{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-14T15:28:00.404431Z",
     "start_time": "2024-05-14T15:27:59.031503Z"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_1523903/650253082.py:1: DeprecationWarning: \n",
      "Pyarrow will become a required dependency of pandas in the next major release of pandas (pandas 3.0),\n",
      "(to allow more performant data types, such as the Arrow string type, and better interoperability with other libraries)\n",
      "but was not found to be installed on your system.\n",
      "If this would cause problems for you,\n",
      "please provide us feedback at https://github.com/pandas-dev/pandas/issues/54466\n",
      "        \n",
      "  import pandas as pd\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import os\n",
    "from tqdm import tqdm\n",
    "from sklearn.model_selection import train_test_split\n",
    "from suno_utils.utils.s3 import download_s3_files\n",
    "import sys\n",
    "from collections import defaultdict\n",
    "from suno_utils.utils.text import (\n",
    "    write_jsonl,\n",
    "    read_jsonl,\n",
    "    write_json,\n",
    "    read_json,\n",
    ")\n",
    "import shutil\n",
    "import ast\n",
    "from preference_helper import *\n",
    "from preference_data_preparation_4min import *\n",
    "from preference_data_preparation_4min import make_dataset\n",
    "\n",
    "import numpy as np\n",
    "\n",
    "pd.set_option('display.max_rows', 500)\n",
    "pd.set_option('display.max_columns', 500)\n",
    "pd.set_option('display.width', 1000)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-14T15:28:00.444294Z",
     "start_time": "2024-05-14T15:28:00.406622Z"
    }
   },
   "outputs": [],
   "source": [
    "OUT_DATA_DIR = \"/app/suno/data/dpo/13b_v2/\"\n",
    "# OUT_DATA_DIR = \"/home/tony/Data/test/7v_v6_full/\"\n",
    "os.makedirs(OUT_DATA_DIR, exist_ok=True)\n",
    "shutil.copyfile(\"/app/suno/data/dpo/7v_v1_full/tokenizer_60k.json\", os.path.join(OUT_DATA_DIR, \"tokenizer_60k.json\"))\n",
    "NPZ_DIR = \"/app/suno/data/dpo/7b_npz\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-14T15:28:00.476141Z",
     "start_time": "2024-05-14T15:28:00.446806Z"
    }
   },
   "outputs": [],
   "source": [
    "# df_origin = pd.read_csv(\"/home/tony/Data/Preference/7b_v1/interesting_clips.csv\")\n",
    "# df_origin[df_origin[\"id\"] == \"75f69d46-1d81-4327-9253-a8a4886777d1\"]\n",
    "# df_origin[df_origin[\"request_id\"] == \"9414f356-88d6-40ba-b95e-9f4c5004a4aa\"]\n",
    "# df_origin[df_origin[\"request_id\"] == \"b2a150c1-f058-4bff-a013-1961e574631d\"]\n",
    "# df_origin[df_origin[\"id\"] == \"574ba431-18a1-4e28-ac7c-d3e401dba6fe\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-14T15:28:31.979977Z",
     "start_time": "2024-05-14T15:28:00.478131Z"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_1523903/2954378535.py:1: DtypeWarning: Columns (3,10,12,13,17,19,25,27,28,29,30) have mixed types. Specify dtype option on import or set low_memory=False.\n",
      "  df = pd.read_csv(\"/home/tony/Data/Preference/v1/interesting_clips.csv\") # , engine='python')\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "(1706214, 31)"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv(\"/home/tony/Data/Preference/v1/interesting_clips.csv\") # , engine='python')\n",
    "df.shape\n",
    "# v0: (68746, 31)\n",
    "# v5: (938008, 37)\n",
    "# v6: (1097024, 38)\n",
    "# v21: (1822704, 41)\n",
    "# r1 \n",
    "# v2: 2620268 (pre fixes...lots of imperfections...)\n",
    "# v3: 1552512"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-14T15:28:39.822128Z",
     "start_time": "2024-05-14T15:28:31.982380Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "3519009\n",
      "3519009\n",
      "pre-downloaded df (1706214, 31)\n",
      "downloaded df (1706204, 31)\n"
     ]
    }
   ],
   "source": [
    "converted_paths = os.listdir(NPZ_DIR)\n",
    "print(len(converted_paths))\n",
    "\n",
    "converted_paths = set([f.replace(\".npz\", \"\") for f in converted_paths])\n",
