{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Spotify Data Exploration: the Popularity Feature\n",
    "\n",
    "## Intro:\n",
    "\n",
    "After retrieving some data from the Spotify API (for more info about that check out [this notebook](https://github.com/tgel0/spotify-data/blob/master/notebooks/SpotifyDataRetrieval.ipynb)) it's time to get some insights. In this notebook, I will use data collected during the months of August and September 2018 to identify the most popular tracks and artists on Spotify using the 'popularity' featue.\n",
    "\n",
    "## About the Popularity Feature:\n",
    "\n",
    "From the [official Spotify docs](https://developer.spotify.com/documentation/web-api/reference/search/search/): \n",
    ">\"The popularity of the track. The value will be between 0, for least popular, and 100 for most popular. \n",
    "The popularity of a track is a value between 0 and 100, with 100 being the most popular. Popularity is based mainly on the total number of playbacks. Duplicate tracks, such as both in a single and in an album, are popularity rated differently. \n",
    "Note: This value is not updated in real-time and may therefore lag behind in actual popularity.\"\n",
    "\n",
    "## Goal of this Notebook:\n",
    "\n",
    "The goal is to use the previously retrieved data to gain insights from the popularity feature such as most popular tracks and most popular artists by analyzing and visualizing the data using Python libraries Pandas, Numpy and Matplotlib."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Shape:  (13257, 7)\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>popularity</th>\n",
       "      <th>artist_name</th>\n",
       "      <th>popularity0920</th>\n",
       "      <th>track_id</th>\n",
       "      <th>track_name</th>\n",
       "      <th>popularity0830</th>\n",
       "      <th>popularity0807</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>NaN</td>\n",
       "      <td>Travis Scott</td>\n",
       "      <td>96.0</td>\n",
       "      <td>2xLMifQCjDGFmkHkpNLD9h</td>\n",
       "      <td>SICKO MODE</td>\n",
       "      <td>94.0</td>\n",
       "      <td>86.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>NaN</td>\n",
       "      <td>6ix9ine</td>\n",
       "      <td>96.0</td>\n",
       "      <td>2E124GmJRnBJuXbTb4cPUB</td>\n",
       "      <td>FEFE (feat. Nicki Minaj &amp; Murda Beatz)</td>\n",
       "      <td>95.0</td>\n",
       "      <td>94.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>NaN</td>\n",
       "      <td>Juice WRLD</td>\n",
       "      <td>96.0</td>\n",
       "      <td>0s3nnoMeVWz3989MkNQiRf</td>\n",
       "      <td>Lucid Dreams</td>\n",
       "      <td>95.0</td>\n",
       "      <td>95.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>NaN</td>\n",
       "      <td>Drake</td>\n",
       "      <td>100.0</td>\n",
       "      <td>2G7V7zsVDxg1yRsu7Ew9RJ</td>\n",
       "      <td>In My Feelings</td>\n",
       "      <td>100.0</td>\n",
       "      <td>100.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>NaN</td>\n",
       "      <td>XXXTENTACION</td>\n",
       "      <td>95.0</td>\n",
       "      <td>3ee8Jmje8o58CHK66QrVC2</td>\n",
       "      <td>SAD!</td>\n",
       "      <td>95.0</td>\n",
       "      <td>98.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  popularity   artist_name  popularity0920                track_id  \\\n",
       "0        NaN  Travis Scott            96.0  2xLMifQCjDGFmkHkpNLD9h   \n",
       "1        NaN       6ix9ine            96.0  2E124GmJRnBJuXbTb4cPUB   \n",
       "2        NaN    Juice WRLD            96.0  0s3nnoMeVWz3989MkNQiRf   \n",
       "3        NaN         Drake           100.0  2G7V7zsVDxg1yRsu7Ew9RJ   \n",
       "4        NaN  XXXTENTACION            95.0  3ee8Jmje8o58CHK66QrVC2   \n",
       "\n",
       "                               track_name  popularity0830  popularity0807  \n",
       "0                              SICKO MODE            94.0            86.0  \n",
       "1  FEFE (feat. Nicki Minaj & Murda Beatz)            95.0            94.0  \n",
       "2                            Lucid Dreams            95.0            95.0  \n",
       "3                          In My Feelings           100.0           100.0  \n",
       "4                                    SAD!            95.0            98.0  "
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# import libraries\n",
    "import glob, os\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline\n",
    "\n",
    "# get all csv files into one variable\n",
