{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "4826cf16",
   "metadata": {},
   "outputs": [],
   "source": [
    "import ipywidgets as widgets\n",
    "from IPython.display import display, HTML\n",
    "import pandas as pd\n",
    "from fastai.tabular.all import *\n",
    "import gradio as gr"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "34fc127c",
   "metadata": {},
   "outputs": [],
   "source": [
    "path = Path()\n",
    "df = pd.read_csv(\"rookie_year.csv\")\n",
    "learn = load_learner(path/\"export.pkl\")\n",
    "columns = [\"Name\", \"G\", \"GS\", \"Cmp\", \"Att\", \"Yds\", \"Cmp%\", \"TD\", \"Int\", \"Y/G\", \"Sk\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "id": "6e82eaae",
   "metadata": {},
   "outputs": [],
   "source": [
    "def predict(data):\n",
    "    row = df[df[\"Name\"] == data]\n",
    "    row = row.loc[:, ~df.columns.str.contains('^Unnamed')]\n",
    "    if not len(row):\n",
    "        print(\"ERROR: No QB in database with this name\")\n",
    "        return        \n",
    "    pred_row, clas, probs = learn.predict(row.iloc[0])\n",
    "    prediction = pred_row.decode()[\"Tier\"].item()    \n",
    "    return row[columns], prediction\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "id": "b9242a91",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Running on local URL:  http://127.0.0.1:7866/\n",
      "\n",
      "To create a public link, set `share=True` in `launch()`.\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div><iframe src=\"http://127.0.0.1:7866/\" width=\"900\" height=\"500\" allow=\"autoplay; camera; microphone;\" frameborder=\"0\" allowfullscreen></iframe></div>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "(<gradio.routes.App at 0x26e1100f1c0>, 'http://127.0.0.1:7866/', None)"
      ]
     },
     "execution_count": 81,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "demo = gr.Interface(fn=predict, \n",
    "                    inputs=\"text\", \n",
    "                    outputs=[\n",
    "                        gr.Dataframe(row_count=1, col_count=11, headers=columns, label=\"Rookie Year Stats\"), \n",
    "                        gr.Textbox(label=\"Prediction\")\n",
    "                    ],\n",
    "                    title=\"Rookie QB Career Prediction (Name)\",\n",
    "                    description=\"Given Name of QB who has played in the NFL, predict their career tier. Uses data from https:\\/\\/www.pro-football-reference.com. Tiers based on PFR Approximate Value.\",\n",
    "                    article=\"See more details at https://github.com/mhrice/Rookie-QB-Predictions\"\n",
    "                    examples=[\"Tom Brady\", \"Joe Burrow\", \"Trevor Lawrence\"]\n",
    "                   )\n",
    "\n",
    "demo.launch()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "id": "46d819f7",
   "metadata": {},
   "outputs": [],
   "source": [
    "def predict2(data):\n",
    "    row = data.drop(\"Name\", axis=1).astype(float)\n",
    "    row[\"Cmp\"] = row[\"Att\"].item() * row[\"Cmp%\"].item()\n",
    "    pred_row, clas, probs = learn.predict(row.iloc[0])\n",
    "    prediction = pred_row.decode()[\"Tier\"].item()    \n",
    "    return prediction\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "id": "dd0aae3a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Running on local URL:  http://127.0.0.1:7865/\n",
      "\n",
      "To create a public link, set `share=True` in `launch()`.\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div><iframe src=\"http://127.0.0.1:7865/\" width=\"900\" height=\"500\" allow=\"autoplay; camera; microphone;\" frameborder=\"0\" allowfullscreen></iframe></div>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "(<gradio.routes.App at 0x26e10daa310>, 'http://127.0.0.1:7865/', None)"
      ]
     },
     "execution_count": 80,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "demo2 = gr.Interface(fn=predict2, \n",
    "                    inputs=gr.Dataframe(row_count=1, col_count=8, headers=[x for x in columns if x not in [\"Cmp\", \"G\", \"GS\"]], label=\"Rookie Year Stats\"), \n",
    "                    outputs=gr.Textbox(label=\"Prediction\"),\n",
    "                    title=\"Rookie QB Career Prediction (Stats)\",\n",
    "                    description=\"Given stats of a presumed rookie QB, predict their career tier. Uses data from https:\\/\\/www.pro-football-reference.com. Tiers based on PFR Approximate Value.\",\n",
    "                    article=\"See more details at https://github.com/mhrice/Rookie-QB-Predictions\"\n",
    "                    )\n",
    "\n",
    "demo2.launch()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5c7e8cbe",
   "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": "3.9.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}