{
 "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": "2025-06-07T13:46:03.138491Z",
     "iopub.status.busy": "2025-06-07T13:46:03.138357Z",
     "iopub.status.idle": "2025-06-07T13:46:04.241752Z",
     "shell.execute_reply": "2025-06-07T13:46:04.241192Z",
     "shell.execute_reply.started": "2025-06-07T13:46:03.138474Z"
    }
   },
   "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": "2025-06-07T13:46:04.242544Z",
     "iopub.status.busy": "2025-06-07T13:46:04.242335Z",
     "iopub.status.idle": "2025-06-07T13:46:04.244724Z",
     "shell.execute_reply": "2025-06-07T13:46:04.244333Z",
     "shell.execute_reply.started": "2025-06-07T13:46:04.242527Z"
    }
   },
   "outputs": [],
   "source": [
    "NPZ_DIR = \"/app2/suno/data/dpo/diff2_v2_d3\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-06-07T13:46:04.245483Z",
     "iopub.status.busy": "2025-06-07T13:46:04.245173Z",
     "iopub.status.idle": "2025-06-07T13:46:04.247394Z",
     "shell.execute_reply": "2025-06-07T13:46:04.247006Z",
     "shell.execute_reply.started": "2025-06-07T13:46:04.245469Z"
    }
   },
   "outputs": [],
   "source": [
    "data_csv_path = \"/home/tony/Data/Preference/up_v2_d3/interesting_clips_ahi_d3_20250606.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": "2025-06-07T13:46:04.247955Z",
     "iopub.status.busy": "2025-06-07T13:46:04.247820Z",
     "iopub.status.idle": "2025-06-07T13:46:16.970724Z",
     "shell.execute_reply": "2025-06-07T13:46:16.970241Z",
     "shell.execute_reply.started": "2025-06-07T13:46:04.247942Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(433426, 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": "2025-06-07T13:46:16.972304Z",
     "iopub.status.busy": "2025-06-07T13:46:16.972130Z",
     "iopub.status.idle": "2025-06-07T13:46:17.688566Z",
     "shell.execute_reply": "2025-06-07T13:46:17.688007Z",
     "shell.execute_reply.started": "2025-06-07T13:46:16.972287Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(433426, 90)\n",
      "model_name\n",
      "chirp-ahi-up-1         409972\n",
      "chirp-v4-up-u-d-2-3     23454\n",
      "Name: count, dtype: int64\n"
     ]
    }
   ],
   "source": [
    "df = df[df[\"model_name\"].str.contains(\"up\")]\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": "2025-06-07T13:46:17.689315Z",
     "iopub.status.busy": "2025-06-07T13:46:17.689155Z",
     "iopub.status.idle": "2025-06-07T13:46:17.691413Z",
     "shell.execute_reply": "2025-06-07T13:46:17.691030Z",
     "shell.execute_reply.started": "2025-06-07T13:46:17.689299Z"
    }
   },
   "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": {
    "execution": {
     "iopub.execute_input": "2025-06-07T13:46:17.691964Z",
     "iopub.status.busy": "2025-06-07T13:46:17.691840Z",
     "iopub.status.idle": "2025-06-07T13:46:18.135262Z",
     "shell.execute_reply": "2025-06-07T13:46:18.134686Z",
     "shell.execute_reply.started": "2025-06-07T13:46:17.691951Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "all 433350\n",
      "unique 210380\n"
     ]
    }
   ],
   "source": [
    "edit_clip_ids = df[\"metadata\"].apply(lambda x: x.get(\"upsample_clip_id\", \"\"))\n",
    "s3_ids = [s3_id for s3_id in edit_clip_ids if s3_id and len(s3_id) > 0]\n",
    "print(\"all\", len(s3_ids))\n",
    "unique_s3_ids = sorted(set(s3_ids))\n",
    "print(\"unique\", len(unique_s3_ids))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-26T00:36:59.940064Z",
     "start_time": "2024-05-26T00:36:59.933947Z"
    },
    "execution": {
     "iopub.execute_input": "2025-06-07T13:46:18.135981Z",
     "iopub.status.busy": "2025-06-07T13:46:18.135831Z",
     "iopub.status.idle": "2025-06-07T13:46:18.216818Z",
     "shell.execute_reply": "2025-06-07T13:46:18.216256Z",
     "shell.execute_reply.started": "2025-06-07T13:46:18.135965Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "210380\n",
      "full 210380\n"
     ]
    }
   ],
   "source": [
    "# download all clips; 883k\n",
