{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Fetch the npz from s3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-26T00:36:56.065152Z",
     "start_time": "2024-05-26T00:36:54.886147Z"
    },
    "execution": {
     "iopub.execute_input": "2025-05-02T03:50:59.376588Z",
     "iopub.status.busy": "2025-05-02T03:50:59.376355Z",
     "iopub.status.idle": "2025-05-02T03:51:00.828392Z",
     "shell.execute_reply": "2025-05-02T03:51:00.827911Z",
     "shell.execute_reply.started": "2025-05-02T03:50:59.376571Z"
    }
   },
   "outputs": [],
   "source": [
    "import ast\n",
    "import os\n",
    "import sys\n",
    "from collections import defaultdict\n",
    "\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "from sklearn.model_selection import train_test_split\n",
    "from suno_utils.utils.s3 import download_s3_files\n",
    "from suno_utils.utils.text import read_json, read_jsonl, write_json, write_jsonl\n",
    "from tqdm import tqdm\n",
    "\n",
    "sys.path.insert(0, \"/home/tony/Work/neon/sunoGPT/scripts/\")\n",
    "\n",
    "import numpy as np\n",
    "from data_preparation_7b import *"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-26T00:36:56.068073Z",
     "start_time": "2024-05-26T00:36:56.066469Z"
    },
    "execution": {
     "iopub.execute_input": "2025-05-02T03:51:00.829079Z",
     "iopub.status.busy": "2025-05-02T03:51:00.828901Z",
     "iopub.status.idle": "2025-05-02T03:51:00.830997Z",
     "shell.execute_reply": "2025-05-02T03:51:00.830675Z",
     "shell.execute_reply.started": "2025-05-02T03:51:00.829065Z"
    }
   },
   "outputs": [],
   "source": [
    "OUT_DATA_DIR = \"/app/suno/data/dpo/v0_1_full/\"\n",
    "# NPZ_DIR = \"/app/suno/data/dpo/13b_npz\"\n",
    "NPZ_DIR = \"/app/suno/data/dpo/13b_s32_npz\"\n",
    "# NPZ_DIR = \"/app/suno/data/dpo/concat_npz\"\n",
    "JSON_DIR = \"/app/suno/data/dpo/13b_s32_json\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-05-02T03:51:00.831587Z",
     "iopub.status.busy": "2025-05-02T03:51:00.831381Z",
     "iopub.status.idle": "2025-05-02T03:51:00.833381Z",
     "shell.execute_reply": "2025-05-02T03:51:00.833063Z",
     "shell.execute_reply.started": "2025-05-02T03:51:00.831575Z"
    }
   },
   "outputs": [],
   "source": [
    "# data_csv_path = \"/home/tony/Data/Preference/13b_v0/interesting_clips_ft_1_20240718.csv\"\n",
    "# data_csv_path = \"/home/tony/Data/Preference/13b_v0/interesting_clips_v3p5_s_8_20240813.csv\"\n",
    "# data_csv_path = \"/home/tony/Data/Preference/13b_v0/interesting_clips_v3p5_s_8_20240830_full.pkl\"\n",
    "# data_csv_path = \"/home/tony/Data/Preference/30b_v2/interesting_clips_13b_s8_20240925_full_l10.pkl\"\n",
    "# data_csv_path = \"/home/tony/Data/Preference/13b_v1/interesting_clips_13b_s8_v29_20241029_full.pkl\"\n",
    "# data_csv_path = \"/home/tony/Data/Preference/13b_v31/interesting_clips_v4_h_s_31_20241214_full.pkl\"\n",
    "# data_csv_path = \"/home/tony/Data/Preference/13b_v32/interesting_clips_v4_h_s_32_20250219_full.pkl\"\n",
    "data_csv_path = \"/home/tony/Data/Preference/13b_v32/interesting_clips_v4_h_s_32_20250501_full_long.pkl\"\n",
    "# data_csv_path = \"/home/tony/Data/Preference/30b_v2/concat_clips_20240908_v0.pkl\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-26T00:36:59.932066Z",
     "start_time": "2024-05-26T00:36:56.069087Z"
    },
    "execution": {
     "iopub.execute_input": "2025-05-02T03:51:00.833965Z",
     "iopub.status.busy": "2025-05-02T03:51:00.833755Z",
