{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/ben/code/hub-recap/.venv/lib/python3.11/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from .autonotebook import tqdm as notebook_tqdm\n"
     ]
    }
   ],
   "source": [
    "from datasets import load_dataset\n",
    "\n",
    "ds = load_dataset(\"cfahlgren1/hub-stats\", \"datasets\")\n",
    "ds_df = ds[\"train\"].to_pandas()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "ds = load_dataset(\"cfahlgren1/hub-stats\", \"models\")\n",
    "md_df = ds[\"train\"].to_pandas()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Generating train split: 100%|██████████| 309714/309714 [00:00<00:00, 353713.86 examples/s]\n"
     ]
    }
   ],
   "source": [
    "ds = load_dataset(\"cfahlgren1/hub-stats\", \"spaces\")\n",
    "sp_df = ds[\"train\"].to_pandas()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'p_99999': 1299, 'p_9999': 491, 'p_999': 125}\n"
     ]
    }
   ],
   "source": [
    "dataset_percentiles = {\n",
    "    \"p_99999\": int(ds_df[\"likes\"].quantile(0.99999)),\n",
    "    \"p_9999\": int(ds_df[\"likes\"].quantile(0.9999)),\n",
    "    \"p_999\": int(ds_df[\"likes\"].quantile(0.999)),\n",
    "}\n",
    "print(dataset_percentiles)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'p_99999': 3698, 'p_9999': 949, 'p_999': 143}\n"
     ]
    }
   ],
   "source": [
    "model_percentiles = {\n",
    "    \"p_99999\": int(md_df[\"likes\"].quantile(0.99999)),\n",
    "    \"p_9999\": int(md_df[\"likes\"].quantile(0.9999)),\n",
    "    \"p_999\": int(md_df[\"likes\"].quantile(0.999)),\n",
    "}\n",
    "print(model_percentiles)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'p_99999': 6040, 'p_9999': 1552, 'p_999': 326}\n"
     ]
    }
   ],
   "source": [
    "space_percentiles = {\n",
    "    \"p_99999\": int(sp_df[\"likes\"].quantile(0.99999)),\n",
    "    \"p_9999\": int(sp_df[\"likes\"].quantile(0.9999)),\n",
    "    \"p_999\": int(sp_df[\"likes\"].quantile(0.999)),\n",
    "}\n",
    "print(space_percentiles)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [],
   "source": [
    "import json\n",
    "\n",
    "with open(\"percentiles.json\", \"w\") as f:\n",
    "    json.dump(\n",
    "        {\n",
    "            \"dataset_percentiles\": dataset_percentiles,\n",
    "            \"model_percentiles\": model_percentiles,\n",
    "            \"space_percentiles\": space_percentiles,\n",
    "        },\n",
    "        f,\n",
    "    )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "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": "3.11.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}