{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "\n",
    "import synthpop.zone_synthesizer as zs"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Specify sample data csv paths. See the files listed here for expected structure. Marginal tables require multi-indexed columns with category name and category value in levels 0 and 1 of the index. Sample file category columns should be labeled with corresponding category names and values in those columns should match the category value headers in the marginal table."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "hh_marginal_file = 'input_data/hh_marginals.csv'\n",
    "person_marginal_file = 'input_data/person_marginals.csv'\n",
    "hh_sample_file = 'input_data/household_sample.csv'\n",
    "person_sample_file = 'input_data/person_sample.csv'"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Load and process input marginals and samples and geography crosswalk"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "hh_marg, p_marg, hh_sample, p_sample, xwalk = zs.load_data(hh_marginal_file, person_marginal_file, hh_sample_file, person_sample_file)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th>cat_name</th>\n",
       "      <th colspan=\"3\" halign=\"left\">cars</th>\n",
       "      <th colspan=\"2\" halign=\"left\">children</th>\n",
       "      <th colspan=\"3\" halign=\"left\">income</th>\n",
       "      <th colspan=\"3\" halign=\"left\">workers</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>cat_values</th>\n",
       "      <th>none</th>\n",
       "      <th>one</th>\n",
       "      <th>two or more</th>\n",
       "      <th>no</th>\n",
       "      <th>yes</th>\n",
       "      <th>gt100</th>\n",
       "      <th>gt35-lt100</th>\n",
       "      <th>lt35</th>\n",
       "      <th>none</th>\n",
       "      <th>one</th>\n",
       "      <th>two or more</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>7</td>\n",
       "      <td>49</td>\n",
       "      <td>197</td>\n",
       "      <td>41</td>\n",
       "      <td>215</td>\n",
       "      <td>57</td>\n",
       "      <td>125</td>\n",
       "      <td>74</td>\n",
       "      <td>72</td>\n",
       "      <td>77</td>\n",
       "      <td>105</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>9</td>\n",
       "      <td>59</td>\n",
       "      <td>237</td>\n",
       "      <td>68</td>\n",
       "      <td>239</td>\n",
       "      <td>83</td>\n",
       "      <td>126</td>\n",
       "      <td>98</td>\n",
       "      <td>87</td>\n",
       "      <td>93</td>\n",
       "      <td>125</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>10</td>\n",
       "      <td>69</td>\n",
       "      <td>275</td>\n",
       "      <td>79</td>\n",
       "      <td>279</td>\n",
       "      <td>74</td>\n",
       "      <td>170</td>\n",
       "      <td>114</td>\n",
       "      <td>102</td>\n",
       "      <td>108</td>\n",
       "      <td>146</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>11</td>\n",
       "      <td>76</td>\n",
       "      <td>302</td>\n",
       "      <td>167</td>\n",
       "      <td>224</td>\n",
       "      <td>42</td>\n",
       "      <td>105</td>\n",
       "      <td>244</td>\n",
       "      <td>111</td>\n",
       "      <td>118</td>\n",
       "      <td>160</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>18</td>\n",
       "      <td>117</td>\n",
       "      <td>466</td>\n",
       "      <td>86</td>\n",
       "      <td>517</td>\n",
       "      <td>50</td>\n",
       "      <td>261</td>\n",
       "      <td>292</td>\n",
       "      <td>171</td>\n",
       "      <td>182</td>\n",
       "      <td>247</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "cat_name   cars                  children      income                 workers  \\\n",
       "cat_values none  one two or more       no  yes  gt100 gt35-lt100 lt35    none   \n",
       "1             7   49         197       41  215     57        125   74      72   \n",
       "2             9   59         237       68  239     83        126   98      87   \n",
       "3            10   69         275       79  279     74        170  114     102   \n",
       "4            11   76         302      167  224     42        105  244     111   \n",
       "5            18  117         466       86  517     50        261  292     171   \n",
       "\n",
       "cat_name                     \n",
       "cat_values  one two or more  \n",
       "1            77         105  \n",
       "2            93         125  \n",
       "3           108         146  \n",
       "4           118         160  \n",
       "5           182         247  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "hh_marg.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th>cat_name</th>\n",
