{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Index: 30 entries, Ainu to Yimas\n",
      "Data columns (total 11 columns):\n",
      " #   Column      Non-Null Count  Dtype  \n",
      "---  ------      --------------  -----  \n",
      " 0   Family      30 non-null     object \n",
      " 1   LID         29 non-null     float64\n",
      " 2   LOID        30 non-null     int64  \n",
      " 3   Continent   30 non-null     object \n",
      " 4   Area        30 non-null     object \n",
      " 5   Analysis    29 non-null     object \n",
      " 6   Forms       30 non-null     object \n",
      " 7   Elim        1 non-null      object \n",
      " 8   Status      30 non-null     object \n",
      " 9   Comments    8 non-null      object \n",
      " 10  Impression  22 non-null     object \n",
      "dtypes: float64(1), int64(1), object(9)\n",
      "memory usage: 2.8+ KB\n"
     ]
    }
   ],
   "source": [
    "%matplotlib inline\n",
    "\n",
    "import pathlib\n",
    "\n",
    "import matplotlib.pyplot as plt\n",
    "from mpl_toolkits.basemap import Basemap\n",
    "import pandas as pd\n",
    "\n",
    "SAMPLE = 'http://proalki.uni-leipzig.de/wiki/Project:Portmanteau_Analyses'\n",
    "\n",
    "SAMPLE_CSV = pathlib.Path('portmanteau_sample.csv')\n",
    "\n",
    "ENCODING = 'utf-8'\n",
    "\n",
    "RENAME = {'Quechua (Ayacucho)': 'Ayacucho',\n",
    "          'Tepehuan': 'Tepehua',\n",
    "          'Lakhota': 'Lakota'}\n",
    "\n",
    "if not SAMPLE_CSV.exists():\n",
    "    _sf, = pd.read_html(SAMPLE, header=0, index_col='Language')\n",
    "    _sf.to_csv(SAMPLE_CSV, encoding=ENCODING)\n",
    "\n",
    "sf = (pd.read_csv(SAMPLE_CSV, encoding=ENCODING)\n",
    "      .assign(Language=lambda x: x['Language'].replace(RENAME))\n",
    "      .rename(columns={'Languoid': 'Family'})\n",
    "      .set_index('Language'))\n",
    "\n",
    "sf.info()\n",
    "assert sf.index.is_unique"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "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>Family</th>\n",
       "      <th>LID</th>\n",
       "      <th>Continent</th>\n",
       "      <th>Area</th>\n",
       "      <th>Analysis</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Language</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>Ainu</th>\n",
       "      <td>Ainu</td>\n",
       "      <td>12</td>\n",
       "      <td>N-C Asia</td>\n",
       "      <td>N Coast Asia</td>\n",
       "      <td>Ain/Paradigms/to X</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Aleut</th>\n",
       "      <td>Aleut</td>\n",
       "      <td>18</td>\n",
       "      <td>N-C Asia</td>\n",
       "      <td>N Coast Asia</td>\n",
       "      <td>Ale/Paradigms/to X</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Bella Coola</th>\n",
       "      <td>Bella Coola</td>\n",
       "      <td>995</td>\n",
       "      <td>W N America</td>\n",
       "      <td>Alaska-Oregon</td>\n",
       "      <td>Blc/Paradigms/to X</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Chuckchi</th>\n",
       "      <td>Chukotkan</td>\n",
       "      <td>56</td>\n",
       "      <td>N-C Asia</td>\n",
       "      <td>N Coast Asia</td>\n",
       "      <td>Ckt/Paradigms/to X</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Darai</th>\n",
       "      <td>Indo-Iranian</td>\n",
       "      <td>1399</td>\n",
       "      <td>S/SE Asia</td>\n",
       "      <td>Indic</td>\n",
       "      <td>Dry/Paradigms/to all/Npst</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                   Family   LID    Continent           Area  \\\n",
       "Language                                                      \n",
       "Ainu                 Ainu    12     N-C Asia   N Coast Asia   \n",
       "Aleut               Aleut    18     N-C Asia   N Coast Asia   \n",
       "Bella Coola   Bella Coola   995  W N America  Alaska-Oregon   \n",
       "Chuckchi        Chukotkan    56     N-C Asia   N Coast Asia   \n",
       "Darai        Indo-Iranian  1399    S/SE Asia          Indic   \n",
       "\n",
       "                              Analysis  \n",
       "Language                                \n",
       "Ainu                Ain/Paradigms/to X  \n",
       "Aleut               Ale/Paradigms/to X  \n",
