Create-Dashboard-dataset.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "b570de38-f284-4c8f-ab5d-608505ff49a7",
   "metadata": {},
   "source": [
    "# Creating Dataset to be used in a DataStudio Dashboard"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f477ffcb-5ea4-4b6c-8659-b482d871e495",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    },
    "tags": []
   },
   "source": [
    "# Expanding the measurement of culture with a sample of two billion humans"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "641b0294-3553-419c-b638-2baa40e92531",
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "## Replication Data and Code"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4fe6cf5c-e5cf-4f03-a340-150562dcb311",
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "This notebook provides all the steps to replicate the results of our paper [Expanding the measurement of culture with a sample of two billion humans](https://doi.org/10.1098/rsif.2022.0085) published in the *Journal of the Royal Society Interface 19:20220085* (2022)."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ace7babb-f36c-46cf-9d3d-00a5d72eeab2",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "# Setup and Pre-requisites"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e6dc6348-189c-4802-bc2c-30d00ccc3845",
   "metadata": {
    "slideshow": {
     "slide_type": "-"
    }
   },
   "source": [
    "Let's start by importing the required packages"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "b2c342fe-8784-489e-a661-8a1640e77bce",
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [],
   "source": [
    "#%pylab --no-import-all\n",
    "%matplotlib inline\n",
    "\n",
    "import sys, os, time\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "pd.set_option('display.width', 160)\n",
    "import matplotlib.pyplot as plt\n",
    "import matplotlib as mpl\n",
    "import matplotlib.patches as mpatches\n",
    "import statsmodels.api as sm\n",
    "import statsmodels.formula.api as smf\n",
    "from statsmodels.iolib.summary2 import summary_col\n",
    "from sklearn.metrics.pairwise import cosine_similarity, cosine_distances, manhattan_distances, pairwise_distances\n",
    "from scipy.stats import zscore\n",
    "from scipy.cluster.hierarchy import dendrogram, linkage\n",
    "from scipy import spatial, stats\n",
    "from scipy.stats import zscore\n",
    "import MantelTest.MantelTest as MantelTest\n",
    "import re\n",
    "import seaborn as sns\n",
    "from geonamescache.mappers import country\n",
    "mapper = country(from_key='name', to_key='iso3')\n",
    "mapper2 = country(from_key='iso3', to_key='iso')\n",
    "mapper3 = country(from_key='iso3', to_key='name')\n",
    "mapper4 = country(from_key='iso', to_key='name')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1a95a094-f798-4cde-b4e2-88e7767851ed",
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "source": [
    "Let's setup our paths"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "7f58f0bd-fa86-4d15-9942-8569f6958199",
   "metadata": {},
   "outputs": [],
   "source": [
    "pathfb = './data/'\n",
    "pathfbor = './data/OriginalData/'\n",
    "pathregs = pathfb   'Regs/'\n",
    "pathsamples = pathfb   '/DemographicData/'  \n",
    "\n",
    "pathout = pathregs   'Categories/'\n",
    "if os.path.exists(pathout) == False:\n",
    "    os.mkdir(pathout)\n",
    "pathshare = pathout\n",
    "if os.path.exists(pathfbor) == False:\n",
    "    os.mkdir(pathfbor)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1d190895-7b26-497b-9d19-e69ba2171dd2",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Import Data"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3e0c1e96-727f-4976-a5fe-93d68284219f",
   "metadata": {},
   "source": [
    "## Merge all the category distances and compare them to original FB and other measures"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "b29fb9eb-744f-4181-8703-c19d4eeb7cae",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['BusinessIndustry',\n",
       " 'Education',\n",
       " 'Empty',\n",
       " 'FamilyRelationships',\n",
       " 'FitnessWellness',\n",
       " 'FoodDrink',\n",
       " 'HobbiesActivities',\n",
       " 'LifestyleCulture',\n",
       " 'NewsEntertainment',\n",
       " 'NonLocalBus',\n",
       " 'People',\n",
       " 'ShoppingFashion',\n",
       " 'SportsOutdoors',\n",
       " 'Technology',\n",
       " 'TravelPlacesEvents']"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mycats = [f[f.find('_') 1:f.find('.')] for f in os.listdir(pathout) if f.endswith('dta')]\n",
    "mycats.sort()\n",
    "mycats"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "14b6457b-7c80-464a-94dc-b6283d78386b",
   "metadata": {
    "slideshow": {
     "slide_type": "skip"
    }
   },
   "outputs": [],
   "source": [
    "# Type of distance measure\n",
    "m = 'Cos'\n",
    "\n",
    "# Load data other distances  \n",
    "df = pd.read_stata(pathregs   'AllDistsFull.dta')\n",
    "\n",
    "for c in mycats:\n",
    "    fbdist2 = pd.read_stata(pathout   'FB'   m   'Dist_'   c   '.dta')\n",
    "    cols = fbdist2.columns.tolist()\n",
    "    cols[0] = 'ISO_CODE_1'\n",
    "    fbdist2.columns = cols\n",
    "    fbdist2 = fbdist2.set_index('ISO_CODE_1').stack().copy()\n",
    "    fbdist2 = fbdist2.reset_index()\n",
    "    fbdist2.columns = ['ISO_CODE_1', 'ISO_CODE_2', 'FBDist_' c]\n",
    "    df = df.merge(fbdist2, on=['ISO_CODE_1', 'ISO_CODE_2'], how='left')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "d508b3ec-d59b-4230-a303-3b9176d9e3fb",
   "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>ISO_CODE_1</th>\n",
       "      <th>ISO_CODE_2</th>\n",
       "      <th>CosDist1</th>\n",
       "      <th>CosDist2</th>\n",
       "      <th>CosDist3</th>\n",
       "      <th>CosDist4</th>\n",
       "      <th>CosDist5</th>\n",
       "      <th>CosDist6</th>\n",
       "      <th>CosDist7</th>\n",
       "      <th>CosDist8</th>\n",
       "      <th>...</th>\n",
       "      <th>FBDist_FoodDrink</th>\n",
       "      <th>FBDist_HobbiesActivities</th>\n",
       "      <th>FBDist_LifestyleCulture</th>\n",
       "      <th>FBDist_NewsEntertainment</th>\n",
       "      <th>FBDist_NonLocalBus</th>\n",
       "      <th>FBDist_People</th>\n",
       "      <th>FBDist_ShoppingFashion</th>\n",
       "      <th>FBDist_SportsOutdoors</th>\n",
       "      <th>FBDist_Technology</th>\n",
       "      <th>FBDist_TravelPlacesEvents</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>AD</td>\n",
       "      <td>AD</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>AD</td>\n",
       "      <td>AE</td>\n",
       "      <td>0.649726</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.178210</td>\n",
       "      <td>0.256747</td>\n",
       "      <td>0.186337</td>\n",
       "      <td>0.083852</td>\n",
       "      <td>0.245167</td>\n",
       "      <td>0.733101</td>\n",
       "      <td>0.133534</td>\n",
       "      <td>0.283705</td>\n",
       "      <td>0.099948</td>\n",
       "      <td>0.519951</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>AD</td>\n",
       "      <td>AF</td>\n",
       "      <td>0.027777</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.294734</td>\n",
       "      <td>0.298884</td>\n",
       "      <td>0.272084</td>\n",
       "      <td>0.124117</td>\n",
       "      <td>0.291968</td>\n",
       "      <td>0.832636</td>\n",
       "      <td>0.165568</td>\n",
       "      <td>0.377505</td>\n",
       "      <td>0.117173</td>\n",
       "      <td>0.531510</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>AD</td>\n",
       "      <td>AG</td>\n",
       "      <td>0.298230</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.251972</td>\n",
       "      <td>0.258350</td>\n",
       "      <td>0.154459</td>\n",
       "      <td>0.099079</td>\n",
       "      <td>0.234904</td>\n",
       "      <td>0.680631</td>\n",
