{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0",
   "metadata": {},
   "outputs": [],
   "source": [
    "from suno_utils.utils.text import read_json, write_json\n",
    "from suno_utils.gpt import chirp_v2_5 as chirp_v3\n",
    "from suno_utils.tasks.ditto_v2 import preload_models\n",
    "from suno_utils.tasks.ditto_v2 import encode_overlap as encode, SAMPLE_RATE, load_model\n",
    "from suno_utils.utils.clip import SunoClip\n",
    "import numpy as np\n",
    "from tqdm import tqdm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "1",
   "metadata": {},
   "outputs": [],
   "source": [
    "def cosine_similarity(a, b):\n",
    "    dot_product = np.dot(a, b)\n",
    "\n",
    "    magnitude_a = np.sqrt(np.dot(a, a))\n",
    "    magnitude_b = np.sqrt(np.dot(b, b))\n",
    "\n",
    "    return dot_product / (magnitude_a * magnitude_b)\n",
    "\n",
    "\n",
    "model_filepath = \"s3://suno-data/minz/models/ditto_v2_epoch_57.pt\"\n",
    "model_path = chirp_v3._get_model_if_needed(model_filepath)\n",
    "_ = preload_models(\n",
    "    model_filepath=model_path,\n",
    ")\n",
    "ditto = load_model()[\"model\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2",
   "metadata": {},
   "outputs": [],
   "source": [
    "subgenres = read_json(\n",
    "    \"/home/sara/glockenspiel/suno_utils/task_eval/rate_your_music_filtered.json\"\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3",
   "metadata": {},
   "outputs": [],
   "source": [
    "genres_to_skip = [\n",
    "    \"Easy Listening\",\n",
    "    \"Scenes & Movements\",\n",
    "    \"Singer-Songwriter\",\n",
    "    \"Spoken Word\",\n",
    "    \"ASMR\",\n",
    "    \"Bugle Call\",\n",
    "    \"Comedy\",\n",
    "    \"Field Recordings\",\n",
    "    \"Sound Effects\",\n",
    "    \"YTPMV\",\n",
    "    \"Mechanical Music\",\n",
    "    \"Mashup\",\n",
    "    \"Parlour Music\",\n",
    "]\n",
    "\n",
    "genres_to_skip = []"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "4",
   "metadata": {},
   "outputs": [],
   "source": [
    "name_to_parent = {}\n",
    "name_to_embed = {}\n",
    "num_subgenres = {}\n",
    "filtered_subgenres = []\n",
    "for genre in tqdm(subgenres):\n",
    "    name = genre[\"name\"]\n",
    "    parent = genre[\"parent_genre\"]\n",
    "    if parent not in num_subgenres:\n",
    "        print(parent)\n",
    "        num_subgenres[parent] = 0\n",
    "    if name in genres_to_skip or parent in genres_to_skip:\n",
    "        continue\n",
    "    # elif genre[\"level\"] > 2:\n",
    "    #    continue\n",
    "    # elif num_subgenres[parent] >= 10:\n",
    "    #    continue\n",
    "    name_to_parent[name] = parent if parent is not None else None\n",
    "    encoding_txt = ditto.text_to_latent(f\"[CLS][Genre]{name}\").squeeze().cpu().numpy()\n",
    "    name_to_embed[name] = encoding_txt\n",
    "    num_subgenres[parent] += 1\n",
    "    filtered_subgenres.append(genre)\n",
    "\n",
    "print(len(filtered_subgenres))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5",
   "metadata": {},
   "outputs": [],
   "source": [
    "np.savez(\"/home/sara/glockenspiel/z_scratch/subgenre_ditto_map.npz\", **name_to_embed)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6",
   "metadata": {},
   "outputs": [],
   "source": [
    "test = np.load(\"/home/sara/glockenspiel/z_scratch/subgenre_ditto_map.npz\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7",
   "metadata": {},
   "outputs": [],
   "source": [
    "for key in test.keys():\n",
    "    print(key)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8",
   "metadata": {},
   "outputs": [],
   "source": [
    "np.save()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9",
   "metadata": {},
   "outputs": [],
   "source": [
    "for genre in filtered_subgenres:\n",
    "    print(genre[\"name\"], genre[\"parent_genre\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "10",
   "metadata": {},
   "outputs": [],
   "source": [
    "write_json(filtered_subgenres, \"rate_your_music_filtered.json\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "11",
   "metadata": {},
   "outputs": [],
   "source": [
    "clip = SunoClip(\"6c9403f3-1c2c-4496-97b6-bd0abd6ad2f3\")\n",
    "audio = clip.audio()\n",
    "audio = audio.convert(sample_rate=SAMPLE_RATE, n_channels=1, byte_width=2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "12",
   "metadata": {},
   "outputs": [],
   "source": [
    "encoding = encode([audio], task=\"genre_sim\")[0]\n",
    "encoding_mean = np.mean(encoding, axis=0)\n",
    "print(encoding_mean.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "13",
   "metadata": {},
   "outputs": [],
   "source": [
    "encoding_txt = ditto.text_to_latent(\"[CLS][Genre]ambient\").squeeze().cpu().numpy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "14",
   "metadata": {},
   "outputs": [],
   "source": [
    "cosine_similarity(encoding_mean, encoding_txt)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "15",
   "metadata": {},
   "outputs": [],
   "source": [
    "cosine_similarity(\n",
    "    name_to_embed[\"dark ambient\"], name_to_embed[name_to_parent[\"dark ambient\"]]\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "16",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "suno_clean",
   "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": "3.10.15"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}