longevity_classifier.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "# imports\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.metrics import classification_report, accuracy_score\n",
    "from sklearn.utils.validation import check_is_fitted\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Knowing the problem  \n",
    "\n",
    "This is a classification problem. The aim is to predict whether an NBA rookie will stay in the league for > 5years (1) or not (0). This is the 'Target' column of the dataset  \n",
    "\n",
    "We will use scikit-learn's KNeighborsClassifier predictor class  \n",
    "\n",
    "The following steps will be taken\n",
    "- Read data (train and test)\n",
    "- Exploratory data analysis (correlation)\n",
    "- Spliting the training data\n",
    "- Standardizing the data\n",
    "- Training the model\n",
    "- Evaluating with training data\n",
    "- Testing with the test data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Step 1: Read the data to a dataframe"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 1101 entries, 0 to 1100\n",
      "Data columns (total 20 columns):\n",
      " #   Column   Non-Null Count  Dtype  \n",
      "---  ------   --------------  -----  \n",
      " 0   GP       1101 non-null   float64\n",
      " 1   MIN      1101 non-null   float64\n",
      " 2   PTS      1101 non-null   float64\n",
      " 3   FGM      1101 non-null   float64\n",
      " 4   FGA      1101 non-null   float64\n",
      " 5   FG%      1101 non-null   float64\n",
      " 6   3P Made  1101 non-null   float64\n",
      " 7   3PA      1101 non-null   float64\n",
      " 8   3P%      1101 non-null   float64\n",
      " 9   FTM      1101 non-null   float64\n",
      " 10  FTA      1101 non-null   float64\n",
      " 11  FT%      1101 non-null   float64\n",
      " 12  OREB     1101 non-null   float64\n",
      " 13  DREB     1101 non-null   float64\n",
      " 14  REB      1101 non-null   float64\n",
      " 15  AST      1101 non-null   float64\n",
      " 16  STL      1101 non-null   float64\n",
      " 17  BLK      1101 non-null   float64\n",
      " 18  TOV      1101 non-null   float64\n",
      " 19  Target   1101 non-null   int64  \n",
      "dtypes: float64(19), int64(1)\n",
      "memory usage: 172.2 KB\n",
      "None\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>GP</th>\n",
       "      <th>MIN</th>\n",
       "      <th>PTS</th>\n",
       "      <th>FGM</th>\n",
       "      <th>FGA</th>\n",
       "      <th>FG%</th>\n",
       "      <th>3P Made</th>\n",
       "      <th>3PA</th>\n",
       "      <th>3P%</th>\n",
       "      <th>FTM</th>\n",
       "      <th>FTA</th>\n",
       "      <th>FT%</th>\n",
       "      <th>OREB</th>\n",
       "      <th>DREB</th>\n",
       "      <th>REB</th>\n",
       "      <th>AST</th>\n",
       "      <th>STL</th>\n",
       "      <th>BLK</th>\n",
       "      <th>TOV</th>\n",
       "      <th>Target</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>59.0</td>\n",
       "      <td>12.8</td>\n",
       "      <td>3.4</td>\n",
       "      <td>1.3</td>\n",
       "      <td>2.6</td>\n",
       "      <td>51.0</td>\n",
       "      <td>0.2</td>\n",
       "      <td>0.3</td>\n",
       "      <td>50.0</td>\n",
       "      <td>0.7</td>\n",
       "      <td>0.8</td>\n",
       "      <td>78.0</td>\n",
       "      <td>1.1</td>\n",
       "      <td>2.3</td>\n",
       "      <td>3.3</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.3</td>\n",
       "      <td>0.4</td>\n",
       "      <td>0.5</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>31.0</td>\n",
       "      <td>10.7</td>\n",
       "      <td>3.4</td>\n",
       "      <td>1.2</td>\n",
       "      <td>3.3</td>\n",
       "      <td>35.3</td>\n",
       "      <td>0.5</td>\n",
       "      <td>2.1</td>\n",
       "      <td>25.8</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.9</td>\n",
       "      <td>55.2</td>\n",
       "      <td>0.3</td>\n",
       "      <td>1.1</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.4</td>\n",
       "      <td>0.3</td>\n",
       "      <td>0.1</td>\n",
       "      <td>0.2</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>48.0</td>\n",
       "      <td>9.3</td>\n",
       "      <td>4.5</td>\n",
       "      <td>1.7</td>\n",
       "      <td>3.4</td>\n",
       "      <td>49.7</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.2</td>\n",
       "      <td>1.9</td>\n",
       "      <td>61.5</td>\n",
       "      <td>0.4</td>\n",
       "      <td>0.8</td>\n",
       "      <td>1.2</td>\n",
       "      <td>0.8</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.4</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>80.0</td>\n",
       "      <td>27.7</td>\n",
       "      <td>11.2</td>\n",
       "      <td>3.5</td>\n",
       "      <td>9.4</td>\n",
       "      <td>37.4</td>\n",
       "      <td>1.3</td>\n",
       "      <td>4.1</td>\n",
       "      <td>32.9</td>\n",
       "      <td>2.8</td>\n",
       "      <td>3.3</td>\n",
       "      <td>85.0</td>\n",
       "      <td>0.8</td>\n",
       "      <td>1.6</td>\n",
       "      <td>2.4</td>\n",
       "      <td>3.9</td>\n",
       "      <td>1.3</td>\n",
       "      <td>0.1</td>\n",
       "      <td>2.2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>58.0</td>\n",
       "      <td>18.4</td>\n",
       "      <td>5.8</td>\n",
       "      <td>1.9</td>\n",
       "      <td>5.3</td>\n",
       "      <td>36.7</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.1</td>\n",
       "      <td>25.0</td>\n",
       "      <td>1.9</td>\n",
       "      <td>3.1</td>\n",
       "      <td>61.7</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.7</td>\n",
       "      <td>1.2</td>\n",
       "      <td>1.9</td>\n",
       "      <td>1.1</td>\n",
       "      <td>0.2</td>\n",
       "      <td>1.7</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     GP   MIN   PTS  FGM  FGA   FG%  3P Made  3PA   3P%  FTM  FTA   FT%  OREB  \\\n",
       "0  59.0  12.8   3.4  1.3  2.6  51.0      0.2  0.3  50.0  0.7  0.8  78.0   1.1   \n",
       "1  31.0  10.7   3.4  1.2  3.3  35.3      0.5  2.1  25.8  0.5  0.9  55.2   0.3   \n",
       "2  48.0   9.3   4.5  1.7  3.4  49.7      0.0  0.1   0.0  1.2  1.9  61.5   0.4   \n",
       "3  80.0  27.7  11.2  3.5  9.4  37.4      1.3  4.1  32.9  2.8  3.3  85.0   0.8   \n",
       "4  58.0  18.4   5.8  1.9  5.3  36.7      0.0  0.1  25.0  1.9  3.1  61.7   0.5   \n",
       "\n",
       "   DREB  REB  AST  STL  BLK  TOV  Target  \n",
       "0   2.3  3.3  0.5  0.3  0.4  0.5       1  \n",
       "1   1.1  1.4  0.4  0.3  0.1  0.2       0  \n",
       "2   0.8  1.2  0.8  0.5  0.4  1.0       0  \n",
       "3   1.6  2.4  3.9  1.3  0.1  2.2       1  \n",
       "4   0.7  1.2  1.9  1.1  0.2  1.7       0  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# read training and test data\n",
    "train_df = pd.read_csv('data/Train_data.csv')\n",
    "print(train_df.info()) # print the info\n",
    "train_df.head() # print first 5\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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>GP</th>\n",
       "      <th>MIN</th>\n",
       "      <th>PTS</th>\n",
       "      <th>FGM</th>\n",
       "      <th>FGA</th>\n",
       "      <th>FG%</th>\n",
       "      <th>3P Made</th>\n",
       "      <th>3PA</th>\n",
       "      <th>3P%</th>\n",
       "      <th>FTM</th>\n",
       "      <th>FTA</th>\n",
       "      <th>FT%</th>\n",
       "      <th>OREB</th>\n",
       "      <th>DREB</th>\n",
       "      <th>REB</th>\n",
       "      <th>AST</th>\n",
       "      <th>STL</th>\n",
       "      <th>BLK</th>\n",
       "      <th>TOV</th>\n",
       "      <th>Target</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>59</td>\n",
       "      <td>12.8</td>\n",
       "      <td>3.4</td>\n",
       "      <td>1.3</td>\n",
       "      <td>2.6</td>\n",
       "      <td>51.0</td>\n",
       "      <td>0.2</td>\n",
       "      <td>0.3</td>\n",
       "      <td>50.0</td>\n",
       "      <td>0.7</td>\n",
       "      <td>0.8</td>\n",
       "      <td>78.0</td>\n",
       "      <td>1.1</td>\n",
       "      <td>2.3</td>\n",
