Skip to content

Instantly share code, notes, and snippets.

Show Gist options
  • Select an option

  • Save unarist/e01f93d743b44656cde70a0416ffddf6 to your computer and use it in GitHub Desktop.

Select an option

Save unarist/e01f93d743b44656cde70a0416ffddf6 to your computer and use it in GitHub Desktop.
Filter "Spotify Extended Streaming History"
Display the source blob
Display the rendered blob
Raw
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"id": "f7835c5f",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import glob\n",
"\n",
"df = pd.concat([pd.read_json(file) for file in glob.glob(\"*.json\")], ignore_index=True)\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "025da194",
"metadata": {},
"outputs": [],
"source": [
"df2 = df.copy()\n",
"df2[\"ip_addr\"] = \"0.0.0.0\"\n",
"df2[\"conn_country\"] = \"\"\n",
"df2[\"platform\"] = \"\"\n",
"df2 = df2[df2[\"skipped\"] == False]\n",
"df2 = df2[~df2[\"episode_name\"].notna()]\n",
"df2 = df2[df2[\"ms_played\"] > 120000]\n",
"df2\n",
"# print(df2.groupby(\"master_metadata_album_artist_name\").size().sort_values(ascending=False).to_dict())\n",
"# pd.to_datetime(df2['ts']).hist(bins=50)\n",
"# df2.to_json(\"Streaming_History_Audio_2000-2099_0.json\", orient=\"records\", lines=False, force_ascii=False, indent=2)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "spotify-extended-streaming-history",
"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": "3.13.2"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment