{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.cluster import KMeans"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "df=pd.read_csv(\"culture2015.csv\", sep=\";\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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>ctr</th>\n",
       "      <th>country</th>\n",
       "      <th>pdi</th>\n",
       "      <th>idv</th>\n",
       "      <th>mas</th>\n",
       "      <th>uai</th>\n",
       "      <th>ltowvs</th>\n",
       "      <th>ivr</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>AFE</td>\n",
       "      <td>Africa East</td>\n",
       "      <td>64</td>\n",
       "      <td>27</td>\n",
       "      <td>41</td>\n",
       "      <td>52</td>\n",
       "      <td>32</td>\n",
       "      <td>40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>AFW</td>\n",
       "      <td>Africa West</td>\n",
       "      <td>77</td>\n",
       "      <td>20</td>\n",
       "      <td>46</td>\n",
       "      <td>54</td>\n",
       "      <td>9</td>\n",
       "      <td>78</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>ALB</td>\n",
       "      <td>Albania</td>\n",
       "      <td>#NULL!</td>\n",
       "      <td>#NULL!</td>\n",
       "      <td>#NULL!</td>\n",
       "      <td>#NULL!</td>\n",
       "      <td>61</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>ALG</td>\n",
       "      <td>Algeria</td>\n",
       "      <td>#NULL!</td>\n",
       "      <td>#NULL!</td>\n",
       "      <td>#NULL!</td>\n",
       "      <td>#NULL!</td>\n",
       "      <td>26</td>\n",
       "      <td>32</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>AND</td>\n",
       "      <td>Andorra</td>\n",
       "      <td>#NULL!</td>\n",
       "      <td>#NULL!</td>\n",
       "      <td>#NULL!</td>\n",
       "      <td>#NULL!</td>\n",
       "      <td>#NULL!</td>\n",
       "      <td>65</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   ctr      country     pdi     idv     mas     uai  ltowvs ivr\n",
       "0  AFE  Africa East      64      27      41      52      32  40\n",
       "1  AFW  Africa West      77      20      46      54       9  78\n",
       "2  ALB      Albania  #NULL!  #NULL!  #NULL!  #NULL!      61  15\n",
       "3  ALG      Algeria  #NULL!  #NULL!  #NULL!  #NULL!      26  32\n",
       "4  AND      Andorra  #NULL!  #NULL!  #NULL!  #NULL!  #NULL!  65"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "ctr        object\n",
       "country    object\n",
       "pdi        object\n",
       "idv        object\n",
       "mas        object\n",
       "uai        object\n",
       "ltowvs     object\n",
       "ivr        object\n",
       "dtype: object"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#df.iloc[:,2]=pd.to_numeric(df.iloc[:,2], errors='coerce')\n",
    "\n",
    "for i in range(2,8):\n",
    "    df.iloc[:,i]=pd.to_numeric(df.iloc[:,i], errors='coerce')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df=df.dropna()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df=df.reset_index()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df1=df.iloc[:,3:9]\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "kmeans = KMeans(n_clusters=6).fit(df1)\n",
    "centroids = kmeans.cluster_centers_\n",
    "print(centroids)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "pred_y =kmeans.predict(df1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df2=pred_y.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df2=pd.DataFrame(pred_y, columns=['groups'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "XY2=df.merge(df2,left_index=True, right_index=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "XY2[XY2.groups == 6]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "XY2[XY2.groups == 4]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "centroids = kmeans.cluster_centers_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "centroids"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df2=pd.DataFrame(pred_y, columns=['groups'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#group=[i for i in range(0,8)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df2=pd.DataFrame(centroids,columns=[\"pdi\",\"idv\",\"mas\",\"uai\",\"ltowvs\",\"ivr\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}