       "      <td>3.3</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.3</td>\n",
       "      <td>0.4</td>\n",
       "      <td>0.5</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>31</td>\n",
       "      <td>10.7</td>\n",
       "      <td>3.4</td>\n",
       "      <td>1.2</td>\n",
       "      <td>3.3</td>\n",
       "      <td>35.3</td>\n",
       "      <td>0.5</td>\n",
       "      <td>2.1</td>\n",
       "      <td>25.8</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.9</td>\n",
       "      <td>55.2</td>\n",
       "      <td>0.3</td>\n",
       "      <td>1.1</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.4</td>\n",
       "      <td>0.3</td>\n",
       "      <td>0.1</td>\n",
       "      <td>0.2</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>48</td>\n",
       "      <td>9.3</td>\n",
       "      <td>4.5</td>\n",
       "      <td>1.7</td>\n",
       "      <td>3.4</td>\n",
       "      <td>49.7</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.2</td>\n",
       "      <td>1.9</td>\n",
       "      <td>61.5</td>\n",
       "      <td>0.4</td>\n",
       "      <td>0.8</td>\n",
       "      <td>1.2</td>\n",
       "      <td>0.8</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.4</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>80</td>\n",
       "      <td>27.7</td>\n",
       "      <td>11.2</td>\n",
       "      <td>3.5</td>\n",
       "      <td>9.4</td>\n",
       "      <td>37.4</td>\n",
       "      <td>1.3</td>\n",
       "      <td>4.1</td>\n",
       "      <td>32.9</td>\n",
       "      <td>2.8</td>\n",
       "      <td>3.3</td>\n",
       "      <td>85.0</td>\n",
       "      <td>0.8</td>\n",
       "      <td>1.6</td>\n",
       "      <td>2.4</td>\n",
       "      <td>3.9</td>\n",
       "      <td>1.3</td>\n",
       "      <td>0.1</td>\n",
       "      <td>2.2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>58</td>\n",
       "      <td>18.4</td>\n",
       "      <td>5.8</td>\n",
       "      <td>1.9</td>\n",
       "      <td>5.3</td>\n",
       "      <td>36.7</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.1</td>\n",
       "      <td>25.0</td>\n",
       "      <td>1.9</td>\n",
       "      <td>3.1</td>\n",
       "      <td>61.7</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.7</td>\n",
       "      <td>1.2</td>\n",
       "      <td>1.9</td>\n",
       "      <td>1.1</td>\n",
       "      <td>0.2</td>\n",
       "      <td>1.7</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   GP   MIN   PTS  FGM  FGA   FG%  3P Made  3PA   3P%  FTM  FTA   FT%  OREB  \\\n",
       "0  59  12.8   3.4  1.3  2.6  51.0      0.2  0.3  50.0  0.7  0.8  78.0   1.1   \n",
       "1  31  10.7   3.4  1.2  3.3  35.3      0.5  2.1  25.8  0.5  0.9  55.2   0.3   \n",
       "2  48   9.3   4.5  1.7  3.4  49.7      0.0  0.1   0.0  1.2  1.9  61.5   0.4   \n",
       "3  80  27.7  11.2  3.5  9.4  37.4      1.3  4.1  32.9  2.8  3.3  85.0   0.8   \n",
       "4  58  18.4   5.8  1.9  5.3  36.7      0.0  0.1  25.0  1.9  3.1  61.7   0.5   \n",
       "\n",
       "   DREB  REB  AST  STL  BLK  TOV  Target  \n",
       "0   2.3  3.3  0.5  0.3  0.4  0.5       1  \n",
       "1   1.1  1.4  0.4  0.3  0.1  0.2       0  \n",
       "2   0.8  1.2  0.8  0.5  0.4  1.0       0  \n",
       "3   1.6  2.4  3.9  1.3  0.1  2.2       1  \n",
       "4   0.7  1.2  1.9  1.1  0.2  1.7       0  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# cast Games played (GP) as integers since they are whole numbers\n",
    "train_df['GP'] = train_df['GP'].astype(int)\n",
    "train_df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Step 2: Exploratory data analysis  \n",
    "\n",
    "- Create a correlation table of Target vs other parameters\n",
    "- Divide the train data in to two, one for target 0 and target 1\n",
    "- Perform summary statitics on both subsets to see trends\n",
    "- Create a scatter plot of GP, MIN, PTS, FG%"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "# create two subsets of train data, target 0 and 1\n",
    "target_0 = train_df[train_df[\"Target\"] == 0]\n",