    "print(len(converted_paths))\n",
    "\n",
    "print(\"pre-downloaded df\", df.shape)\n",
    "df[df[\"s3_id\"].isin(converted_paths)].shape\n",
    "df = df[df[\"s3_id\"].isin(converted_paths)].copy()\n",
    "print(\"downloaded df\", df.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-14T15:28:40.107763Z",
     "start_time": "2024-05-14T15:28:39.823845Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "is_7b\n",
       "False    1706204\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"is_7b\"] = df[\"model_name\"].str.contains(\"v3\")\n",
    "df[\"is_7b\"].value_counts()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# LET's do the data prep"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-14T15:28:40.384428Z",
     "start_time": "2024-05-14T15:28:40.110041Z"
    }
   },
   "outputs": [],
   "source": [
    "assert df.shape[0] == df[\"request_id\"].nunique() * 2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-14T15:28:41.471634Z",
     "start_time": "2024-05-14T15:28:40.386623Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "853102 135358\n"
     ]
    }
   ],
   "source": [
    "neg_filter_selection_mask_v2 = (df[\"dislike_count\"] > 0)\n",
    "pos_filter_selectin_mask_v2 = (df[\"play_count\"] > 1)\n",
    "neg_filter_requests_v2 = df[neg_filter_selection_mask_v2][\"request_id\"].unique()\n",
    "pos_filter_requests_v2 = df[pos_filter_selectin_mask_v2][\"request_id\"].unique()\n",
    "# looking for very strong signal here: \n",
    "# listen to the positive/negative more than once\n",
    "# disliked one of the clips\n",
    "unique_requests_v2 = set(pos_filter_requests_v2).intersection(neg_filter_requests_v2)\n",
    "print(df[\"request_id\"].nunique(), len(unique_requests_v2))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-14T15:28:41.799074Z",
     "start_time": "2024-05-14T15:28:41.474518Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(270716, 32)\n"
     ]
    }
   ],
   "source": [
    "df_slice_v2 = df[df[\"request_id\"].isin(set(unique_requests_v2))].copy()\n",
    "print(df_slice_v2.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-14T15:28:55.996197Z",
     "start_time": "2024-05-14T15:28:41.801542Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "135358\n",
      "(270716, 32)\n"
     ]
    }
   ],
   "source": [
    "df_slice_v2[\"has_gpt_prompt\"] = df_slice_v2[\"metadata\"].apply(lambda x: ast.literal_eval(x).get(\"gpt_description_prompt\", None) is not None)\n",
    "final_filtered_requests_v2 = df_slice_v2[~df_slice_v2[\"has_gpt_prompt\"]][\"request_id\"].unique()\n",
    "print(len(final_filtered_requests_v2))\n",
    "df_slice_v2 = df[df[\"request_id\"].isin(set(final_filtered_requests_v2))].copy()\n",
    "print(df_slice_v2.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-14T15:29:50.050790Z",
     "start_time": "2024-05-14T15:28:55.998278Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "unique_requests 135358\n"
     ]
    }
   ],
   "source": [
    "test_slice_v2 = df_slice_v2[\"metadata\"].apply(lambda x: ast.literal_eval(x))\n",
    "test_slice_series_v2 = test_slice_v2.apply(pd.Series)\n",
    "df_slice_v2 = pd.concat([df_slice_v2, test_slice_series_v2], axis=1, join=\"inner\")\n",
    "print(\"unique_requests\", df_slice_v2[\"request_id\"].nunique())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-14T15:29:50.085413Z",
     "start_time": "2024-05-14T15:29:50.075677Z"
    }
   },
   "outputs": [],
   "source": [
    "df_slice_v2[\"total_start_s\"] = 0\n",
    "df_slice_v2[\"total_clip_s\"] = -1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-14T15:29:50.473658Z",
     "start_time": "2024-05-14T15:29:50.087342Z"
    }
   },
   "outputs": [],
   "source": [
    "df_slice = df_slice_v2.copy()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Need to kick out the ones has gpt prompt -- these are pairs with different text inputs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-16T13:57:42.528447Z",
     "start_time": "2024-05-16T13:57:30.991498Z"
