{
 "cells": [
  {
   "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": "2024-08-15T04:05:57.597142Z",
     "iopub.status.busy": "2024-08-15T04:05:57.596999Z",
     "iopub.status.idle": "2024-08-15T04:05:58.443279Z",
     "shell.execute_reply": "2024-08-15T04:05:58.442786Z",
     "shell.execute_reply.started": "2024-08-15T04:05:57.597127Z"
    }
   },
   "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": "2024-08-15T04:05:58.444082Z",
     "iopub.status.busy": "2024-08-15T04:05:58.443897Z",
     "iopub.status.idle": "2024-08-15T04:05:58.446256Z",
     "shell.execute_reply": "2024-08-15T04:05:58.445856Z",
     "shell.execute_reply.started": "2024-08-15T04:05:58.444067Z"
    }
   },
   "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_cycle_npz\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-08-15T04:05:58.446942Z",
     "iopub.status.busy": "2024-08-15T04:05:58.446808Z",
     "iopub.status.idle": "2024-08-15T04:05:58.479989Z",
     "shell.execute_reply": "2024-08-15T04:05:58.479612Z",
     "shell.execute_reply.started": "2024-08-15T04:05:58.446927Z"
    }
   },
   "outputs": [],
   "source": [
    "data_csv_path = (\n",
    "    \"/home/tony/Data/Preference/13b_v0/interesting_clips_v3p5_s_8_20240809_slice.csv\"\n",
    ")"
   ]
  },
  {
   "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": "2024-08-15T04:05:58.480648Z",
     "iopub.status.busy": "2024-08-15T04:05:58.480514Z",
     "iopub.status.idle": "2024-08-15T04:06:05.515124Z",
     "shell.execute_reply": "2024-08-15T04:06:05.514646Z",
     "shell.execute_reply.started": "2024-08-15T04:05:58.480634Z"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_2389581/427577943.py:1: DtypeWarning: Columns (87,88,90,91) have mixed types. Specify dtype option on import or set low_memory=False.\n",
      "  df = pd.read_csv(data_csv_path)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "(157256, 98)"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv(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": "2024-08-15T04:06:05.515945Z",
     "iopub.status.busy": "2024-08-15T04:06:05.515794Z",
     "iopub.status.idle": "2024-08-15T04:06:05.609078Z",
     "shell.execute_reply": "2024-08-15T04:06:05.608588Z",
     "shell.execute_reply.started": "2024-08-15T04:06:05.515930Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(157256, 98)\n",
      "model_name\n",
      "chirp-v3p5-engine-s-8    157256\n",
      "Name: count, dtype: int64\n"
     ]
    }
   ],
   "source": [
    "df = df[df[\"model_name\"].str.contains(\"v3p5\")]\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": "2024-08-15T04:06:05.610660Z",
     "iopub.status.busy": "2024-08-15T04:06:05.610502Z",
     "iopub.status.idle": "2024-08-15T04:06:05.612641Z",
     "shell.execute_reply": "2024-08-15T04:06:05.612245Z",
     "shell.execute_reply.started": "2024-08-15T04:06:05.610644Z"
    }
   },
   "outputs": [],
   "source": [
    "# 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": "2024-08-15T04:06:05.613314Z",
     "iopub.status.busy": "2024-08-15T04:06:05.613181Z",
     "iopub.status.idle": "2024-08-15T04:06:05.649566Z",
     "shell.execute_reply": "2024-08-15T04:06:05.649159Z",
     "shell.execute_reply.started": "2024-08-15T04:06:05.613300Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2857"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(set(df[\"audio_prompt_id\"].values))"
   ]
  },
  {
   "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": "2024-08-15T04:06:05.650377Z",
     "iopub.status.busy": "2024-08-15T04:06:05.650242Z",
     "iopub.status.idle": "2024-08-15T04:06:05.802359Z",
     "shell.execute_reply": "2024-08-15T04:06:05.801843Z",