       "      <th colspan=\"4\" halign=\"left\">age</th>\n",
       "      <th colspan=\"4\" halign=\"left\">race</th>\n",
       "      <th colspan=\"2\" halign=\"left\">sex</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>cat_values</th>\n",
       "      <th>19 and under</th>\n",
       "      <th>20 to 35</th>\n",
       "      <th>35 to 60</th>\n",
       "      <th>above 60</th>\n",
       "      <th>asian</th>\n",
       "      <th>black</th>\n",
       "      <th>other</th>\n",
       "      <th>white</th>\n",
       "      <th>female</th>\n",
       "      <th>male</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>312</td>\n",
       "      <td>108</td>\n",
       "      <td>223</td>\n",
       "      <td>177</td>\n",
       "      <td>64</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>756</td>\n",
       "      <td>440</td>\n",
       "      <td>380</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>235</td>\n",
       "      <td>143</td>\n",
       "      <td>296</td>\n",
       "      <td>181</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>855</td>\n",
       "      <td>452</td>\n",
       "      <td>403</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>303</td>\n",
       "      <td>229</td>\n",
       "      <td>445</td>\n",
       "      <td>174</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>24</td>\n",
       "      <td>1127</td>\n",
       "      <td>565</td>\n",
       "      <td>586</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>215</td>\n",
       "      <td>77</td>\n",
       "      <td>356</td>\n",
       "      <td>189</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>29</td>\n",
       "      <td>808</td>\n",
       "      <td>389</td>\n",
       "      <td>448</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>506</td>\n",
       "      <td>539</td>\n",
       "      <td>619</td>\n",
       "      <td>262</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1926</td>\n",
       "      <td>981</td>\n",
       "      <td>945</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "cat_name            age                             race                    \\\n",
       "cat_values 19 and under 20 to 35 35 to 60 above 60 asian black other white   \n",
       "1                   312      108      223      177    64     0     0   756   \n",
       "2                   235      143      296      181     0     0     0   855   \n",
       "3                   303      229      445      174     0     0    24  1127   \n",
       "4                   215       77      356      189     0     0    29   808   \n",
       "5                   506      539      619      262     0     0     0  1926   \n",
       "\n",
       "cat_name      sex       \n",
       "cat_values female male  \n",
       "1             440  380  \n",
       "2             452  403  \n",
       "3             565  586  \n",
       "4             389  448  \n",
       "5             981  945  "
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "p_marg.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>serialno</th>\n",
       "      <th>sample_geog</th>\n",
       "      <th>age</th>\n",
       "      <th>race</th>\n",
       "      <th>sex</th>\n",
       "      <th>AGEP</th>\n",
       "      <th>SEX</th>\n",
       "      <th>RAC1P</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2012000005576</td>\n",
       "      <td>1</td>\n",
       "      <td>20 to 35</td>\n",
       "      <td>white</td>\n",
       "      <td>male</td>\n",
       "      <td>27</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2012000017760</td>\n",
       "      <td>1</td>\n",
       "      <td>20 to 35</td>\n",
       "      <td>white</td>\n",
       "      <td>male</td>\n",
       "      <td>34</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2012000021787</td>\n",
       "      <td>1</td>\n",
       "      <td>20 to 35</td>\n",
       "      <td>white</td>\n",
       "      <td>male</td>\n",
       "      <td>32</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2012000021815</td>\n",
       "      <td>1</td>\n",
       "      <td>20 to 35</td>\n",
       "      <td>white</td>\n",
       "      <td>male</td>\n",
       "      <td>23</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2012000065237</td>\n",
       "      <td>1</td>\n",
       "      <td>20 to 35</td>\n",
       "      <td>white</td>\n",
       "      <td>male</td>\n",
       "      <td>24</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        serialno  sample_geog       age   race   sex  AGEP  SEX  RAC1P\n",
       "0  2012000005576            1  20 to 35  white  male    27    1      1\n",
       "1  2012000017760            1  20 to 35  white  male    34    1      1\n",