       "      <td>0.143881</td>\n",
       "      <td>0.376967</td>\n",
       "      <td>0.085136</td>\n",
       "      <td>0.504606</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>AD</td>\n",
       "      <td>AI</td>\n",
       "      <td>0.917672</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.261493</td>\n",
       "      <td>0.279948</td>\n",
       "      <td>0.195226</td>\n",
       "      <td>0.153596</td>\n",
       "      <td>0.263495</td>\n",
       "      <td>0.651478</td>\n",
       "      <td>0.164097</td>\n",
       "      <td>0.371870</td>\n",
       "      <td>0.081088</td>\n",
       "      <td>0.506484</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 69 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "  ISO_CODE_1 ISO_CODE_2  CosDist1  CosDist2  CosDist3  CosDist4  CosDist5  CosDist6  CosDist7  CosDist8  ...  FBDist_FoodDrink  FBDist_HobbiesActivities  \\\n",
       "0         AD         AD  0.000000       0.0       0.0       0.0       0.0       0.0       0.0       0.0  ...          0.000000                  0.000000   \n",
       "1         AD         AE  0.649726       1.0       1.0       1.0       1.0       1.0       1.0       1.0  ...          0.178210                  0.256747   \n",
       "2         AD         AF  0.027777       1.0       1.0       1.0       1.0       1.0       1.0       1.0  ...          0.294734                  0.298884   \n",
       "3         AD         AG  0.298230       1.0       1.0       1.0       1.0       1.0       1.0       1.0  ...          0.251972                  0.258350   \n",
       "4         AD         AI  0.917672       1.0       1.0       1.0       1.0       1.0       1.0       1.0  ...          0.261493                  0.279948   \n",
       "\n",
       "   FBDist_LifestyleCulture  FBDist_NewsEntertainment  FBDist_NonLocalBus  FBDist_People  FBDist_ShoppingFashion FBDist_SportsOutdoors  FBDist_Technology  \\\n",
       "0                 0.000000                  0.000000            0.000000       0.000000                0.000000              0.000000           0.000000   \n",
       "1                 0.186337                  0.083852            0.245167       0.733101                0.133534              0.283705           0.099948   \n",
       "2                 0.272084                  0.124117            0.291968       0.832636                0.165568              0.377505           0.117173   \n",
       "3                 0.154459                  0.099079            0.234904       0.680631                0.143881              0.376967           0.085136   \n",
       "4                 0.195226                  0.153596            0.263495       0.651478                0.164097              0.371870           0.081088   \n",
       "\n",
       "   FBDist_TravelPlacesEvents  \n",
       "0                   0.000000  \n",
       "1                   0.519951  \n",
       "2                   0.531510  \n",
       "3                   0.504606  \n",
       "4                   0.506484  \n",
       "\n",
       "[5 rows x 69 columns]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "3fee634b-f0f2-4ff4-ba96-aa3f915af9ac",
   "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>FBDist</th>\n",
       "      <th>FBDist_BusinessIndustry</th>\n",
       "      <th>FBDist_Education</th>\n",
       "      <th>FBDist_Empty</th>\n",
       "      <th>FBDist_FamilyRelationships</th>\n",
       "      <th>FBDist_FitnessWellness</th>\n",
       "      <th>FBDist_FoodDrink</th>\n",
       "      <th>FBDist_HobbiesActivities</th>\n",
       "      <th>FBDist_LifestyleCulture</th>\n",
       "      <th>FBDist_NewsEntertainment</th>\n",
       "      <th>FBDist_NonLocalBus</th>\n",
       "      <th>FBDist_People</th>\n",
       "      <th>FBDist_ShoppingFashion</th>\n",
       "      <th>FBDist_SportsOutdoors</th>\n",
       "      <th>FBDist_Technology</th>\n",
       "      <th>FBDist_TravelPlacesEvents</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.233552</td>\n",
       "      <td>0.288817</td>\n",
       "      <td>0.189267</td>\n",
       "      <td>0.174565</td>\n",
       "      <td>0.153039</td>\n",
       "      <td>0.132261</td>\n",
       "      <td>0.178210</td>\n",
       "      <td>0.256747</td>\n",
       "      <td>0.186337</td>\n",
       "      <td>0.083852</td>\n",
       "      <td>0.245167</td>\n",
       "      <td>0.733101</td>\n",
       "      <td>0.133534</td>\n",
       "      <td>0.283705</td>\n",
       "      <td>0.099948</td>\n",
       "      <td>0.519951</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.279233</td>\n",
       "      <td>0.314991</td>\n",
       "      <td>0.340453</td>\n",
       "      <td>0.207937</td>\n",
       "      <td>0.298100</td>\n",
       "      <td>0.226512</td>\n",
       "      <td>0.294734</td>\n",
       "      <td>0.298884</td>\n",
       "      <td>0.272084</td>\n",
       "      <td>0.124117</td>\n",
       "      <td>0.291968</td>\n",
       "      <td>0.832636</td>\n",
       "      <td>0.165568</td>\n",
       "      <td>0.377505</td>\n",
       "      <td>0.117173</td>\n",
       "      <td>0.531510</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.227161</td>\n",
       "      <td>0.279893</td>\n",
       "      <td>0.282477</td>\n",
       "      <td>0.154556</td>\n",
       "      <td>0.135234</td>\n",
       "      <td>0.133760</td>\n",
       "      <td>0.251972</td>\n",
       "      <td>0.258350</td>\n",
       "      <td>0.154459</td>\n",
       "      <td>0.099079</td>\n",
       "      <td>0.234904</td>\n",
       "      <td>0.680631</td>\n",
       "      <td>0.143881</td>\n",
       "      <td>0.376967</td>\n",
       "      <td>0.085136</td>\n",
       "      <td>0.504606</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.262021</td>\n",
       "      <td>0.288825</td>\n",
       "      <td>0.347721</td>\n",
       "      <td>0.213974</td>\n",
       "      <td>0.205464</td>\n",
       "      <td>0.188863</td>\n",
       "      <td>0.261493</td>\n",
       "      <td>0.279948</td>\n",
       "      <td>0.195226</td>\n",
       "      <td>0.153596</td>\n",
       "      <td>0.263495</td>\n",
       "      <td>0.651478</td>\n",
       "      <td>0.164097</td>\n",
       "      <td>0.371870</td>\n",
       "      <td>0.081088</td>\n",
       "      <td>0.506484</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     FBDist  FBDist_BusinessIndustry  FBDist_Education  FBDist_Empty  FBDist_FamilyRelationships  FBDist_FitnessWellness  FBDist_FoodDrink  \\\n",
       "0  0.000000                 0.000000          0.000000      0.000000                    0.000000                0.000000          0.000000   \n",
       "1  0.233552                 0.288817          0.189267      0.174565                    0.153039                0.132261          0.178210   \n",
       "2  0.279233                 0.314991          0.340453      0.207937                    0.298100                0.226512          0.294734   \n",
       "3  0.227161                 0.279893          0.282477      0.154556                    0.135234                0.133760          0.251972   \n",
       "4  0.262021                 0.288825          0.347721      0.213974                    0.205464                0.188863          0.261493   \n",
       "\n",
       "   FBDist_HobbiesActivities  FBDist_LifestyleCulture  FBDist_NewsEntertainment  FBDist_NonLocalBus  FBDist_People  FBDist_ShoppingFashion  \\\n",
       "0                  0.000000                 0.000000                  0.000000            0.000000       0.000000                0.000000   \n",
       "1                  0.256747                 0.186337                  0.083852            0.245167       0.733101                0.133534   \n",
       "2                  0.298884                 0.272084                  0.124117            0.291968       0.832636                0.165568   \n",
