cmkl_assignments/fall-2024/math/mat-203/00010/Whr2024Descriptive-Original.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "# Gamma function\n",
    "from scipy.special import gamma\n",
    "\n",
    "# To calculate statistics\n",
    "from scipy.stats import norm\n",
    "from scipy.stats import hmean, trim_mean, iqr, median_abs_deviation, skew, kurtosis\n",
    "from scipy.stats.mstats import gmean, winsorize"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Reading and preprocessing data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "DataWhr2024 = pd.read_csv(\"DataWhr2024.csv\")\n",
    "UnM49 = pd.read_csv(\"UnM49.csv\", sep=';')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "UnM49 = UnM49[['Country or Area', 'Sub-region Name', 'Region Name']]\n",
    "UnM49 = UnM49.rename({'Country or Area':'Country name', 'Sub-region Name':'Subregion', 'Region Name':'Continent'}, axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "DataWhr2024.loc[DataWhr2024[\"Country name\"].str.startswith(\"Hong\"), \"Country name\"] = \"Hong Kong\"\n",
    "DataWhr2024.loc[DataWhr2024[\"Country name\"].str.startswith(\"Somaliland\"), \"Country name\"] = \"Somaliland\"\n",
    "DataWhr2024.loc[DataWhr2024[\"Country name\"].str.startswith(\"Taiwan\"), \"Country name\"] = \"Taiwan\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "UnM49.loc[97, \"Country name\"] = \"Bolivia\"\n",
    "UnM49.loc[33, \"Country name\"] = \"Congo (Brazzaville)\"\n",
    "UnM49.loc[34, \"Country name\"] = \"Congo (Kinshasa)\"\n",
    "UnM49.loc[124, \"Country name\"] = \"Hong Kong\"\n",
    "UnM49.loc[125, \"Country name\"] = \"Macao\"\n",
    "UnM49.loc[126, \"Country name\"] = \"North Korea\"\n",
    "UnM49.loc[145, \"Country name\"] = \"Iran\"\n",
    "UnM49.loc[46, \"Country name\"] = \"Ivory Coast\"\n",
    "UnM49.loc[133, \"Country name\"] = \"Laos\"\n",
    "UnM49.loc[129, \"Country name\"] = \"South Korea\"\n",
    "UnM49.loc[173, \"Country name\"] = \"Moldova\"\n",
    "UnM49.loc[217, \"Country name\"] = \"Netherlands\"\n",
    "UnM49.loc[175, \"Country name\"] = \"Russia\"\n",
    "UnM49.loc[164, \"Country name\"] = \"Syria\"\n",
    "UnM49.loc[26, \"Country name\"] = \"Tanzania\"\n",
    "UnM49.loc[116, \"Country name\"] = \"United States\"\n",
    "UnM49.loc[193, \"Country name\"] = \"United Kingdom\"\n",
    "UnM49.loc[111, \"Country name\"] = \"Venezuela\"\n",
    "UnM49.loc[140, \"Country name\"] = \"Vietnam\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "_ = pd.DataFrame(\n",
    "    {\n",
    "        \"Country name\": [\"Kosovo\", \"Somaliland\", \"Taiwan\"],\n",
    "        \"Subregion\": [\"Southern Europe\", \"Sub-Saharan Africa\", \"Eastern Asia\"],\n",
    "        \"Continent\": [\"Europe\", \"Africa\", \"Asia\"],\n",
    "    }\n",
    ")\n",
    "\n",
    "UnM49 = pd.concat([UnM49, _], axis=0)\n",
    "UnM49 = UnM49.reset_index(drop=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Data\n",
    "Dat = pd.merge(DataWhr2024, UnM49)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Data of 2023\n",
    "Dat2023 = Dat[Dat['year'] == 2023]\n",
    "Dat2023 = Dat2023.reset_index(drop=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['Iceland',\n",
       " 'India',\n",
       " 'Indonesia',\n",
       " 'Iran',\n",
       " 'Iraq',\n",
       " 'Ireland',\n",
       " 'Israel',\n",
       " 'Italy',\n",
       " 'Ivory Coast']"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Countries that starts with the same letter that your name\n",
    "StartsWith = 'I' # The first letter of your name\n",
    "list(Dat[Dat['Country name'].str.startswith(StartsWith)]['Country name'].unique())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Data of 2023 from the region selected\n",
    "CountrySelected = 'Iraq' # Change to the country that you selected\n",
    "SubregionSelected = Dat[Dat['Country name']==CountrySelected]['Subregion'].unique()[0]\n",
    "\n",
    "DatSelected = Dat2023[Dat2023['Subregion']==SubregionSelected]\n",
    "DatSelected = DatSelected.reset_index(drop=True)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}