       "2  2012000021787            1  20 to 35  white  male    32    1      1\n",
       "3  2012000021815            1  20 to 35  white  male    23    1      1\n",
       "4  2012000065237            1  20 to 35  white  male    24    1      1"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "p_sample.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Iterate over all marginals in the geography crosswalk and synthesize in-line"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\users\\juan\\documents\\github\\synthpop\\synthpop\\ipu\\ipu.py:190: RuntimeWarning: divide by zero encountered in double_scalars\n",
      "  adj = constraint / (column * weights).sum()\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Drawing 254 households\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\users\\juan\\documents\\github\\synthpop\\synthpop\\ipu\\ipu.py:190: RuntimeWarning: divide by zero encountered in double_scalars\n",
      "  adj = constraint / (column * weights).sum()\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Drawing 306 households\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\users\\juan\\documents\\github\\synthpop\\synthpop\\ipu\\ipu.py:190: RuntimeWarning: divide by zero encountered in double_scalars\n",
      "  adj = constraint / (column * weights).sum()\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Drawing 356 households\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\users\\juan\\documents\\github\\synthpop\\synthpop\\ipu\\ipu.py:190: RuntimeWarning: divide by zero encountered in double_scalars\n",
      "  adj = constraint / (column * weights).sum()\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Drawing 390 households\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\users\\juan\\documents\\github\\synthpop\\synthpop\\ipu\\ipu.py:190: RuntimeWarning: divide by zero encountered in double_scalars\n",
      "  adj = constraint / (column * weights).sum()\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Drawing 601 households\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\users\\juan\\documents\\github\\synthpop\\synthpop\\ipu\\ipu.py:190: RuntimeWarning: divide by zero encountered in double_scalars\n",
      "  adj = constraint / (column * weights).sum()\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Drawing 324 households\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\users\\juan\\documents\\github\\synthpop\\synthpop\\ipu\\ipu.py:190: RuntimeWarning: divide by zero encountered in double_scalars\n",
      "  adj = constraint / (column * weights).sum()\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Drawing 556 households\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\users\\juan\\documents\\github\\synthpop\\synthpop\\ipu\\ipu.py:190: RuntimeWarning: divide by zero encountered in double_scalars\n",
      "  adj = constraint / (column * weights).sum()\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Drawing 342 households\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\users\\juan\\documents\\github\\synthpop\\synthpop\\ipu\\ipu.py:190: RuntimeWarning: divide by zero encountered in double_scalars\n",
      "  adj = constraint / (column * weights).sum()\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Drawing 273 households\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\users\\juan\\documents\\github\\synthpop\\synthpop\\ipu\\ipu.py:190: RuntimeWarning: divide by zero encountered in double_scalars\n",
      "  adj = constraint / (column * weights).sum()\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Drawing 228 households\n",
      "Drawing 857 households\n",
      "Drawing 748 households\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\users\\juan\\documents\\github\\synthpop\\synthpop\\ipu\\ipu.py:190: RuntimeWarning: divide by zero encountered in double_scalars\n",
      "  adj = constraint / (column * weights).sum()\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Drawing 744 households\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\users\\juan\\documents\\github\\synthpop\\synthpop\\ipu\\ipu.py:190: RuntimeWarning: divide by zero encountered in double_scalars\n",
      "  adj = constraint / (column * weights).sum()\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Drawing 953 households\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\users\\juan\\documents\\github\\synthpop\\synthpop\\ipu\\ipu.py:190: RuntimeWarning: divide by zero encountered in double_scalars\n",
      "  adj = constraint / (column * weights).sum()\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Drawing 719 households\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\users\\juan\\documents\\github\\synthpop\\synthpop\\ipu\\ipu.py:190: RuntimeWarning: divide by zero encountered in double_scalars\n",