    }
   },
   "outputs": [],
   "source": [
    "# df_slice.to_csv(\"/home/tony/Data/Preference/v1/interesting_clips_v2_processed.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-14T15:29:50.681937Z",
     "start_time": "2024-05-14T15:29:50.475768Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "130883"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# don't have continue at\n",
    "df_slice[df_slice[\"continue_at\"].isna()][\"request_id\"].nunique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-14T15:29:50.731207Z",
     "start_time": "2024-05-14T15:29:50.683886Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "135358\n"
     ]
    }
   ],
   "source": [
    "final_filtered_requests = df_slice[\"request_id\"].unique()\n",
    "print(len(final_filtered_requests))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-14T15:29:51.664587Z",
     "start_time": "2024-05-14T15:29:50.732738Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "134004 1354\n",
      "(268008, 53) (2708, 53)\n"
     ]
    }
   ],
   "source": [
    "train_requests, val_requests = train_test_split(\n",
    "    sorted(list(final_filtered_requests)), test_size=0.01, random_state=42\n",
    ")\n",
    "print(len(train_requests), len(val_requests))\n",
    "\n",
    "train_df = df_slice[df_slice[\"request_id\"].isin(set(train_requests))].copy()\n",
    "val_df = df_slice[df_slice[\"request_id\"].isin(set(val_requests))].copy()\n",
    "train_df = train_df.sort_values(by=[\"request_id\", \"preference\"])\n",
    "train_df = train_df.reset_index()\n",
    "val_df = val_df.sort_values(by=[\"request_id\", \"preference\"])\n",
    "val_df = val_df.reset_index()\n",
    "\n",
    "print(train_df.shape, val_df.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Actually make"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-14T15:29:51.668784Z",
     "start_time": "2024-05-14T15:29:51.666548Z"
    }
   },
   "outputs": [],
   "source": [
    "# val_df[[\"request_id\", \"metadata\", \"updated_at\", \"user_id\", \"preference\"]].head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-14T15:30:03.562358Z",
     "start_time": "2024-05-14T15:29:51.670693Z"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|█████████████████████████████████████████████████████████████████████████████████████████████████████| 268008/268008 [00:11<00:00, 22665.32it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "4,692 hours of 268008 clips, 8.37525 nodes\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    }
   ],
   "source": [
    "total_duration = 0\n",
    "for i, row in tqdm.tqdm(train_df.iterrows(), total=len(train_df)):\n",
    "    # we need to alternate between preference: neg, pos\n",
    "    # print(i, row)\n",
    "    try:\n",
    "        assert row[\"preference\"] == (i % 2 == 1)\n",
    "    except:\n",
    "        print(i, row)\n",
    "    total_duration += row[\"duration\"]\n",
    "print(f\"{round(total_duration / 60 / 60):,} hours of {train_df.shape[0]} clips, {train_df.shape[0] / 8 / 4 / 1000} nodes\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-14T15:30:42.320836Z",
     "start_time": "2024-05-14T15:30:03.564357Z"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2708/2708 [00:38<00:00, 70.77it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Total 2708 clips\n",
      "23 hours of False\n",
      "24 hours of True\n",
      "Done\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    }
   ],
   "source": [
    "make_dataset(val_df, OUT_DATA_DIR, is_val=True, npz_dir=NPZ_DIR)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-14T16:45:27.758626Z",
     "start_time": "2024-05-14T15:30:42.322010Z"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████████████████████████████████████████████████████████████████████████████████████████████████| 268008/268008 [1:14:45<00:00, 59.75it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Total 268008 clips\n",
      "2,337 hours of False\n",
      "2,352 hours of True\n",