    "target_1 = train_df[train_df[\"Target\"] == 1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "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>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>GP</th>\n",
       "      <td>551.0</td>\n",
       "      <td>51.760436</td>\n",
       "      <td>16.420740</td>\n",
       "      <td>11.0</td>\n",
       "      <td>41.000000</td>\n",
       "      <td>51.000000</td>\n",
       "      <td>64.000000</td>\n",
       "      <td>82.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>MIN</th>\n",
       "      <td>551.0</td>\n",
       "      <td>14.086825</td>\n",
       "      <td>6.193561</td>\n",
       "      <td>3.1</td>\n",
       "      <td>9.391092</td>\n",
       "      <td>13.100000</td>\n",
       "      <td>17.256120</td>\n",
       "      <td>37.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PTS</th>\n",
       "      <td>551.0</td>\n",
       "      <td>5.029547</td>\n",
       "      <td>2.942369</td>\n",
       "      <td>1.1</td>\n",
       "      <td>3.100000</td>\n",
       "      <td>4.200000</td>\n",
       "      <td>6.137233</td>\n",
       "      <td>21.900000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>FGM</th>\n",
       "      <td>551.0</td>\n",
       "      <td>1.938020</td>\n",
       "      <td>1.139236</td>\n",
       "      <td>0.4</td>\n",
       "      <td>1.200000</td>\n",
       "      <td>1.624857</td>\n",
       "      <td>2.399082</td>\n",
       "      <td>8.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>FGA</th>\n",
       "      <td>551.0</td>\n",
       "      <td>4.524805</td>\n",
       "      <td>2.449288</td>\n",
       "      <td>1.2</td>\n",
       "      <td>2.812043</td>\n",
       "      <td>3.890405</td>\n",
       "      <td>5.418301</td>\n",
       "      <td>17.600000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>FG%</th>\n",
       "      <td>551.0</td>\n",
       "      <td>42.374270</td>\n",
       "      <td>6.141850</td>\n",
       "      <td>25.0</td>\n",
       "      <td>38.400000</td>\n",
       "      <td>41.949429</td>\n",
       "      <td>45.979053</td>\n",
       "      <td>59.600000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3P Made</th>\n",
       "      <td>551.0</td>\n",
       "      <td>0.228489</td>\n",
       "      <td>0.298401</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.100000</td>\n",
       "      <td>0.400000</td>\n",
       "      <td>1.580128</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3PA</th>\n",
       "      <td>551.0</td>\n",
       "      <td>0.748400</td>\n",
       "      <td>0.868977</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.065540</td>\n",
       "      <td>0.367431</td>\n",
       "      <td>1.203554</td>\n",
       "      <td>4.444359</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3P%</th>\n",
       "      <td>551.0</td>\n",
       "      <td>19.030522</td>\n",
       "      <td>14.787113</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>23.300000</td>\n",
       "      <td>31.600000</td>\n",
       "      <td>50.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>FTM</th>\n",
       "      <td>551.0</td>\n",
       "      <td>0.930031</td>\n",
       "      <td>0.640112</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.500000</td>\n",
       "      <td>0.779553</td>\n",
       "      <td>1.150084</td>\n",
       "      <td>5.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>FTA</th>\n",
       "      <td>551.0</td>\n",
       "      <td>1.316651</td>\n",
       "      <td>0.850968</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.791364</td>\n",
       "      <td>1.100000</td>\n",
       "      <td>1.700000</td>\n",
       "      <td>6.200000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>FT%</th>\n",
       "      <td>551.0</td>\n",
       "      <td>69.577365</td>\n",
       "      <td>10.887896</td>\n",
       "      <td>0.0</td>\n",
       "      <td>64.300000</td>\n",
       "      <td>70.378649</td>\n",
       "      <td>76.629009</td>\n",
       "      <td>100.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>OREB</th>\n",
