{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "1de28f74",
   "metadata": {},
   "source": [
    "# Data Cleaning"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "bc4c415f",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "6455bf8f",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv('dataset.csv')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "1c2440e4",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Index(['Unnamed: 0', 'track_id', 'artists', 'album_name', 'track_name',\n",
      "       'popularity', 'duration_ms', 'explicit', 'danceability', 'energy',\n",
      "       'key', 'loudness', 'mode', 'speechiness', 'acousticness',\n",
      "       'instrumentalness', 'liveness', 'valence', 'tempo', 'time_signature',\n",
      "       'track_genre'],\n",
      "      dtype='object')\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>Unnamed: 0</th>\n",
       "      <th>track_id</th>\n",
       "      <th>artists</th>\n",
       "      <th>album_name</th>\n",
       "      <th>track_name</th>\n",
       "      <th>popularity</th>\n",
       "      <th>duration_ms</th>\n",
       "      <th>explicit</th>\n",
       "      <th>danceability</th>\n",
       "      <th>energy</th>\n",
       "      <th>...</th>\n",
       "      <th>loudness</th>\n",
       "      <th>mode</th>\n",
       "      <th>speechiness</th>\n",
       "      <th>acousticness</th>\n",
       "      <th>instrumentalness</th>\n",
       "      <th>liveness</th>\n",
       "      <th>valence</th>\n",
       "      <th>tempo</th>\n",
       "      <th>time_signature</th>\n",
       "      <th>track_genre</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>5SuOikwiRyPMVoIQDJUgSV</td>\n",
       "      <td>Gen Hoshino</td>\n",
       "      <td>Comedy</td>\n",
       "      <td>Comedy</td>\n",
       "      <td>73</td>\n",
       "      <td>230666</td>\n",
       "      <td>False</td>\n",
       "      <td>0.676</td>\n",
       "      <td>0.4610</td>\n",
       "      <td>...</td>\n",
       "      <td>-6.746</td>\n",
       "      <td>0</td>\n",
       "      <td>0.1430</td>\n",
       "      <td>0.0322</td>\n",
       "      <td>0.000001</td>\n",
       "      <td>0.3580</td>\n",
       "      <td>0.715</td>\n",
       "      <td>87.917</td>\n",
       "      <td>4</td>\n",
       "      <td>acoustic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>4qPNDBW1i3p13qLCt0Ki3A</td>\n",
       "      <td>Ben Woodward</td>\n",
       "      <td>Ghost (Acoustic)</td>\n",
       "      <td>Ghost - Acoustic</td>\n",
       "      <td>55</td>\n",
       "      <td>149610</td>\n",
       "      <td>False</td>\n",
       "      <td>0.420</td>\n",
       "      <td>0.1660</td>\n",
       "      <td>...</td>\n",
       "      <td>-17.235</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0763</td>\n",
       "      <td>0.9240</td>\n",
       "      <td>0.000006</td>\n",
       "      <td>0.1010</td>\n",
       "      <td>0.267</td>\n",
       "      <td>77.489</td>\n",
       "      <td>4</td>\n",
       "      <td>acoustic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>1iJBSr7s7jYXzM8EGcbK5b</td>\n",
       "      <td>Ingrid Michaelson;ZAYN</td>\n",
       "      <td>To Begin Again</td>\n",
       "      <td>To Begin Again</td>\n",
       "      <td>57</td>\n",
       "      <td>210826</td>\n",
       "      <td>False</td>\n",
       "      <td>0.438</td>\n",
       "      <td>0.3590</td>\n",
       "      <td>...</td>\n",
       "      <td>-9.734</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0557</td>\n",
       "      <td>0.2100</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.1170</td>\n",
       "      <td>0.120</td>\n",
       "      <td>76.332</td>\n",
       "      <td>4</td>\n",
       "      <td>acoustic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>6lfxq3CG4xtTiEg7opyCyx</td>\n",
       "      <td>Kina Grannis</td>\n",
       "      <td>Crazy Rich Asians (Original Motion Picture Sou...</td>\n",
       "      <td>Can't Help Falling In Love</td>\n",
       "      <td>71</td>\n",
       "      <td>201933</td>\n",
       "      <td>False</td>\n",
       "      <td>0.266</td>\n",
       "      <td>0.0596</td>\n",
       "      <td>...</td>\n",
       "      <td>-18.515</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0363</td>\n",
       "      <td>0.9050</td>\n",
       "      <td>0.000071</td>\n",
       "      <td>0.1320</td>\n",
       "      <td>0.143</td>\n",
       "      <td>181.740</td>\n",
       "      <td>3</td>\n",
       "      <td>acoustic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4</td>\n",
       "      <td>5vjLSffimiIP26QG5WcN2K</td>\n",
       "      <td>Chord Overstreet</td>\n",
       "      <td>Hold On</td>\n",
       "      <td>Hold On</td>\n",
       "      <td>82</td>\n",
       "      <td>198853</td>\n",
       "      <td>False</td>\n",
       "      <td>0.618</td>\n",
       "      <td>0.4430</td>\n",
       "      <td>...</td>\n",
       "      <td>-9.681</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0526</td>\n",
       "      <td>0.4690</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0829</td>\n",
       "      <td>0.167</td>\n",
       "      <td>119.949</td>\n",
       "      <td>4</td>\n",
       "      <td>acoustic</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 21 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   Unnamed: 0                track_id                 artists  \\\n",
       "0           0  5SuOikwiRyPMVoIQDJUgSV             Gen Hoshino   \n",
       "1           1  4qPNDBW1i3p13qLCt0Ki3A            Ben Woodward   \n",