       "Bella Coola         Blc/Paradigms/to X  \n",
       "Chuckchi            Ckt/Paradigms/to X  \n",
       "Darai        Dry/Paradigms/to all/Npst  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = sf.loc[sf['Status'] == 'ready', :'Analysis'].drop('LOID', axis=1)\n",
    "\n",
    "df['LID'] = pd.to_numeric(df['LID'].fillna(0), downcast='integer')\n",
    "\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Index: 2913 entries, 199 to 3213\n",
      "Data columns (total 15 columns):\n",
      " #   Column             Non-Null Count  Dtype  \n",
      "---  ------             --------------  -----  \n",
      " 0   ISO639.3           2846 non-null   object \n",
      " 1   language           2913 non-null   object \n",
      " 2   alt.language.name  2873 non-null   object \n",
      " 3   language.search    2913 non-null   object \n",
      " 4   lsbranch           301 non-null    object \n",
      " 5   ssbranch           529 non-null    object \n",
      " 6   sbranch            1322 non-null   object \n",
      " 7   mbranch            2070 non-null   object \n",
      " 8   stock              2913 non-null   object \n",
      " 9   alt.stock.name     366 non-null    object \n",
      " 10  stock.search       2913 non-null   object \n",
      " 11  longitude          2913 non-null   float64\n",
      " 12  latitude           2913 non-null   float64\n",
      " 13  area               2913 non-null   object \n",
      " 14  continent          2913 non-null   object \n",
      "dtypes: float64(2), object(13)\n",
      "memory usage: 364.1+ KB\n"
     ]
    },
    {
     "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>ISO639.3</th>\n",
       "      <th>language</th>\n",
       "      <th>alt.language.name</th>\n",
       "      <th>language.search</th>\n",
       "      <th>lsbranch</th>\n",
       "      <th>ssbranch</th>\n",
       "      <th>sbranch</th>\n",
       "      <th>mbranch</th>\n",
       "      <th>stock</th>\n",
       "      <th>alt.stock.name</th>\n",
       "      <th>stock.search</th>\n",
       "      <th>longitude</th>\n",
       "      <th>latitude</th>\n",
       "      <th>area</th>\n",
       "      <th>continent</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>LID</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",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>199</th>\n",
       "      <td>naq</td>\n",
       "      <td>Nama</td>\n",
       "      <td>Nama, Khoekhoe</td>\n",
       "      <td>Nama, Nama, Khoekhoe</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Khoekhoe</td>\n",
       "      <td>Kwadi-Khoe</td>\n",
       "      <td>Central Khoisan</td>\n",
       "      <td>Kwadi-Khoe, Central Khoisan</td>\n",
       "      <td>18.00</td>\n",
       "      <td>-25.50</td>\n",
       "      <td>S Africa</td>\n",
       "      <td>Africa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>148</th>\n",
       "      <td>knw</td>\n",
       "      <td>!Kung</td>\n",
       "      <td>!Xu, !Kung, \\t!Hu, !Khung, !Ku, !Kung, !Xu, !X...</td>\n",
       "      <td>!Kung, !Xu, !Kung, \\t!Hu, !Khung, !Ku, !Kung, ...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Ju</td>\n",
       "      <td>Northern Khoisan</td>\n",
       "      <td>Ju, Northern Khoisan</td>\n",
       "      <td>18.00</td>\n",
       "      <td>-19.67</td>\n",
       "      <td>S Africa</td>\n",
       "      <td>Africa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>94</th>\n",
       "      <td>hts</td>\n",
       "      <td>Hadza</td>\n",
       "      <td>Hadza</td>\n",
       "      <td>Hadza, Hadza</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Hadza</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Hadza</td>\n",
       "      <td>35.17</td>\n",
       "      <td>-3.75</td>\n",
       "      <td>S Africa</td>\n",
       "      <td>Africa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>347</th>\n",
       "      <td>sad</td>\n",
       "      <td>Sandawe</td>\n",
       "      <td>Sandawe</td>\n",
       "      <td>Sandawe, Sandawe</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Sandawe</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Sandawe</td>\n",
       "      <td>35.00</td>\n",
       "      <td>-5.00</td>\n",
