{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import os\n",
    "import gzip\n",
    "import pickle\n",
    "import openai\n",
    "import torch.nn.functional as F\n",
    "import torch\n",
    "import re\n",
    "import copy\n",
    "from tqdm import tqdm\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from hardware_mapping import map_hardware_to_table\n",
    "hardware_instances = pd.read_csv('hardware_instances.csv') # columns: date,hardware\n",
    "hardware_instances = hardware_instances.assign(hardware_mapped = hardware_instances[\"hardware\"].apply(map_hardware_to_table))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "for index, row in hardware_instances.iterrows():\n",
    "    if row[\"hardware_mapped\"] == \"bfl single 'sc'\" and row[\"date\"] < \"2013-04-01\":\n",
    "        hardware_instances.at[index, \"hardware_mapped\"] = \"bitforce sha256 single\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "hardware_instances.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "len(hardware_instances)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "efficiency = pd.read_csv('../../hardwarelist/hardware_merged.csv') # columns: hardware_name,Mhash/J\n",
    "efficiency = efficiency.rename(columns={\"hardware_name\":\"hardware_mapped\"})\n",
    "\n",
    "efficiency.head(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "joined = hardware_instances.merge(efficiency, on=\"hardware_mapped\", how=\"left\")\n",
    "joined = joined.dropna(subset=[\"Mhash/J\"])\n",
    "joined.head(4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(len(joined))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "table = joined[[\"date\",\"hardware_mapped\",\"Mhash/J\"]]\n",
    "table = table.rename(columns={\"hardware_mapped\":\"hardware_name\"})\n",
    "table[\"Mhash/J\"] = table[\"Mhash/J\"].astype(float).map(lambda x: x/1000000).map(lambda x: f\"{x:.10f}\")\n",
    "table = table.rename(columns={\"Mhash/J\":\"TH/J\"})\n",
    "table = table.sort_values([\"date\",\"hardware_name\"])\n",
    "table = table.reset_index(drop=True)\n",
    "table.head(8)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "# all of these are manually verified to be random noobs trying to use a gpu during the asic era\n",
    "for index, row in table.iterrows():\n",
    "    eff = float(row[\"TH/J\"])\n",
    "    if row[\"date\"] > \"2015-07-01\" and np.log10(eff*1000000) < 1.5:\n",
    "        print(\"a\")\n",
    "        # delete the row\n",
    "        table = table.drop(index)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "table.to_csv(\"hardware_instances_with_efficiency.csv\", index=False)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "py310",
   "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"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}