       "      <td>551.0</td>\n",
       "      <td>0.704578</td>\n",
       "      <td>0.521747</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.321546</td>\n",
       "      <td>0.565062</td>\n",
       "      <td>0.900000</td>\n",
       "      <td>3.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>DREB</th>\n",
       "      <td>551.0</td>\n",
       "      <td>1.503361</td>\n",
       "      <td>0.968942</td>\n",
       "      <td>0.2</td>\n",
       "      <td>0.808471</td>\n",
       "      <td>1.206163</td>\n",
       "      <td>1.900000</td>\n",
       "      <td>7.700000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>REB</th>\n",
       "      <td>551.0</td>\n",
       "      <td>2.202925</td>\n",
       "      <td>1.404875</td>\n",
       "      <td>0.3</td>\n",
       "      <td>1.248112</td>\n",
       "      <td>1.800000</td>\n",
       "      <td>2.809531</td>\n",
       "      <td>10.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>AST</th>\n",
       "      <td>551.0</td>\n",
       "      <td>1.179038</td>\n",
       "      <td>0.986661</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.500000</td>\n",
       "      <td>0.900000</td>\n",
       "      <td>1.500000</td>\n",
       "      <td>8.700000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>STL</th>\n",
       "      <td>551.0</td>\n",
       "      <td>0.485903</td>\n",
       "      <td>0.297171</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.300000</td>\n",
       "      <td>0.400000</td>\n",
       "      <td>0.600000</td>\n",
       "      <td>2.100000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>BLK</th>\n",
       "      <td>551.0</td>\n",
       "      <td>0.249126</td>\n",
       "      <td>0.284076</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.100000</td>\n",
       "      <td>0.197293</td>\n",
       "      <td>0.300000</td>\n",
       "      <td>2.100000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>TOV</th>\n",
       "      <td>551.0</td>\n",
       "      <td>0.934844</td>\n",
       "      <td>0.522951</td>\n",
       "      <td>0.1</td>\n",
       "      <td>0.600000</td>\n",
       "      <td>0.800000</td>\n",
       "      <td>1.100000</td>\n",
       "      <td>3.900000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         count       mean        std   min        25%        50%        75%  \\\n",
       "GP       551.0  51.760436  16.420740  11.0  41.000000  51.000000  64.000000   \n",
       "MIN      551.0  14.086825   6.193561   3.1   9.391092  13.100000  17.256120   \n",
       "PTS      551.0   5.029547   2.942369   1.1   3.100000   4.200000   6.137233   \n",
       "FGM      551.0   1.938020   1.139236   0.4   1.200000   1.624857   2.399082   \n",
       "FGA      551.0   4.524805   2.449288   1.2   2.812043   3.890405   5.418301   \n",
       "FG%      551.0  42.374270   6.141850  25.0  38.400000  41.949429  45.979053   \n",
       "3P Made  551.0   0.228489   0.298401   0.0   0.000000   0.100000   0.400000   \n",
       "3PA      551.0   0.748400   0.868977   0.0   0.065540   0.367431   1.203554   \n",
       "3P%      551.0  19.030522  14.787113   0.0   0.000000  23.300000  31.600000   \n",
       "FTM      551.0   0.930031   0.640112   0.0   0.500000   0.779553   1.150084   \n",
       "FTA      551.0   1.316651   0.850968   0.0   0.791364   1.100000   1.700000   \n",
       "FT%      551.0  69.577365  10.887896   0.0  64.300000  70.378649  76.629009   \n",
       "OREB     551.0   0.704578   0.521747   0.0   0.321546   0.565062   0.900000   \n",
       "DREB     551.0   1.503361   0.968942   0.2   0.808471   1.206163   1.900000   \n",
       "REB      551.0   2.202925   1.404875   0.3   1.248112   1.800000   2.809531   \n",
       "AST      551.0   1.179038   0.986661   0.0   0.500000   0.900000   1.500000   \n",
       "STL      551.0   0.485903   0.297171   0.0   0.300000   0.400000   0.600000   \n",
       "BLK      551.0   0.249126   0.284076   0.0   0.100000   0.197293   0.300000   \n",
       "TOV      551.0   0.934844   0.522951   0.1   0.600000   0.800000   1.100000   \n",
