File size: 9,429 Bytes
a852755 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 | {
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Importing the libraries"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"import pandas as pd\n",
"import numpy as np\n",
"import json\n",
"import spotipy\n",
"import spotipy.oauth2 as oauth2\n",
"from spotipy.oauth2 import SpotifyOAuth,SpotifyClientCredentials\n",
"import yaml\n",
"import re\n",
"from tqdm import tqdm\n",
"import multiprocessing as mp\n",
"import time\n",
"import random\n",
"import datetime"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"stream= open(\"spotify/spotify.yaml\")\n",
"spotify_details = yaml.safe_load(stream)\n",
"auth_manager = SpotifyClientCredentials(client_id=spotify_details['Client_id'],\n",
" client_secret=spotify_details['client_secret'])\n",
"sp = spotipy.client.Spotify(auth_manager=auth_manager)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Importing the dataset"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"- Reading the 1 million playlists and keeping only the unique track URIs for the content-based recommendation system.\n",
"- The first for loop Read the 1,000 JSON files one at a time.\n",
"- The second for loop is for getting only the unique track."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"def loop_slices(path, num_slices=20):\n",
" cnt = 0\n",
" cnt1 = 0\n",
" mpd_playlists = []\n",
" unique_tracks= pd.DataFrame()\n",
" filenames = os.listdir(path)\n",
" for fname in tqdm(sorted(filenames, key=len)):\n",
" if fname.startswith(\"mpd.slice.\") and fname.endswith(\".json\"):\n",
" cnt += 1\n",
" fullpath = os.sep.join((path, fname))\n",
" f = open(fullpath)\n",
" js = f.read()\n",
" f.close()\n",
" current_slice = json.loads(js)\n",
" # Create a list of all playlists\n",
" for playlist in current_slice['playlists']:\n",
" cnt1 +=1\n",
" mpd_playlists.append(playlist)\n",
" if cnt1 == 1000:\n",
" cnt1=0\n",
" temp=pd.DataFrame(mpd_playlists)\n",
" temp=temp.explode('tracks')\n",
" temp=pd.DataFrame(temp['tracks'].apply(pd.Series))\n",
" unique_tracks=pd.concat([unique_tracks,temp],axis=0)\n",
" unique_tracks.drop_duplicates(subset=['track_uri'],inplace=True)\n",
" mpd_playlists = []\n",
" if cnt == num_slices:\n",
" break\n",
" return unique_tracks\n",
"# Path where the json files are extracted\n",
"path = 'spotify_million_playlist_dataset/data/'"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df = loop_slices(path, num_slices=1000)\n",
"df.to_csv('data/1m.csv')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df[\"track_uri\"] = df[\"track_uri\"].apply(lambda x: re.findall(r'\\w+$', x)[0])\n",
"df[\"artist_uri\"] = df[\"artist_uri\"].apply(lambda x: re.findall(r'\\w+$', x)[0])\n",
"df[\"album_uri\"] = df[\"album_uri\"].apply(lambda x: re.findall(r'\\w+$', x)[0])"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"df=pd.read_csv('Data/1mV3.csv') #Dropped all columns except ['track_uri', 'artist_uri', 'album_uri']"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Index(['track_uri', 'artist_uri', 'album_uri'], dtype='object')"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.columns"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"t_uri=df[\"track_uri\"].unique()\n",
"a_uri=df[\"artist_uri\"].unique()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Feature extraction"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Using the Spotify API for Feature Extraction and Saving Results to a CSV File and Errors to a Log File\n",
"\n",