       "3                  0.258350                 0.154459                  0.099079            0.234904       0.680631                0.143881   \n",
       "4                  0.279948                 0.195226                  0.153596            0.263495       0.651478                0.164097   \n",
       "\n",
       "   FBDist_SportsOutdoors  FBDist_Technology  FBDist_TravelPlacesEvents  \n",
       "0               0.000000           0.000000                   0.000000  \n",
       "1               0.283705           0.099948                   0.519951  \n",
       "2               0.377505           0.117173                   0.531510  \n",
       "3               0.376967           0.085136                   0.504606  \n",
       "4               0.371870           0.081088                   0.506484  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[[c for c in df.columns if c.startswith('FB')]].head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "22bf7edc-0af7-4f04-a106-caafdc8361c5",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Import all distances\n",
    "mypairs = pd.read_stata(pathregs   'AllDists.dta')\n",
    "\n",
    "# Merge category distances\n",
    "mypairs = mypairs.merge(df[df.columns.difference(mypairs.columns).tolist()   ['ISO_CODE_1', 'ISO_CODE_2']], how='left', on=['ISO_CODE_1', 'ISO_CODE_2'])\n",
    "mypairs.drop([x for x in mypairs.columns if x.endswith('uk') or x.endswith('usa')], inplace=True, axis=1)\n",
    "mypairs.drop([x for x in mypairs.columns if x.find('cognate')!=-1], inplace=True, axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "98221b3b-0109-4f91-973a-222ebd5b80be",
   "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>ISO_CODE_1</th>\n",
       "      <th>ISO_CODE_2</th>\n",
       "      <th>CosDist1</th>\n",
       "      <th>CosDist2</th>\n",
       "      <th>CosDist3</th>\n",
       "      <th>CosDist4</th>\n",
       "      <th>CosDist5</th>\n",
       "      <th>CosDist6</th>\n",
       "      <th>CosDist7</th>\n",
       "      <th>CosDist8</th>\n",
       "      <th>...</th>\n",
       "      <th>FBDist_FoodDrink</th>\n",
       "      <th>FBDist_HobbiesActivities</th>\n",
       "      <th>FBDist_LifestyleCulture</th>\n",
       "      <th>FBDist_NewsEntertainment</th>\n",
       "      <th>FBDist_NonLocalBus</th>\n",
       "      <th>FBDist_People</th>\n",
       "      <th>FBDist_ShoppingFashion</th>\n",
       "      <th>FBDist_SportsOutdoors</th>\n",
       "      <th>FBDist_Technology</th>\n",
       "      <th>FBDist_TravelPlacesEvents</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>AD</td>\n",
       "      <td>AE</td>\n",
       "      <td>0.649726</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.178210</td>\n",
       "      <td>0.256747</td>\n",
       "      <td>0.186337</td>\n",
       "      <td>0.083852</td>\n",
       "      <td>0.245167</td>\n",
       "      <td>0.733101</td>\n",
       "      <td>0.133534</td>\n",
       "      <td>0.283705</td>\n",
       "      <td>0.099948</td>\n",
       "      <td>0.519951</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>AD</td>\n",
       "      <td>AF</td>\n",
       "      <td>0.027777</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.294734</td>\n",
       "      <td>0.298884</td>\n",
       "      <td>0.272084</td>\n",
       "      <td>0.124117</td>\n",
       "      <td>0.291968</td>\n",
       "      <td>0.832636</td>\n",
       "      <td>0.165568</td>\n",
       "      <td>0.377505</td>\n",
       "      <td>0.117173</td>\n",
       "      <td>0.531510</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>AD</td>\n",
       "      <td>AG</td>\n",
       "      <td>0.298230</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.251972</td>\n",
       "      <td>0.258350</td>\n",
       "      <td>0.154459</td>\n",
       "      <td>0.099079</td>\n",
       "      <td>0.234904</td>\n",
       "      <td>0.680631</td>\n",
       "      <td>0.143881</td>\n",
       "      <td>0.376967</td>\n",
       "      <td>0.085136</td>\n",
       "      <td>0.504606</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>AD</td>\n",
       "      <td>AI</td>\n",
       "      <td>0.917672</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.261493</td>\n",
       "      <td>0.279948</td>\n",
       "      <td>0.195226</td>\n",
       "      <td>0.153596</td>\n",
       "      <td>0.263495</td>\n",
       "      <td>0.651478</td>\n",
       "      <td>0.164097</td>\n",
       "      <td>0.371870</td>\n",
       "      <td>0.081088</td>\n",
       "      <td>0.506484</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>AD</td>\n",
       "      <td>AL</td>\n",
       "      <td>0.002674</td>\n",
       "      <td>0.998614</td>\n",
       "      <td>0.998062</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.999967</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.158682</td>\n",
       "      <td>0.203463</td>\n",
       "      <td>0.211969</td>\n",
       "      <td>0.104971</td>\n",
       "      <td>0.221430</td>\n",
       "      <td>0.672669</td>\n",
       "      <td>0.115245</td>\n",
       "      <td>0.234657</td>\n",
       "      <td>0.088875</td>\n",
       "      <td>0.511526</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27490</th>\n",
       "      <td>YT</td>\n",
       "      <td>ZM</td>\n",
       "      <td>0.078120</td>\n",
       "      <td>0.078460</td>\n",
       "      <td>0.078460</td>\n",
       "      <td>0.078427</td>\n",
       "      <td>0.078427</td>\n",
       "      <td>0.078427</td>\n",
       "      <td>0.078427</td>\n",
       "      <td>0.078427</td>\n",
       "      <td>...</td>\n",
       "      <td>0.314180</td>\n",
       "      <td>0.264914</td>\n",
       "      <td>0.104575</td>\n",
       "      <td>0.053099</td>\n",
       "      <td>0.202428</td>\n",
       "      <td>0.674473</td>\n",
       "      <td>0.142165</td>\n",
       "      <td>0.317044</td>\n",
       "      <td>0.112804</td>\n",
       "      <td>0.425856</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27491</th>\n",
       "      <td>YT</td>\n",
       "      <td>ZW</td>\n",
       "      <td>0.078103</td>\n",
       "      <td>0.078497</td>\n",
       "      <td>0.078497</td>\n",
       "      <td>0.078497</td>\n",
       "      <td>0.078497</td>\n",
       "      <td>0.078497</td>\n",
       "      <td>0.078497</td>\n",
       "      <td>0.078497</td>\n",
       "      <td>...</td>\n",
       "      <td>0.342396</td>\n",
       "      <td>0.293738</td>\n",
       "      <td>0.078400</td>\n",
       "      <td>0.051409</td>\n",
       "      <td>0.185660</td>\n",
       "      <td>0.752413</td>\n",
       "      <td>0.130497</td>\n",
       "      <td>0.398470</td>\n",
       "      <td>0.089990</td>\n",
       "      <td>0.391816</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27492</th>\n",
       "      <td>ZA</td>\n",
       "      <td>ZM</td>\n",
       "      <td>0.042589</td>\n",
       "      <td>0.040391</td>\n",
       "      <td>0.040391</td>\n",
       "      <td>0.021715</td>\n",
       "      <td>0.021725</td>\n",
       "      <td>0.021725</td>\n",
       "      <td>0.021725</td>\n",
       "      <td>0.021725</td>\n",
       "      <td>...</td>\n",
       "      <td>0.131968</td>\n",
       "      <td>0.114329</td>\n",
       "      <td>0.076315</td>\n",
       "      <td>0.018861</td>\n",
       "      <td>0.104667</td>\n",
       "      <td>0.293089</td>\n",
       "      <td>0.065884</td>\n",
       "      <td>0.149984</td>\n",
       "      <td>0.051544</td>\n",
       "      <td>0.296675</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27493</th>\n",
       "      <td>ZA</td>\n",
       "      <td>ZW</td>\n",
       "      <td>0.042107</td>\n",
       "      <td>0.039633</td>\n",
       "      <td>0.039633</td>\n",
       "      <td>0.021641</td>\n",
       "      <td>0.021641</td>\n",
       "      <td>0.021641</td>\n",
       "      <td>0.021641</td>\n",
       "      <td>0.021641</td>\n",