       "\n",
       "                max  \n",
       "GP        82.000000  \n",
       "MIN       37.000000  \n",
       "PTS       21.900000  \n",
       "FGM        8.000000  \n",
       "FGA       17.600000  \n",
       "FG%       59.600000  \n",
       "3P Made    1.580128  \n",
       "3PA        4.444359  \n",
       "3P%       50.000000  \n",
       "FTM        5.000000  \n",
       "FTA        6.200000  \n",
       "FT%      100.000000  \n",
       "OREB       3.000000  \n",
       "DREB       7.700000  \n",
       "REB       10.500000  \n",
       "AST        8.700000  \n",
       "STL        2.100000  \n",
       "BLK        2.100000  \n",
       "TOV        3.900000  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# summary statistics of those < 5 years, excluding the Target column\n",
    "target_0.drop(columns=[\"Target\"]).describe().T"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "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>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>GP</th>\n",
       "      <td>550.0</td>\n",
       "      <td>66.083636</td>\n",
       "      <td>14.974426</td>\n",
       "      <td>22.0</td>\n",
       "      <td>55.000</td>\n",
       "      <td>70.00</td>\n",
       "      <td>80.000</td>\n",
       "      <td>82.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>MIN</th>\n",
       "      <td>550.0</td>\n",
       "      <td>19.774909</td>\n",
       "      <td>8.641803</td>\n",
       "      <td>4.5</td>\n",
       "      <td>12.625</td>\n",
       "      <td>19.10</td>\n",
       "      <td>25.475</td>\n",
       "      <td>40.9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PTS</th>\n",
       "      <td>550.0</td>\n",
       "      <td>7.977818</td>\n",
       "      <td>4.659102</td>\n",
       "      <td>1.2</td>\n",
       "      <td>4.500</td>\n",
       "      <td>6.80</td>\n",
       "      <td>10.300</td>\n",
       "      <td>24.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>FGM</th>\n",
       "      <td>550.0</td>\n",
       "      <td>3.085273</td>\n",
       "      <td>1.800896</td>\n",
       "      <td>0.4</td>\n",
       "      <td>1.800</td>\n",
       "      <td>2.60</td>\n",
       "      <td>3.975</td>\n",
       "      <td>9.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>FGA</th>\n",
       "      <td>550.0</td>\n",
       "      <td>6.768727</td>\n",
       "      <td>3.864250</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3.900</td>\n",
       "      <td>5.70</td>\n",
       "      <td>8.600</td>\n",
       "      <td>18.9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>FG%</th>\n",
       "      <td>550.0</td>\n",
       "      <td>45.453636</td>\n",
       "      <td>5.672682</td>\n",
       "      <td>30.1</td>\n",
       "      <td>41.600</td>\n",
       "      <td>45.30</td>\n",
       "      <td>49.100</td>\n",
       "      <td>73.7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3P Made</th>\n",
       "      <td>550.0</td>\n",
       "      <td>0.255455</td>\n",
       "      <td>0.417684</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.375</td>\n",
       "      <td>2.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3PA</th>\n",
       "      <td>550.0</td>\n",
       "      <td>0.786545</td>\n",
       "      <td>1.147168</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.20</td>\n",
       "      <td>1.100</td>\n",
       "      <td>6.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3P%</th>\n",
       "      <td>550.0</td>\n",
       "      <td>19.070364</td>\n",
       "      <td>16.222362</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>21.95</td>\n",
       "      <td>33.200</td>\n",
       "      <td>100.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>FTM</th>\n",
       "      <td>550.0</td>\n",
       "      <td>1.554364</td>\n",
       "      <td>1.074904</td>\n",
       "      <td>0.1</td>\n",
       "      <td>0.800</td>\n",
       "      <td>1.30</td>\n",
       "      <td>2.075</td>\n",
       "      <td>7.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>FTA</th>\n",