     "iopub.status.idle": "2025-05-02T03:52:14.871526Z",
     "shell.execute_reply": "2025-05-02T03:52:14.871114Z",
     "shell.execute_reply.started": "2025-05-02T03:51:00.833954Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(2962820, 90)"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# df = pd.read_csv(data_csv_path)\n",
    "df = pd.read_pickle(data_csv_path)\n",
    "df.shape\n",
    "# v2: (2341508, 31)\n",
    "# v3: (2609830, 31)\n",
    "# v4: (1926120, 35)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-05-02T03:52:14.872900Z",
     "iopub.status.busy": "2025-05-02T03:52:14.872704Z",
     "iopub.status.idle": "2025-05-02T03:52:16.076612Z",
     "shell.execute_reply": "2025-05-02T03:52:16.076123Z",
     "shell.execute_reply.started": "2025-05-02T03:52:14.872886Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(2962820, 90)\n",
      "model_name\n",
      "chirp-v4-h-s-32    2962820\n",
      "Name: count, dtype: int64\n"
     ]
    }
   ],
   "source": [
    "df = df[df[\"model_name\"].str.contains(\"v4\")]\n",
    "print(df.shape)\n",
    "# for extend, also fetch their parents\n",
    "print(df[\"model_name\"].value_counts())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-05-02T03:52:16.077318Z",
     "iopub.status.busy": "2025-05-02T03:52:16.077151Z",
     "iopub.status.idle": "2025-05-02T03:52:16.079041Z",
     "shell.execute_reply": "2025-05-02T03:52:16.078715Z",
     "shell.execute_reply.started": "2025-05-02T03:52:16.077306Z"
    }
   },
   "outputs": [],
   "source": [
    "# if \"extend\" in data_csv_path:\n",
    "# test_slice = df[\"metadata\"].apply(lambda x: ast.literal_eval(x))\n",
    "# test_slice_series = test_slice.apply(pd.Series)\n",
    "# df = pd.concat([df, test_slice_series], axis=1, join=\"inner\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-26T00:36:59.940064Z",
     "start_time": "2024-05-26T00:36:59.933947Z"
    },
    "execution": {
     "iopub.execute_input": "2025-05-02T03:52:16.079694Z",
     "iopub.status.busy": "2025-05-02T03:52:16.079424Z",
     "iopub.status.idle": "2025-05-02T03:52:16.554672Z",
     "shell.execute_reply": "2025-05-02T03:52:16.554170Z",
     "shell.execute_reply.started": "2025-05-02T03:52:16.079682Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2962820\n",
      "full 2962820\n"
     ]
    }
   ],
   "source": [
    "# download all clips; 883k\n",
    "from suno_utils.utils.s3 import download_s3_files\n",
    "\n",
    "s3_ids = df[\"s3_id\"].values\n",
    "print(len(s3_ids))\n",
    "# s3_ids = set(s3_ids).union(set(df[\"audio_prompt_id\"].values))\n",
    "print(\"full\", len(s3_ids))\n",
    "s3_paths = [f\"s3://suno-data-uploads/studio/uploads/{s3_id}.npz\" for s3_id in s3_ids]\n",
    "local_paths = [f\"{NPZ_DIR}/{s3_id}.npz\" for s3_id in s3_ids]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-26T00:37:00.153602Z",
     "start_time": "2024-05-26T00:36:59.941125Z"
    },
    "execution": {
     "iopub.execute_input": "2025-05-02T03:52:16.555481Z",
     "iopub.status.busy": "2025-05-02T03:52:16.555200Z",
     "iopub.status.idle": "2025-05-02T03:55:56.871459Z",
     "shell.execute_reply": "2025-05-02T03:55:56.870960Z",
     "shell.execute_reply.started": "2025-05-02T03:52:16.555468Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "jobs to be done 300146 300146\n"
     ]
    }
   ],
   "source": [
    "finished_paths = os.listdir(NPZ_DIR)\n",
    "finished_paths_set = set(finished_paths)\n",
    "unfinished_s3_paths = [\n",