    "path = 'Datasets/Summer2018'\n",
    "all_files = glob.glob(os.path.join(path, \"*.csv\"))\n",
    "\n",
    "# create lists of columns to be used when reading/merging the csv's\n",
    "columns = ['artist_name','track_id', 'track_name', 'popularity']\n",
    "merge_columns = ['artist_name','track_id', 'track_name']\n",
    "\n",
    "# create dataframes by reading the csv's in all_files\n",
    "df_from_each_file = (pd.read_csv(f, usecols=columns) for f in all_files)\n",
    "\n",
    "# create empty dataframe with the defined column structure\n",
    "df = pd.DataFrame(columns=columns)\n",
    "\n",
    "# loop over dataframes and merge into one dataframe\n",
    "# outer join in order to keep the popularity column from each file\n",
    "for df_, files in zip(df_from_each_file, all_files): # all_files are here to provide the column suffix (0920,0830 etc)\n",
    "    df = df.merge(df_, how='outer', on=merge_columns, suffixes=('',str(files)[-8:-4]))\n",
    "\n",
    "print('Shape: ', df.shape)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Since I have merged 3 files based on artist and track names there shouldn't be a lot duplicates.\n",
    "\n",
    "However, it is still worth to do a quick drop_duplicates here."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Shape after dropping:  (12933, 7)\n"
     ]
    }
   ],
   "source": [
    "# drop duplicate tracks\n",
    "df.drop_duplicates(subset=['artist_name','track_name'], inplace=True)\n",
    "print('Shape after dropping: ', df.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 1. Top 50 most Popular Tracks"
   ]
  },
  {
   "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>artist_name</th>\n",
       "      <th>track_name</th>\n",
       "      <th>popularity</th>\n",
       "      <th>popularity_mean</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Drake</td>\n",
       "      <td>In My Feelings</td>\n",
       "      <td>300.0</td>\n",
       "      <td>100.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>XXXTENTACION</td>\n",
       "      <td>SAD!</td>\n",
       "      <td>288.0</td>\n",
       "      <td>96.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>Cardi B</td>\n",
       "      <td>I Like It</td>\n",
       "      <td>288.0</td>\n",
       "      <td>96.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Tyga</td>\n",
       "      <td>Taste (feat. Offset)</td>\n",
       "      <td>287.0</td>\n",
       "      <td>95.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>Post Malone</td>\n",
       "      <td>Better Now</td>\n",
       "      <td>287.0</td>\n",
       "      <td>95.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>80</th>\n",
       "      <td>Clean Bandit</td>\n",
       "      <td>Solo (feat. Demi Lovato)</td>\n",
       "      <td>287.0</td>\n",
       "      <td>95.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Juice WRLD</td>\n",
       "      <td>Lucid Dreams</td>\n",
       "      <td>286.0</td>\n",
       "      <td>95.333333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>72</th>\n",
       "      <td>Calvin Harris</td>\n",
       "      <td>One Kiss (with Dua Lipa)</td>\n",
       "      <td>285.0</td>\n",
       "      <td>95.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>6ix9ine</td>\n",
       "      <td>FEFE (feat. Nicki Minaj &amp; Murda Beatz)</td>\n",
       "      <td>285.0</td>\n",
       "      <td>95.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>benny blanco</td>\n",
       "      <td>Eastside (with Halsey &amp; Khalid)</td>\n",
       "      <td>284.0</td>\n",
       "      <td>94.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>33</th>\n",
       "      <td>Tiësto</td>\n",
       "      <td>Jackie Chan</td>\n",
       "      <td>284.0</td>\n",
       "      <td>94.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>Maroon 5</td>\n",
       "      <td>Girls Like You (feat. Cardi B)</td>\n",
       "      <td>284.0</td>\n",
       "      <td>94.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>55</th>\n",
       "      <td>Jonas Blue</td>\n",
       "      <td>Rise</td>\n",
       "      <td>283.0</td>\n",
       "      <td>94.333333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>DJ Khaled</td>\n",
       "      <td>No Brainer</td>\n",
       "      <td>283.0</td>\n",
       "      <td>94.333333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>40</th>\n",
       "      <td>Nio Garcia</td>\n",
       "      <td>Te Boté - Remix</td>\n",
       "      <td>282.0</td>\n",
       "      <td>94.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>XXXTENTACION</td>\n",
       "      <td>Moonlight</td>\n",
       "      <td>281.0</td>\n",
       "      <td>93.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>58</th>\n",
       "      <td>Dynoro</td>\n",
       "      <td>In My Mind</td>\n",
       "      <td>280.0</td>\n",
       "      <td>93.333333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>144</th>\n",
       "      <td>Becky G</td>\n",
       "      <td>Sin Pijama</td>\n",
       "      <td>278.0</td>\n",
       "      <td>92.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Travis Scott</td>\n",
       "      <td>SICKO MODE</td>\n",
       "      <td>276.0</td>\n",
       "      <td>92.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>87</th>\n",
       "      <td>Martin Garrix</td>\n",
       "      <td>Ocean (feat. Khalid)</td>\n",
       "      <td>275.0</td>\n",
       "      <td>91.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>XXXTENTACION</td>\n",
       "      <td>changes</td>\n",
       "      <td>275.0</td>\n",
       "      <td>91.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>163</th>\n",
       "      <td>Ozuna</td>\n",
       "      <td>Vaina Loca</td>\n",
       "      <td>274.0</td>\n",
       "      <td>91.333333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Drake</td>\n",
       "      <td>Nonstop</td>\n",
       "      <td>274.0</td>\n",
       "      <td>91.333333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>45</th>\n",
       "      <td>5 Seconds of Summer</td>\n",
       "      <td>Youngblood</td>\n",
       "      <td>274.0</td>\n",
       "      <td>91.333333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>Post Malone</td>\n",
       "      <td>Psycho (feat. Ty Dolla $ign)</td>\n",
       "      <td>273.0</td>\n",
       "      <td>91.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>Post Malone</td>\n",
       "      <td>rockstar (feat. 21 Savage)</td>\n",
       "      <td>273.0</td>\n",
       "      <td>91.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>31</th>\n",
       "      <td>A$AP Rocky</td>\n",
       "      <td>Praise The Lord (Da Shine)</td>\n",
       "      <td>271.0</td>\n",
       "      <td>90.333333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>240</th>\n",
       "      <td>Nicky Jam</td>\n",
       "      <td>X</td>\n",
       "      <td>271.0</td>\n",
       "      <td>90.333333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>134</th>\n",
       "      <td>Marshmello</td>\n",
       "      <td>FRIENDS</td>\n",
       "      <td>270.0</td>\n",
       "      <td>90.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>Lil Baby</td>\n",
       "      <td>Yes Indeed</td>\n",
       "      <td>270.0</td>\n",
       "      <td>90.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>Drake</td>\n",
       "      <td>God's Plan</td>\n",
       "      <td>269.0</td>\n",
       "      <td>89.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>184</th>\n",
       "      <td>Shakira</td>\n",
       "      <td>Clandestino</td>\n",
       "      <td>269.0</td>\n",
       "      <td>89.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>Travis Scott</td>\n",
       "      <td>STARGAZING</td>\n",
       "      <td>269.0</td>\n",
       "      <td>89.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>397</th>\n",
       "      <td>David Guetta</td>\n",
       "      <td>Flames</td>\n",
       "      <td>268.0</td>\n",
       "      <td>89.333333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>263</th>\n",
       "      <td>Reik</td>\n",
       "      <td>Me Niego</td>\n",
       "      <td>268.0</td>\n",
       "      <td>89.333333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>177</th>\n",
       "      <td>George Ezra</td>\n",
       "      <td>Shotgun</td>\n",
       "      <td>268.0</td>\n",
       "      <td>89.333333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>66</th>\n",
       "      <td>Drake</td>\n",
       "      <td>Don’t Matter To Me (with Michael Jackson)</td>\n",
       "      <td>268.0</td>\n",
       "      <td>89.333333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>37</th>\n",
       "      <td>Zedd</td>\n",
       "      <td>Happy Now</td>\n",
       "      <td>268.0</td>\n",
       "      <td>89.333333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>89</th>\n",
       "      <td>Zedd</td>\n",
       "      <td>The Middle</td>\n",
       "      <td>267.0</td>\n",
       "      <td>89.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>35</th>\n",