       "      <td>550.0</td>\n",
       "      <td>2.167818</td>\n",
       "      <td>1.467449</td>\n",
       "      <td>0.1</td>\n",
       "      <td>1.100</td>\n",
       "      <td>1.80</td>\n",
       "      <td>2.800</td>\n",
       "      <td>10.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>FT%</th>\n",
       "      <td>550.0</td>\n",
       "      <td>71.416000</td>\n",
       "      <td>9.770805</td>\n",
       "      <td>28.6</td>\n",
       "      <td>66.100</td>\n",
       "      <td>72.40</td>\n",
       "      <td>78.100</td>\n",
       "      <td>100.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>OREB</th>\n",
       "      <td>550.0</td>\n",
       "      <td>1.212364</td>\n",
       "      <td>0.888887</td>\n",
       "      <td>0.1</td>\n",
       "      <td>0.500</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1.700</td>\n",
       "      <td>5.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>DREB</th>\n",
       "      <td>550.0</td>\n",
       "      <td>2.371455</td>\n",
       "      <td>1.514425</td>\n",
       "      <td>0.3</td>\n",
       "      <td>1.200</td>\n",
       "      <td>2.00</td>\n",
       "      <td>3.175</td>\n",
       "      <td>9.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>REB</th>\n",
       "      <td>550.0</td>\n",
       "      <td>3.582182</td>\n",
       "      <td>2.324827</td>\n",
       "      <td>0.4</td>\n",
       "      <td>1.825</td>\n",
       "      <td>3.00</td>\n",
       "      <td>4.700</td>\n",
       "      <td>13.9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>AST</th>\n",
       "      <td>550.0</td>\n",
       "      <td>1.766909</td>\n",
       "      <td>1.627383</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.700</td>\n",
       "      <td>1.30</td>\n",
       "      <td>2.200</td>\n",
       "      <td>10.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>STL</th>\n",
       "      <td>550.0</td>\n",
       "      <td>0.693091</td>\n",
       "      <td>0.434475</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.400</td>\n",
       "      <td>0.60</td>\n",
       "      <td>0.900</td>\n",
       "      <td>2.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>BLK</th>\n",
       "      <td>550.0</td>\n",
       "      <td>0.439455</td>\n",
       "      <td>0.502478</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.100</td>\n",
       "      <td>0.30</td>\n",
       "      <td>0.600</td>\n",
       "      <td>3.9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>TOV</th>\n",
       "      <td>550.0</td>\n",
       "      <td>1.366545</td>\n",
       "      <td>0.761702</td>\n",
       "      <td>0.1</td>\n",
       "      <td>0.800</td>\n",
       "      <td>1.20</td>\n",
       "      <td>1.800</td>\n",
       "      <td>4.2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         count       mean        std   min     25%    50%     75%    max\n",
       "GP       550.0  66.083636  14.974426  22.0  55.000  70.00  80.000   82.0\n",
       "MIN      550.0  19.774909   8.641803   4.5  12.625  19.10  25.475   40.9\n",
       "PTS      550.0   7.977818   4.659102   1.2   4.500   6.80  10.300   24.3\n",
       "FGM      550.0   3.085273   1.800896   0.4   1.800   2.60   3.975    9.0\n",
       "FGA      550.0   6.768727   3.864250   1.0   3.900   5.70   8.600   18.9\n",
       "FG%      550.0  45.453636   5.672682  30.1  41.600  45.30  49.100   73.7\n",
       "3P Made  550.0   0.255455   0.417684   0.0   0.000   0.00   0.375    2.3\n",
       "3PA      550.0   0.786545   1.147168   0.0   0.000   0.20   1.100    6.5\n",
       "3P%      550.0  19.070364  16.222362   0.0   0.000  21.95  33.200  100.0\n",
       "FTM      550.0   1.554364   1.074904   0.1   0.800   1.30   2.075    7.5\n",
       "FTA      550.0   2.167818   1.467449   0.1   1.100   1.80   2.800   10.2\n",
       "FT%      550.0  71.416000   9.770805  28.6  66.100  72.40  78.100  100.0\n",
       "OREB     550.0   1.212364   0.888887   0.1   0.500   1.00   1.700    5.3\n",
       "DREB     550.0   2.371455   1.514425   0.3   1.200   2.00   3.175    9.6\n",