       "2           2  1iJBSr7s7jYXzM8EGcbK5b  Ingrid Michaelson;ZAYN   \n",
       "3           3  6lfxq3CG4xtTiEg7opyCyx            Kina Grannis   \n",
       "4           4  5vjLSffimiIP26QG5WcN2K        Chord Overstreet   \n",
       "\n",
       "                                          album_name  \\\n",
       "0                                             Comedy   \n",
       "1                                   Ghost (Acoustic)   \n",
       "2                                     To Begin Again   \n",
       "3  Crazy Rich Asians (Original Motion Picture Sou...   \n",
       "4                                            Hold On   \n",
       "\n",
       "                   track_name  popularity  duration_ms  explicit  \\\n",
       "0                      Comedy          73       230666     False   \n",
       "1            Ghost - Acoustic          55       149610     False   \n",
       "2              To Begin Again          57       210826     False   \n",
       "3  Can't Help Falling In Love          71       201933     False   \n",
       "4                     Hold On          82       198853     False   \n",
       "\n",
       "   danceability  energy  ...  loudness  mode  speechiness  acousticness  \\\n",
       "0         0.676  0.4610  ...    -6.746     0       0.1430        0.0322   \n",
       "1         0.420  0.1660  ...   -17.235     1       0.0763        0.9240   \n",
       "2         0.438  0.3590  ...    -9.734     1       0.0557        0.2100   \n",
       "3         0.266  0.0596  ...   -18.515     1       0.0363        0.9050   \n",
       "4         0.618  0.4430  ...    -9.681     1       0.0526        0.4690   \n",
       "\n",
       "   instrumentalness  liveness  valence    tempo  time_signature  track_genre  \n",
       "0          0.000001    0.3580    0.715   87.917               4     acoustic  \n",
       "1          0.000006    0.1010    0.267   77.489               4     acoustic  \n",
       "2          0.000000    0.1170    0.120   76.332               4     acoustic  \n",
       "3          0.000071    0.1320    0.143  181.740               3     acoustic  \n",
       "4          0.000000    0.0829    0.167  119.949               4     acoustic  \n",
       "\n",
       "[5 rows x 21 columns]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "print(df.columns)\n",
    "df.head()"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "f1a88b42",
   "metadata": {},
   "source": [
    "### Remove unique columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "ece13796",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.drop(['Unnamed: 0','track_id', 'album_name'],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "060fbd33",
   "metadata": {
    "scrolled": false
   },
   "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>artists</th>\n",
       "      <th>track_name</th>\n",
       "      <th>popularity</th>\n",
       "      <th>duration_ms</th>\n",
       "      <th>explicit</th>\n",
       "      <th>danceability</th>\n",
       "      <th>energy</th>\n",
       "      <th>key</th>\n",
       "      <th>loudness</th>\n",
       "      <th>mode</th>\n",
       "      <th>speechiness</th>\n",
       "      <th>acousticness</th>\n",
       "      <th>instrumentalness</th>\n",
       "      <th>liveness</th>\n",
       "      <th>valence</th>\n",
       "      <th>tempo</th>\n",
       "      <th>time_signature</th>\n",
       "      <th>track_genre</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Gen Hoshino</td>\n",
       "      <td>Comedy</td>\n",
       "      <td>73</td>\n",
       "      <td>230666</td>\n",
       "      <td>False</td>\n",
       "      <td>0.676</td>\n",
       "      <td>0.4610</td>\n",
       "      <td>1</td>\n",
       "      <td>-6.746</td>\n",
       "      <td>0</td>\n",
       "      <td>0.1430</td>\n",
       "      <td>0.0322</td>\n",
       "      <td>0.000001</td>\n",
       "      <td>0.3580</td>\n",
       "      <td>0.7150</td>\n",
       "      <td>87.917</td>\n",
       "      <td>4</td>\n",
       "      <td>acoustic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Ben Woodward</td>\n",
       "      <td>Ghost - Acoustic</td>\n",
       "      <td>55</td>\n",
       "      <td>149610</td>\n",
       "      <td>False</td>\n",
       "      <td>0.420</td>\n",
       "      <td>0.1660</td>\n",
       "      <td>1</td>\n",
       "      <td>-17.235</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0763</td>\n",
       "      <td>0.9240</td>\n",
       "      <td>0.000006</td>\n",
       "      <td>0.1010</td>\n",
       "      <td>0.2670</td>\n",
       "      <td>77.489</td>\n",
       "      <td>4</td>\n",
       "      <td>acoustic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Ingrid Michaelson;ZAYN</td>\n",
       "      <td>To Begin Again</td>\n",
       "      <td>57</td>\n",
       "      <td>210826</td>\n",
       "      <td>False</td>\n",
       "      <td>0.438</td>\n",
       "      <td>0.3590</td>\n",
       "      <td>0</td>\n",
       "      <td>-9.734</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0557</td>\n",
       "      <td>0.2100</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.1170</td>\n",
       "      <td>0.1200</td>\n",
       "      <td>76.332</td>\n",
       "      <td>4</td>\n",
       "      <td>acoustic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Kina Grannis</td>\n",
       "      <td>Can't Help Falling In Love</td>\n",
       "      <td>71</td>\n",
       "      <td>201933</td>\n",
       "      <td>False</td>\n",
       "      <td>0.266</td>\n",