       "      <td>Dean Lewis</td>\n",
       "      <td>Be Alright</td>\n",
       "      <td>267.0</td>\n",
       "      <td>89.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>107</th>\n",
       "      <td>Camila Cabello</td>\n",
       "      <td>Havana</td>\n",
       "      <td>267.0</td>\n",
       "      <td>89.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>43</th>\n",
       "      <td>Billie Eilish</td>\n",
       "      <td>lovely (with Khalid)</td>\n",
       "      <td>266.0</td>\n",
       "      <td>88.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>BlocBoy JB</td>\n",
       "      <td>Look Alive (feat. Drake)</td>\n",
       "      <td>266.0</td>\n",
       "      <td>88.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>170</th>\n",
       "      <td>Nicky Jam</td>\n",
       "      <td>X - Remix</td>\n",
       "      <td>266.0</td>\n",
       "      <td>88.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>393</th>\n",
       "      <td>Sofia Reyes</td>\n",
       "      <td>1, 2, 3 (feat. Jason Derulo &amp; De La Ghetto)</td>\n",
       "      <td>266.0</td>\n",
       "      <td>88.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>130</th>\n",
       "      <td>Selena Gomez</td>\n",
       "      <td>Back To You - From 13 Reasons Why – Season 2 S...</td>\n",
       "      <td>266.0</td>\n",
       "      <td>88.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>334</th>\n",
       "      <td>Zion &amp; Lennox</td>\n",
       "      <td>La Player (Bandolera)</td>\n",
       "      <td>265.0</td>\n",
       "      <td>88.333333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>42</th>\n",
       "      <td>Khalid</td>\n",
       "      <td>Love Lies (with Normani)</td>\n",
       "      <td>264.0</td>\n",
       "      <td>88.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>30</th>\n",
       "      <td>Imagine Dragons</td>\n",
       "      <td>Natural</td>\n",
       "      <td>264.0</td>\n",
       "      <td>88.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>44</th>\n",
       "      <td>Panic! At The Disco</td>\n",
       "      <td>High Hopes</td>\n",
       "      <td>263.0</td>\n",
       "      <td>87.666667</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             artist_name                                         track_name  \\\n",
       "3                  Drake                                     In My Feelings   \n",
       "4           XXXTENTACION                                               SAD!   \n",
       "12               Cardi B                                          I Like It   \n",
       "6                   Tyga                               Taste (feat. Offset)   \n",
       "10           Post Malone                                         Better Now   \n",
       "80          Clean Bandit                           Solo (feat. Demi Lovato)   \n",
       "2             Juice WRLD                                       Lucid Dreams   \n",
       "72         Calvin Harris                           One Kiss (with Dua Lipa)   \n",
       "1                6ix9ine             FEFE (feat. Nicki Minaj & Murda Beatz)   \n",
       "9           benny blanco                    Eastside (with Halsey & Khalid)   \n",
       "33                Tiësto                                        Jackie Chan   \n",
       "20              Maroon 5                     Girls Like You (feat. Cardi B)   \n",
       "55            Jonas Blue                                               Rise   \n",
       "14             DJ Khaled                                         No Brainer   \n",
       "40            Nio Garcia                                    Te Boté - Remix   \n",
       "7           XXXTENTACION                                          Moonlight   \n",
       "58                Dynoro                                         In My Mind   \n",
       "144              Becky G                                         Sin Pijama   \n",
       "0           Travis Scott                                         SICKO MODE   \n",
       "87         Martin Garrix                               Ocean (feat. Khalid)   \n",
       "21          XXXTENTACION                                            changes   \n",
       "163                Ozuna                                         Vaina Loca   \n",
       "8                  Drake                                            Nonstop   \n",
       "45   5 Seconds of Summer                                         Youngblood   \n",