    "from suno_utils.utils.s3 import download_s3_files\n",
    "\n",
    "s3_ids = unique_s3_ids.copy()\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": 9,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-26T00:37:00.153602Z",
     "start_time": "2024-05-26T00:36:59.941125Z"
    },
    "execution": {
     "iopub.execute_input": "2025-06-07T13:46:18.217543Z",
     "iopub.status.busy": "2025-06-07T13:46:18.217388Z",
     "iopub.status.idle": "2025-06-07T13:46:18.708972Z",
     "shell.execute_reply": "2025-06-07T13:46:18.708392Z",
     "shell.execute_reply.started": "2025-06-07T13:46:18.217528Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "jobs to be done 9265 9265\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": 10,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-26T00:49:33.275556Z",
     "start_time": "2024-05-26T00:37:00.154648Z"
    },
    "execution": {
     "iopub.execute_input": "2025-06-07T13:46:18.709652Z",
     "iopub.status.busy": "2025-06-07T13:46:18.709503Z",
     "iopub.status.idle": "2025-06-07T13:53:37.914220Z",
     "shell.execute_reply": "2025-06-07T13:53:37.913637Z",
     "shell.execute_reply.started": "2025-06-07T13:46:18.709636Z"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 10/10 [07:19<00:00, 43.90s/it]\n"
     ]
    }
   ],
   "source": [
    "_ = download_s3_files(unfinished_s3_paths, unfinished_paths, n_cores=32)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-26T00:59:42.420025Z",
     "start_time": "2024-05-26T00:49:33.276845Z"
    },
    "execution": {
     "iopub.execute_input": "2025-06-07T13:53:37.915012Z",
     "iopub.status.busy": "2025-06-07T13:53:37.914850Z",
     "iopub.status.idle": "2025-06-07T13:53:58.828414Z",
     "shell.execute_reply": "2025-06-07T13:53:58.827889Z",
     "shell.execute_reply.started": "2025-06-07T13:53:37.914994Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "jobs to be done 96 96\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:04<00:00,  4.40s/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": 12,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-26T00:59:42.423220Z",
     "start_time": "2024-05-26T00:59:42.421231Z"
    },
    "execution": {
     "iopub.execute_input": "2025-06-07T13:53:58.829150Z",
     "iopub.status.busy": "2025-06-07T13:53:58.828998Z",
     "iopub.status.idle": "2025-06-07T13:53:58.831707Z",
     "shell.execute_reply": "2025-06-07T13:53:58.831303Z",
     "shell.execute_reply.started": "2025-06-07T13:53:58.829135Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Finish downloads\n"
     ]
    }
   ],
   "source": [
    "print(\"Finish downloads\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# VAE"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-06-07T13:53:58.832323Z",
     "iopub.status.busy": "2025-06-07T13:53:58.832189Z",
     "iopub.status.idle": "2025-06-07T13:53:59.022308Z",
     "shell.execute_reply": "2025-06-07T13:53:59.021784Z",
     "shell.execute_reply.started": "2025-06-07T13:53:58.832310Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "433426\n",
      "full 433426\n"
     ]
    }
   ],
   "source": [
    "# download all clips; 883k\n",
    "from suno_utils.utils.s3 import download_s3_files\n",
    "\n",
    "# for vae...we actually need the original s3 id\n",
    "s3_ids = df[\"s3_id\"].unique()\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}_vae.npz\" for s3_id in s3_ids]\n",
    "local_paths = [f\"{NPZ_DIR}/{s3_id}_vae.npz\" for s3_id in s3_ids]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-06-07T13:53:59.023009Z",
     "iopub.status.busy": "2025-06-07T13:53:59.022860Z",
     "iopub.status.idle": "2025-06-07T13:54:13.065682Z",
     "shell.execute_reply": "2025-06-07T13:54:13.065144Z",
     "shell.execute_reply.started": "2025-06-07T13:53:59.022993Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "jobs to be done 19092 19092\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": 15,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-06-07T13:54:13.066414Z",