      "Done\n"
     ]
    }
   ],
   "source": [
    "make_dataset(train_df, OUT_DATA_DIR, is_val=False, npz_dir=NPZ_DIR)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-01-29T19:46:47.549860Z",
     "start_time": "2024-01-29T19:46:47.548015Z"
    }
   },
   "source": [
    "# Validation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-14T16:45:27.794244Z",
     "start_time": "2024-05-14T16:45:27.759859Z"
    }
   },
   "outputs": [],
   "source": [
    "# verify\n",
    "mm = np.memmap(os.path.join(OUT_DATA_DIR, f\"data_val.bin\"), dtype=np.uint16, mode=\"r\")\n",
    "test_metas = read_jsonl(os.path.join(OUT_DATA_DIR, f\"meta_val.jsonl\"))\n",
    "test_info = read_json(os.path.join(OUT_DATA_DIR, f\"info_val.json\"))\n",
    "mm = mm.reshape(-1, 6016, 13)\n",
    "assert len(mm) == len(test_metas)\n",
    "assert mm[:100, :, 0].min() >= 0\n",
    "assert mm[:100, :, 0].max() <= 4000\n",
    "assert mm[:100, :, 1:].min() >= 0\n",
    "assert mm[:100, :, 1:].max() <= 2048"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-14T16:45:27.827354Z",
     "start_time": "2024-05-14T16:45:27.795406Z"
    }
   },
   "outputs": [],
   "source": [
    "# # randomly listen to some stuff\n",
    "# from suno_utils.tasks.dac_2c_12cb import preload_models as preload_codec_models\n",
    "# from suno_utils.tasks.dac_2c_12cb import (\n",
    "#     encode as codec_encode,\n",
    "#     decode_stream_to_full_audio as codec_decode,\n",
    "#     EMBEDDING_RATE as CODEC_EMBEDDING_RATE,\n",
    "#     decode as decode\n",
    "# )\n",
    "# os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"3\"\n",
    "# _ = preload_codec_models(\"/app/suno/tony/v3/dac_2c_25x12.pt\", device=\"cuda\")\n",
    "# assert len(test_metas) == len(mm)\n",
    "# idx_list = list(range(len(test_metas)))\n",
    "# # random.shuffle(idx_list)\n",
    "# # idx_list = [idx for idx in idx_list if \"text\" in test_metas[idx]]\n",
    "# print(len(mm))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-14T16:45:27.890048Z",
     "start_time": "2024-05-14T16:45:27.828377Z"
    }
   },
   "outputs": [],
   "source": [
    "# import random\n",
    "# idx = random.choice(test_info[\"perference_0\"][\"idx_list\"])\n",
    "# assert \"original_duration_s\" in test_metas[idx]\n",
    "# # positive index should be shifted by 1\n",
    "# pos_idx = idx + 1\n",
    "# print(\n",
    "#     \"tags:\",\n",
    "#     test_metas[idx].get(\"tags\") == test_metas[pos_idx].get(\"tags\"),\n",
    "#     test_metas[idx].get(\"tags\"),\n",
    "# )\n",
    "# arr = mm[idx, 1:].copy().astype(np.int16)[:, 1:]\n",
    "# pos_arr = mm[pos_idx, 1:].copy().astype(np.int16)[:, 1:]\n",
    "# pad_idx_arr = np.where(arr == COARSE_PAD_TOKEN)[0]\n",
    "# if len(pad_idx_arr) > 0:\n",
    "#     arr = arr[: pad_idx_arr[0], :]\n",
    "# pos_pad_idx_arr = np.where(pos_arr == COARSE_PAD_TOKEN)[0]\n",
    "# if len(pos_pad_idx_arr) > 0:\n",
    "#     pos_arr = pos_arr[: pos_pad_idx_arr[0], :]\n",
    "# a = decode(arr)\n",
    "# print(\"negative example\", test_metas[idx])\n",
    "# a.play(compress=False)\n",
    "# pos_a = decode(pos_arr)\n",
    "# print(\"positive example\", test_metas[pos_idx])\n",
    "# pos_a.play(compress=False)\n",
    "# print(\n",
    "#     \"text:\",\n",
    "#     test_metas[idx].get(\"text\") == test_metas[pos_idx].get(\"text\"),\n",
    "#     test_metas[idx].get(\"text\"),\n",
    "# )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-14T16:45:27.954181Z",
     "start_time": "2024-05-14T16:45:27.891450Z"
    }
   },
   "outputs": [],
   "source": [
    "# val_df[val_df[\"tags\"] == 'a vibrant blend of experimental jazz fusion, drum-and-bass and swagger fuzzed-out guitars']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-14T16:45:28.016016Z",
     "start_time": "2024-05-14T16:45:27.955085Z"
    }
   },
   "outputs": [],
   "source": [
    "# from collections import Counter\n",
    "# c = Counter()\n",
    "# for _, row in df_slice.iterrows():\n",
    "#     # print(row[\"metadata\"])\n",