     "shell.execute_reply.started": "2024-08-15T04:06:05.650362Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "157256 157256\n",
      "full 157256\n"
     ]
    }
   ],
   "source": [
    "# download all clips; 883k\n",
    "from suno_utils.utils.s3 import download_s3_files\n",
    "\n",
    "s3_ids = set(df[\"s3_id\"].values)\n",
    "s3_cycle_ids = set(i + \"_gen_cycle\" for i in s3_ids)\n",
    "print(len(s3_ids), len(s3_cycle_ids))\n",
    "# s3_ids = set(s3_ids).union(set(df[\"audio_prompt_id\"].values)).union(s3_cycle_ids)\n",
    "s3_ids = s3_cycle_ids\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": "2024-08-15T04:06:05.803134Z",
     "iopub.status.busy": "2024-08-15T04:06:05.802980Z",
     "iopub.status.idle": "2024-08-15T04:06:06.007892Z",
     "shell.execute_reply": "2024-08-15T04:06:06.007419Z",
     "shell.execute_reply.started": "2024-08-15T04:06:05.803119Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "jobs to be done 582 582\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",
    "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": "2024-08-15T04:06:06.008742Z",
     "iopub.status.busy": "2024-08-15T04:06:06.008598Z",
     "iopub.status.idle": "2024-08-15T04:06:26.165561Z",
     "shell.execute_reply": "2024-08-15T04:06:26.164744Z",
     "shell.execute_reply.started": "2024-08-15T04:06:06.008726Z"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:20<00:00, 20.13s/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": "2024-08-15T04:06:26.167363Z",
     "iopub.status.busy": "2024-08-15T04:06:26.166840Z",
     "iopub.status.idle": "2024-08-15T04:06:43.894188Z",
     "shell.execute_reply": "2024-08-15T04:06:43.893664Z",
     "shell.execute_reply.started": "2024-08-15T04:06:26.167339Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "jobs to be done 582 582\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:17<00:00, 17.47s/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": 12,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-26T00:59:42.423220Z",
     "start_time": "2024-05-26T00:59:42.421231Z"
    },
    "execution": {
     "iopub.execute_input": "2024-08-15T04:06:43.895077Z",
     "iopub.status.busy": "2024-08-15T04:06:43.894918Z",
     "iopub.status.idle": "2024-08-15T04:06:43.897724Z",
     "shell.execute_reply": "2024-08-15T04:06:43.897310Z",
     "shell.execute_reply.started": "2024-08-15T04:06:43.895060Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Finish downloads\n"
     ]
    }
   ],
   "source": [
    "print(\"Finish downloads\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-08-15T04:06:43.898449Z",
     "iopub.status.busy": "2024-08-15T04:06:43.898304Z",
     "iopub.status.idle": "2024-08-15T04:06:43.935886Z",
     "shell.execute_reply": "2024-08-15T04:06:43.935469Z",
     "shell.execute_reply.started": "2024-08-15T04:06:43.898434Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "582\n"
     ]
    }
   ],
   "source": [
    "unfinished_ids = [os.path.basename(path).replace(\"_gen_cycle.npz\", \"\") for path in unfinished_deleted_s3_paths]\n",
    "print(len(unfinished_ids))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-08-15T04:06:43.936589Z",
     "iopub.status.busy": "2024-08-15T04:06:43.936452Z",
     "iopub.status.idle": "2024-08-15T04:06:43.972709Z",
     "shell.execute_reply": "2024-08-15T04:06:43.972338Z",
     "shell.execute_reply.started": "2024-08-15T04:06:43.936575Z"
    }
   },
   "outputs": [],
   "source": [
    "# with open(\"temp_unfinished_ids.json\", \"w\") as fp:\n",
    "#     json.dump(unfinished_ids, fp)"
   ]
  },
  {
   "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": "3.10.14"
  },
  "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
}