       "      <td>0.0596</td>\n",
       "      <td>0</td>\n",
       "      <td>-18.515</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0363</td>\n",
       "      <td>0.9050</td>\n",
       "      <td>0.000071</td>\n",
       "      <td>0.1320</td>\n",
       "      <td>0.1430</td>\n",
       "      <td>181.740</td>\n",
       "      <td>3</td>\n",
       "      <td>acoustic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Chord Overstreet</td>\n",
       "      <td>Hold On</td>\n",
       "      <td>82</td>\n",
       "      <td>198853</td>\n",
       "      <td>False</td>\n",
       "      <td>0.618</td>\n",
       "      <td>0.4430</td>\n",
       "      <td>2</td>\n",
       "      <td>-9.681</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0526</td>\n",
       "      <td>0.4690</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0829</td>\n",
       "      <td>0.1670</td>\n",
       "      <td>119.949</td>\n",
       "      <td>4</td>\n",
       "      <td>acoustic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Tyrone Wells</td>\n",
       "      <td>Days I Will Remember</td>\n",
       "      <td>58</td>\n",
       "      <td>214240</td>\n",
       "      <td>False</td>\n",
       "      <td>0.688</td>\n",
       "      <td>0.4810</td>\n",
       "      <td>6</td>\n",
       "      <td>-8.807</td>\n",
       "      <td>1</td>\n",
       "      <td>0.1050</td>\n",
       "      <td>0.2890</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.1890</td>\n",
       "      <td>0.6660</td>\n",
       "      <td>98.017</td>\n",
       "      <td>4</td>\n",
       "      <td>acoustic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>A Great Big World;Christina Aguilera</td>\n",
       "      <td>Say Something</td>\n",
       "      <td>74</td>\n",
       "      <td>229400</td>\n",
       "      <td>False</td>\n",
       "      <td>0.407</td>\n",
       "      <td>0.1470</td>\n",
       "      <td>2</td>\n",
       "      <td>-8.822</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0355</td>\n",
       "      <td>0.8570</td>\n",
       "      <td>0.000003</td>\n",
       "      <td>0.0913</td>\n",
       "      <td>0.0765</td>\n",
       "      <td>141.284</td>\n",
       "      <td>3</td>\n",
       "      <td>acoustic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Jason Mraz</td>\n",
       "      <td>I'm Yours</td>\n",
       "      <td>80</td>\n",
       "      <td>242946</td>\n",
       "      <td>False</td>\n",
       "      <td>0.703</td>\n",
       "      <td>0.4440</td>\n",
       "      <td>11</td>\n",
       "      <td>-9.331</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0417</td>\n",
       "      <td>0.5590</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0973</td>\n",
       "      <td>0.7120</td>\n",
       "      <td>150.960</td>\n",
       "      <td>4</td>\n",
       "      <td>acoustic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Jason Mraz;Colbie Caillat</td>\n",
       "      <td>Lucky</td>\n",
       "      <td>74</td>\n",
       "      <td>189613</td>\n",
       "      <td>False</td>\n",
       "      <td>0.625</td>\n",
       "      <td>0.4140</td>\n",
       "      <td>0</td>\n",
       "      <td>-8.700</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0369</td>\n",
       "      <td>0.2940</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.1510</td>\n",
       "      <td>0.6690</td>\n",
       "      <td>130.088</td>\n",
       "      <td>4</td>\n",
       "      <td>acoustic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>Ross Copperman</td>\n",
       "      <td>Hunger</td>\n",
       "      <td>56</td>\n",
       "      <td>205594</td>\n",
       "      <td>False</td>\n",
       "      <td>0.442</td>\n",
       "      <td>0.6320</td>\n",
       "      <td>1</td>\n",
       "      <td>-6.770</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0295</td>\n",
       "      <td>0.4260</td>\n",
       "      <td>0.004190</td>\n",
       "      <td>0.0735</td>\n",
       "      <td>0.1960</td>\n",
       "      <td>78.899</td>\n",
       "      <td>4</td>\n",
       "      <td>acoustic</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                artists                  track_name  \\\n",
       "0                           Gen Hoshino                      Comedy   \n",
       "1                          Ben Woodward            Ghost - Acoustic   \n",
       "2                Ingrid Michaelson;ZAYN              To Begin Again   \n",
       "3                          Kina Grannis  Can't Help Falling In Love   \n",
       "4                      Chord Overstreet                     Hold On   \n",
       "5                          Tyrone Wells        Days I Will Remember   \n",
       "6  A Great Big World;Christina Aguilera               Say Something   \n",
       "7                            Jason Mraz                   I'm Yours   \n",
       "8             Jason Mraz;Colbie Caillat                       Lucky   \n",
       "9                        Ross Copperman                      Hunger   \n",
       "\n",
       "   popularity  duration_ms  explicit  danceability  energy  key  loudness  \\\n",
       "0          73       230666     False         0.676  0.4610    1    -6.746   \n",
       "1          55       149610     False         0.420  0.1660    1   -17.235   \n",
       "2          57       210826     False         0.438  0.3590    0    -9.734   \n",
       "3          71       201933     False         0.266  0.0596    0   -18.515   \n",
       "4          82       198853     False         0.618  0.4430    2    -9.681   \n",
