three_pointer_classification.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "0099265c-5104-489d-a514-2cba769c5323",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d4926b53-587e-4e6e-b773-a909a47d035a",
   "metadata": {},
   "source": [
    "# 3-point Classification\n",
    "In order to classify if a shot is a 3-pointer or not, I need to recreate a 3-point line. I will \"hack\" this\n",
    "solution by creating a circle from the hoop and determining if the (x, y) location of a shot is inside or\n",
    "outside that circle."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "73ed7065-ed97-4df5-b87a-32b048d434f6",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load the CSV\n",
    "shots_data = pd.read_csv(\"data/all_shots.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "e9626180-9fbc-4808-9f11-f6019477dc21",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Compute Euclidean distance between two points (ChatGPT-generated code)\n",
    "def distance(x1, y1, x2, y2):\n",
    "    return np.sqrt((x1 - x2)**2 + (y1 - y2)**2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "0f3ce793-a38f-4abd-af95-78fdc5dc9198",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Hoop Location\n",
    "hoop_x = 306\n",
    "hoop_y = 547\n",
    "circle_radius = 275  # Assumed radius for the 3-point line. I played around with this value until it looked right on the chart\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "7349a290-d0f7-4d52-bb8f-a390ee95d2d2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x1100 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Plot the shots with the given hoop location (ChatGPT-generated code)\n",
    "plt.figure(figsize=(12, 11))\n",
    "plt.scatter(shots_data['c_shot_x'], shots_data['c_shot_y'], marker='o', color='blue', label='Shots')\n",
    "plt.scatter(hoop_x, hoop_y, marker='o', color='red', s=100, label='Hoop')\n",
    "\n",
    "# Draw an approximate 3-point line as an arc around the hoop (ChatGPT-generated code)\n",
    "circle = plt.Circle((hoop_x, hoop_y), circle_radius, color='green', fill=False, label='3-Point Line')\n",
    "plt.gca().add_patch(circle)\n",
    "plt.gca().set_aspect('equal', adjustable='box')\n",
    "plt.legend()\n",
    "plt.title(\"Basketball Shot Chart with Approximate 3-Point Line (Given Hoop Location)\")\n",
    "plt.xlim(0, 612)\n",
    "plt.ylim(0, 578)\n",
    "plt.gca().invert_yaxis()  # Invert y-axis to match the usual basketball court visualization\n",
    "\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "58b93e99-1865-438c-98de-9b6c6ee3a6ef",
   "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>c_shot_x</th>\n",
       "      <th>c_shot_y</th>\n",
       "      <th>shot_type</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>213</td>\n",
       "      <td>491</td>\n",
       "      <td>2PA</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>304</td>\n",
       "      <td>509</td>\n",
       "      <td>2PA</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>276</td>\n",
       "      <td>245</td>\n",
       "      <td>3PA</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>362</td>\n",
       "      <td>522</td>\n",
       "      <td>2PA</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>413</td>\n",
       "      <td>253</td>\n",
       "      <td>3PA</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>391</td>\n",
       "      <td>250</td>\n",
       "      <td>3PA</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>457</td>\n",
       "      <td>533</td>\n",
       "      <td>2PA</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>302</td>\n",
       "      <td>473</td>\n",
       "      <td>2PA</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>303</td>\n",
       "      <td>241</td>\n",
       "      <td>3PA</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>77</td>\n",
       "      <td>357</td>\n",
       "      <td>3PA</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>322</td>\n",
       "      <td>518</td>\n",
       "      <td>2PA</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>243</td>\n",
       "      <td>505</td>\n",
       "      <td>2PA</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>524</td>\n",
       "      <td>506</td>\n",
       "      <td>2PA</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>263</td>\n",
       "      <td>529</td>\n",
       "      <td>2PA</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>338</td>\n",
       "      <td>528</td>\n",
       "      <td>2PA</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    c_shot_x  c_shot_y shot_type\n",
       "0        213       491       2PA\n",
       "1        304       509       2PA\n",
       "2        276       245       3PA\n",
       "3        362       522       2PA\n",
       "4        413       253       3PA\n",
       "5        391       250       3PA\n",
       "6        457       533       2PA\n",
       "7        302       473       2PA\n",
       "8        303       241       3PA\n",
       "9         77       357       3PA\n",
       "10       322       518       2PA\n",
       "11       243       505       2PA\n",
       "12       524       506       2PA\n",
       "13       263       529       2PA\n",
       "14       338       528       2PA"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Save the shot type as 3PA or 2PA depending if it's inside or outside the cirlce\n",
    "shots_data['shot_type'] = shots_data.apply(lambda row: '3PA' if distance(row['c_shot_x'], row['c_shot_y'], hoop_x, hoop_y) > circle_radius else '2PA', axis=1)\n",
    "\n",
    "shots_data.head(15)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "16ed10e1-89bc-4d8c-bb52-1e6e4cafd94e",
   "metadata": {},
   "source": [
    "# Shot Distance\n",
    "As I built the 3PA or 2PA classifier, I thought it would be good to also get the distance (in feet) the shot was\n",