    "#     for k in ast.literal_eval(row[\"metadata\"]).keys():\n",
    "#         c[k] += 1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-14T16:45:28.079534Z",
     "start_time": "2024-05-14T16:45:28.016977Z"
    }
   },
   "outputs": [],
   "source": [
    "# original_npz_path = f\"/app/suno/data/dpo/7b_npz/{test_metas[idx]['id']}.npz\"\n",
    "# original_npz_path = \"/app/suno/data/dpo/7b_npz/729c3011-f672-4ccd-8d82-1cbf2b52ff69.npz\"\n",
    "# original_arr = np.load(original_npz_path)[\"v2_raw\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-14T16:45:28.164362Z",
     "start_time": "2024-05-14T16:45:28.082143Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1354 0\n"
     ]
    }
   ],
   "source": [
    "def validation_on_metas(input_metas):\n",
    "\n",
    "    total_bad = 0\n",
    "    total_good = 0\n",
    "    for idx in range(len(input_metas)):\n",
    "        if idx % 2 == 0:\n",
    "            pos_idx = idx + 1\n",
    "            if input_metas[idx].get(\"tags\") != input_metas[pos_idx].get(\"tags\"):\n",
    "                # print(test_metas[idx].get(\"text\") == test_metas[pos_idx].get(\"text\"), test_metas[idx].get(\"tags\"), test_metas[pos_idx].get(\"tags\"))\n",
    "                total_bad += 1\n",
    "            else:\n",
    "                total_good += 1\n",
    "    print(total_good, total_bad)\n",
    "    return\n",
    "\n",
    "\n",
    "validation_on_metas(test_metas)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-14T16:45:28.264954Z",
     "start_time": "2024-05-14T16:45:28.165332Z"
    }
   },
   "outputs": [],
   "source": [
    "train_info = read_json(os.path.join(OUT_DATA_DIR, f\"info_tr.json\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-14T16:45:28.315585Z",
     "start_time": "2024-05-14T16:45:28.266532Z"
    }
   },
   "outputs": [],
   "source": [
    "n_neg_tr = train_info[\"perference_0\"][\"idx_list\"]\n",
    "n_pos_tr = train_info[\"perference_1\"][\"idx_list\"]\n",
    "assert len(n_pos_tr) == len(n_neg_tr)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-14T16:45:28.411814Z",
     "start_time": "2024-05-14T16:45:28.316610Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "total samples 268008 (268008, 53)\n"
     ]
    }
   ],
   "source": [
    "total_iters = (len(n_neg_tr) + len(n_pos_tr))\n",
    "print(\"total samples\", total_iters, train_df.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-14T16:45:28.475216Z",
     "start_time": "2024-05-14T16:45:28.412824Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1 epoch per batch 4, total 2093.8125\n"
     ]
    }
   ],
   "source": [
    "print(\"1 epoch per batch 4, total\", total_iters / 8 / 4 / 4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-14T16:45:28.552594Z",
     "start_time": "2024-05-14T16:45:28.476261Z"
    }
   },
   "outputs": [],
   "source": [
    "# !cd /home/tony/Work/tony/slurm && sbatch sbatch_ipo_2b"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# some gymathtics loading prev data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-14T16:45:28.621601Z",
     "start_time": "2024-05-14T16:45:28.553589Z"
    }
   },
   "outputs": [],
   "source": [
    "# prev_v3_data = \"/app/suno/data/dpo/7v_v20_full/\"\n",
    "\n",
    "# test_val_metas = read_jsonl(os.path.join(prev_v3_data, f\"meta_val.jsonl\"))\n",
    "# test_tr_metas = read_jsonl(os.path.join(prev_v3_data, f\"meta_tr.jsonl\"))\n",
    "\n",
    "# all_ids = set()\n",
    "# for meta in test_val_metas:\n",
    "#     all_ids.add(meta[\"id\"])\n",
    "# for meta in test_tr_metas:\n",
    "#     all_ids.add(meta[\"id\"])\n",
    "# print(len(all_ids), len(test_val_metas) + len(test_tr_metas))\n",
    "\n",
    "# all_ids = list(all_ids)\n",
    "# with open(\"/home/tony/Data/Preference/7b_v2/7v_v20_full_recut_id.json\", \"w\") as fp:\n",
    "#     json.dump(all_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": "3.10.13"
  },
  "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": 2
}