       "5          58       214240     False         0.688  0.4810    6    -8.807   \n",
       "6          74       229400     False         0.407  0.1470    2    -8.822   \n",
       "7          80       242946     False         0.703  0.4440   11    -9.331   \n",
       "8          74       189613     False         0.625  0.4140    0    -8.700   \n",
       "9          56       205594     False         0.442  0.6320    1    -6.770   \n",
       "\n",
       "   mode  speechiness  acousticness  instrumentalness  liveness  valence  \\\n",
       "0     0       0.1430        0.0322          0.000001    0.3580   0.7150   \n",
       "1     1       0.0763        0.9240          0.000006    0.1010   0.2670   \n",
       "2     1       0.0557        0.2100          0.000000    0.1170   0.1200   \n",
       "3     1       0.0363        0.9050          0.000071    0.1320   0.1430   \n",
       "4     1       0.0526        0.4690          0.000000    0.0829   0.1670   \n",
       "5     1       0.1050        0.2890          0.000000    0.1890   0.6660   \n",
       "6     1       0.0355        0.8570          0.000003    0.0913   0.0765   \n",
       "7     1       0.0417        0.5590          0.000000    0.0973   0.7120   \n",
       "8     1       0.0369        0.2940          0.000000    0.1510   0.6690   \n",
       "9     1       0.0295        0.4260          0.004190    0.0735   0.1960   \n",
       "\n",
       "     tempo  time_signature track_genre  \n",
       "0   87.917               4    acoustic  \n",
       "1   77.489               4    acoustic  \n",
       "2   76.332               4    acoustic  \n",
       "3  181.740               3    acoustic  \n",
       "4  119.949               4    acoustic  \n",
       "5   98.017               4    acoustic  \n",
       "6  141.284               3    acoustic  \n",
       "7  150.960               4    acoustic  \n",
       "8  130.088               4    acoustic  \n",
       "9   78.899               4    acoustic  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "d801195c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "artists              object\n",
       "track_name           object\n",
       "popularity            int64\n",
       "duration_ms           int64\n",
       "explicit               bool\n",
       "danceability        float64\n",
       "energy              float64\n",
       "key                   int64\n",
       "loudness            float64\n",
       "mode                  int64\n",
       "speechiness         float64\n",
       "acousticness        float64\n",
       "instrumentalness    float64\n",
       "liveness            float64\n",
       "valence             float64\n",
       "tempo               float64\n",
       "time_signature        int64\n",
       "track_genre          object\n",
       "dtype: object"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.dtypes"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "aeb25f1a",
   "metadata": {},
   "source": [
    "### Drop Null Values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "ce3c3319",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "artists             1\n",
      "track_name          1\n",
      "popularity          0\n",
      "duration_ms         0\n",
      "explicit            0\n",
      "danceability        0\n",
      "energy              0\n",
      "key                 0\n",
      "loudness            0\n",
      "mode                0\n",
      "speechiness         0\n",
      "acousticness        0\n",
      "instrumentalness    0\n",
      "liveness            0\n",
      "valence             0\n",
      "tempo               0\n",
      "time_signature      0\n",
      "track_genre         0\n",
      "dtype: int64\n"
     ]
    }
   ],
   "source": [
    "print(df.isna().sum())\n",
    "df=df.dropna()"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "de7960de",
   "metadata": {},
   "source": [
    "### Drop Duplicated Rows (Same artists and track_name)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "eb46cc03",
   "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>artists</th>\n",
       "      <th>track_name</th>\n",
       "      <th>popularity</th>\n",
       "      <th>duration_ms</th>\n",
       "      <th>explicit</th>\n",
       "      <th>danceability</th>\n",
       "      <th>energy</th>\n",
       "      <th>key</th>\n",
       "      <th>loudness</th>\n",
       "      <th>mode</th>\n",
       "      <th>speechiness</th>\n",
       "      <th>acousticness</th>\n",
       "      <th>instrumentalness</th>\n",
       "      <th>liveness</th>\n",
       "      <th>valence</th>\n",
       "      <th>tempo</th>\n",
       "      <th>time_signature</th>\n",
       "      <th>track_genre</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>Jason Mraz;Colbie Caillat</td>\n",
       "      <td>Lucky</td>\n",
       "      <td>68</td>\n",
       "      <td>189613</td>\n",
       "      <td>False</td>\n",
       "      <td>0.625</td>\n",
       "      <td>0.414</td>\n",
       "      <td>0</td>\n",
       "      <td>-8.700</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0369</td>\n",
       "      <td>0.29400</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.1510</td>\n",
       "      <td>0.6690</td>\n",
       "      <td>130.088</td>\n",
       "      <td>4</td>\n",
       "      <td>acoustic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>Jason Mraz</td>\n",
       "      <td>I'm Yours</td>\n",
       "      <td>75</td>\n",
       "      <td>242946</td>\n",
       "      <td>False</td>\n",
