{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Sample workflow: 2000 block group parts to 2010 tracts\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": "2020-06-21T01:22:31.407006Z",
     "start_time": "2020-06-21T01:22:31.388628Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2020-06-20T21:22:31-04:00\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": "2020-06-21T01:22:31.667253Z",
     "start_time": "2020-06-21T01:22:31.409541Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "watermark 2.0.2\n",
      "nhgisxwalk 0.0.4\n",
      "pandas     1.0.4\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": "2020-06-21T01:22:31.688421Z",
     "start_time": "2020-06-21T01:22:31.669855Z"
    }
   },
   "outputs": [],
   "source": [
    "source_year, target_year = \"2000\", \"2010\""
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Source-target building base"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-06-21T01:22:31.755998Z",
     "start_time": "2020-06-21T01:22:31.690527Z"
    }
   },
   "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.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": [
    "### Convenience code shorthand/lookup"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-06-21T01:22:31.778102Z",
     "start_time": "2020-06-21T01:22:31.757835Z"
    }
   },
   "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": 6,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-06-21T01:22:31.799993Z",
     "start_time": "2020-06-21T01:22:31.779860Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'block': 'blk',\n",
       " 'block group part': 'bgp',\n",
       " 'block group': 'bkg',\n",
       " 'tract': 'trt',\n",
       " 'county': 'cty'}"
      ]
     },
     "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/jGaboardi/nhgisxwalk/blob/92b4fe55de0a9c53d0315dcda8ec121faaf20aef/nhgisxwalk/geocrosswalk.py#L19) for full details"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-06-21T01:22:31.822916Z",
     "start_time": "2020-06-21T01:22:31.801539Z"
    }
   },
   "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": "2020-06-21T01:22:31.847713Z",
     "start_time": "2020-06-21T01:22:31.826537Z"
    }
   },
   "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": "2020-06-21T01:22:31.869571Z",
     "start_time": "2020-06-21T01:22:31.849456Z"
    }
   },
   "outputs": [],
   "source": [
    "input_var_tags = [\"pop\", \"fam\", \"hh\", \"hu\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-06-21T01:22:32.182393Z",
     "start_time": "2020-06-21T01:22:31.871777Z"
    }
   },
   "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>trt2010gj</th>\n",
       "      <th>trt2010ge</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>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>1</th>\n",
       "      <td>G10000109044461265042201R1</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>2</th>\n",
       "      <td>G10000109044461265042201U1</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>3</th>\n",
       "      <td>G10000109044461265042201U2</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>G10000109044461480042202R2</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>...</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>1038</th>\n",
       "      <td>G10000509355299999051500R4</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>1039</th>\n",
       "      <td>G10000509355299999051500U1</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>1040</th>\n",
       "      <td>G10000509355299999051500U3</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>1041</th>\n",
       "      <td>G10000509355299999051500U4</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>1042</th>\n",
       "      <td>G34003301061010600020400U2</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",
       "  </tbody>\n",
       "</table>\n",
       "<p>1043 rows × 7 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                       bgp2000gj       trt2010gj    trt2010ge  wt_pop  wt_fam  \\\n",
       "0     G10000109044444430042202U1  G1000010042202  10001042202     1.0     1.0   \n",
       "1     G10000109044461265042201R1  G1000010042201  10001042201     1.0     1.0   \n",
       "2     G10000109044461265042201U1  G1000010042201  10001042201     1.0     1.0   \n",
       "3     G10000109044461265042201U2  G1000010042201  10001042201     1.0     1.0   \n",
       "4     G10000109044461480042202R2  G1000010042202  10001042202     1.0     1.0   \n",
       "...                          ...             ...          ...     ...     ...   \n",
       "1038  G10000509355299999051500R4  G1000050051500  10005051500     1.0     1.0   \n",
       "1039  G10000509355299999051500U1  G1000050051500  10005051500     1.0     1.0   \n",
       "1040  G10000509355299999051500U3  G1000050051500  10005051500     1.0     1.0   \n",