       "      <td>S Africa</td>\n",
       "      <td>Africa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>151</th>\n",
       "      <td>kwz</td>\n",
       "      <td>Kwadi</td>\n",
       "      <td>Kwadi, Cuepe, Curoca</td>\n",
       "      <td>Kwadi, Kwadi, Cuepe, Curoca</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Kwadi</td>\n",
       "      <td>Kwadi-Khoe</td>\n",
       "      <td>Central Khoisan</td>\n",
       "      <td>Kwadi-Khoe, Central Khoisan</td>\n",
       "      <td>12.00</td>\n",
       "      <td>-16.00</td>\n",
       "      <td>S Africa</td>\n",
       "      <td>Africa</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    ISO639.3 language                                  alt.language.name  \\\n",
       "LID                                                                        \n",
       "199      naq     Nama                                     Nama, Khoekhoe   \n",
       "148      knw    !Kung  !Xu, !Kung, \\t!Hu, !Khung, !Ku, !Kung, !Xu, !X...   \n",
       "94       hts    Hadza                                              Hadza   \n",
       "347      sad  Sandawe                                            Sandawe   \n",
       "151      kwz    Kwadi                               Kwadi, Cuepe, Curoca   \n",
       "\n",
       "                                       language.search lsbranch ssbranch  \\\n",
       "LID                                                                        \n",
       "199                               Nama, Nama, Khoekhoe      NaN      NaN   \n",
       "148  !Kung, !Xu, !Kung, \\t!Hu, !Khung, !Ku, !Kung, ...      NaN      NaN   \n",
       "94                                        Hadza, Hadza      NaN      NaN   \n",
       "347                                   Sandawe, Sandawe      NaN      NaN   \n",
       "151                        Kwadi, Kwadi, Cuepe, Curoca      NaN      NaN   \n",
       "\n",
       "    sbranch   mbranch       stock    alt.stock.name  \\\n",
       "LID                                                   \n",
       "199     NaN  Khoekhoe  Kwadi-Khoe   Central Khoisan   \n",
       "148     NaN       NaN          Ju  Northern Khoisan   \n",
       "94      NaN       NaN       Hadza               NaN   \n",
       "347     NaN       NaN     Sandawe               NaN   \n",
       "151     NaN     Kwadi  Kwadi-Khoe   Central Khoisan   \n",
       "\n",
       "                    stock.search  longitude  latitude      area continent  \n",
       "LID                                                                        \n",
       "199  Kwadi-Khoe, Central Khoisan      18.00    -25.50  S Africa    Africa  \n",
       "148         Ju, Northern Khoisan      18.00    -19.67  S Africa    Africa  \n",
       "94                         Hadza      35.17     -3.75  S Africa    Africa  \n",
       "347                      Sandawe      35.00     -5.00  S Africa    Africa  \n",
       "151  Kwadi-Khoe, Central Khoisan      12.00    -16.00  S Africa    Africa  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "AUTOTYP = 'https://www.autotyp.uzh.ch/download/release_2013/autotyp.csv'\n",
    "\n",
    "AUTOTYP_CSV = pathlib.Path(AUTOTYP.rpartition('/')[2])\n",
    "\n",
    "AUTOTYP_FORMAT = {'encoding': 'utf-8',\n",
    "                  'na_values': '', 'keep_default_na': False,\n",
    "                  'index_col': 'LID'}\n",
    "\n",
    "if not AUTOTYP_CSV.exists():\n",
    "    _af = pd.read_csv(AUTOTYP, **AUTOTYP_FORMAT)\n",
    "    _af.to_csv(AUTOTYP_CSV, encoding=AUTOTYP_FORMAT['encoding'])\n",
    "\n",
    "af = pd.read_csv(AUTOTYP_CSV, **AUTOTYP_FORMAT)\n",
    "\n",
    "af.info()\n",
    "assert af.index.is_unique\n",
    "af.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "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>nunique</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>language</th>\n",
       "      <td>2913</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>stock</th>\n",
       "      <td>399</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mbranch</th>\n",
       "      <td>236</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>sbranch</th>\n",
       "      <td>154</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>area</th>\n",