       "      <td>...</td>\n",
       "      <td>0.115236</td>\n",
       "      <td>0.112350</td>\n",
       "      <td>0.056001</td>\n",
       "      <td>0.023694</td>\n",
       "      <td>0.100517</td>\n",
       "      <td>0.430028</td>\n",
       "      <td>0.076627</td>\n",
       "      <td>0.208669</td>\n",
       "      <td>0.043190</td>\n",
       "      <td>0.263977</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27494</th>\n",
       "      <td>ZM</td>\n",
       "      <td>ZW</td>\n",
       "      <td>0.000001</td>\n",
       "      <td>0.000004</td>\n",
       "      <td>0.000004</td>\n",
       "      <td>0.000028</td>\n",
       "      <td>0.000028</td>\n",
       "      <td>0.000028</td>\n",
       "      <td>0.000028</td>\n",
       "      <td>0.000028</td>\n",
       "      <td>...</td>\n",
       "      <td>0.141001</td>\n",
       "      <td>0.092225</td>\n",
       "      <td>0.048161</td>\n",
       "      <td>0.022689</td>\n",
       "      <td>0.085157</td>\n",
       "      <td>0.248501</td>\n",
       "      <td>0.055595</td>\n",
       "      <td>0.109604</td>\n",
       "      <td>0.023119</td>\n",
       "      <td>0.239920</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>27495 rows × 61 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      ISO_CODE_1 ISO_CODE_2  CosDist1  CosDist2  CosDist3  CosDist4  CosDist5  CosDist6  CosDist7  CosDist8  ...  FBDist_FoodDrink  FBDist_HobbiesActivities  \\\n",
       "0             AD         AE  0.649726  1.000000  1.000000  1.000000  1.000000  1.000000  1.000000  1.000000  ...          0.178210                  0.256747   \n",
       "1             AD         AF  0.027777  1.000000  1.000000  1.000000  1.000000  1.000000  1.000000  1.000000  ...          0.294734                  0.298884   \n",
       "2             AD         AG  0.298230  1.000000  1.000000  1.000000  1.000000  1.000000  1.000000  1.000000  ...          0.251972                  0.258350   \n",
       "3             AD         AI  0.917672  1.000000  1.000000  1.000000  1.000000  1.000000  1.000000  1.000000  ...          0.261493                  0.279948   \n",
       "4             AD         AL  0.002674  0.998614  0.998062  1.000000  0.999967  1.000000  1.000000  1.000000  ...          0.158682                  0.203463   \n",
       "...          ...        ...       ...       ...       ...       ...       ...       ...       ...       ...  ...               ...                       ...   \n",
       "27490         YT         ZM  0.078120  0.078460  0.078460  0.078427  0.078427  0.078427  0.078427  0.078427  ...          0.314180                  0.264914   \n",
       "27491         YT         ZW  0.078103  0.078497  0.078497  0.078497  0.078497  0.078497  0.078497  0.078497  ...          0.342396                  0.293738   \n",
       "27492         ZA         ZM  0.042589  0.040391  0.040391  0.021715  0.021725  0.021725  0.021725  0.021725  ...          0.131968                  0.114329   \n",
       "27493         ZA         ZW  0.042107  0.039633  0.039633  0.021641  0.021641  0.021641  0.021641  0.021641  ...          0.115236                  0.112350   \n",
       "27494         ZM         ZW  0.000001  0.000004  0.000004  0.000028  0.000028  0.000028  0.000028  0.000028  ...          0.141001                  0.092225   \n",
       "\n",
       "       FBDist_LifestyleCulture  FBDist_NewsEntertainment  FBDist_NonLocalBus  FBDist_People  FBDist_ShoppingFashion FBDist_SportsOutdoors  FBDist_Technology  \\\n",
       "0                     0.186337                  0.083852            0.245167       0.733101                0.133534              0.283705           0.099948   \n",
       "1                     0.272084                  0.124117            0.291968       0.832636                0.165568              0.377505           0.117173   \n",
       "2                     0.154459                  0.099079            0.234904       0.680631                0.143881              0.376967           0.085136   \n",
       "3                     0.195226                  0.153596            0.263495       0.651478                0.164097              0.371870           0.081088   \n",
       "4                     0.211969                  0.104971            0.221430       0.672669                0.115245              0.234657           0.088875   \n",
       "...                        ...                       ...                 ...            ...                     ...                   ...                ...   \n",
       "27490                 0.104575                  0.053099            0.202428       0.674473                0.142165              0.317044           0.112804   \n",
       "27491                 0.078400                  0.051409            0.185660       0.752413                0.130497              0.398470           0.089990   \n",
       "27492                 0.076315                  0.018861            0.104667       0.293089                0.065884              0.149984           0.051544   \n",
       "27493                 0.056001                  0.023694            0.100517       0.430028                0.076627              0.208669           0.043190   \n",
       "27494                 0.048161                  0.022689            0.085157       0.248501                0.055595              0.109604           0.023119   \n",
       "\n",
       "       FBDist_TravelPlacesEvents  \n",
       "0                       0.519951  \n",
       "1                       0.531510  \n",
       "2                       0.504606  \n",
       "3                       0.506484  \n",
       "4                       0.511526  \n",
       "...                          ...  \n",
       "27490                   0.425856  \n",
       "27491                   0.391816  \n",
       "27492                   0.296675  \n",
       "27493                   0.263977  \n",
       "27494                   0.239920  \n",
       "\n",
       "[27495 rows x 61 columns]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mypairs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "8cd21871-4b10-4af5-910e-7c0d4f1b53e7",
   "metadata": {},
   "outputs": [],
   "source": [
    "mypairs['Origin Country'] = mypairs.ISO_CODE_1.apply(mapper4)\n",
    "mypairs['Destination Country'] = mypairs.ISO_CODE_2.apply(mapper4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "91caaa20-e1bf-4e4b-a882-2c9ad889f41e",
   "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>Origin Country</th>\n",
       "      <th>Destination Country</th>\n",
       "      <th>ISO_CODE_1</th>\n",
       "      <th>ISO_CODE_2</th>\n",
       "      <th>CosDist1</th>\n",
       "      <th>CosDist2</th>\n",
       "      <th>CosDist3</th>\n",
       "      <th>CosDist4</th>\n",
       "      <th>CosDist5</th>\n",
       "      <th>CosDist6</th>\n",
       "      <th>...</th>\n",
       "      <th>FBDist_FoodDrink</th>\n",
       "      <th>FBDist_HobbiesActivities</th>\n",
       "      <th>FBDist_LifestyleCulture</th>\n",
       "      <th>FBDist_NewsEntertainment</th>\n",
       "      <th>FBDist_NonLocalBus</th>\n",
       "      <th>FBDist_People</th>\n",
       "      <th>FBDist_ShoppingFashion</th>\n",
       "      <th>FBDist_SportsOutdoors</th>\n",
       "      <th>FBDist_Technology</th>\n",
       "      <th>FBDist_TravelPlacesEvents</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Andorra</td>\n",
       "      <td>United Arab Emirates</td>\n",
       "      <td>AD</td>\n",
       "      <td>AE</td>\n",
       "      <td>0.649726</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.178210</td>\n",
       "      <td>0.256747</td>\n",
       "      <td>0.186337</td>\n",
       "      <td>0.083852</td>\n",
       "      <td>0.245167</td>\n",
       "      <td>0.733101</td>\n",
       "      <td>0.133534</td>\n",
       "      <td>0.283705</td>\n",
       "      <td>0.099948</td>\n",