       "      <td>0.703</td>\n",
       "      <td>0.444</td>\n",
       "      <td>11</td>\n",
       "      <td>-9.331</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0417</td>\n",
       "      <td>0.55900</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0973</td>\n",
       "      <td>0.7120</td>\n",
       "      <td>150.960</td>\n",
       "      <td>4</td>\n",
       "      <td>acoustic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>A Great Big World;Christina Aguilera</td>\n",
       "      <td>Say Something</td>\n",
       "      <td>70</td>\n",
       "      <td>229400</td>\n",
       "      <td>False</td>\n",
       "      <td>0.407</td>\n",
       "      <td>0.147</td>\n",
       "      <td>2</td>\n",
       "      <td>-8.822</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0355</td>\n",
       "      <td>0.85700</td>\n",
       "      <td>0.000003</td>\n",
       "      <td>0.0913</td>\n",
       "      <td>0.0765</td>\n",
       "      <td>141.284</td>\n",
       "      <td>3</td>\n",
       "      <td>acoustic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>Jason Mraz</td>\n",
       "      <td>Winter Wonderland</td>\n",
       "      <td>0</td>\n",
       "      <td>131760</td>\n",
       "      <td>False</td>\n",
       "      <td>0.620</td>\n",
       "      <td>0.309</td>\n",
       "      <td>5</td>\n",
       "      <td>-9.209</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0495</td>\n",
       "      <td>0.78800</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.1460</td>\n",
       "      <td>0.6640</td>\n",
       "      <td>145.363</td>\n",
       "      <td>4</td>\n",
       "      <td>acoustic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>Jason Mraz</td>\n",
       "      <td>Winter Wonderland</td>\n",
       "      <td>0</td>\n",
       "      <td>131760</td>\n",
       "      <td>False</td>\n",
       "      <td>0.620</td>\n",
       "      <td>0.309</td>\n",
       "      <td>5</td>\n",
       "      <td>-9.209</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0495</td>\n",
       "      <td>0.78800</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.1460</td>\n",
       "      <td>0.6640</td>\n",
       "      <td>145.363</td>\n",
       "      <td>4</td>\n",
       "      <td>acoustic</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>113845</th>\n",
       "      <td>Hillsong Worship;Brooke Ligertwood</td>\n",
       "      <td>King Of Kings - Live at Hillsong Conference</td>\n",
       "      <td>40</td>\n",
       "      <td>291565</td>\n",
       "      <td>False</td>\n",
       "      <td>0.454</td>\n",
       "      <td>0.427</td>\n",
       "      <td>2</td>\n",
       "      <td>-8.049</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0290</td>\n",
       "      <td>0.02050</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.6900</td>\n",
       "      <td>0.1840</td>\n",
       "      <td>135.887</td>\n",
       "      <td>4</td>\n",
       "      <td>world-music</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>113882</th>\n",
       "      <td>Bryan &amp; Katie Torwalt</td>\n",
       "      <td>Good News - Live</td>\n",
       "      <td>23</td>\n",
       "      <td>266632</td>\n",
       "      <td>False</td>\n",
       "      <td>0.473</td>\n",
       "      <td>0.474</td>\n",
       "      <td>6</td>\n",
       "      <td>-9.175</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0558</td>\n",
       "      <td>0.39500</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.1630</td>\n",
       "      <td>0.2510</td>\n",
       "      <td>140.746</td>\n",
       "      <td>4</td>\n",
       "      <td>world-music</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>113917</th>\n",
       "      <td>Hillsong Worship;Mi-kaisha Rose</td>\n",
       "      <td>Never Walk Alone - Live</td>\n",
       "      <td>41</td>\n",
       "      <td>348619</td>\n",
       "      <td>False</td>\n",
       "      <td>0.420</td>\n",
       "      <td>0.553</td>\n",
       "      <td>5</td>\n",
       "      <td>-8.049</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0332</td>\n",
       "      <td>0.14100</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.1030</td>\n",
       "      <td>0.2140</td>\n",
       "      <td>143.804</td>\n",
       "      <td>4</td>\n",
       "      <td>world-music</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>113951</th>\n",
       "      <td>Passion;Kristian Stanfill</td>\n",
       "      <td>More Like Jesus - Live</td>\n",
       "      <td>44</td>\n",
       "      <td>338694</td>\n",
       "      <td>False</td>\n",
       "      <td>0.404</td>\n",
       "      <td>0.676</td>\n",
       "      <td>10</td>\n",
       "      <td>-5.468</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0354</td>\n",
       "      <td>0.02740</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.3520</td>\n",
       "      <td>0.1630</td>\n",
       "      <td>144.056</td>\n",
       "      <td>3</td>\n",
       "      <td>world-music</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>113991</th>\n",
       "      <td>Chris Tomlin</td>\n",
       "      <td>At The Cross (Love Ran Red)</td>\n",
       "      <td>32</td>\n",
       "      <td>250629</td>\n",
       "      <td>False</td>\n",
       "      <td>0.387</td>\n",
       "      <td>0.531</td>\n",
       "      <td>8</td>\n",
       "      <td>-4.788</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0290</td>\n",
       "      <td>0.00305</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.2010</td>\n",
