  \\\n",
       "0    G100001090444072500423009999999999921  G1000010     10001     1.0   \n",
       "1    G100001090444444300422009999999999926  G1000010     10001     1.0   \n",
       "2    G100001090444612650422009999999219011  G1000010     10001     1.0   \n",
       "3    G100001090444612650422009999999219012  G1000010     10001     1.0   \n",
       "4    G100001090444614800422009999999999924  G1000010     10001     1.0   \n",
       "..                                     ...       ...       ...     ...   \n",
       "772  G100005093552999990515009999999999922  G1000050     10005     1.0   \n",
       "773  G100005093552999990515009999999999923  G1000050     10005     1.0   \n",
       "774  G100005093552999990515009999999999924  G1000050     10005     1.0   \n",
       "775  G100005093552999990516009999999999921  G1000050     10005     1.0   \n",
       "776  G340033010610106000204029999999916014  G1000030     10003     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",
       "772     1.0    1.0    1.0  \n",
       "773     1.0    1.0    1.0  \n",
       "774     1.0    1.0    1.0  \n",
       "775     1.0    1.0    1.0  \n",
       "776     0.0    0.0    0.0  \n",
       "\n",
       "[777 rows x 7 columns]"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "subset_state = \"10\"\n",
    "bgp1990_to_cty2010 = nhgisxwalk.GeoCrossWalk(\n",
    "    base_xwalk,\n",
    "    source_year=source_year,\n",
    "    target_year=target_year,\n",
    "    source_geo=\"bgp\",\n",
    "    target_geo=\"cty\",\n",
    "    base_source_table=subset_data_dir+\"/1990_block.csv.zip\",\n",
    "    supp_source_table=subset_data_dir+\"/1990_blck_grp_598_103.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",
    "bgp1990_to_cty2010.xwalk"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Write crosswalk to a `.csv`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-06-22T00:26:46.621188Z",
     "start_time": "2020-06-22T00:26:46.509756Z"
    }
   },
   "outputs": [],
   "source": [
    "state_dir = \"../../crosswalks/nhgis_bgp1990_cty2010_state/\"\n",
    "nhgisxwalk.xwalk_df_to_csv(\n",
    "    cls=bgp1990_to_cty2010,\n",
    "    path=state_dir\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Read crosswalk from a `.csv`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-06-22T00:26:49.866489Z",
     "start_time": "2020-06-22T00:26:49.833544Z"
    }
   },
   "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>cty2010gj</th>\n",
       "      <th>cty2010ge</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>G1000010</td>\n",
       "      <td>10001</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>G1000010</td>\n",
       "      <td>10001</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>G1000010</td>\n",
       "      <td>10001</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>G100001090444612650422009999999219012</td>\n",
       "      <td>G1000010</td>\n",
       "      <td>10001</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>G100001090444614800422009999999999924</td>\n",
       "      <td>G1000010</td>\n",
       "      <td>10001</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>772</th>\n",
       "      <td>G100005093552999990515009999999999922</td>\n",
       "      <td>G1000050</td>\n",
       "      <td>10005</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>773</th>\n",
       "      <td>G100005093552999990515009999999999923</td>\n",
       "      <td>G1000050</td>\n",
       "      <td>10005</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>774</th>\n",
       "      <td>G100005093552999990515009999999999924</td>\n",
       "      <td>G1000050</td>\n",
       "      <td>10005</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>775</th>\n",
       "      <td>G100005093552999990516009999999999921</td>\n",
       "      <td>G1000050</td>\n",
       "      <td>10005</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>776</th>\n",
       "      <td>G340033010610106000204029999999916014</td>\n",
       "      <td>G1000030</td>\n",
       "      <td>10003</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>777 rows × 7 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                 bgp1990gj cty2010gj  cty2010ge  wt_pop  \\\n",
       "0    G100001090444072500423009999999999921  G1000010      10001     1.0   \n",
       "1    G100001090444444300422009999999999926  G1000010      10001     1.0   \n",
       "2    G100001090444612650422009999999219011  G1000010      10001     1.0   \n",
       "3    G100001090444612650422009999999219012  G1000010      10001     1.0   \n",
       "4    G100001090444614800422009999999999924  G1000010      10001     1.0   \n",
       "..                                     ...       ...        ...     ...   \n",
       "772  G100005093552999990515009999999999922  G1000050      10005     1.0   \n",
       "773  G100005093552999990515009999999999923  G1000050      10005     1.0   \n",
       "774  G100005093552999990515009999999999924  G1000050      10005     1.0   \n",
       "775  G100005093552999990516009999999999921  G1000050      10005     1.0   \n",
       "776  G340033010610106000204029999999916014  G1000030      10003     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",
       "772     1.0    1.0    1.0  \n",
       "773     1.0    1.0    1.0  \n",
       "774     1.0    1.0    1.0  \n",
       "775     1.0    1.0    1.0  \n",
       "776     0.0    0.0    0.0  \n",
       "\n",
       "[777 rows x 7 columns]"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fname = state_dir + bgp1990_to_cty2010.xwalk_name\n",
    "bgp1990_to_bkg2010_df = nhgisxwalk.xwalk_df_from_csv(fname)\n",
    "bgp1990_to_bkg2010_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": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}