{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "a1b2c3d4-0001-0000-0000-000000000001",
   "metadata": {},
   "source": [
    "# DataFrame Analytics\n",
    "\n",
    "Load the full registry into a pandas DataFrame and run analytics.\n",
    "\n",
    "Requires the analytics extra:\n",
    "\n",
    "```bash\n",
    "pip install anchorregistry[analytics]\n",
    "```\n",
    "\n",
    "> These examples run against Sepolia testnet (`network=\"sepolia\"`).\n",
    "> To run against Base mainnet: replace `configure(network=\"sepolia\")` with `configure(network=\"base\")`.\n",
    "> All function calls, record structures, and output shapes are identical across networks."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "a1b2c3d4-0001-0000-0000-000000000002",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Cell 1 — setup\n",
    "from anchorregistry import configure, get_all, to_dataframe, BASE_SEPOLIA_RPC, V1A_BASE_SEPOLIA\n",
    "import pandas as pd\n",
    "\n",
    "configure(\n",
    "    network=\"base-sepolia\",\n",
    "    contract_address=V1A_BASE_SEPOLIA,\n",
    "    rpc_url=BASE_SEPOLIA_RPC,  # swap for Infura / Alchemy URL for faster scans\n",
    ")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "a1b2c3d4-0001-0000-0000-000000000003",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Shape: (5, 28)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "ar_id                     str\n",
       "registered               bool\n",
       "artifact_type_index     int64\n",
       "artifact_type_name        str\n",
       "tx                        str\n",
       "block                   int64\n",
       "registrant                str\n",
       "manifest_hash             str\n",
       "parent_ar_id              str\n",
       "descriptor                str\n",
       "title                     str\n",
       "author                    str\n",
       "tree_id                   str\n",
       "token_commitment          str\n",
       "research_doi              str\n",
       "research_institution      str\n",
       "research_co_authors       str\n",
       "research_url              str\n",
       "data_data_version         str\n",
       "data_format               str\n",
       "data_row_count            str\n",
       "data_schema_url           str\n",
       "data_url                  str\n",
       "code_git_hash             str\n",
       "code_license              str\n",
       "code_language             str\n",
       "code_version              str\n",
       "code_url                  str\n",
       "dtype: object"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Cell 2 — load full registry into DataFrame\n",
    "df = to_dataframe(get_all())\n",
    "print(f\"Shape: {df.shape}\")\n",
    "df.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "a1b2c3d4-0001-0000-0000-000000000004",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>ar_id</th>\n",
       "      <th>title</th>\n",
       "      <th>research_doi</th>\n",
       "      <th>research_institution</th>\n",
       "      <th>research_url</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>AR-2026-dPXazj6</td>\n",
       "      <td>test sepolia anchor</td>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "      <td>https://anchorregistry.com/</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             ar_id                title research_doi research_institution  \\\n",
       "0  AR-2026-dPXazj6  test sepolia anchor                                     \n",
       "\n",
       "                  research_url  \n",
       "0  https://anchorregistry.com/  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Cell 3 — filter by artifact type\n",
    "# Type-specific data fields are flattened as {type_name}_{field_name}\n",
    "# e.g. RESEARCH fields -> research_doi, research_institution, research_co_authors, research_url\n",
    "research_df = df[df.artifact_type_name == \"RESEARCH\"]\n",
    "cols = [\"ar_id\", \"title\", \"research_doi\", \"research_institution\", \"research_url\"]\n",
    "research_df[[c for c in cols if c in research_df.columns]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "a1b2c3d4-0001-0000-0000-000000000005",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>ar_id</th>\n",
       "      <th>artifact_type_name</th>\n",
       "      <th>title</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>AR-2026-dPXazj6</td>\n",
       "      <td>RESEARCH</td>\n",
       "      <td>test sepolia anchor</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>AR-2026-86pNXz1</td>\n",
       "      <td>DATA</td>\n",
       "      <td>test sepolia data anchor</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>AR-2026-yPZBgoP</td>\n",
       "      <td>CODE</td>\n",
       "      <td>test show/hide toggle</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>AR-2026-A5kgam5</td>\n",
       "      <td>CODE</td>\n",
       "      <td>test hide/show toggle</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>AR-2026-L5RMQQ6</td>\n",
       "      <td>CODE</td>\n",
       "      <td>test show/hide toggle</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             ar_id artifact_type_name                     title\n",
       "0  AR-2026-dPXazj6           RESEARCH       test sepolia anchor\n",
       "1  AR-2026-86pNXz1               DATA  test sepolia data anchor\n",
       "2  AR-2026-yPZBgoP               CODE     test show/hide toggle\n",
       "3  AR-2026-A5kgam5               CODE     test hide/show toggle\n",
       "4  AR-2026-L5RMQQ6               CODE     test show/hide toggle"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Cell 4 — filter by registrant\n",
    "registrant_df = df[df.registrant == \"0xc7a7afde1177fbf0bb265ea5a616d1b8d7ed8c44\"]\n",
    "registrant_df[[\"ar_id\", \"artifact_type_name\", \"title\"]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "a1b2c3d4-0001-0000-0000-000000000006",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "artifact_type_name\n",
       "CODE        3\n",
       "DATA        1\n",
       "RESEARCH    1\n",
       "dtype: int64"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Cell 5 — group by artifact type\n",
    "df.groupby(\"artifact_type_name\").size().sort_values(ascending=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "a1b2c3d4-0001-0000-0000-000000000007",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tree_id\n",
       "0x06d9d299e3cea4b6e4d5f332ffb1a50f191ad942ed594b1bd734873fd2e42496    1\n",
       "0x3cdfef20d8c9dc273fdd8d74245833b99cc6d87a1fbd40f6cd5293dcd59beaed    1\n",
       "0xaed54c1022c6f3ac608de2a26c49859f451b268d378b5e6045643f18e6afc651    1\n",
       "0xb7b004b53c169d317554f22176971e3e20b0f81612f1ea54ee60ec285ea66ff8    1\n",
       "0xf07140ce4deaf3b5dac859091a079f82e9656f173593feda7895d940b8fa5d13    1\n",
       "dtype: int64"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Cell 6 — tree analysis\n",
    "df.groupby(\"tree_id\").size().sort_values(ascending=False)"
   ]
  }
 ],
 "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": "3.11.15"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}