       "      <td>0.1530</td>\n",
       "      <td>146.003</td>\n",
       "      <td>4</td>\n",
       "      <td>world-music</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>32656 rows × 18 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                     artists  \\\n",
       "18                 Jason Mraz;Colbie Caillat   \n",
       "20                                Jason Mraz   \n",
       "22      A Great Big World;Christina Aguilera   \n",
       "28                                Jason Mraz   \n",
       "29                                Jason Mraz   \n",
       "...                                      ...   \n",
       "113845    Hillsong Worship;Brooke Ligertwood   \n",
       "113882                 Bryan & Katie Torwalt   \n",
       "113917       Hillsong Worship;Mi-kaisha Rose   \n",
       "113951             Passion;Kristian Stanfill   \n",
       "113991                          Chris Tomlin   \n",
       "\n",
       "                                         track_name  popularity  duration_ms  \\\n",
       "18                                            Lucky          68       189613   \n",
       "20                                        I'm Yours          75       242946   \n",
       "22                                    Say Something          70       229400   \n",
       "28                                Winter Wonderland           0       131760   \n",
       "29                                Winter Wonderland           0       131760   \n",
       "...                                             ...         ...          ...   \n",
       "113845  King Of Kings - Live at Hillsong Conference          40       291565   \n",
       "113882                             Good News - Live          23       266632   \n",
       "113917                      Never Walk Alone - Live          41       348619   \n",
       "113951                       More Like Jesus - Live          44       338694   \n",
       "113991                  At The Cross (Love Ran Red)          32       250629   \n",
       "\n",
       "        explicit  danceability  energy  key  loudness  mode  speechiness  \\\n",
       "18         False         0.625   0.414    0    -8.700     1       0.0369   \n",
       "20         False         0.703   0.444   11    -9.331     1       0.0417   \n",
       "22         False         0.407   0.147    2    -8.822     1       0.0355   \n",
       "28         False         0.620   0.309    5    -9.209     1       0.0495   \n",
       "29         False         0.620   0.309    5    -9.209     1       0.0495   \n",
       "...          ...           ...     ...  ...       ...   ...          ...   \n",
       "113845     False         0.454   0.427    2    -8.049     1       0.0290   \n",
       "113882     False         0.473   0.474    6    -9.175     1       0.0558   \n",
       "113917     False         0.420   0.553    5    -8.049     1       0.0332   \n",
       "113951     False         0.404   0.676   10    -5.468     1       0.0354   \n",
       "113991     False         0.387   0.531    8    -4.788     1       0.0290   \n",
       "\n",
       "        acousticness  instrumentalness  liveness  valence    tempo  \\\n",
       "18           0.29400          0.000000    0.1510   0.6690  130.088   \n",
       "20           0.55900          0.000000    0.0973   0.7120  150.960   \n",
       "22           0.85700          0.000003    0.0913   0.0765  141.284   \n",
       "28           0.78800          0.000000    0.1460   0.6640  145.363   \n",
       "29           0.78800          0.000000    0.1460   0.6640  145.363   \n",
       "...              ...               ...       ...      ...      ...   \n",
       "113845       0.02050          0.000000    0.6900   0.1840  135.887   \n",
       "113882       0.39500          0.000000    0.1630   0.2510  140.746   \n",
       "113917       0.14100          0.000000    0.1030   0.2140  143.804   \n",
       "113951       0.02740          0.000000    0.3520   0.1630  144.056   \n",
       "113991       0.00305          0.000000    0.2010   0.1530  146.003   \n",
       "\n",
       "        time_signature  track_genre  \n",
       "18                   4     acoustic  \n",
       "20                   4     acoustic  \n",
       "22                   3     acoustic  \n",
       "28                   4     acoustic  \n",
       "29                   4     acoustic  \n",
       "...                ...          ...  \n",
       "113845               4  world-music  \n",
       "113882               4  world-music  \n",
       "113917               4  world-music  \n",
       "113951               3  world-music  \n",
       "113991               4  world-music  \n",
       "\n",
       "[32656 rows x 18 columns]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "duplicated_rows = df[df.duplicated(['artists', 'track_name'])]\n",
    "\n",
    "# print duplicated rows\n",
    "duplicated_rows"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "251df65d",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.drop_duplicates(['artists', 'track_name'], keep='first')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "d6eea5b5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "study          996\n",
       "black-metal    991\n",
       "comedy         987\n",
       "heavy-metal    985\n",
       "bluegrass      978\n",
       "              ... \n",
       "rock           167\n",
       "reggae         166\n",
       "house          134\n",
       "indie          107\n",
       "reggaeton       63\n",