       "      <td>0.519951</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Andorra</td>\n",
       "      <td>Afghanistan</td>\n",
       "      <td>AD</td>\n",
       "      <td>AF</td>\n",
       "      <td>0.027777</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.294734</td>\n",
       "      <td>0.298884</td>\n",
       "      <td>0.272084</td>\n",
       "      <td>0.124117</td>\n",
       "      <td>0.291968</td>\n",
       "      <td>0.832636</td>\n",
       "      <td>0.165568</td>\n",
       "      <td>0.377505</td>\n",
       "      <td>0.117173</td>\n",
       "      <td>0.531510</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Andorra</td>\n",
       "      <td>Antigua and Barbuda</td>\n",
       "      <td>AD</td>\n",
       "      <td>AG</td>\n",
       "      <td>0.298230</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.251972</td>\n",
       "      <td>0.258350</td>\n",
       "      <td>0.154459</td>\n",
       "      <td>0.099079</td>\n",
       "      <td>0.234904</td>\n",
       "      <td>0.680631</td>\n",
       "      <td>0.143881</td>\n",
       "      <td>0.376967</td>\n",
       "      <td>0.085136</td>\n",
       "      <td>0.504606</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Andorra</td>\n",
       "      <td>Anguilla</td>\n",
       "      <td>AD</td>\n",
       "      <td>AI</td>\n",
       "      <td>0.917672</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.261493</td>\n",
       "      <td>0.279948</td>\n",
       "      <td>0.195226</td>\n",
       "      <td>0.153596</td>\n",
       "      <td>0.263495</td>\n",
       "      <td>0.651478</td>\n",
       "      <td>0.164097</td>\n",
       "      <td>0.371870</td>\n",
       "      <td>0.081088</td>\n",
       "      <td>0.506484</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Andorra</td>\n",
       "      <td>Albania</td>\n",
       "      <td>AD</td>\n",
       "      <td>AL</td>\n",
       "      <td>0.002674</td>\n",
       "      <td>0.998614</td>\n",
       "      <td>0.998062</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.999967</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.158682</td>\n",
       "      <td>0.203463</td>\n",
       "      <td>0.211969</td>\n",
       "      <td>0.104971</td>\n",
       "      <td>0.221430</td>\n",
       "      <td>0.672669</td>\n",
       "      <td>0.115245</td>\n",
       "      <td>0.234657</td>\n",
       "      <td>0.088875</td>\n",
       "      <td>0.511526</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 63 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "  Origin Country   Destination Country ISO_CODE_1 ISO_CODE_2  CosDist1  CosDist2  CosDist3  CosDist4  CosDist5  CosDist6  ...  FBDist_FoodDrink  \\\n",
       "0        Andorra  United Arab Emirates         AD         AE  0.649726  1.000000  1.000000       1.0  1.000000       1.0  ...          0.178210   \n",
       "1        Andorra           Afghanistan         AD         AF  0.027777  1.000000  1.000000       1.0  1.000000       1.0  ...          0.294734   \n",
       "2        Andorra   Antigua and Barbuda         AD         AG  0.298230  1.000000  1.000000       1.0  1.000000       1.0  ...          0.251972   \n",
       "3        Andorra              Anguilla         AD         AI  0.917672  1.000000  1.000000       1.0  1.000000       1.0  ...          0.261493   \n",
       "4        Andorra               Albania         AD         AL  0.002674  0.998614  0.998062       1.0  0.999967       1.0  ...          0.158682   \n",
       "\n",
       "   FBDist_HobbiesActivities  FBDist_LifestyleCulture  FBDist_NewsEntertainment  FBDist_NonLocalBus  FBDist_People  FBDist_ShoppingFashion  \\\n",
       "0                  0.256747                 0.186337                  0.083852            0.245167       0.733101                0.133534   \n",
       "1                  0.298884                 0.272084                  0.124117            0.291968       0.832636                0.165568   \n",
       "2                  0.258350                 0.154459                  0.099079            0.234904       0.680631                0.143881   \n",
       "3                  0.279948                 0.195226                  0.153596            0.263495       0.651478                0.164097   \n",
       "4                  0.203463                 0.211969                  0.104971            0.221430       0.672669                0.115245   \n",
       "\n",
       "   FBDist_SportsOutdoors  FBDist_Technology FBDist_TravelPlacesEvents  \n",
       "0               0.283705           0.099948                  0.519951  \n",
       "1               0.377505           0.117173                  0.531510  \n",
       "2               0.376967           0.085136                  0.504606  \n",
       "3               0.371870           0.081088                  0.506484  \n",
       "4               0.234657           0.088875                  0.511526  \n",
       "\n",
       "[5 rows x 63 columns]"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mypairs = mypairs[['Origin Country', 'Destination Country']   mypairs.columns.tolist()[:-2]]\n",
    "mypairs.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "110d35b1-96ba-4a0f-a716-0b566a2d926e",
   "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>Origin Country</th>\n",
       "      <th>Destination Country</th>\n",
       "      <th>ISO_CODE_1</th>\n",
       "      <th>ISO_CODE_2</th>\n",
       "      <th>FBDist</th>\n",
       "      <th>FBDist_BusinessIndustry</th>\n",
       "      <th>FBDist_Education</th>\n",
       "      <th>FBDist_Empty</th>\n",
       "      <th>FBDist_FamilyRelationships</th>\n",
       "      <th>FBDist_FitnessWellness</th>\n",
       "      <th>FBDist_FoodDrink</th>\n",
       "      <th>FBDist_HobbiesActivities</th>\n",
       "      <th>FBDist_LifestyleCulture</th>\n",
       "      <th>FBDist_NewsEntertainment</th>\n",
       "      <th>FBDist_NonLocalBus</th>\n",
       "      <th>FBDist_People</th>\n",
       "      <th>FBDist_ShoppingFashion</th>\n",
       "      <th>FBDist_SportsOutdoors</th>\n",
       "      <th>FBDist_Technology</th>\n",
       "      <th>FBDist_TravelPlacesEvents</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Andorra</td>\n",
       "      <td>United Arab Emirates</td>\n",
       "      <td>AD</td>\n",
       "      <td>AE</td>\n",
       "      <td>0.233552</td>\n",
       "      <td>0.288817</td>\n",
       "      <td>0.189267</td>\n",
       "      <td>0.174565</td>\n",
       "      <td>0.153039</td>\n",
       "      <td>0.132261</td>\n",
       "      <td>0.178210</td>\n",
       "      <td>0.256747</td>\n",
       "      <td>0.186337</td>\n",
       "      <td>0.083852</td>\n",
       "      <td>0.245167</td>\n",
       "      <td>0.733101</td>\n",
       "      <td>0.133534</td>\n",
       "      <td>0.283705</td>\n",
       "      <td>0.099948</td>\n",
       "      <td>0.519951</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Andorra</td>\n",
       "      <td>Afghanistan</td>\n",
       "      <td>AD</td>\n",
       "      <td>AF</td>\n",
       "      <td>0.279233</td>\n",
       "      <td>0.314991</td>\n",
       "      <td>0.340453</td>\n",
       "      <td>0.207937</td>\n",
       "      <td>0.298100</td>\n",
       "      <td>0.226512</td>\n",
       "      <td>0.294734</td>\n",
       "      <td>0.298884</td>\n",
       "      <td>0.272084</td>\n",
       "      <td>0.124117</td>\n",
       "      <td>0.291968</td>\n",
       "      <td>0.832636</td>\n",
       "      <td>0.165568</td>\n",
       "      <td>0.377505</td>\n",
       "      <td>0.117173</td>\n",
       "      <td>0.531510</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Andorra</td>\n",
       "      <td>Antigua and Barbuda</td>\n",
       "      <td>AD</td>\n",
       "      <td>AG</td>\n",
       "      <td>0.227161</td>\n",
       "      <td>0.279893</td>\n",
       "      <td>0.282477</td>\n",