       "      <td>24</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>continent</th>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           nunique\n",
       "language      2913\n",
       "stock          399\n",
       "mbranch        236\n",
       "sbranch        154\n",
       "area            24\n",
       "continent       10"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "af[['language','stock', 'mbranch', 'sbranch', 'area', 'continent']].nunique().to_frame('nunique')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "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>stock</th>\n",
       "      <th>mbranch</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Chibchan</th>\n",
       "      <td>16</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Great Andamanese</th>\n",
       "      <td>5</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Morehead and Upper Maro Rivers</th>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                stock  mbranch\n",
       "Chibchan                           16        5\n",
       "Great Andamanese                    5        4\n",
       "Morehead and Upper Maro Rivers      3        1"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.concat([af.groupby('stock').size(), af.groupby('mbranch').size()],\n",
    "          axis=1, join='inner', keys=['stock', 'mbranch'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "593"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "af['family'] = af['mbranch'].fillna(af['stock'])\n",
    "\n",
    "af['family'].nunique()"
   ]
  },
  {
   "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 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>n</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>family</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Malayo-Polynesian</th>\n",
       "      <td>326</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Bantoid</th>\n",
       "      <td>164</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Indo-Iranian</th>\n",
       "      <td>109</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>West Semitic</th>\n",
       "      <td>51</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Germanic</th>\n",
       "      <td>50</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                     n\n",
       "family                \n",
       "Malayo-Polynesian  326\n",
       "Bantoid            164\n",
       "Indo-Iranian       109\n",
       "West Semitic        51\n",
       "Germanic            50"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "af['family'].value_counts().to_frame('n').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>ISO639.3</th>\n",
       "      <th>family</th>\n",
       "      <th>continent</th>\n",
       "      <th>area</th>\n",
       "      <th>latitude</th>\n",
       "      <th>longitude</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Language</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>Ainu</th>\n",
       "      <td>ain</td>\n",
       "      <td>Ainu</td>\n",
       "      <td>N-C Asia</td>\n",
       "      <td>N Coast Asia</td>\n",
       "      <td>43.0</td>\n",
       "      <td>143.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Aleut</th>\n",
       "      <td>ale</td>\n",
       "      <td>Aleut</td>\n",
       "      <td>N-C Asia</td>\n",
       "      <td>N Coast Asia</td>\n",
       "      <td>54.0</td>\n",
       "      <td>-166.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Bella Coola</th>\n",
       "      <td>blc</td>\n",
       "      <td>Salishan</td>\n",
       "      <td>W N America</td>\n",
       "      <td>Alaska-Oregon</td>\n",
       "      <td>52.5</td>\n",
       "      <td>-126.67</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Chuckchi</th>\n",
       "      <td>ckt</td>\n",
       "      <td>Chukotkan</td>\n",
       "      <td>N-C Asia</td>\n",
       "      <td>N Coast Asia</td>\n",
       "      <td>67.0</td>\n",
       "      <td>170.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Darai</th>\n",
       "      <td>dry</td>\n",
       "      <td>Indo-Iranian</td>\n",
       "      <td>S/SE Asia</td>\n",
       "      <td>Indic</td>\n",
       "      <td>24.0</td>\n",