       "18           Post Malone                       Psycho (feat. Ty Dolla $ign)   \n",
       "25           Post Malone                         rockstar (feat. 21 Savage)   \n",
       "31            A$AP Rocky                         Praise The Lord (Da Shine)   \n",
       "240            Nicky Jam                                                  X   \n",
       "134           Marshmello                                            FRIENDS   \n",
       "11              Lil Baby                                         Yes Indeed   \n",
       "23                 Drake                                         God's Plan   \n",
       "184              Shakira                                        Clandestino   \n",
       "13          Travis Scott                                         STARGAZING   \n",
       "397         David Guetta                                             Flames   \n",
       "263                 Reik                                           Me Niego   \n",
       "177          George Ezra                                            Shotgun   \n",
       "66                 Drake          Don’t Matter To Me (with Michael Jackson)   \n",
       "37                  Zedd                                          Happy Now   \n",
       "89                  Zedd                                         The Middle   \n",
       "35            Dean Lewis                                         Be Alright   \n",
       "107       Camila Cabello                                             Havana   \n",
       "43         Billie Eilish                               lovely (with Khalid)   \n",
       "28            BlocBoy JB                           Look Alive (feat. Drake)   \n",
       "170            Nicky Jam                                          X - Remix   \n",
       "393          Sofia Reyes        1, 2, 3 (feat. Jason Derulo & De La Ghetto)   \n",
       "130         Selena Gomez  Back To You - From 13 Reasons Why – Season 2 S...   \n",
       "334        Zion & Lennox                              La Player (Bandolera)   \n",
       "42                Khalid                           Love Lies (with Normani)   \n",
       "30       Imagine Dragons                                            Natural   \n",
       "44   Panic! At The Disco                                         High Hopes   \n",
       "\n",
       "     popularity  popularity_mean  \n",
       "3         300.0       100.000000  \n",
       "4         288.0        96.000000  \n",
       "12        288.0        96.000000  \n",
       "6         287.0        95.666667  \n",
       "10        287.0        95.666667  \n",
       "80        287.0        95.666667  \n",
       "2         286.0        95.333333  \n",
       "72        285.0        95.000000  \n",
       "1         285.0        95.000000  \n",
       "9         284.0        94.666667  \n",
       "33        284.0        94.666667  \n",
       "20        284.0        94.666667  \n",
       "55        283.0        94.333333  \n",
       "14        283.0        94.333333  \n",
       "40        282.0        94.000000  \n",
       "7         281.0        93.666667  \n",
       "58        280.0        93.333333  \n",
       "144       278.0        92.666667  \n",
       "0         276.0        92.000000  \n",
       "87        275.0        91.666667  \n",
       "21        275.0        91.666667  \n",
       "163       274.0        91.333333  \n",
       "8         274.0        91.333333  \n",
       "45        274.0        91.333333  \n",
       "18        273.0        91.000000  \n",
       "25        273.0        91.000000  \n",
       "31        271.0        90.333333  \n",
       "240       271.0        90.333333  \n",
       "134       270.0        90.000000  \n",
       "11        270.0        90.000000  \n",
       "23        269.0        89.666667  \n",
       "184       269.0        89.666667  \n",
       "13        269.0        89.666667  \n",
       "397       268.0        89.333333  \n",
       "263       268.0        89.333333  \n",
       "177       268.0        89.333333  \n",
       "66        268.0        89.333333  \n",
       "37        268.0        89.333333  \n",
       "89        267.0        89.000000  \n",
       "35        267.0        89.000000  \n",
       "107       267.0        89.000000  \n",
       "43        266.0        88.666667  \n",
       "28        266.0        88.666667  \n",
       "170       266.0        88.666667  \n",
       "393       266.0        88.666667  \n",
       "130       266.0        88.666667  \n",
       "334       265.0        88.333333  \n",