       "      <td>0.154556</td>\n",
       "      <td>0.135234</td>\n",
       "      <td>0.133760</td>\n",
       "      <td>0.251972</td>\n",
       "      <td>0.258350</td>\n",
       "      <td>0.154459</td>\n",
       "      <td>0.099079</td>\n",
       "      <td>0.234904</td>\n",
       "      <td>0.680631</td>\n",
       "      <td>0.143881</td>\n",
       "      <td>0.376967</td>\n",
       "      <td>0.085136</td>\n",
       "      <td>0.504606</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Andorra</td>\n",
       "      <td>Anguilla</td>\n",
       "      <td>AD</td>\n",
       "      <td>AI</td>\n",
       "      <td>0.262021</td>\n",
       "      <td>0.288825</td>\n",
       "      <td>0.347721</td>\n",
       "      <td>0.213974</td>\n",
       "      <td>0.205464</td>\n",
       "      <td>0.188863</td>\n",
       "      <td>0.261493</td>\n",
       "      <td>0.279948</td>\n",
       "      <td>0.195226</td>\n",
       "      <td>0.153596</td>\n",
       "      <td>0.263495</td>\n",
       "      <td>0.651478</td>\n",
       "      <td>0.164097</td>\n",
       "      <td>0.371870</td>\n",
       "      <td>0.081088</td>\n",
       "      <td>0.506484</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Andorra</td>\n",
       "      <td>Albania</td>\n",
       "      <td>AD</td>\n",
       "      <td>AL</td>\n",
       "      <td>0.216498</td>\n",
       "      <td>0.225739</td>\n",
       "      <td>0.192321</td>\n",
       "      <td>0.153686</td>\n",
       "      <td>0.073003</td>\n",
       "      <td>0.129123</td>\n",
       "      <td>0.158682</td>\n",
       "      <td>0.203463</td>\n",
       "      <td>0.211969</td>\n",
       "      <td>0.104971</td>\n",
       "      <td>0.221430</td>\n",
       "      <td>0.672669</td>\n",
       "      <td>0.115245</td>\n",
       "      <td>0.234657</td>\n",
       "      <td>0.088875</td>\n",
       "      <td>0.511526</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Origin Country   Destination Country ISO_CODE_1 ISO_CODE_2    FBDist  FBDist_BusinessIndustry  FBDist_Education  FBDist_Empty  FBDist_FamilyRelationships  \\\n",
       "0        Andorra  United Arab Emirates         AD         AE  0.233552                 0.288817          0.189267      0.174565                    0.153039   \n",
       "1        Andorra           Afghanistan         AD         AF  0.279233                 0.314991          0.340453      0.207937                    0.298100   \n",
       "2        Andorra   Antigua and Barbuda         AD         AG  0.227161                 0.279893          0.282477      0.154556                    0.135234   \n",
       "3        Andorra              Anguilla         AD         AI  0.262021                 0.288825          0.347721      0.213974                    0.205464   \n",
       "4        Andorra               Albania         AD         AL  0.216498                 0.225739          0.192321      0.153686                    0.073003   \n",
       "\n",
       "   FBDist_FitnessWellness  FBDist_FoodDrink  FBDist_HobbiesActivities  FBDist_LifestyleCulture  FBDist_NewsEntertainment  FBDist_NonLocalBus  FBDist_People  \\\n",
       "0                0.132261          0.178210                  0.256747                 0.186337                  0.083852            0.245167       0.733101   \n",
       "1                0.226512          0.294734                  0.298884                 0.272084                  0.124117            0.291968       0.832636   \n",
       "2                0.133760          0.251972                  0.258350                 0.154459                  0.099079            0.234904       0.680631   \n",
       "3                0.188863          0.261493                  0.279948                 0.195226                  0.153596            0.263495       0.651478   \n",
       "4                0.129123          0.158682                  0.203463                 0.211969                  0.104971            0.221430       0.672669   \n",
       "\n",
       "   FBDist_ShoppingFashion  FBDist_SportsOutdoors  FBDist_Technology  FBDist_TravelPlacesEvents  \n",
       "0                0.133534               0.283705           0.099948                   0.519951  \n",
       "1                0.165568               0.377505           0.117173                   0.531510  \n",
       "2                0.143881               0.376967           0.085136                   0.504606  \n",
       "3                0.164097               0.371870           0.081088                   0.506484  \n",
       "4                0.115245               0.234657           0.088875                   0.511526  "
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mypairs[mypairs.columns.tolist()[:4]   [c for c in mypairs.columns if c.startswith('FB')]].head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "24a2b7dc-f1d9-46b7-b67e-294d7ae8b728",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(55225, 69)"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "88d7ba26-d63b-4081-96c4-38b87922d40b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(27495, 63)"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mypairs.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "d8428b3a-5437-4773-a3d7-b8b6615be0a1",
   "metadata": {},
   "outputs": [],
   "source": [
    "df['same'] = (df.ISO_CODE_1==df.ISO_CODE_2).astype(int)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "686efc21-6cd3-49ec-93d9-4b258c0aab65",
   "metadata": {},
   "outputs": [],
   "source": [
    "df['Origin Country'] = df.ISO_CODE_1.apply(mapper4)\n",
    "df['Destination Country'] = df.ISO_CODE_2.apply(mapper4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "0f083922-4350-416b-827f-b04d2b55e8a9",
   "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>Origin Country</th>\n",
       "      <th>Destination Country</th>\n",
       "      <th>ISO_CODE_1</th>\n",
       "      <th>ISO_CODE_2</th>\n",
       "      <th>CosDist1</th>\n",
       "      <th>CosDist2</th>\n",
       "      <th>CosDist3</th>\n",
       "      <th>CosDist4</th>\n",
       "      <th>CosDist5</th>\n",
       "      <th>CosDist6</th>\n",
       "      <th>...</th>\n",
       "      <th>FBDist_HobbiesActivities</th>\n",
       "      <th>FBDist_LifestyleCulture</th>\n",
       "      <th>FBDist_NewsEntertainment</th>\n",
       "      <th>FBDist_NonLocalBus</th>\n",
       "      <th>FBDist_People</th>\n",
       "      <th>FBDist_ShoppingFashion</th>\n",
       "      <th>FBDist_SportsOutdoors</th>\n",
       "      <th>FBDist_Technology</th>\n",
       "      <th>FBDist_TravelPlacesEvents</th>\n",
       "      <th>same</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Andorra</td>\n",
       "      <td>Andorra</td>\n",
       "      <td>AD</td>\n",
       "      <td>AD</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Andorra</td>\n",
       "      <td>United Arab Emirates</td>\n",
       "      <td>AD</td>\n",
       "      <td>AE</td>\n",
       "      <td>0.649726</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.256747</td>\n",
       "      <td>0.186337</td>\n",
       "      <td>0.083852</td>\n",
       "      <td>0.245167</td>\n",
       "      <td>0.733101</td>\n",
       "      <td>0.133534</td>\n",
       "      <td>0.283705</td>\n",
       "      <td>0.099948</td>\n",
       "      <td>0.519951</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Andorra</td>\n",
       "      <td>Afghanistan</td>\n",
       "      <td>AD</td>\n",
       "      <td>AF</td>\n",
       "      <td>0.027777</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.298884</td>\n",
       "      <td>0.272084</td>\n",
       "      <td>0.124117</td>\n",
       "      <td>0.291968</td>\n",
       "      <td>0.832636</td>\n",
       "      <td>0.165568</td>\n",
       "      <td>0.377505</td>\n",
       "      <td>0.117173</td>\n",
       "      <td>0.531510</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Andorra</td>\n",