       "      <td>84.00</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            ISO639.3        family    continent           area  latitude  \\\n",
       "Language                                                                   \n",
       "Ainu             ain          Ainu     N-C Asia   N Coast Asia      43.0   \n",
       "Aleut            ale         Aleut     N-C Asia   N Coast Asia      54.0   \n",
       "Bella Coola      blc      Salishan  W N America  Alaska-Oregon      52.5   \n",
       "Chuckchi         ckt     Chukotkan     N-C Asia   N Coast Asia      67.0   \n",
       "Darai            dry  Indo-Iranian    S/SE Asia          Indic      24.0   \n",
       "\n",
       "             longitude  \n",
       "Language                \n",
       "Ainu            143.00  \n",
       "Aleut          -166.00  \n",
       "Bella Coola    -126.67  \n",
       "Chuckchi        170.00  \n",
       "Darai            84.00  "
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "JUM = pd.Series({'ISO639.3': 'jum',  # missing in autotyp\n",
    "                 'family': 'Western Nilotic',\n",
    "                 'continent': 'Africa',\n",
    "                 'area': 'African Savannah',\n",
    "                 'longitude': 33.7494, 'latitude': 10.4349})\n",
    "\n",
    "jf = df[['LID']].reset_index().set_index('LID').join(af).set_index('Language')\n",
    "jf = jf[['ISO639.3', 'family', 'continent', 'area', 'latitude', 'longitude']]\n",
    "jf.loc['Jumjum'] = JUM\n",
    "assert jf.notnull().all().all()\n",
    "\n",
    "jf.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "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>ISO639.3</th>\n",
       "      <th>family</th>\n",
       "      <th>continent</th>\n",
       "      <th>area</th>\n",
       "      <th>n</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Language</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>Jumjum</th>\n",
       "      <td>jum</td>\n",
       "      <td>Western Nilotic</td>\n",
       "      <td>Africa</td>\n",
       "      <td>African Savannah</td>\n",
       "      <td>375</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Kunama</th>\n",
       "      <td>kun</td>\n",
       "      <td>Kunama</td>\n",
       "      <td>Africa</td>\n",
       "      <td>Greater Abyssinia</td>\n",
       "      <td>61</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Turkana</th>\n",
       "      <td>tuv</td>\n",
       "      <td>Eastern Nilotic</td>\n",
       "      <td>Africa</td>\n",
       "      <td>S Africa</td>\n",
       "      <td>190</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Maung</th>\n",
       "      <td>mph</td>\n",
       "      <td>Iwaidjan</td>\n",
       "      <td>Australia</td>\n",
       "      <td>N Australia</td>\n",
       "      <td>108</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Wardaman</th>\n",
       "      <td>wrr</td>\n",
       "      <td>Wagiman - Wardaman</td>\n",
       "      <td>Australia</td>\n",
       "      <td>N Australia</td>\n",
       "      <td>108</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Tepehua</th>\n",
       "      <td>tee</td>\n",
       "      <td>Totonac-Tepehuan</td>\n",
       "      <td>C America</td>\n",
       "      <td>Mesoamerica</td>\n",
       "      <td>173</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Lakota</th>\n",
       "      <td>lkt</td>\n",
       "      <td>Siouan</td>\n",
       "      <td>E N America</td>\n",
       "      <td>Basin and Plains</td>\n",
       "      <td>68</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Maricopa</th>\n",
       "      <td>mrc</td>\n",
       "      <td>Yuman</td>\n",
       "      <td>E N America</td>\n",
       "      <td>Basin and Plains</td>\n",
       "      <td>68</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Fox</th>\n",
       "      <td>sac</td>\n",
       "      <td>Algonquian</td>\n",
       "      <td>E N America</td>\n",
       "      <td>E North America</td>\n",
       "      <td>69</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Ket</th>\n",
       "      <td>ket</td>\n",
       "      <td>Yeniseian</td>\n",
       "      <td>N-C Asia</td>\n",
       "      <td>Inner Asia</td>\n",
       "      <td>113</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Mordvin</th>\n",