       "42        264.0        88.000000  \n",
       "30        264.0        88.000000  \n",
       "44        263.0        87.666667  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# sum individual popularity scores\n",
    "df['popularity'] = df[['popularity0920', 'popularity0830', 'popularity0807']].sum(axis=1)\n",
    "\n",
    "# calculate also the mean popularity score\n",
    "df['popularity_mean'] = df[['popularity0920', 'popularity0830', 'popularity0807']].mean(axis=1)\n",
    "\n",
    "# create new dataframe df_top ordered consisting of the 100 most popular tracks\n",
    "df_top = df.sort_values('popularity', ascending=False).head(100)\n",
    "\n",
    "# show the first 50 results\n",
    "df_top[['artist_name', 'track_name', 'popularity', 'popularity_mean']].head(50)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 2. Top Artists by Popularity\n",
    "\n",
    "Note: the Spotify API offers a special popularity score on artist-level as well. That score is not used here.\n",
    "\n",
    "Instead, I have used only the popularity scores of their individual tracks."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>track_name</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>artist_name</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Drake</th>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>XXXTENTACION</th>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Travis Scott</th>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Post Malone</th>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Juice WRLD</th>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Khalid</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>David Guetta</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Daddy Yankee</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Ozuna</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Nicky Jam</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Childish Gambino</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Selena Gomez</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Billie Eilish</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Tyga</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zedd</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Marshmello</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Maroon 5</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Martin Garrix</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Migos</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Maluma</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                  track_name\n",
       "artist_name                 \n",
       "Drake                      5\n",
       "XXXTENTACION               5\n",
       "Travis Scott               5\n",
       "Post Malone                5\n",
       "Juice WRLD                 3\n",
       "Khalid                     2\n",
       "David Guetta               2\n",
       "Daddy Yankee               2\n",
       "Ozuna                      2\n",
       "Nicky Jam                  2\n",
       "Childish Gambino           2\n",
       "Selena Gomez               2\n",
       "Billie Eilish              2\n",
       "Tyga                       2\n",
       "Zedd                       2\n",
       "Marshmello                 1\n",
       "Maroon 5                   1\n",
       "Martin Garrix              1\n",
       "Migos                      1\n",
       "Maluma                     1"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# show top 20 artists by number of tracks in top 100\n",
    "df_top[['artist_name','track_name']].groupby('artist_name').count().sort_values('track_name', ascending=False).head(20)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>popularity</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>artist_name</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Drake</th>\n",
       "      <td>1364.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>XXXTENTACION</th>\n",
       "      <td>1362.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Post Malone</th>\n",
       "      <td>1343.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Travis Scott</th>\n",
       "      <td>1303.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Juice WRLD</th>\n",
       "      <td>797.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Tyga</th>\n",
       "      <td>544.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Nicky Jam</th>\n",
       "      <td>537.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Ozuna</th>\n",
