Added another data source
[battle-of-the-bands.git] / beatles-vs-stones-gather-data.ipynb
index a902935c59d59193144e34405faaaec8cde59644..05b77a0e81f4ae0b21d7041de35237790c0341c9 100644 (file)
     "\n",
     "I'm also on a bit of a Beatles jag, so I've also done the analysis for Beatles songs.\n",
     "\n",
-    "http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0115255#s5\n",
-    "https://www.discogs.com/developers/#page:database,header:database-artist-releases\n",
-    "http://data.discogs.com/\n",
+    "### Some data sources\n",
+    "\n",
+    "* http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0115255#s5\n",
+    "* https://www.discogs.com/developers/#page:database,header:database-artist-releases\n",
+    "* http://data.discogs.com/\n",
+    "\n",
+    "* https://labrosa.ee.columbia.edu/millionsong/\n",
+    "\n",
+    "* https://twitter.com/kcimc/status/893855561590157312?s=09 and https://drive.google.com/file/d/0B9tyIRZ76JCdN3NtaVpPU3c4QWs/view (stored locally in the [1m.pkl](1m.pkl) folder)\n",
     "\n",
     "\n",
     "## Contents\n",
   {
    "cell_type": "code",
    "execution_count": 3,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "# try:\n",
   {
    "cell_type": "code",
    "execution_count": 4,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "# Create a database and a collections within it.\n",
   {
    "cell_type": "code",
    "execution_count": 5,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 6,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "def get_artists(artist_name):\n",
   {
    "cell_type": "code",
    "execution_count": 7,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 8,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 9,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "def get_albums(artist_id):\n",
   {
    "cell_type": "code",
    "execution_count": 41,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 13,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 13,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
    "cell_type": "code",
    "execution_count": 11,
    "metadata": {
-    "collapsed": false,
     "scrolled": true
    },
    "outputs": [
   {
    "cell_type": "code",
    "execution_count": 16,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "def get_tracks(album_id):\n",
    "cell_type": "code",
    "execution_count": 45,
    "metadata": {
-    "collapsed": false,
     "scrolled": true
    },
    "outputs": [
    "cell_type": "code",
    "execution_count": 17,
    "metadata": {
-    "collapsed": false,
     "scrolled": true
    },
    "outputs": [
    "cell_type": "code",
    "execution_count": 18,
    "metadata": {
-    "collapsed": false,
     "scrolled": true
    },
    "outputs": [
   {
    "cell_type": "code",
    "execution_count": 49,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 15,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
    "cell_type": "code",
    "execution_count": 16,
    "metadata": {
-    "collapsed": false,
     "scrolled": true
    },
    "outputs": [
   {
    "cell_type": "code",
    "execution_count": 30,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "a_type, a_token = get_spotify_auth_token()\n",
    "cell_type": "code",
    "execution_count": 37,
    "metadata": {
-    "collapsed": false,
     "scrolled": true
    },
    "outputs": [
    "cell_type": "code",
    "execution_count": 33,
    "metadata": {
-    "collapsed": false,
     "scrolled": true
    },
    "outputs": [
   {
    "cell_type": "code",
    "execution_count": 38,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 35,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 31,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 39,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "def genius_artist_search(artist_name, per_page=20):\n",
   {
    "cell_type": "code",
    "execution_count": 40,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 41,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 42,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "def genius_song_search(artist_id):\n",
   {
    "cell_type": "code",
    "execution_count": 43,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 44,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 45,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
    "cell_type": "code",
    "execution_count": 46,
    "metadata": {
-    "collapsed": false,
     "scrolled": false
    },
    "outputs": [
   {
    "cell_type": "code",
    "execution_count": 47,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "def genius_lyrics(song_url):\n",
   {
    "cell_type": "code",
    "execution_count": 48,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 49,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 50,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
    "cell_type": "code",
    "execution_count": 51,
    "metadata": {
-    "collapsed": false,
     "scrolled": true
    },
    "outputs": [
   {
    "cell_type": "code",
    "execution_count": 53,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 55,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
    "cell_type": "code",
    "execution_count": 56,
    "metadata": {
-    "collapsed": false,
     "scrolled": true
    },
    "outputs": [
   {
    "cell_type": "code",
    "execution_count": 57,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 58,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 59,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 52,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 79,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 80,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "for t in tracks.find({}, ['ctitle', 'duration_ms']):\n",
    "cell_type": "code",
    "execution_count": 81,
    "metadata": {
-    "collapsed": false,
     "scrolled": true
    },
    "outputs": [],
   {
    "cell_type": "code",
    "execution_count": 82,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 83,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 84,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 85,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 86,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 88,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 89,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
    "cell_type": "code",
    "execution_count": 90,
    "metadata": {
-    "collapsed": false,
     "scrolled": true
    },
    "outputs": [
    "cell_type": "code",
    "execution_count": 91,
    "metadata": {
-    "collapsed": false,
     "scrolled": true
    },
    "outputs": [
   {
    "cell_type": "code",
    "execution_count": 92,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 93,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 95,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 97,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 471,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 98,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
    "cell_type": "code",
    "execution_count": 99,
    "metadata": {
-    "collapsed": false,
     "scrolled": true
    },
    "outputs": [
   {
    "cell_type": "code",
    "execution_count": 100,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 101,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 102,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 103,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 104,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 105,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
    "cell_type": "code",
    "execution_count": 106,
    "metadata": {
-    "collapsed": false,
     "scrolled": true
    },
    "outputs": [
   {
    "cell_type": "code",
    "execution_count": 107,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 108,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 109,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
    "cell_type": "code",
    "execution_count": 110,
    "metadata": {
-    "collapsed": false,
     "scrolled": true
    },
    "outputs": [],
    "cell_type": "code",
    "execution_count": 111,
    "metadata": {
-    "collapsed": false,
     "scrolled": true
    },
    "outputs": [
    "cell_type": "code",
    "execution_count": 112,
    "metadata": {
-    "collapsed": false,
     "scrolled": true
    },
    "outputs": [
   {
    "cell_type": "code",
    "execution_count": 113,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 114,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 115,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 116,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 117,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
    "cell_type": "code",
    "execution_count": 118,
    "metadata": {
-    "collapsed": false,
     "scrolled": true
    },
    "outputs": [
    "cell_type": "code",
    "execution_count": 119,
    "metadata": {
-    "collapsed": false,
     "scrolled": true
    },
    "outputs": [
   {
    "cell_type": "code",
    "execution_count": 120,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 121,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 122,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "pipeline = [\n",
   {
    "cell_type": "code",
    "execution_count": 123,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   {
    "cell_type": "code",
    "execution_count": 124,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
   }
  },
  "nbformat": 4,
- "nbformat_minor": 0
+ "nbformat_minor": 1
 }