       "      <td>Antigua and Barbuda</td>\n",
       "      <td>AD</td>\n",
       "      <td>AG</td>\n",
       "      <td>0.298230</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.258350</td>\n",
       "      <td>0.154459</td>\n",
       "      <td>0.099079</td>\n",
       "      <td>0.234904</td>\n",
       "      <td>0.680631</td>\n",
       "      <td>0.143881</td>\n",
       "      <td>0.376967</td>\n",
       "      <td>0.085136</td>\n",
       "      <td>0.504606</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Andorra</td>\n",
       "      <td>Anguilla</td>\n",
       "      <td>AD</td>\n",
       "      <td>AI</td>\n",
       "      <td>0.917672</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.279948</td>\n",
       "      <td>0.195226</td>\n",
       "      <td>0.153596</td>\n",
       "      <td>0.263495</td>\n",
       "      <td>0.651478</td>\n",
       "      <td>0.164097</td>\n",
       "      <td>0.371870</td>\n",
       "      <td>0.081088</td>\n",
       "      <td>0.506484</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 72 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "  Origin Country   Destination Country ISO_CODE_1 ISO_CODE_2  CosDist1  CosDist2  CosDist3  CosDist4  CosDist5  CosDist6  ...  FBDist_HobbiesActivities  \\\n",
       "0        Andorra               Andorra         AD         AD  0.000000       0.0       0.0       0.0       0.0       0.0  ...                  0.000000   \n",
       "1        Andorra  United Arab Emirates         AD         AE  0.649726       1.0       1.0       1.0       1.0       1.0  ...                  0.256747   \n",
       "2        Andorra           Afghanistan         AD         AF  0.027777       1.0       1.0       1.0       1.0       1.0  ...                  0.298884   \n",
       "3        Andorra   Antigua and Barbuda         AD         AG  0.298230       1.0       1.0       1.0       1.0       1.0  ...                  0.258350   \n",
       "4        Andorra              Anguilla         AD         AI  0.917672       1.0       1.0       1.0       1.0       1.0  ...                  0.279948   \n",
       "\n",
       "   FBDist_LifestyleCulture  FBDist_NewsEntertainment  FBDist_NonLocalBus  FBDist_People  FBDist_ShoppingFashion  FBDist_SportsOutdoors  FBDist_Technology  \\\n",
       "0                 0.000000                  0.000000            0.000000       0.000000                0.000000               0.000000           0.000000   \n",
       "1                 0.186337                  0.083852            0.245167       0.733101                0.133534               0.283705           0.099948   \n",
       "2                 0.272084                  0.124117            0.291968       0.832636                0.165568               0.377505           0.117173   \n",
       "3                 0.154459                  0.099079            0.234904       0.680631                0.143881               0.376967           0.085136   \n",
       "4                 0.195226                  0.153596            0.263495       0.651478                0.164097               0.371870           0.081088   \n",
       "\n",
       "   FBDist_TravelPlacesEvents same  \n",
       "0                   0.000000    1  \n",
       "1                   0.519951    0  \n",
       "2                   0.531510    0  \n",
       "3                   0.504606    0  \n",
       "4                   0.506484    0  \n",
       "\n",
       "[5 rows x 72 columns]"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = df[['Origin Country', 'Destination Country']   df.columns.tolist()[:-2]]\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "e402bb5b-22a1-40ae-a21c-a5e6c15f8a2f",
   "metadata": {},
   "outputs": [],
   "source": [
    "df.set_index(df.columns.tolist()[:1], inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "8c163787-ee83-4242-a1d3-7df34b3e7e1b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Origin Country\n",
       "Afghanistan          0.251204\n",
       "Albania              0.229590\n",
       "Algeria              0.203205\n",
       "American Samoa       0.270945\n",
       "Andorra              0.244827\n",
       "                       ...   \n",
       "Vietnam              0.300195\n",
       "Wallis and Futuna    0.500607\n",
       "Yemen                0.228066\n",
       "Zambia               0.205705\n",
       "Zimbabwe             0.212998\n",
       "Name: FBDist, Length: 235, dtype: float64"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.groupby(level=0).FBDist.mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "4d80a96c-9ef6-413d-bdcd-ba362662887c",
   "metadata": {},
   "outputs": [],
   "source": [
    "df['FBDist_mean'] = df.groupby(level=0).FBDist.mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "64abb444-c3d9-44e5-a137-e902d9226c46",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[<AxesSubplot:title={'center':'FBDist_mean'}>]], dtype=object)"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYQAAAEICAYAAABfz4NwAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjQuMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/MnkTPAAAACXBIWXMAAAsTAAALEwEAmpwYAAAaoklEQVR4nO3de5Cd9X3f8ffHyMWKCReDvaWIWKSomQCKcVEIjpt2HdwiOxdwC4lcxkBMRw6DO8lUbS2SNnGGqsHtEBImAVcJGS5JLKskGGIgiQvZOo65WGSwhcDEqlFAQKGYi1nXUFb 9o/z2/hoOdo9e/Zyds37NfPMec73eX7P f32SPs5z U8m6pCkqTXDbsDkqSlwUCQJAEGgiSpMRAkSYCBIElqDARJEmAgSJIaA0HqIcnHk/zHYfdDWkwGgpatJHuSfDPJeNf0w0mq6/lTSa5K8voe7V5M8nySzyf52SR/ / hqn62qi7tsw/vXqgxSovJQNBy9xNVdcjkBDzR6oe352uBdwAX92j33cBbgcuAjwDXLFanpaXIQNB3tKp6GvgMcMIBlr9QVbcAPw2cn QkgCTXJvlPbf6oJJ9uexPPJvmLJK9LcgPwPcAft72Rf3 gfiRZ3fZcfibJY0mea3slP5jkS23bvzmlzQeTPNTW/dMkb 1a9httO19Pcl SH la9tEk25Nc3/aCdiVZN/hPUa8VBoK oyX5e8AZwN3TrVdV9wJ7gR/psXhTW/ZmYAT4hU6T gDwKN/eS/kvfXTph4A1dALo14FfBN4NnAj8VJJ/0vp9Vnudf95e9y AT3Rt5wvAycCbgD8A/nuSN3Qt/0lgG3A4cAuwX9hIvRgIWu4 1T5dP5/kU131Z5I8DzwOfAO4sY9tPUHnF xUrwBHA2 tqleq6i9q8LtCXlpVL1XVn7V faKqnq6qx n80n97W 9DwK9W1UNVNQH8Z Dkyb2Eqvq9qvpaVU1U1eXAwcD3db3O56rqtqraB9wAvG3A/uo1xEDQcndWVR3eprO66kdV1eHAdwF/CfxJH9s6Bni2R/2/AruBP0vy1SSb59Dfp7rmv9nj SFt/q3Ab0yGXetXWh9JsqkdTnqhLT8MOKprW/ 7a/7/Am9IsmIO/dZrgIGg72hV9U3gWuAdSY460HpJfpDOL9vP9djGi1W1qaq F/gJ4N8kOX1y8fz3GoDHgA91hd3hVbWyqj7fzhd8BPgp4IgWfC/QCQxpYAaCvqMlORj4AJ1PzF/rsfzQJD9O53j771XVzh7r/HiS45ME Dqwr03Q YT/vQvQ9Y8DlyQ5sfXhsCTntGXfDUwA/wdYkeSXgEMXoA96jTEQ9J3q STjdH5hvwP4ySnH/f84yYt0Pon/IvBrwM8cYFtrgP8BjAN3AVdV1Vhb9qvAf2iHdv7tfHW qm4CPgZsS/J14AHgPW3xnwK3A38N/A3wUhuHNCfxL6ZJksA9BElSYyBI8yTJuVNuozE57Rp236R eMhIkgTAsr0u aijjqrVq1cv2ut94xvf4I1vfOOivd5icmzLk2NbnoY9tvvuu  Zqnpzr2XLNhBWr17Njh07Fu31xsbGGB0dXbTXW0yObXlybMvTsMeW5G8OtMxzCJIkwECQJDUGgiQJMBAkSY2BIEkCDARJUmMgSJIAA0GS1BgIkiRgGX9TeS5Wb7511m02rZ3gggHaTbXnsh b8zYkaSHMuIeQ5A1J7k3yxSS7kvxKq380yeNJ7m/Te7vaXJJkd5KHk5zRVT8lyc627Mr2F6hIcnCST7b6PUlWL8BYJUnT6OeQ0cvAj1bV24CTgfVJTmvLrqiqk9t0G0CSE4ANwInAeuCqJAe19a8GNtL5C1Rr2nKAC4Hnqup44Ao6fylKkrSIZgyE6hhvT1/fpunumX0msK2qXq6qR4DdwKlJjgYOraq72p8yvB44q6vNdW3 RuD0yb0HSdLi6OscQvuEfx9wPPBbVXVPkvcAH05yHrAD2FRVzwHHAHd3Nd/baq 0 al12uNjAFU1keQF4EjgmSn92EhnD4ORkRHGxsb6H2mXTWsnZt1mZOVg7aYatM8LaXx8fEn2az44tuXJsQ1HX4FQVfuAk5McDtyU5CQ6h38upbO3cClwOfBBoNcn 5qmzgzLuvuxFdgKsG7duhr0FrKDnBzetHaCy3fO/Rz8nnNH57yN Tbs2/EuJMe2PDm24ZjVZadV9TwwBqyvqqeqal9VfQv4beDUttpe4NiuZquAJ1p9VY/6fm2SrAAOA56dTd8kSXPTz1VGb257BiRZCbwb HI7JzDpfcADbf4WYEO7cug4OieP762qJ4EXk5zWzg cB9zc1eb8Nn82cGf5tz0laVH1cwzkaOC6dh7hdcD2qvp0khuSnEzn0M4e4EMAVbUryXbgQWACuLgdcgK4CLgWWAnc3iaAa4Abkuyms2ewYe5DkyTNxoyBUFVfAt7eo/6BadpsAbb0qO8ATupRfwk4Z6a SJIWjreukCQBBoIkqTEQJEmAgSBJagwESRJgIEiSGgNBkgQYCJKkxkCQJAEGgiSpMRAkSYCBIElqDARJEmAgSJIaA0GSBBgIkqTGQJAkAQaCJKkxECRJgIEgSWpmDIQkb0hyb5IvJtmV5Fda/U1JPpPkK 3xiK42lyTZneThJGd01U9JsrMtuzJJWv3gJJ9s9XuSrF6AsUqSptHPHsLLwI9W1duAk4H1SU4DNgN3VNUa4I72nCQnABuAE4H1wFVJDmrbuhrYCKxp0/pWvxB4rqqOB64APjb3oUmSZmPGQKiO8fb09W0q4Ezgula/DjirzZ8JbKuql6vqEWA3cGqSo4FDq quqirg iltJrd1I3D65N6DJGlxrOhnpfYJ/z7geOC3quqeJCNV9SRAVT2Z5C1t9WOAu7ua7221V9r81Ppkm8fatiaSvAAcCTwzpR8b6exhMDIywtjYWJ/D3N mtROzbjOycrB2Uw3a54U0Pj6 