      "  adj = constraint / (column * weights).sum()\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Drawing 185 households\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\users\\juan\\documents\\github\\synthpop\\synthpop\\ipu\\ipu.py:190: RuntimeWarning: divide by zero encountered in double_scalars\n",
      "  adj = constraint / (column * weights).sum()\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Drawing 183 households\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\users\\juan\\documents\\github\\synthpop\\synthpop\\ipu\\ipu.py:190: RuntimeWarning: divide by zero encountered in double_scalars\n",
      "  adj = constraint / (column * weights).sum()\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Drawing 286 households\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\users\\juan\\documents\\github\\synthpop\\synthpop\\ipu\\ipu.py:190: RuntimeWarning: divide by zero encountered in double_scalars\n",
      "  adj = constraint / (column * weights).sum()\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Drawing 317 households\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\users\\juan\\documents\\github\\synthpop\\synthpop\\ipu\\ipu.py:190: RuntimeWarning: divide by zero encountered in double_scalars\n",
      "  adj = constraint / (column * weights).sum()\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Drawing 711 households\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\users\\juan\\documents\\github\\synthpop\\synthpop\\ipu\\ipu.py:190: RuntimeWarning: divide by zero encountered in double_scalars\n",
      "  adj = constraint / (column * weights).sum()\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Drawing 345 households\n"
     ]
    }
   ],
   "source": [
    "all_households, all_persons, all_stats = zs.synthesize_all_zones(hh_marg, p_marg, hh_sample, p_sample, xwalk)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>serialno</th>\n",
       "      <th>sample_geog</th>\n",
       "      <th>cars</th>\n",
       "      <th>workers</th>\n",
       "      <th>children</th>\n",
       "      <th>income</th>\n",
       "      <th>VEH</th>\n",
       "      <th>FINCP</th>\n",
       "      <th>NOC</th>\n",
       "      <th>WIF</th>\n",
       "      <th>cat_id</th>\n",
       "      <th>geog</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>household_id</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2010001229265</td>\n",
       "      <td>1</td>\n",
       "      <td>none</td>\n",
       "      <td>none</td>\n",
       "      <td>no</td>\n",
       "      <td>lt35</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2010000262947</td>\n",
       "      <td>1</td>\n",
       "      <td>none</td>\n",
       "      <td>none</td>\n",
       "      <td>yes</td>\n",
       "      <td>lt35</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>15</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2010000141368</td>\n",
       "      <td>1</td>\n",
       "      <td>none</td>\n",
       "      <td>none</td>\n",
       "      <td>yes</td>\n",
       "      <td>lt35</td>\n",
       "      <td>0</td>\n",
       "      <td>3500.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>15</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2012000162541</td>\n",
       "      <td>1</td>\n",
       "      <td>none</td>\n",
       "      <td>none</td>\n",
       "      <td>yes</td>\n",
       "      <td>lt35</td>\n",
       "      <td>0</td>\n",
       "      <td>18300.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0.0</td>\n",
       "      <td>15</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>2012001476110</td>\n",
       "      <td>1</td>\n",
       "      <td>none</td>\n",
       "      <td>none</td>\n",
       "      <td>yes</td>\n",
       "      <td>lt35</td>\n",
       "      <td>0</td>\n",
       "      <td>3100.0</td>\n",
       "      <td>3</td>\n",
       "      <td>0.0</td>\n",
       "      <td>15</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                   serialno  sample_geog  cars workers children income  VEH  \\\n",
       "household_id                                                                  \n",
       "1             2010001229265            1  none    none       no   lt35    0   \n",
       "2             2010000262947            1  none    none      yes   lt35    0   \n",
       "3             2010000141368            1  none    none      yes   lt35    0   \n",
       "4             2012000162541            1  none    none      yes   lt35    0   \n",
       "5             2012001476110            1  none    none      yes   lt35    0   \n",
       "\n",
       "                FINCP  NOC  WIF  cat_id  geog  \n",
       "household_id                                   \n",
       "1                 NaN    0  NaN       6     1  \n",
       "2                 0.0    1  0.0      15     1  \n",
       "3              3500.0    1  0.0      15     1  \n",
       "4             18300.0    2  0.0      15     1  \n",
       "5              3100.0    3  0.0      15     1  "
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "all_households.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### all_persons.household_id maps person records to all_households.index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>serialno</th>\n",
       "      <th>sample_geog</th>\n",
       "      <th>age</th>\n",
       "      <th>race</th>\n",
       "      <th>sex</th>\n",
       "      <th>AGEP</th>\n",
       "      <th>SEX</th>\n",
       "      <th>RAC1P</th>\n",
       "      <th>cat_id</th>\n",
       "      <th>geog</th>\n",
       "      <th>household_id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2012000136005</td>\n",
       "      <td>1</td>\n",
       "      <td>20 to 35</td>\n",
       "      <td>white</td>\n",
       "      <td>male</td>\n",
       "      <td>31</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>69</td>\n",
       "      <td>1</td>\n",
       "      <td>85</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2012000136005</td>\n",
       "      <td>1</td>\n",
       "      <td>35 to 60</td>\n",
       "      <td>white</td>\n",
       "      <td>female</td>\n",
       "      <td>36</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>76</td>\n",
       "      <td>1</td>\n",
       "      <td>85</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2012000136005</td>\n",
       "      <td>1</td>\n",
       "      <td>19 and under</td>\n",
       "      <td>white</td>\n",
       "      <td>male</td>\n",
       "      <td>10</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>61</td>\n",
       "      <td>1</td>\n",
       "      <td>85</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2012000136005</td>\n",
       "      <td>1</td>\n",
       "      <td>19 and under</td>\n",
       "      <td>white</td>\n",
       "      <td>male</td>\n",
       "      <td>8</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>61</td>\n",
       "      <td>1</td>\n",
       "      <td>85</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2012000136005</td>\n",
       "      <td>1</td>\n",
       "      <td>19 and under</td>\n",
       "      <td>white</td>\n",
       "      <td>male</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>61</td>\n",
       "      <td>1</td>\n",
       "      <td>85</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        serialno  sample_geog           age   race     sex  AGEP  SEX  RAC1P  \\\n",
       "0  2012000136005            1      20 to 35  white    male    31    1      1   \n",
       "1  2012000136005            1      35 to 60  white  female    36    2      1   \n",
       "2  2012000136005            1  19 and under  white    male    10    1      1   \n",
       "3  2012000136005            1  19 and under  white    male     8    1      1   \n",
       "4  2012000136005            1  19 and under  white    male     5    1      1   \n",
       "\n",
       "   cat_id  geog  household_id  \n",
       "0      69     1            85  \n",
       "1      76     1            85  \n",
       "2      61     1            85  \n",
       "3      61     1            85  \n",
       "4      61     1            85  "
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "all_persons.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Synthesize all marginal geographies in the crosswalk using a specified or default number of cores via multiprocessing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "all_persons, all_households, all_stats = zs.multiprocess_synthesize(hh_marg, p_marg, hh_sample, p_sample, xwalk)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>serialno</th>\n",
       "      <th>sample_geog</th>\n",
       "      <th>age</th>\n",
       "      <th>race</th>\n",
       "      <th>sex</th>\n",
       "      <th>AGEP</th>\n",
       "      <th>SEX</th>\n",
       "      <th>RAC1P</th>\n",
       "      <th>cat_id</th>\n",
       "      <th>geog</th>\n",
       "      <th>household_id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2012000136005</td>\n",
       "      <td>1</td>\n",
       "      <td>20 to 35</td>\n",
       "      <td>white</td>\n",
       "      <td>male</td>\n",
       "      <td>31</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>69</td>\n",
       "      <td>1</td>\n",
       "      <td>81</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2012000136005</td>\n",
       "      <td>1</td>\n",
       "      <td>35 to 60</td>\n",
       "      <td>white</td>\n",
       "      <td>female</td>\n",