       "      <td>535.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zedd</th>\n",
       "      <td>535.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>David Guetta</th>\n",
       "      <td>525.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Khalid</th>\n",
       "      <td>524.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Selena Gomez</th>\n",
       "      <td>520.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Billie Eilish</th>\n",
       "      <td>518.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Daddy Yankee</th>\n",
       "      <td>515.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Childish Gambino</th>\n",
       "      <td>513.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Cardi B</th>\n",
       "      <td>288.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Clean Bandit</th>\n",
       "      <td>287.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6ix9ine</th>\n",
       "      <td>285.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Calvin Harris</th>\n",
       "      <td>285.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>benny blanco</th>\n",
       "      <td>284.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                  popularity\n",
       "artist_name                 \n",
       "Drake                 1364.0\n",
       "XXXTENTACION          1362.0\n",
       "Post Malone           1343.0\n",
       "Travis Scott          1303.0\n",
       "Juice WRLD             797.0\n",
       "Tyga                   544.0\n",
       "Nicky Jam              537.0\n",
       "Ozuna                  535.0\n",
       "Zedd                   535.0\n",
       "David Guetta           525.0\n",
       "Khalid                 524.0\n",
       "Selena Gomez           520.0\n",
       "Billie Eilish          518.0\n",
       "Daddy Yankee           515.0\n",
       "Childish Gambino       513.0\n",
       "Cardi B                288.0\n",
       "Clean Bandit           287.0\n",
       "6ix9ine                285.0\n",
       "Calvin Harris          285.0\n",
       "benny blanco           284.0"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# show top 20 artists by total popularity of their tracks in top 100\n",
    "df_top[['artist_name','popularity']].groupby('artist_name').sum().sort_values('popularity', ascending=False).head(20)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 4. Visualizing Popularity\n",
    "\n",
    "For this visualization I borrowed the code from another project of mine - [Twitter 10k (plot number 5)](https://github.com/tgel0/twitter-10k/blob/master/Twitter10k.ipynb)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 864x1296 with 10 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# create a new transposed dataframe where the track names are the columns and individual popularities the rows\n",
    "df_top10_pop = df_top[['track_name','popularity0807','popularity0830','popularity0920']].set_index('track_name').head(10).T\n",
    "\n",
    "# set the figure size\n",
    "plt.figure(figsize=(12,18))\n",
    " \n",
    "# create a color palette\n",
    "palette = plt.get_cmap('Set1')\n",
    "\n",
    "# multiple line plot of the top10 track popularities\n",
    "num=0\n",
    "for track in df_top10_pop.columns:\n",
    "    num+=1\n",
    " \n",
    "    # find the right spot on the plot\n",
    "    plt.subplot(10,1, num)\n",
    "    \n",
    "    # plot the individual popularities\n",
    "    df_top10_pop.loc[['popularity0807', 'popularity0830', 'popularity0920'],track].plot(marker='', color=palette(num), linewidth=2.5)\n",
    "    \n",
    "    # same limits for every subplot\n",
    "    plt.ylim(90,100)\n",
    "    \n",
    "    # get current position of the ticks\n",
    "    locs, labels = plt.xticks()\n",
    "\n",
    "    # add ticks with custom labels\n",
    "    mylabels = ['','7th August', '','', '','30th August', '','','', '20th September'] # a bit ugly but it works\n",
    "    plt.xticks(locs, mylabels)\n",
    "\n",
    "    # not ticks everywhere\n",
    "    if num in range(10) :\n",
    "        plt.tick_params(labelbottom=False)\n",
    "        \n",
    "    # add title\n",
    "    plt.title(track, loc='left', fontsize=10, fontweight=0, color=palette(num))\n",
    "    \n",
    "# add general title\n",
    "plt.suptitle(\"Popularity of Top 10 Tracks during Summer 2018\", fontsize=13, fontweight=0, color='black', style='italic');"
   ]
  }
 ],
 "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": "3.5.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}