{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ac1c2d62",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "\n",
    "filepath = \"/home/tony/Data/user_upload_df_20250601_to_20250820.pkl\"\n",
    "df = pd.read_pickle(filepath)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e907dc40",
   "metadata": {},
   "outputs": [],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8e9e272a",
   "metadata": {},
   "outputs": [],
   "source": [
    "# filter to wav only\n",
    "df_filtered = df[df.s3_files.apply(lambda x: x[0].endswith(\"wav\"))]\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e81a95bd",
   "metadata": {},
   "outputs": [],
   "source": [
    "print(len(df_filtered))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "4b9ba2c6",
   "metadata": {},
   "outputs": [],
   "source": [
    "s3_bucket = \"s3://suno-uploads/raw_uploads/\"\n",
    "\n",
    "from suno_utils.audio import Audio\n",
    "\n",
    "idx = 80\n",
    "print(df_filtered.iloc[idx].title)\n",
    "filepath = f\"{s3_bucket}{df_filtered.iloc[idx].id}.{df_filtered.iloc[idx].s3_files[0]}\"\n",
    "print(filepath)\n",
    "audio = Audio.from_s3(filepath, n_channels=2).play()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bfd45ad1",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "suno_diff",
   "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": "3.12.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}