       "      <td>36</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>76</td>\n",
       "      <td>1</td>\n",
       "      <td>81</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2012000136005</td>\n",
       "      <td>1</td>\n",
       "      <td>19 and under</td>\n",
       "      <td>white</td>\n",
       "      <td>male</td>\n",
       "      <td>10</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>61</td>\n",
       "      <td>1</td>\n",
       "      <td>81</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2012000136005</td>\n",
       "      <td>1</td>\n",
       "      <td>19 and under</td>\n",
       "      <td>white</td>\n",
       "      <td>male</td>\n",
       "      <td>8</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>61</td>\n",
       "      <td>1</td>\n",
       "      <td>81</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2012000136005</td>\n",
       "      <td>1</td>\n",
       "      <td>19 and under</td>\n",
       "      <td>white</td>\n",
       "      <td>male</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>61</td>\n",
       "      <td>1</td>\n",
       "      <td>81</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        serialno  sample_geog           age   race     sex  AGEP  SEX  RAC1P  \\\n",
       "0  2012000136005            1      20 to 35  white    male    31    1      1   \n",
       "1  2012000136005            1      35 to 60  white  female    36    2      1   \n",
       "2  2012000136005            1  19 and under  white    male    10    1      1   \n",
       "3  2012000136005            1  19 and under  white    male     8    1      1   \n",
       "4  2012000136005            1  19 and under  white    male     5    1      1   \n",
       "\n",
       "   cat_id  geog  household_id  \n",
       "0      69     1            81  \n",
       "1      76     1            81  \n",
       "2      61     1            81  \n",
       "3      61     1            81  \n",
       "4      61     1            81  "
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "all_persons.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>serialno</th>\n",
       "      <th>sample_geog</th>\n",
       "      <th>cars</th>\n",
       "      <th>workers</th>\n",
       "      <th>children</th>\n",
       "      <th>income</th>\n",
       "      <th>VEH</th>\n",
       "      <th>FINCP</th>\n",
       "      <th>NOC</th>\n",
       "      <th>WIF</th>\n",
       "      <th>cat_id</th>\n",
       "      <th>geog</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>household_id</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2009000465330</td>\n",
       "      <td>1</td>\n",
       "      <td>none</td>\n",
       "      <td>none</td>\n",
       "      <td>no</td>\n",
       "      <td>lt35</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2009000455972</td>\n",
       "      <td>1</td>\n",
       "      <td>none</td>\n",
       "      <td>none</td>\n",
       "      <td>yes</td>\n",
       "      <td>lt35</td>\n",
       "      <td>0</td>\n",
       "      <td>3500.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0.0</td>\n",
       "      <td>15</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2012001476110</td>\n",
       "      <td>1</td>\n",
       "      <td>none</td>\n",
       "      <td>none</td>\n",
       "      <td>yes</td>\n",
       "      <td>lt35</td>\n",
       "      <td>0</td>\n",
       "      <td>3100.0</td>\n",
       "      <td>3</td>\n",
       "      <td>0.0</td>\n",
       "      <td>15</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2012001476110</td>\n",
       "      <td>1</td>\n",
       "      <td>none</td>\n",
       "      <td>none</td>\n",
       "      <td>yes</td>\n",
       "      <td>lt35</td>\n",
       "      <td>0</td>\n",
       "      <td>3100.0</td>\n",
       "      <td>3</td>\n",
       "      <td>0.0</td>\n",
       "      <td>15</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>2010000141368</td>\n",
       "      <td>1</td>\n",
       "      <td>none</td>\n",
       "      <td>none</td>\n",
       "      <td>yes</td>\n",
       "      <td>lt35</td>\n",
       "      <td>0</td>\n",
       "      <td>3500.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>15</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                   serialno  sample_geog  cars workers children income  VEH  \\\n",
       "household_id                                                                  \n",
       "1             2009000465330            1  none    none       no   lt35    0   \n",
       "2             2009000455972            1  none    none      yes   lt35    0   \n",
       "3             2012001476110            1  none    none      yes   lt35    0   \n",
       "4             2012001476110            1  none    none      yes   lt35    0   \n",
       "5             2010000141368            1  none    none      yes   lt35    0   \n",
       "\n",
       "               FINCP  NOC  WIF  cat_id  geog  \n",
       "household_id                                  \n",
       "1                NaN    0  NaN       6     1  \n",
       "2             3500.0    2  0.0      15     1  \n",
       "3             3100.0    3  0.0      15     1  \n",
       "4             3100.0    3  0.0      15     1  \n",
       "5             3500.0    1  0.0      15     1  "
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "all_households.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>chi-square</th>\n",
       "      <th>geog</th>\n",
       "      <th>p-score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2.070855</td>\n",
       "      <td>1</td>\n",
       "      <td>9.998970e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>154.420913</td>\n",
       "      <td>2</td>\n",
       "      <td>4.782383e-30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>182.585670</td>\n",
       "      <td>3</td>\n",
       "      <td>5.033580e-32</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>96.436446</td>\n",
       "      <td>4</td>\n",
       "      <td>2.276937e-14</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>468.714250</td>\n",
       "      <td>5</td>\n",
       "      <td>4.243758e-97</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>5.642968</td>\n",
       "      <td>6</td>\n",
       "      <td>9.581878e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>516.866875</td>\n",
       "      <td>7</td>\n",
       "      <td>2.458698e-101</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>79.638305</td>\n",
       "      <td>8</td>\n",
       "      <td>1.632443e-14</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>117.238663</td>\n",
       "      <td>9</td>\n",
       "      <td>1.836683e-20</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>2000.143804</td>\n",
       "      <td>10</td>\n",
       "      <td>0.000000e+00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>642.117025</td>\n",
       "      <td>11</td>\n",
       "      <td>2.372825e-117</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>62.442878</td>\n",
       "      <td>12</td>\n",
       "      <td>4.130503e-07</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>1174.759712</td>\n",
       "      <td>13</td>\n",
       "      <td>8.130438e-234</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>670.414502</td>\n",
       "      <td>14</td>\n",
       "      <td>2.542384e-132</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>1081.225334</td>\n",
       "      <td>15</td>\n",
       "      <td>4.449635e-220</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>12.940226</td>\n",
       "      <td>16</td>\n",
       "      <td>7.357824e-02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>1.161109</td>\n",
       "      <td>17</td>\n",
       "      <td>9.917950e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>159.879713</td>\n",
       "      <td>18</td>\n",
       "      <td>2.084872e-27</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>0.507767</td>\n",
       "      <td>19</td>\n",
       "      <td>9.994175e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>116.945628</td>\n",
       "      <td>20</td>\n",
       "      <td>7.393055e-18</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>14.386659</td>\n",
       "      <td>21</td>\n",
       "      <td>4.471640e-02</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     chi-square  geog        p-score\n",
       "0      2.070855     1   9.998970e-01\n",
       "1    154.420913     2   4.782383e-30\n",
       "2    182.585670     3   5.033580e-32\n",
       "3     96.436446     4   2.276937e-14\n",
       "4    468.714250     5   4.243758e-97\n",
       "5      5.642968     6   9.581878e-01\n",
       "6    516.866875     7  2.458698e-101\n",
       "7     79.638305     8   1.632443e-14\n",
       "8    117.238663     9   1.836683e-20\n",
       "9   2000.143804    10   0.000000e+00\n",
       "10   642.117025    11  2.372825e-117\n",
       "11    62.442878    12   4.130503e-07\n",
       "12  1174.759712    13  8.130438e-234\n",
       "13   670.414502    14  2.542384e-132\n",
       "14  1081.225334    15  4.449635e-220\n",
       "15    12.940226    16   7.357824e-02\n",
       "16     1.161109    17   9.917950e-01\n",
       "17   159.879713    18   2.084872e-27\n",
       "18     0.507767    19   9.994175e-01\n",
       "19   116.945628    20   7.393055e-18\n",
       "20    14.386659    21   4.471640e-02"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "all_stats"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}