    "    path for path in s3_paths if os.path.basename(path) not in finished_paths_set\n",
    "]\n",
    "unfinished_paths = [\n",
    "    path for path in local_paths if os.path.basename(path) not in finished_paths_set\n",
    "]\n",
    "unfinished_ids_set = set([os.path.basename(path).replace(\".npz\", \"\") for path in unfinished_paths])\n",
    "unfinished_ids = [i for i in s3_ids if i in unfinished_ids_set]\n",
    "print(\"jobs to be done\", len(unfinished_paths), len(unfinished_s3_paths))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-26T00:49:33.275556Z",
     "start_time": "2024-05-26T00:37:00.154648Z"
    },
    "execution": {
     "iopub.execute_input": "2025-05-02T03:55:56.872184Z",
     "iopub.status.busy": "2025-05-02T03:55:56.871961Z",
     "iopub.status.idle": "2025-05-02T09:29:29.019360Z",
     "shell.execute_reply": "2025-05-02T09:29:29.018716Z",
     "shell.execute_reply.started": "2025-05-02T03:55:56.872171Z"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████| 301/301 [5:33:28<00:00, 66.47s/it]\n"
     ]
    }
   ],
   "source": [
    "_ = download_s3_files(unfinished_s3_paths, unfinished_paths, n_cores=32)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-26T00:59:42.420025Z",
     "start_time": "2024-05-26T00:49:33.276845Z"
    },
    "execution": {
     "iopub.execute_input": "2025-05-02T09:29:29.020207Z",
     "iopub.status.busy": "2025-05-02T09:29:29.020056Z",
     "iopub.status.idle": "2025-05-02T09:34:50.641884Z",
     "shell.execute_reply": "2025-05-02T09:34:50.641298Z",
     "shell.execute_reply.started": "2025-05-02T09:29:29.020192Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "jobs to be done 997 997\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [01:05<00:00, 65.47s/it]\n"
     ]
    }
   ],
   "source": [
    "# # deleted files are at: deleted; try to get them as well\n",
    "finished_paths = os.listdir(NPZ_DIR)\n",
    "finished_paths_set = set(finished_paths)\n",
    "unfinished_s3_paths = [\n",
    "    path for path in s3_paths if os.path.basename(path) not in finished_paths_set\n",
    "]\n",
    "unfinished_paths = [\n",
    "    path for path in local_paths if os.path.basename(path) not in finished_paths_set\n",
    "]\n",
    "print(\"jobs to be done\", len(unfinished_paths), len(unfinished_s3_paths))\n",
    "unfinished_deleted_s3_paths = [\n",
    "    path.replace(\"/uploads/\", \"/deleted/\") for path in unfinished_s3_paths\n",
    "]\n",
    "_ = download_s3_files(unfinished_deleted_s3_paths, unfinished_paths, n_cores=32)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-26T00:59:42.423220Z",
     "start_time": "2024-05-26T00:59:42.421231Z"
    },
    "execution": {
     "iopub.execute_input": "2025-05-02T09:34:50.642627Z",
     "iopub.status.busy": "2025-05-02T09:34:50.642489Z",
     "iopub.status.idle": "2025-05-02T09:34:50.645457Z",
     "shell.execute_reply": "2025-05-02T09:34:50.645043Z",
     "shell.execute_reply.started": "2025-05-02T09:34:50.642612Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Finish downloads\n"
     ]
    }
   ],
   "source": [
    "print(\"Finish downloads\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Hoot"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-05-02T09:34:50.646313Z",
     "iopub.status.busy": "2025-05-02T09:34:50.645927Z",
     "iopub.status.idle": "2025-05-02T09:34:50.815287Z",
     "shell.execute_reply": "2025-05-02T09:34:50.814670Z",
     "shell.execute_reply.started": "2025-05-02T09:34:50.646299Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "300146\n"