       "Name: track_genre, Length: 113, dtype: int64"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape\n",
    "df['track_genre'].value_counts()"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "363cf332",
   "metadata": {},
   "source": [
    "### Drop artists and track name columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "2f11bf72",
   "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>popularity</th>\n",
       "      <th>duration_ms</th>\n",
       "      <th>explicit</th>\n",
       "      <th>danceability</th>\n",
       "      <th>energy</th>\n",
       "      <th>key</th>\n",
       "      <th>loudness</th>\n",
       "      <th>mode</th>\n",
       "      <th>speechiness</th>\n",
       "      <th>acousticness</th>\n",
       "      <th>instrumentalness</th>\n",
       "      <th>liveness</th>\n",
       "      <th>valence</th>\n",
       "      <th>tempo</th>\n",
       "      <th>time_signature</th>\n",
       "      <th>track_genre</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>73</td>\n",
       "      <td>230666</td>\n",
       "      <td>False</td>\n",
       "      <td>0.676</td>\n",
       "      <td>0.4610</td>\n",
       "      <td>1</td>\n",
       "      <td>-6.746</td>\n",
       "      <td>0</td>\n",
       "      <td>0.1430</td>\n",
       "      <td>0.0322</td>\n",
       "      <td>0.000001</td>\n",
       "      <td>0.3580</td>\n",
       "      <td>0.715</td>\n",
       "      <td>87.917</td>\n",
       "      <td>4</td>\n",
       "      <td>acoustic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>55</td>\n",
       "      <td>149610</td>\n",
       "      <td>False</td>\n",
       "      <td>0.420</td>\n",
       "      <td>0.1660</td>\n",
       "      <td>1</td>\n",
       "      <td>-17.235</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0763</td>\n",
       "      <td>0.9240</td>\n",
       "      <td>0.000006</td>\n",
       "      <td>0.1010</td>\n",
       "      <td>0.267</td>\n",
       "      <td>77.489</td>\n",
       "      <td>4</td>\n",
       "      <td>acoustic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>57</td>\n",
       "      <td>210826</td>\n",
       "      <td>False</td>\n",
       "      <td>0.438</td>\n",
       "      <td>0.3590</td>\n",
       "      <td>0</td>\n",
       "      <td>-9.734</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0557</td>\n",
       "      <td>0.2100</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.1170</td>\n",
       "      <td>0.120</td>\n",
       "      <td>76.332</td>\n",
       "      <td>4</td>\n",
       "      <td>acoustic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>71</td>\n",
       "      <td>201933</td>\n",
       "      <td>False</td>\n",
       "      <td>0.266</td>\n",
       "      <td>0.0596</td>\n",
       "      <td>0</td>\n",
       "      <td>-18.515</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0363</td>\n",
       "      <td>0.9050</td>\n",
       "      <td>0.000071</td>\n",
       "      <td>0.1320</td>\n",
       "      <td>0.143</td>\n",
       "      <td>181.740</td>\n",
       "      <td>3</td>\n",
       "      <td>acoustic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>82</td>\n",
       "      <td>198853</td>\n",
       "      <td>False</td>\n",
       "      <td>0.618</td>\n",
       "      <td>0.4430</td>\n",
       "      <td>2</td>\n",
       "      <td>-9.681</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0526</td>\n",
       "      <td>0.4690</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0829</td>\n",
       "      <td>0.167</td>\n",
       "      <td>119.949</td>\n",
       "      <td>4</td>\n",
       "      <td>acoustic</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   popularity  duration_ms  explicit  danceability  energy  key  loudness  \\\n",
       "0          73       230666     False         0.676  0.4610    1    -6.746   \n",
       "1          55       149610     False         0.420  0.1660    1   -17.235   \n",
       "2          57       210826     False         0.438  0.3590    0    -9.734   \n",
       "3          71       201933     False         0.266  0.0596    0   -18.515   \n",
       "4          82       198853     False         0.618  0.4430    2    -9.681   \n",
       "\n",
       "   mode  speechiness  acousticness  instrumentalness  liveness  valence  \\\n",
       "0     0       0.1430        0.0322          0.000001    0.3580    0.715   \n",
       "1     1       0.0763        0.9240          0.000006    0.1010    0.267   \n",
       "2     1       0.0557        0.2100          0.000000    0.1170    0.120   \n",
       "3     1       0.0363        0.9050          0.000071    0.1320    0.143   \n",
       "4     1       0.0526        0.4690          0.000000    0.0829    0.167   \n",
       "\n",
       "     tempo  time_signature track_genre  \n",
       "0   87.917               4    acoustic  \n",
       "1   77.489               4    acoustic  \n",
       "2   76.332               4    acoustic  \n",
       "3  181.740               3    acoustic  \n",
       "4  119.949               4    acoustic  "
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = df.drop(['artists','track_name'],axis=1)\n",
    "df.head()"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "e7d572f5",
   "metadata": {},
   "source": [
    "### Drop invalid tempo and time signature according to Spotify API"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "69b1cceb",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "4    71986\n",
       "3     6944\n",
       "5     1488\n",
       "1      775\n",