     "iopub.status.busy": "2025-06-07T13:54:13.066256Z",
     "iopub.status.idle": "2025-06-07T14:09:46.285313Z",
     "shell.execute_reply": "2025-06-07T14:09:46.284725Z",
     "shell.execute_reply.started": "2025-06-07T13:54:13.066398Z"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [15:32<00:00, 46.65s/it]\n"
     ]
    }
   ],
   "source": [
    "_ = download_s3_files(unfinished_s3_paths, unfinished_paths, n_cores=32)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-06-07T14:09:46.286079Z",
     "iopub.status.busy": "2025-06-07T14:09:46.285923Z",
     "iopub.status.idle": "2025-06-07T14:10:03.578032Z",
     "shell.execute_reply": "2025-06-07T14:10:03.577496Z",
     "shell.execute_reply.started": "2025-06-07T14:09:46.286063Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "jobs to be done 0 0\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": 17,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-06-07T14:10:03.578739Z",
     "iopub.status.busy": "2025-06-07T14:10:03.578587Z",
     "iopub.status.idle": "2025-06-07T14:10:03.581236Z",
     "shell.execute_reply": "2025-06-07T14:10:03.580840Z",
     "shell.execute_reply.started": "2025-06-07T14:10:03.578723Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "DONE with vaes\n"
     ]
    }
   ],
   "source": [
    "print(\"DONE with vaes\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-06-07T14:10:03.581854Z",
     "iopub.status.busy": "2025-06-07T14:10:03.581720Z",
     "iopub.status.idle": "2025-06-07T14:10:04.775868Z",
     "shell.execute_reply": "2025-06-07T14:10:04.775084Z",
     "shell.execute_reply.started": "2025-06-07T14:10:03.581841Z"
    }
   },
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'BREAK' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[18], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mBREAK\u001b[49m\n",
      "\u001b[0;31mNameError\u001b[0m: name 'BREAK' is not defined"
     ]
    }
   ],
   "source": [
    "BREAK"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Hoot"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "execution": {
     "iopub.status.busy": "2025-06-07T14:10:04.776289Z",
     "iopub.status.idle": "2025-06-07T14:10:04.776478Z",
     "shell.execute_reply": "2025-06-07T14:10:04.776397Z",
     "shell.execute_reply.started": "2025-06-07T14:10:04.776388Z"
    }
   },
   "outputs": [],
   "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": null,
   "metadata": {
    "execution": {
     "iopub.status.busy": "2025-06-07T14:10:04.777238Z",
     "iopub.status.idle": "2025-06-07T14:10:04.777413Z",
     "shell.execute_reply": "2025-06-07T14:10:04.777327Z",
     "shell.execute_reply.started": "2025-06-07T14:10:04.777319Z"
    }
   },
   "outputs": [],
   "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": null,
   "metadata": {
    "execution": {
     "iopub.status.busy": "2025-06-07T14:10:04.777802Z",
     "iopub.status.idle": "2025-06-07T14:10:04.777963Z",
     "shell.execute_reply": "2025-06-07T14:10:04.777887Z",
     "shell.execute_reply.started": "2025-06-07T14:10:04.777880Z"
    }
   },
   "outputs": [],
   "source": [
    "_ = download_s3_files(unfinished_s3_paths, unfinished_paths, n_cores=32)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "execution": {
     "iopub.status.busy": "2025-06-07T14:10:04.778546Z",
     "iopub.status.idle": "2025-06-07T14:10:04.778706Z",
     "shell.execute_reply": "2025-06-07T14:10:04.778629Z",
     "shell.execute_reply.started": "2025-06-07T14:10:04.778621Z"
    }
   },
   "outputs": [],
   "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": null,
   "metadata": {
    "execution": {
     "iopub.status.busy": "2025-06-07T14:10:04.779148Z",
     "iopub.status.idle": "2025-06-07T14:10:04.779303Z",
     "shell.execute_reply": "2025-06-07T14:10:04.779228Z",
     "shell.execute_reply.started": "2025-06-07T14:10:04.779221Z"
    }
   },
   "outputs": [],
   "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
}