{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import time\n",
    "import requests\n",
    "import pandas as pd\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "from matplotlib.pyplot import figure\n",
    "from matplotlib.offsetbox import OffsetImage, AnnotationBbox\n",
    "from scipy import stats\n",
    "import matplotlib.lines as mlines\n",
    "import matplotlib.transforms as mtransforms\n",
    "import numpy as np\n",
    "import time\n",
    "#import plotly.express as px\n",
    "#!pip install chart_studio\n",
    "#import chart_studio.tools as tls\n",
    "from bs4 import BeautifulSoup\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "import matplotlib.font_manager as font_manager\n",
    "from datetime import datetime\n",
    "import pytz\n",
    "from matplotlib.ticker import MaxNLocator\n",
    "from matplotlib.patches import Ellipse\n",
    "import matplotlib.transforms as transforms\n",
    "from matplotlib.gridspec import GridSpec\n",
    "from datasets import load_dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Starting Everything:\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Found cached dataset csv (C:/Users/thoma/.cache/huggingface/datasets/nesticot___csv/nesticot--mlb_data-a391519415fcbccf/0.0.0/6954658bab30a358235fa864b05cf819af0e179325c740e4bc853bcc7ec513e1)\n",
      "100%|██████████| 1/1 [00:00<00:00,  2.02it/s]\n"
     ]
    }
   ],
   "source": [
    "\n",
    "colour_palette = ['#FFB000','#648FFF','#785EF0',\n",
    "                  '#DC267F','#FE6100','#3D1EB2','#894D80','#16AA02','#B5592B','#A3C1ED']\n",
    "\n",
    "print('Starting Everything:')\n",
    "# exit_velo_df = milb_a_ev_df.append([triple_a_ev_df,double_a_ev_df,a_high_a_ev_df,single_a_ev_df]).reset_index(drop=True)\n",
    "# player_df_all = mlb_a_player_df.append([triple_a_player_df,double_a_player_df,a_high_a_player_df,single_a_player_df]).reset_index(drop=True)\n",
    "# exit_velo_df = pd.read_csv('exit_velo_df_all.csv',index_col=[0])\n",
    "# player_df_all = pd.read_csv('player_df_all.csv',index_col=[0])\n",
    "\n",
    "# pa_df = pd.read_csv('pa_df_all.csv',index_col=[0])\n",
    "# pa_df_full_na = pa_df.dropna()\n",
    "\n",
    "### Import Datasets\n",
    "dataset = load_dataset('nesticot/mlb_data', data_files=['a_pitch_data_2023.csv',\n",
    "                                                         ])\n",
    "dataset_train = dataset['train']\n",
    "exit_velo_df = dataset_train.to_pandas().set_index(list(dataset_train.features.keys())[0]).reset_index(drop=True)\n",
    "colour_palette = ['#FFB000','#648FFF','#785EF0',\n",
    "                  '#DC267F','#FE6100','#3D1EB2','#894D80','#16AA02','#B5592B','#A3C1ED']\n",
    "\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0         True\n",
       "1         True\n",
       "2         True\n",
       "3         True\n",
       "4         True\n",
       "          ... \n",
       "575260    True\n",
       "575261    True\n",
       "575262    True\n",
       "575263    True\n",
       "575264    True\n",
       "Name: is_pitch, Length: 575265, dtype: bool"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "exit_velo_df['is_pitch']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "tl_df = exit_velo_df[exit_velo_df['batter_id'] == 699073].groupby(['batter_id','batter_name','batter_hand']).agg(\n",
    "    pitches = ('is_pitch','sum'),\n",
    "    swings = ('is_swing','sum'),\n",
    "    whiffs = ('is_whiff','sum')\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "tl_df['whiff_rate'] = tl_df['whiffs'] / tl_df['swings']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "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></th>\n",
       "      <th></th>\n",
       "      <th>pitches</th>\n",
       "      <th>swings</th>\n",
       "      <th>whiffs</th>\n",
       "      <th>whiff_rate</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>batter_id</th>\n",
       "      <th>batter_name</th>\n",
       "      <th>batter_hand</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">699073</th>\n",
       "      <th rowspan=\"2\" valign=\"top\">Thayron Liranzo</th>\n",
       "      <th>L</th>\n",
       "      <td>1344</td>\n",
       "      <td>554</td>\n",
       "      <td>189</td>\n",
       "      <td>0.341155</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>R</th>\n",
       "      <td>343</td>\n",
       "      <td>160</td>\n",
       "      <td>60</td>\n",
       "      <td>0.375</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                       pitches swings whiffs whiff_rate\n",
       "batter_id batter_name     batter_hand                                  \n",
       "699073    Thayron Liranzo L               1344    554    189   0.341155\n",
       "                          R                343    160     60      0.375"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tl_df"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.9.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}