{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "from tqdm import tqdm\n",
    "from suno_utils.utils.text import read_jsonl, write_jsonl\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "# load the popularity matching metas \n",
    "genius_popularity_metas = read_jsonl(\"/home/christian/code/christian/metadata/popularity/genius_hq_chart_metas.jsonl\")\n",
    "genius_popularity_metas_map = {meta[\"id\"] : meta for meta in genius_popularity_metas}\n",
    "youtube_popularity_metas = read_jsonl(\"/home/christian/code/christian/metadata/popularity/youtube_music_chart_metas.jsonl\")\n",
    "youtube_popularity_metas_map = {meta[\"id\"] : meta for meta in youtube_popularity_metas}\n",
    "\n",
    "# combine the two maps\n",
    "popularity_metas_map = {**genius_popularity_metas_map, **youtube_popularity_metas_map}\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# load the base jsonl file \n",
    "base_dir = \"/app/suno/data/diffusion_mix/dac_vae_fixed_25hz/\"\n",
    "\n",
    "for subset in [\"val\", \"tr\"]:\n",
    "    base_jsonl = os.path.join(base_dir, f\"metas_{subset}.jsonl\")\n",
    "    base_metas = read_jsonl(base_jsonl)\n",
    "    print(len(base_metas))\n",
    "\n",
    "    new_subset_metas = []\n",
    "\n",
    "    found_ids = []\n",
    "    for base_meta in tqdm(base_metas):\n",
    "        new_meta = base_meta.copy()\n",
    "\n",
    "        # check if the id is in the combined_ap dataframe\n",
    "        if base_meta[\"id\"] in popularity_metas_map:\n",
    "            # add the audio production features to the base meta\n",
    "            tags_dict = popularity_metas_map[base_meta[\"id\"]]\n",
    "            tags = tags_dict[\"tags\"]\n",
    "            new_meta[\"tags\"].extend(tags)\n",
    "            found_ids.append(base_meta[\"id\"])\n",
    "        \n",
    "        new_subset_metas.append(new_meta)\n",
    "\n",
    "    print(f\"Found {len(found_ids)}/{len(base_metas)} ids in the combined_ap dataframe\")\n",
    "    # write the updated base metas to a new jsonl file\n",
    "    write_jsonl(new_subset_metas, os.path.join(base_dir, f\"metas_{subset}_with_popularity_tags.jsonl\"))\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "popularity_metas_map[found_ids[30]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "for subset_meta in new_subset_metas:\n",
    "    tags = subset_meta[\"tags\"]\n",
    "    if \"Billboard\" in tags:\n",
    "        print(subset_meta)\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "suno_env",
   "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": "3.10.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}