       "      <td>myv</td>\n",
       "      <td>Finno-Ugric</td>\n",
       "      <td>N-C Asia</td>\n",
       "      <td>Inner Asia</td>\n",
       "      <td>113</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Ainu</th>\n",
       "      <td>ain</td>\n",
       "      <td>Ainu</td>\n",
       "      <td>N-C Asia</td>\n",
       "      <td>N Coast Asia</td>\n",
       "      <td>27</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Aleut</th>\n",
       "      <td>ale</td>\n",
       "      <td>Aleut</td>\n",
       "      <td>N-C Asia</td>\n",
       "      <td>N Coast Asia</td>\n",
       "      <td>27</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Chuckchi</th>\n",
       "      <td>ckt</td>\n",
       "      <td>Chukotkan</td>\n",
       "      <td>N-C Asia</td>\n",
       "      <td>N Coast Asia</td>\n",
       "      <td>27</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Yimas</th>\n",
       "      <td>yee</td>\n",
       "      <td>Lower Sepik</td>\n",
       "      <td>NG and Oceania</td>\n",
       "      <td>N Coast New Guinea</td>\n",
       "      <td>163</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Sahu</th>\n",
       "      <td>saj</td>\n",
       "      <td>North Halmaheran</td>\n",
       "      <td>NG and Oceania</td>\n",
       "      <td>Oceania</td>\n",
       "      <td>240</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Jaqaru</th>\n",
       "      <td>jqr</td>\n",
       "      <td>Aymaran</td>\n",
       "      <td>S America</td>\n",
       "      <td>Andean</td>\n",
       "      <td>47</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Ayacucho</th>\n",
       "      <td>quy</td>\n",
       "      <td>Quechuan</td>\n",
       "      <td>S America</td>\n",
       "      <td>Andean</td>\n",
       "      <td>47</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Hixkaryana</th>\n",
       "      <td>hix</td>\n",
       "      <td>Cariban</td>\n",
       "      <td>S America</td>\n",
       "      <td>NE South America</td>\n",
       "      <td>192</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Reyesano</th>\n",
       "      <td>rey</td>\n",
       "      <td>Tacanan</td>\n",
       "      <td>S America</td>\n",
       "      <td>NE South America</td>\n",
       "      <td>192</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Darai</th>\n",
       "      <td>dry</td>\n",
       "      <td>Indo-Iranian</td>\n",
       "      <td>S/SE Asia</td>\n",
       "      <td>Indic</td>\n",
       "      <td>203</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Thangmi</th>\n",
       "      <td>thf</td>\n",
       "      <td>Remnant Himalayish</td>\n",
       "      <td>S/SE Asia</td>\n",
       "      <td>Indic</td>\n",
       "      <td>203</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Nocte</th>\n",
       "      <td>njb</td>\n",
       "      <td>Brahmaputran (Sal)</td>\n",
       "      <td>S/SE Asia</td>\n",
       "      <td>Southeast Asia</td>\n",
       "      <td>216</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Bella Coola</th>\n",
       "      <td>blc</td>\n",
       "      <td>Salishan</td>\n",
       "      <td>W N America</td>\n",
       "      <td>Alaska-Oregon</td>\n",
       "      <td>59</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Siuslawan</th>\n",
       "      <td>sis</td>\n",
       "      <td>Siuslawan</td>\n",
       "      <td>W N America</td>\n",
       "      <td>Alaska-Oregon</td>\n",
       "      <td>59</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Karuk</th>\n",
       "      <td>kyh</td>\n",
       "      <td>Karok</td>\n",
       "      <td>W N America</td>\n",
       "      <td>California</td>\n",
       "      <td>47</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            ISO639.3              family       continent                area  \\\n",
       "Language                                                                       \n",
       "Jumjum           jum     Western Nilotic          Africa    African Savannah   \n",
       "Kunama           kun              Kunama          Africa   Greater Abyssinia   \n",
       "Turkana          tuv     Eastern Nilotic          Africa            S Africa   \n",
       "Maung            mph            Iwaidjan       Australia         N Australia   \n",