       "1041  G10000509355299999051500U4  G1000050051500  10005051500     1.0     1.0   \n",
       "1042  G34003301061010600020400U2  G1000030990100  10003990100     0.0     0.0   \n",
       "\n",
       "      wt_hh  wt_hu  \n",
       "0       1.0    1.0  \n",
       "1       1.0    1.0  \n",
       "2       1.0    1.0  \n",
       "3       1.0    1.0  \n",
       "4       1.0    1.0  \n",
       "...     ...    ...  \n",
       "1038    1.0    1.0  \n",
       "1039    1.0    1.0  \n",
       "1040    1.0    1.0  \n",
       "1041    1.0    1.0  \n",
       "1042    0.0    0.0  \n",
       "\n",
       "[1043 rows x 7 columns]"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "subset_state = \"10\"\n",
    "bgp2000_to_trt2010 = nhgisxwalk.GeoCrossWalk(\n",
    "    base_xwalk,\n",
    "    source_year=source_year,\n",
    "    target_year=target_year,\n",
    "    source_geo=\"bgp\",\n",
    "    target_geo=\"trt\",\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_trt2010.xwalk"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Write crosswalk to a `.csv`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-06-21T01:22:32.212868Z",
     "start_time": "2020-06-21T01:22:32.184589Z"
    }
   },
   "outputs": [],
   "source": [
    "state_dir = \"../../crosswalks/nhgis_bgp2000_trt2010_state/\"\n",
    "nhgisxwalk.xwalk_df_to_csv(\n",
    "    cls=bgp2000_to_trt2010,\n",
    "    path=state_dir\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Read crosswalk from a `.csv`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-06-21T01:22:32.248147Z",
     "start_time": "2020-06-21T01:22:32.215631Z"
    }
   },
   "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>trt2010gj</th>\n",
       "      <th>trt2010ge</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>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>1</th>\n",
       "      <td>G10000109044461265042201R1</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>2</th>\n",
       "      <td>G10000109044461265042201U1</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>3</th>\n",
       "      <td>G10000109044461265042201U2</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>G10000109044461480042202R2</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>...</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>1038</th>\n",
       "      <td>G10000509355299999051500R4</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>1039</th>\n",
       "      <td>G10000509355299999051500U1</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>1040</th>\n",
       "      <td>G10000509355299999051500U3</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>1041</th>\n",
       "      <td>G10000509355299999051500U4</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>1042</th>\n",
       "      <td>G34003301061010600020400U2</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",
       "  </tbody>\n",
       "</table>\n",
       "<p>1043 rows × 7 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                       bgp2000gj       trt2010gj    trt2010ge  wt_pop  wt_fam  \\\n",
       "0     G10000109044444430042202U1  G1000010042202  10001042202     1.0     1.0   \n",
       "1     G10000109044461265042201R1  G1000010042201  10001042201     1.0     1.0   \n",
       "2     G10000109044461265042201U1  G1000010042201  10001042201     1.0     1.0   \n",
       "3     G10000109044461265042201U2  G1000010042201  10001042201     1.0     1.0   \n",
       "4     G10000109044461480042202R2  G1000010042202  10001042202     1.0     1.0   \n",
       "...                          ...             ...          ...     ...     ...   \n",
       "1038  G10000509355299999051500R4  G1000050051500  10005051500     1.0     1.0   \n",
       "1039  G10000509355299999051500U1  G1000050051500  10005051500     1.0     1.0   \n",
       "1040  G10000509355299999051500U3  G1000050051500  10005051500     1.0     1.0   \n",
       "1041  G10000509355299999051500U4  G1000050051500  10005051500     1.0     1.0   \n",
       "1042  G34003301061010600020400U2  G1000030990100  10003990100     0.0     0.0   \n",
       "\n",
       "      wt_hh  wt_hu  \n",
       "0       1.0    1.0  \n",
       "1       1.0    1.0  \n",
       "2       1.0    1.0  \n",
       "3       1.0    1.0  \n",
       "4       1.0    1.0  \n",
       "...     ...    ...  \n",
       "1038    1.0    1.0  \n",
       "1039    1.0    1.0  \n",
       "1040    1.0    1.0  \n",
       "1041    1.0    1.0  \n",
       "1042    0.0    0.0  \n",
       "\n",
       "[1043 rows x 7 columns]"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fname = state_dir + bgp2000_to_trt2010.xwalk_name\n",
    "bgp2000_to_trt2010_df = nhgisxwalk.xwalk_df_from_csv(fname)\n",
    "bgp2000_to_trt2010_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
}