    "taken. My coordinates are in pixels, so I need to code a way to convert pixels to feet. I know the free throw \n",
    "line is 15 feet away from the hoop, and the center of the free line is (306, 336) on my south-facing coordinate, \n",
    "so I can use that information to get the distance, in feet, of a given coordinate from the hoop"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "bf7b265f-c833-4dd1-b335-492206920210",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "14.066666666666666\n"
     ]
    },
    {
     "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>c_shot_x</th>\n",
       "      <th>c_shot_y</th>\n",
       "      <th>shot_type</th>\n",
       "      <th>shot_distance_feet</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>213</td>\n",
       "      <td>491</td>\n",
       "      <td>2PA</td>\n",
       "      <td>7.717446</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>304</td>\n",
       "      <td>509</td>\n",
       "      <td>2PA</td>\n",
       "      <td>2.705161</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>276</td>\n",
       "      <td>245</td>\n",
       "      <td>3PA</td>\n",
       "      <td>21.574863</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>362</td>\n",
       "      <td>522</td>\n",
       "      <td>2PA</td>\n",
       "      <td>4.359739</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>413</td>\n",
       "      <td>253</td>\n",
       "      <td>3PA</td>\n",
       "      <td>22.241644</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>391</td>\n",
       "      <td>250</td>\n",
       "      <td>3PA</td>\n",
       "      <td>21.961417</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>457</td>\n",
       "      <td>533</td>\n",
       "      <td>2PA</td>\n",
       "      <td>10.780636</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>302</td>\n",
       "      <td>473</td>\n",
       "      <td>2PA</td>\n",
       "      <td>5.268343</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>303</td>\n",
       "      <td>241</td>\n",
       "      <td>3PA</td>\n",
       "      <td>21.754600</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>77</td>\n",
       "      <td>357</td>\n",
       "      <td>3PA</td>\n",
       "      <td>21.153441</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>322</td>\n",
       "      <td>518</td>\n",
       "      <td>2PA</td>\n",
       "      <td>2.354573</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>243</td>\n",
       "      <td>505</td>\n",
       "      <td>2PA</td>\n",
       "      <td>5.382695</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>524</td>\n",
       "      <td>506</td>\n",
       "      <td>2PA</td>\n",
       "      <td>15.769337</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>263</td>\n",
       "      <td>529</td>\n",
       "      <td>2PA</td>\n",
       "      <td>3.313894</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>338</td>\n",
       "      <td>528</td>\n",
       "      <td>2PA</td>\n",
       "      <td>2.645658</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    c_shot_x  c_shot_y shot_type  shot_distance_feet\n",
       "0        213       491       2PA            7.717446\n",
       "1        304       509       2PA            2.705161\n",
       "2        276       245       3PA           21.574863\n",
       "3        362       522       2PA            4.359739\n",
       "4        413       253       3PA           22.241644\n",
       "5        391       250       3PA           21.961417\n",
       "6        457       533       2PA           10.780636\n",
       "7        302       473       2PA            5.268343\n",
       "8        303       241       3PA           21.754600\n",
       "9         77       357       3PA           21.153441\n",
       "10       322       518       2PA            2.354573\n",
       "11       243       505       2PA            5.382695\n",
       "12       524       506       2PA           15.769337\n",
       "13       263       529       2PA            3.313894\n",
       "14       338       528       2PA            2.645658"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# First, calculate the pixel distance of each shot from the hoop\n",
    "shots_data['distance_pixels'] = shots_data.apply(lambda row: distance(row['c_shot_x'], row['c_shot_y'], hoop_x, hoop_y), axis=1)\n",
    "\n",
    "# Center free throw line\n",
    "free_throw_line_x = 306\n",
    "free_throw_line_y = 336\n",
    "\n",
    "free_throw_distance_pixels = distance(hoop_x, hoop_y, free_throw_line_x, free_throw_line_y)\n",
    "\n",
    "# Recalculate the pixel-to-foot ratio using the 15 feet assumption\n",
    "pixel_to_foot_ratio = free_throw_distance_pixels / 15\n",
    "\n",
    "print(pixel_to_foot_ratio)\n",
    "\n",
    "# Convert the pixel distances to feet for all shots\n",
    "shots_data['shot_distance_feet'] = shots_data['distance_pixels'] / pixel_to_foot_ratio\n",
    "\n",
    "# Classify shots based on their distance from the given hoop location\n",
    "shots_data['shot_type'] = shots_data.apply(lambda row: '3PA' if distance(row['c_shot_x'], row['c_shot_y'], hoop_x, hoop_y) > circle_radius else '2PA', axis=1)\n",
    "\n",
    "# Drop the distance_pixels column. It was a helper column. Thanks for your help!\n",
    "shots_data = shots_data.drop(['distance_pixels'], axis=1)\n",
    "\n",
    "shots_data.head(15)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "db48f81c-5476-4d00-af24-106268fd7722",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Save the data with the new columns (shot_distance_feet, and shot_type)\n",
    "shots_data.to_csv(\"data/all_shots_enhanced.csv\", index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "cb518b17-f793-4085-9625-6ab979c2d969",
   "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": "3.11.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}