       "0      150\n",
       "Name: time_signature, dtype: int64"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['time_signature'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "39a08b22",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df[df['time_signature'] >2]\n",
    "df = df[df['tempo'] > 0]"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "0b7c8cea",
   "metadata": {},
   "source": [
    "### Save the cleaned dataset into csv"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "8c064cb0",
   "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>popularity</th>\n",
       "      <th>duration_ms</th>\n",
       "      <th>explicit</th>\n",
       "      <th>danceability</th>\n",
       "      <th>energy</th>\n",
       "      <th>key</th>\n",
       "      <th>loudness</th>\n",
       "      <th>mode</th>\n",
       "      <th>speechiness</th>\n",
       "      <th>acousticness</th>\n",
       "      <th>instrumentalness</th>\n",
       "      <th>liveness</th>\n",
       "      <th>valence</th>\n",
       "      <th>tempo</th>\n",
       "      <th>time_signature</th>\n",
       "      <th>track_genre</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>73</td>\n",
       "      <td>230666</td>\n",
       "      <td>False</td>\n",
       "      <td>0.676</td>\n",
       "      <td>0.4610</td>\n",
       "      <td>1</td>\n",
       "      <td>-6.746</td>\n",
       "      <td>0</td>\n",
       "      <td>0.1430</td>\n",
       "      <td>0.0322</td>\n",
       "      <td>0.000001</td>\n",
       "      <td>0.3580</td>\n",
       "      <td>0.715</td>\n",
       "      <td>87.917</td>\n",
       "      <td>4</td>\n",
       "      <td>acoustic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>55</td>\n",
       "      <td>149610</td>\n",
       "      <td>False</td>\n",
       "      <td>0.420</td>\n",
       "      <td>0.1660</td>\n",
       "      <td>1</td>\n",
       "      <td>-17.235</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0763</td>\n",
       "      <td>0.9240</td>\n",
       "      <td>0.000006</td>\n",
       "      <td>0.1010</td>\n",
       "      <td>0.267</td>\n",
       "      <td>77.489</td>\n",
       "      <td>4</td>\n",
       "      <td>acoustic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>57</td>\n",
       "      <td>210826</td>\n",
       "      <td>False</td>\n",
       "      <td>0.438</td>\n",
       "      <td>0.3590</td>\n",
       "      <td>0</td>\n",
       "      <td>-9.734</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0557</td>\n",
       "      <td>0.2100</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.1170</td>\n",
       "      <td>0.120</td>\n",
       "      <td>76.332</td>\n",
       "      <td>4</td>\n",
       "      <td>acoustic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>71</td>\n",
       "      <td>201933</td>\n",
       "      <td>False</td>\n",
       "      <td>0.266</td>\n",
       "      <td>0.0596</td>\n",
       "      <td>0</td>\n",
       "      <td>-18.515</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0363</td>\n",
       "      <td>0.9050</td>\n",
       "      <td>0.000071</td>\n",
       "      <td>0.1320</td>\n",
       "      <td>0.143</td>\n",
       "      <td>181.740</td>\n",
       "      <td>3</td>\n",
       "      <td>acoustic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>82</td>\n",
       "      <td>198853</td>\n",
       "      <td>False</td>\n",
       "      <td>0.618</td>\n",
       "      <td>0.4430</td>\n",
       "      <td>2</td>\n",
       "      <td>-9.681</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0526</td>\n",
       "      <td>0.4690</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0829</td>\n",
       "      <td>0.167</td>\n",
       "      <td>119.949</td>\n",
       "      <td>4</td>\n",
       "      <td>acoustic</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   popularity  duration_ms  explicit  danceability  energy  key  loudness  \\\n",
       "0          73       230666     False         0.676  0.4610    1    -6.746   \n",
       "1          55       149610     False         0.420  0.1660    1   -17.235   \n",
       "2          57       210826     False         0.438  0.3590    0    -9.734   \n",
       "3          71       201933     False         0.266  0.0596    0   -18.515   \n",
       "4          82       198853     False         0.618  0.4430    2    -9.681   \n",
       "\n",
       "   mode  speechiness  acousticness  instrumentalness  liveness  valence  \\\n",
       "0     0       0.1430        0.0322          0.000001    0.3580    0.715   \n",
       "1     1       0.0763        0.9240          0.000006    0.1010    0.267   \n",
       "2     1       0.0557        0.2100          0.000000    0.1170    0.120   \n",
       "3     1       0.0363        0.9050          0.000071    0.1320    0.143   \n",
       "4     1       0.0526        0.4690          0.000000    0.0829    0.167   \n",
       "\n",
       "     tempo  time_signature track_genre  \n",
       "0   87.917               4    acoustic  \n",
       "1   77.489               4    acoustic  \n",
       "2   76.332               4    acoustic  \n",
       "3  181.740               3    acoustic  \n",
       "4  119.949               4    acoustic  "
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "12bea66e",
   "metadata": {},
   "outputs": [],
   "source": [
    "df.to_csv(\"cleaned_dataset.csv\",index = False)"
   ]
  }
 ],
 "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": "3.10.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}