"I was using SP.track first, but I realised that it would take a lot of time and I would have to counter a lot of Api rate limits, so I used SP.tracks and SP.artists instead. They accept lists with a 50-URI maximum and handle them in a single request, so it took a lot less time."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"f = open('data/audio_features.csv','a')\n",
"e=0\n",
"for i in tqdm(range(0,len(t_uri),100)):\n",
" try:\n",
" track_feature = sp.audio_features(t_uri[i:i+100])\n",
" track_df = pd.DataFrame(track_feature)\n",
" csv_data = track_df.to_csv(header=False,index=False)\n",
" f.write(csv_data)\n",
" except Exception as error:\n",
" e+=1\n",
" r = open(\"audio_features_log.txt\", \"a\")\n",
" r.write(datetime.datetime.now().strftime(\"%d.%b %Y %H:%M:%S\")+\": \"+str(error)+'\\n')\n",
" r.close()\n",
" time.sleep(3)\n",
" continue\n",
"r = open(\"audio_features_log.txt\", \"a\")\n",
"r.write(datetime.datetime.now().strftime(\"%d.%b %Y %H:%M:%S\")+\" _________________________ \"+\"Total Number Of Errors : \"+str(e)+\" _________________________ \"+'\\n')\n",
"r.close()\n",
"f.close()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"f = open('data/track_features.csv','a')\n",
"e=0\n",
"for i in tqdm(range(0,len(t_uri),50)):\n",
" try:\n",
" track_features = sp.tracks(t_uri[i:i+50])\n",
" for x in range(50):\n",
" track_pop=pd.DataFrame([t_uri[i+x]])\n",
" track_pop['release_date']=track_features['tracks'][x]['album']['release_date']\n",
" track_pop['pop'] = track_features['tracks'][x][\"popularity\"]\n",
" csv_data = track_pop.to_csv(header=False,index=False)\n",
" f.write(csv_data)\n",
" except Exception as error:\n",
" e+=1\n",
" r = open(\"track_features.txt\", \"a\")\n",
" r.write(datetime.datetime.now().strftime(\"%d.%b %Y %H:%M:%S\")+\": \"+str(error)+'\\n')\n",
" r.close()\n",
" time.sleep(3)\n",
" continue\n",
"r = open(\"track_features.txt\", \"a\")\n",
"r.write(datetime.datetime.now().strftime(\"%d.%b %Y %H:%M:%S\")+\" _________________________ \"+\"Total Number Of Errors : \"+str(e)+\" _________________________ \"+'\\n')\n",
"r.close()\n",
"f.close()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"f = open('data/artist_features.csv','a')\n",
"e=0\n",
"for i in tqdm(range(0,len(a_uri),50)):\n",
" try:\n",
" artist_features = sp.artists(a_uri[i:i+50])\n",
" for x in range(50):\n",
" artist_df=pd.DataFrame([a_uri[i+x]])\n",
" artist_pop = artist_features['artists'][x][\"popularity\"]\n",
" artist_genres = artist_features['artists'][x][\"genres\"]\n",
" artist_df[\"artist_pop\"] = artist_pop\n",
" if artist_genres: \n",
" artist_df[\"genres\"] = \" \".join([re.sub(' ','_',i) for i in artist_genres])\n",
" else:\n",
" artist_df[\"genres\"] = \"unknown\"\n",
" csv_data = artist_df.to_csv(header=False,index=False)\n",
" f.write(csv_data)\n",
" except Exception as error:\n",
" e+=1\n",
" r = open(\"artist_features.txt\", \"a\")\n",
" r.write(datetime.datetime.now().strftime(\"%d.%b %Y %H:%M:%S\")+\": \"+str(error)+'\\n')\n",
" r.close()\n",
" time.sleep(3)\n",
" continue\n",
"r = open(\"artist_features.txt\", \"a\")\n",
"r.write(datetime.datetime.now().strftime(\"%d.%b %Y %H:%M:%S\")+\" _________________________ \"+\"Total Number Of Errors : \"+str(e)+\" _________________________ \"+'\\n')\n",
"r.close()\n",
"f.close()"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3.9.13 ('base')",
"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": "3.9.13"
},
"orig_nbformat": 4,
"vscode": {
"interpreter": {
"hash": "e246d2215c418239c9316a1ebf2d8abb44dc50b2e5b0e29defd87143398aa387"
}
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|