       "Wardaman         wrr  Wagiman - Wardaman       Australia         N Australia   \n",
       "Tepehua          tee    Totonac-Tepehuan       C America         Mesoamerica   \n",
       "Lakota           lkt              Siouan     E N America    Basin and Plains   \n",
       "Maricopa         mrc               Yuman     E N America    Basin and Plains   \n",
       "Fox              sac          Algonquian     E N America     E North America   \n",
       "Ket              ket           Yeniseian        N-C Asia          Inner Asia   \n",
       "Mordvin          myv         Finno-Ugric        N-C Asia          Inner Asia   \n",
       "Ainu             ain                Ainu        N-C Asia        N Coast Asia   \n",
       "Aleut            ale               Aleut        N-C Asia        N Coast Asia   \n",
       "Chuckchi         ckt           Chukotkan        N-C Asia        N Coast Asia   \n",
       "Yimas            yee         Lower Sepik  NG and Oceania  N Coast New Guinea   \n",
       "Sahu             saj    North Halmaheran  NG and Oceania             Oceania   \n",
       "Jaqaru           jqr             Aymaran       S America              Andean   \n",
       "Ayacucho         quy            Quechuan       S America              Andean   \n",
       "Hixkaryana       hix             Cariban       S America    NE South America   \n",
       "Reyesano         rey             Tacanan       S America    NE South America   \n",
       "Darai            dry        Indo-Iranian       S/SE Asia               Indic   \n",
       "Thangmi          thf  Remnant Himalayish       S/SE Asia               Indic   \n",
       "Nocte            njb  Brahmaputran (Sal)       S/SE Asia      Southeast Asia   \n",
       "Bella Coola      blc            Salishan     W N America       Alaska-Oregon   \n",
       "Siuslawan        sis           Siuslawan     W N America       Alaska-Oregon   \n",
       "Karuk            kyh               Karok     W N America          California   \n",
       "\n",
       "               n  \n",
       "Language          \n",
       "Jumjum       375  \n",
       "Kunama        61  \n",
       "Turkana      190  \n",
       "Maung        108  \n",
       "Wardaman     108  \n",
       "Tepehua      173  \n",
       "Lakota        68  \n",
       "Maricopa      68  \n",
       "Fox           69  \n",
       "Ket          113  \n",
       "Mordvin      113  \n",
       "Ainu          27  \n",
       "Aleut         27  \n",
       "Chuckchi      27  \n",
       "Yimas        163  \n",
       "Sahu         240  \n",
       "Jaqaru        47  \n",
       "Ayacucho      47  \n",
       "Hixkaryana   192  \n",
       "Reyesano     192  \n",
       "Darai        203  \n",
       "Thangmi      203  \n",
       "Nocte        216  \n",
       "Bella Coola   59  \n",
       "Siuslawan     59  \n",
       "Karuk         47  "
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(jf.merge(af.groupby('area').size().to_frame('n'),\n",
    "          left_on='area', right_index=True)\n",
    " .sort_values(['continent', 'area'])\n",
    " .drop(['latitude', 'longitude'], axis=1))"
   ]
  },
  {
   "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></th>\n",
       "      <th>language</th>\n",
       "      <th>Language</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>continent</th>\n",
       "      <th>area</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Africa</th>\n",
       "      <th>N Africa</th>\n",
       "      <td>28</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Australia</th>\n",
       "      <th>S Australia</th>\n",
       "      <td>81</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">NG and Oceania</th>\n",
       "      <th>Interior New Guinea</th>\n",
       "      <td>81</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>S New Guinea</th>\n",
       "      <td>67</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>S America</th>\n",
       "      <th>SE South America</th>\n",
       "      <td>32</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">W and SW Eurasia</th>\n",
       "      <th>Europe</th>\n",
       "      <td>142</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Greater Mesopotamia</th>\n",