JPs1Hxzb8uTYhqOvQKiqfcDJSQ4Hbkpy0jSr9/pkX9PUp2sztR9bga0A69atq9HR0Wm6cWAXbL511m02rZ3g8p19/bimtefc0TlvY76NjY0x6M9yqXNsy5NjG45ZXWVUVc8DY3SO/T/VDgPRHp9uq 0Fju1qtgp4otVX9ajv1ybJCuAw4NnZ9E2SNDf9XGX05rZnQJKVwLuBLwO3AOe31c4Hbm7ztwAb2pVDx9E5eXxvO7z0YpLT2vmB86a0mdzW2cCd7TyDJGmR9HMM5GjgunYe4XXA9qr6dJK7gO1JLgQeBc4BqKpdSbYDDwITwMXtkBPARcC1wErg9jYBXAPckGQ3nT2DDfMxOElS/2YMhKr6EvD2HvWvAacfoM0WYEuP g7gVecfquolWqBIkobDbypLkgADQZLUGAiSJMBAkCQ1BoIkCTAQJEmNgSBJAgwESVJjIEiSAANBktQYCJIkwECQJDUGgiQJMBAkSY2BIEkCDARJUmMgSJIAA0GS1BgIkiTAQJAkNTMGQpJjk/x5koeS7Eryc63 0SSPJ7m/Te/tanNJkt1JHk5yRlf9lCQ727Irk6TVD07yyVa/J8nqBRirJGka/ewhTACbqur7gdOAi5Oc0JZdUVUnt k2gLZsA3AisB64KslBbf2rgY3Amjatb/ULgeeq6njgCuBjcx aJGk2ZgyEqnqyqv6qzb8IPAQcM02TM4FtVfVyVT0C7AZOTXI0cGhV3VVVBVwPnNXV5ro2fyNw uTegyRpcayYzcrtUM7bgXuAdwIfTnIesIPOXsRzdMLi7q5me1vtlTY/tU57fAygqiaSvAAcCTwz5fU30tnDYGRkhLGxsdl0/29tWjsx6zYjKwdrN9WgfV5I4 PjS7Jf88GxLU ObTj6DoQkhwB/CPx8VX09ydXApUC1x8uBDwK9PtnXNHVmWPbtQtVWYCvAunXranR0tN/u7 eCzbfOus2mtRNcvnNW dnTnnNH57yN TY2NsagP8ulzrEtT45tOPq6yijJ6 mEwe9X1R8BVNVTVbWvqr4F/DZwalt9L3BsV/NVwBOtvqpHfb82SVYAhwHPDjIgSdJg rnKKMA1wENV9Wtd9aO7Vnsf8ECbvwXY0K4cOo7OyeN7q pJ4MUkp7Vtngfc3NXm/DZ/NnBnO88gSVok/RwDeSfwAWBnkvtb7ReA9yc5mc6hnT3AhwCqaleS7cCDdK5Quriq9rV2FwHXAiuB29sEncC5IcluOnsGG YyKEnS7M0YCFX1OXof479tmjZbgC096juAk3rUXwLOmakvkqSF4zeVJUmAgSBJagwESRJgIEiSGgNBkgQYCJKkxkCQJAEGgiSpMRAkSYCBIElqDARJEmAgSJIaA0GSBBgIkqTGQJAkAQaCJKkxECRJgIEgSWoMBEkSYCBIkpoZAyHJsUn PMlDSXYl blWf1OSzyT5Sns8oqvNJUl2J3k4yRld9VOS7GzLrkySVj84ySdb/Z4kqxdgrJKkafSzhzABbKqq7wdOAy5OcgKwGbijqtYAd7TntGUbgBOB9cBVSQ5q27oa2AisadP6Vr8QeK6qjgeuAD42D2OTJM3CjIFQVU9W1V 1 ReBh4BjgDOB69pq1wFntfkzgW1V9XJVPQLsBk5NcjRwaFXdVVUFXD lzeS2bgROn9x7kCQtjhWzWbkdynk7cA8wUlVPQic0krylrXYMcHdXs72t9kqbn1qfbPNY29ZEkheAI4Fnprz Rjp7GIyMjDA2Njab7v tTWsnZt1mZOVg7aYatM8LaXx8fEn2az44tuXJsQ1H34GQ5BDgD4Gfr6qvT/MBvteCmqY XZv9C1Vbga0A69atq9HR0Rl63dsFm2 ddZtNaye4fOes8rOnPeeOznkb821sbIxBf5ZLnWNbnhzbcPR1lVGS19MJg9 vqj9q5afaYSDa49Otvhc4tqv5KuCJVl/Vo75fmyQrgMOAZ2c7GEnS4Pq5yijANcBDVfVrXYtuAc5v8 cDN3fVN7Qrh46jc/L43nZ46cUkp7VtnjelzeS2zgbubOcZJEmLpJ9jIO8EPgDsTHJ/q/0CcBmwPcmFwKPAOQBVtSvJduBBOlcoXVxV 1q7i4BrgZXA7W2CTuDckGQ3nT2DDXMbliRptmYMhKr6HL2P8QOcfoA2W4AtPeo7gJN61F iBYokaTj8prIkCTAQJEmNgSBJAgwESVJjIEiSAANBktQYCJIkwECQJDUGgiQJMBAkSY2BIEkCDARJUmMgSJIAA0GS1BgIkiTAQJAkNQaCJAkwECRJjYEgSQIMBElSM2MgJPndJE8neaCr9tEkjye5v03v7Vp2SZLdSR5OckZX/ZQkO9uyK5Ok1Q9O8slWvyfJ6nkeoySpD/3sIVwLrO9Rv6KqTm7TbQBJTgA2ACe2NlclOaitfzWwEVjTpsltXgg8V1XHA1cAHxtwLJKkOZgxEKrqs8CzfW7vTGBbVb1cVY8Au4FTkxwNHFpVd1VVAdcDZ3W1ua7N3wicPrn3IElaPCvm0PbDSc4DdgCbquo54Bjg7q519rbaK21 ap32 BhAVU0keQE4Enhm6gsm2UhnL4ORkRHGxsYG6vimtROzbjOycrB2Uw3a54U0Pj6 JPs1Hxzb8uTYhmPQQLgauBSo9ng58EGg1yf7mqbODMv2L1ZtBbYCrFu3rkZHR2fV6UkXbL511m02rZ3g8p1zyc OPeeOznkb821sbIxBf5ZLnWNbnhzbcAx0lVFVPVVV 6rqW8BvA6e2RXuBY7tWXQU80eqretT3a5NkBXAY/R ikiTNk4ECoZ0TmPQ YPIKpFuADe3KoePonDy t6qeBF5Mclo7P3AecHNXm/Pb/NnAne08gyRpEc14DCTJJ4BR4Kgke4FfBkaTnEzn0M4e4EMAVbUryXbgQWACuLiq9rVNXUTniqWVwO1tArgGuCHJbjp7BhvmYVySpFmaMRCq6v09ytdMs/4WYEuP g7gpB71l4BzZuqHJGlh U1lSRJgIEiSGgNBkgQYCJKkxkCQJAEGgiSpMRAkSYCBIElqDARJEmAgSJIaA0GSBBgIkqTGQJAkAQaCJKkxECRJgIEgSWoMBEkS0MdfTNP8Wr351qG87p7Lfmworytp XAPQZIEGAiSpGbGQEjyu0meTvJAV 1NST6T5Cvt8YiuZZck2Z3k4SRndNVPSbKzLbsySVr94CSfbPV7kqye5zFKkvrQzx7CtcD6KbXNwB1VtQa4oz0nyQnABuDE1uaqJAe1NlcDG4E1bZrc5oXAc1V1PHAF8LFBByNJGtyMgVBVnwWenVI E7iuzV8HnNVV31ZVL1fVI8Bu4NQkRwOHVtVdVVXA9VPaTG7rRuD0yb0HSdLiGfQqo5GqehKgqp5M8pZWPwa4u2u9va32SpufWp9s81jb1kSSF4AjgWemvmiSjXT2MhgZGWFsbGygzm9aOzHrNiMrB2u3VEz3sxofHx/4Z7nUObblybENx3xfdtrrk31NU5 uzauLVVuBrQDr1q2r0dHRAboIFwxw6eemtRNcvnP5XqW759zRAy4bGxtj0J/lUufYlifHNhyDXmX0VDsMRHt8utX3Asd2rbcKeKLVV/Wo79cmyQrgMF59iEqStMAGDYRbgPPb/PnAzV31De3KoePonDy tx1eejHJae38wHlT2kxu62zgznaeQZK0iGY8BpLkE8AocFSSvcAvA5cB25NcCDwKnANQVbuSbAceBCaAi6tqX9vURXSuWFoJ3N4mgGuAG5LsprNnsGFeRiZJmpUZA6Gq3n ARacfYP0twJYe9R3AST3qL9ECRZI0PH5TWZIEGAiSpMZAkCQBBoIkqTEQJEmAgSBJagwESRJgIEiSGgNBkgQYCJKkxkCQJAEGgiSpMRAkSYCBIElqDARJEmAgSJIaA0GSBBgIkqTGQJAkAQaCJKmZUyAk2ZNkZ5L7k xotTcl UySr7THI7rWvyTJ7iQPJzmjq35K287uJFcmyVz6JUmavfnYQ3hXVZ1cVeva883AHVW1BrijPSfJCcAG4ERgPXBVkoNam6uBjcCaNq2fh35JkmZhIQ4ZnQlc1 avA87qqm rqper6hFgN3BqkqOBQ6vqrqoq4PquNpKkRZLO7 ABGyePAM8BBfy3qtqa5PmqOrxrneeq6ogkvwncXVW/1 rXALcDe4DLqurdrf4jwEeq6sd7vN5GOnsSjIyMnLJt27aB r3z8Rdm3WZkJTz1zYFebklYe8xhB1w2Pj7OIYccsoi9WTyObXlybAvnXe96131dR3T2s2KO235nVT2R5C3AZ5J8eZp1e50XqGnqry5WbQW2Aqxbt65GR0dn2d2OCzbfOus2m9ZOcPnOuf64hmfPuaMHXDY2NsagP8ulzrEtT45tOOZ0yKiqnmiPTwM3AacCT7XDQLTHp9vqe4Fju5qvAp5o9VU96pKkRTRwICR5Y5LvnpwH/hnwAHALcH5b7Xzg5jZ/C7AhycFJjqNz8vjeqnoSeDHJae3qovO62kiSFslcjoGMADe1K0RXAH9QVX S5AvA9iQXAo8C5wBU1a4k24EHgQng4qra17Z1EXAtsJLOeYXb59AvSdIABg6Eqvoq8LYe9a8Bpx gzRZgS4/6DuCkQfsiSZo7v6ksSQIMBElSYyBIkgADQZLUGAiSJMBAkCQ1y/deDJqV1dPcrmPT2omBbufRrz2X/diCbVvS/HEPQZIEGAiSpMZAkCQBBoIkqTEQJEmAgSBJagwESRJgIEiSGgNBkgQYCJKkxltXaMFNd9uMhTSsW2Ys1nh73XLE24RoLtxDkCQBBoIkqVkyh4ySrAd AzgI J2qumzIXZKWnWEdnptvs7kDr4fJ5s SCIQkBwG/BfxTYC/whSS3VNWDw 2ZlrPVm29d8Ft767Vr0PCdj3 TCxWCS WQ0anA7qr6alX9P2AbcOaQ yRJrympqmH3gSRnA ur6l 15x8AfqiqPjxlvY3Axvb0 4CHF7GbRwHPLOLrLSbHtjw5tuVp2GN7a1W9udeCJXHICEiP2quSqqq2AlsXvjuvlmRHVa0bxmsvNMe2PDm25Wkpj22pHDLaCxzb9XwV8MSQ iJJr0lLJRC AKxJclySvwNsAG4Zcp8k6TVlSRwyqqqJJB8G/pTOZae/W1W7htytqYZyqGqROLblybEtT0t2bEvipLIkafiWyiEjSdKQGQiSJMBAeJUk65M8nGR3ks09lp b5Ett nyStw2jn4PoY2xntnHdn2RHkn80jH4OYqaxda33g0n2te  LAt9vG jSV5o79v9SX5pGP2crX7esza2 5PsSvI/F7uPg rjPft3Xe/XA 3f5JuG0df9VJVTm ic0P5fwPcCfwf4InDClHV GDiizb8HuGfY/Z7HsR3Ct88r/QDw5WH3e77G1rXencBtwNnD7vc8vm jwKeH3dcFGNfhwIPA97Tnbxl2v drbFPW/wngzmH3u6rcQ5hixltoVNXnq q59vRuOt ZWA76Gdt4tX hwBvp8eXAJarfW5/8a APgacXs3Nz9J16W5d xvUvgT qqkcBqmq5vG zfc/eD3xiUXo2AwNhf8cAj3U939tqB3IhcPuC9mj 9DW2JO9L8mXgVuCDi9S3uZpxbEmOAd4HfHwR zUf v03 Y4kX0xye5ITF6drc9LPuP4BcESSsST3JTlv0Xo3N33/HknyXcB6Oh9Uhm5JfA9hCenrFhoASd5FJxCWy3H2fm8PchNwU5J/DFwKvHuhOzYP hnbrwMfqap9Sa/Vl6x xvZXdO5PM57kvcCngDUL3bE56mdcK4BTgNOBlcBdSe6uqr9e6M7NUd /R gcLvrLqnp2AfvTNwNhf33dQiPJDwC/A7ynqr62SH2bq1ndHqSqPpvk7yc5qqqW k3G hnbOmBbC4OjgPcmmaiqTy1KDwc349iq6utd87cluWoZvG/9vGd7gWeq6hvAN5J8FngbsNQDYTb/1zawRA4XAZ5U7p7oBORXgeP49smgE6es8z3AbuCHh93fBRjb8Xz7pPI/BB6ffL6Up37GNmX9a1k J5X7ed/ btf7dirw6FJ/3/oc1/cDd7R1vwt4ADhp2H2fj7G19Q4DngXeOOw T07uIXSpA9xCI8nPtuUfB34JOBK4qn3anKgleufCbn2O7V8A5yV5Bfgm8NPV/uUuZX2ObVnqc2xnAxclmaDzvm1Y6u9bP OqqoeS/AnwJeBbdP6S4gPD63V/ZvHv8X3An1VnD2hJ8NYVkiTAq4wkSY2BIEkCDARJUmMgSJIAA0GS1BgIkiTAQJAkNf8fyBlqXqCuCVkAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "df[['FBDist_mean']].hist()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "c76e0cfb-0377-4a07-8334-6051d0b8b737",
   "metadata": {},
   "outputs": [],
   "source": [
    "df.reset_index(inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "e959151e-2d61-49da-8103-61e9d1ed46ef",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['Bonaire, Saint Eustatius and Saba ',\n",
       " 'Cook Islands',\n",
       " 'Eritrea',\n",
       " 'Liechtenstein',\n",
       " 'Monaco',\n",
       " 'Saint Martin',\n",
       " 'Montserrat',\n",
       " 'Nauru',\n",
       " 'Niue',\n",
       " 'Saint Pierre and Miquelon',\n",
       " 'Palau',\n",
       " 'San Marino',\n",
       " 'Tokelau',\n",
       " 'Tuvalu',\n",
       " 'British Virgin Islands',\n",
       " 'Wallis and Futuna']"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "drop_dash = list(df.loc[(df.FBDist_mean>0.32), 'Origin Country'].unique())\n",
    "drop_dash.remove('Turkmenistan')\n",
    "drop_dash"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "9c53a9dd-c52a-4f3a-93b8-a4011c4b5228",
   "metadata": {},
   "outputs": [],
   "source": [
    "df['drop_dash'] = (df['Origin Country'].isin(drop_dash)) | (df['Destination Country'].isin(drop_dash))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "46496e81-4aea-4426-8c53-61cd8bccd1c0",
   "metadata": {},
   "outputs": [],
   "source": [
    "df.to_csv(pathregs   'FBDists_dashboard.csv', index=False, encoding='utf=8')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e96f80de-e85f-46fc-8287-c2ab0cb0054a",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.9.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}