     ]
    }
   ],
   "source": [
    "s3_ids = unfinished_ids\n",
    "print(len(s3_ids))\n",
    "s3_paths = [f\"s3://suno-data-uploads/studio/uploads/{s3_id}_hoot.json\" for s3_id in s3_ids]\n",
    "local_paths = [f\"{JSON_DIR}/{s3_id}_hoot.json\" for s3_id in s3_ids]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-05-02T09:34:50.816061Z",
     "iopub.status.busy": "2025-05-02T09:34:50.815927Z",
     "iopub.status.idle": "2025-05-02T09:34:56.711863Z",
     "shell.execute_reply": "2025-05-02T09:34:56.711275Z",
     "shell.execute_reply.started": "2025-05-02T09:34:50.816047Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "jobs to be done 300142 300142\n"
     ]
    }
   ],
   "source": [
    "finished_paths = os.listdir(JSON_DIR)\n",
    "finished_paths_set = set(finished_paths)\n",
    "unfinished_s3_paths = [\n",
    "    path for path in s3_paths if os.path.basename(path) not in finished_paths_set\n",
    "]\n",
    "unfinished_paths = [\n",
    "    path for path in local_paths if os.path.basename(path) not in finished_paths_set\n",
    "]\n",
    "print(\"jobs to be done\", len(unfinished_paths), len(unfinished_s3_paths))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-05-02T09:34:56.712629Z",
     "iopub.status.busy": "2025-05-02T09:34:56.712492Z",
     "iopub.status.idle": "2025-05-02T15:00:13.969615Z",
     "shell.execute_reply": "2025-05-02T15:00:13.968979Z",
     "shell.execute_reply.started": "2025-05-02T09:34:56.712615Z"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████| 301/301 [5:25:14<00:00, 64.83s/it]\n"
     ]
    }
   ],
   "source": [
    "_ = download_s3_files(unfinished_s3_paths, unfinished_paths, n_cores=32)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-05-02T15:00:13.970670Z",
     "iopub.status.busy": "2025-05-02T15:00:13.970359Z",
     "iopub.status.idle": "2025-05-02T15:03:57.454624Z",
     "shell.execute_reply": "2025-05-02T15:03:57.454017Z",
     "shell.execute_reply.started": "2025-05-02T15:00:13.970653Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "jobs to be done 70 70\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:04<00:00,  4.01s/it]\n"
     ]
    }
   ],
   "source": [
    "# # deleted files are at: deleted; try to get them as well\n",
    "finished_paths = os.listdir(JSON_DIR)\n",
    "finished_paths_set = set(finished_paths)\n",
    "unfinished_s3_paths = [\n",
    "    path for path in s3_paths if os.path.basename(path) not in finished_paths_set\n",
    "]\n",
    "unfinished_paths = [\n",
    "    path for path in local_paths if os.path.basename(path) not in finished_paths_set\n",
    "]\n",
    "print(\"jobs to be done\", len(unfinished_paths), len(unfinished_s3_paths))\n",
    "unfinished_deleted_s3_paths = [\n",
    "    path.replace(\"/uploads/\", \"/deleted/\") for path in unfinished_s3_paths\n",
    "]\n",
    "_ = download_s3_files(unfinished_deleted_s3_paths, unfinished_paths, n_cores=32)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-05-02T15:03:57.455445Z",
     "iopub.status.busy": "2025-05-02T15:03:57.455304Z",
     "iopub.status.idle": "2025-05-02T15:03:57.458285Z",
     "shell.execute_reply": "2025-05-02T15:03:57.457870Z",
     "shell.execute_reply.started": "2025-05-02T15:03:57.455431Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Finish downloads hoot!\n"
     ]
    }
   ],
   "source": [
    "print(\"Finish downloads hoot!\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}