       "      <td>131</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                      language Language\n",
       "continent        area                                  \n",
       "Africa           N Africa                   28      NaN\n",
       "Australia        S Australia                81      NaN\n",
       "NG and Oceania   Interior New Guinea        81      NaN\n",
       "                 S New Guinea               67      NaN\n",
       "S America        SE South America           32      NaN\n",
       "W and SW Eurasia Europe                    142      NaN\n",
       "                 Greater Mesopotamia       131      NaN"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(af.groupby(['area', 'continent'], as_index=False)['language'].count()\n",
    " .merge(jf[['area']].reset_index(), how='left', on='area')\n",
    " .set_index(['continent', 'area'])\n",
    " .sort_index()\n",
    " .query('Language != Language'))"
   ]
  },
  {
   "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>present</th>\n",
       "      <th>left_only</th>\n",
       "      <th>both</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>languages</th>\n",
       "      <td>562</td>\n",
       "      <td>2351</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "present    left_only  both\n",
       "languages        562  2351"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(af.groupby('area').size().to_frame('languages')\n",
    " .merge(jf.groupby('area').size().to_frame(),\n",
    "        how='left', left_index=True, right_index=True, indicator='present')\n",
    " .groupby('present', observed=False)['languages'].sum()\n",
    " .drop('right_only')\n",
    " .astype(int)\n",
    " .to_frame().T)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "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>nunique</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>family</th>\n",
       "      <td>593</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>continent</th>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>area</th>\n",
       "      <td>24</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           nunique\n",
       "family         593\n",
       "continent       10\n",
       "area            24"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "af[['family', 'continent', 'area']].nunique().to_frame('nunique')"
   ]
  },
  {
   "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>nunique</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>family</th>\n",
       "      <td>26</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>continent</th>\n",
       "      <td>9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>area</th>\n",
       "      <td>17</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           nunique\n",
       "family          26\n",
       "continent        9\n",
       "area            17"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "jf[['family', 'continent', 'area']].nunique().to_frame('nunique')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "(fig, ax) = plt.subplots(figsize=(12, 6))\n",
    "\n",
    "m = Basemap(ax=ax, projection='eck4', lon_0=155)\n",
    "m.fillcontinents()\n",
    "#m.drawparallels(range(-90, 120, 30), dashes=[], linewidth=.25, labels=[1, 0, 0, 0])\n",
    "#m.drawmeridians(range(0, 360, 60), dashes=[], linewidth=.25, labels=[0, 0, 0, 1])\n",
    "\n",
    "offsets = {'Jumjum': (3e5, -1e5),\n",
    "           'Thangmi': (0, 3e5), 'Nocte': (3e5, -2e5), 'Darai': (3e5, -4e5),\n",
    "           'Wardaman': (3e5, -2e5),\n",
    "           'Siuslawan': (-2.6e6, 0), 'Karuk': (2e5, -3e5), 'Maricopa': (3e5, -2e5),\n",
    "           'Lakota': (1e5, 2e5), 'Fox': (2e5, -3e5),\n",
    "           'Jaqaru': (0, 5e5), 'Ayacucho': (0e5, -6e5)}\n",
    "\n",
    "for l, (x, y) in jf[['longitude', 'latitude']].iterrows():\n",
    "    x, y = m(x, y)\n",
    "    m.plot(x, y, marker='.', color='b', markersize=7)\n",
    "    xoff, yoff = offsets.get(l, (2e5, 1e5))\n",
    "    ax.text(x + xoff, y + yoff, l)\n",
    "\n",
    "#fig.savefig('map.pdf', bbox_inches='tight', pad_inches=.01)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.13.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}