       "REB      550.0   3.582182   2.324827   0.4   1.825   3.00   4.700   13.9\n",
       "AST      550.0   1.766909   1.627383   0.0   0.700   1.30   2.200   10.6\n",
       "STL      550.0   0.693091   0.434475   0.0   0.400   0.60   0.900    2.5\n",
       "BLK      550.0   0.439455   0.502478   0.0   0.100   0.30   0.600    3.9\n",
       "TOV      550.0   1.366545   0.761702   0.1   0.800   1.20   1.800    4.2"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# summary statistics of those > 5 years, excluding the target column \n",
    "target_1.drop(columns=[\"Target\"]).describe().T"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Comparing the summary statistics for the two target cartegories above, players with >= 5 career years played tend to do better across most of the metrics compared to their counterparts. This is evident from the mean, median and the other quartiles."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "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>GP</th>\n",
       "      <th>MIN</th>\n",
       "      <th>PTS</th>\n",
       "      <th>FGM</th>\n",
       "      <th>FGA</th>\n",
       "      <th>FG%</th>\n",
       "      <th>3P Made</th>\n",
       "      <th>3PA</th>\n",
       "      <th>3P%</th>\n",
       "      <th>FTM</th>\n",
       "      <th>FTA</th>\n",
       "      <th>FT%</th>\n",
       "      <th>OREB</th>\n",
       "      <th>DREB</th>\n",
       "      <th>REB</th>\n",
       "      <th>AST</th>\n",
       "      <th>STL</th>\n",
       "      <th>BLK</th>\n",
       "      <th>TOV</th>\n",
       "      <th>Target</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>GP</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.597446</td>\n",
       "      <td>0.559332</td>\n",
       "      <td>0.562213</td>\n",
       "      <td>0.538190</td>\n",
       "      <td>0.311106</td>\n",
       "      <td>0.119768</td>\n",
       "      <td>0.106866</td>\n",
       "      <td>0.026659</td>\n",
       "      <td>0.503171</td>\n",
       "      <td>0.491696</td>\n",
       "      <td>0.200386</td>\n",
       "      <td>0.416948</td>\n",
       "      <td>0.479671</td>\n",
       "      <td>0.473715</td>\n",
       "      <td>0.362790</td>\n",
       "      <td>0.456121</td>\n",
       "      <td>0.303153</td>\n",
       "      <td>0.523640</td>\n",
       "      <td>0.415001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>MIN</th>\n",
       "      <td>0.597446</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.918264</td>\n",
       "      <td>0.905489</td>\n",
       "      <td>0.914114</td>\n",
       "      <td>0.211973</td>\n",
       "      <td>0.390542</td>\n",
       "      <td>0.398589</td>\n",
       "      <td>0.169725</td>\n",
       "      <td>0.811353</td>\n",
       "      <td>0.795711</td>\n",
       "      <td>0.241640</td>\n",
       "      <td>0.586255</td>\n",
       "      <td>0.756072</td>\n",
       "      <td>0.719870</td>\n",
       "      <td>0.625946</td>\n",
       "      <td>0.766311</td>\n",
       "      <td>0.432429</td>\n",
       "      <td>0.830394</td>\n",
       "      <td>0.354152</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PTS</th>\n",
       "      <td>0.559332</td>\n",
       "      <td>0.918264</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.991033</td>\n",
       "      <td>0.980013</td>\n",
       "      <td>0.272255</td>\n",
       "      <td>0.337452</td>\n",
       "      <td>0.341765</td>\n",
       "      <td>0.147124</td>\n",
       "      <td>0.899845</td>\n",
       "      <td>0.882502</td>\n",
       "      <td>0.246680</td>\n",
       "      <td>0.590605</td>\n",
       "      <td>0.716958</td>\n",
       "      <td>0.696668</td>\n",
       "      <td>0.546482</td>\n",
       "      <td>0.669969</td>\n",
       "      <td>0.433771</td>\n",
       "      <td>0.853030</td>\n",
       "      <td>0.354192</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>FGM</th>\n",
       "      <td>0.562213</td>\n",
       "      <td>0.905489</td>\n",
       "      <td>0.991033</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.979742</td>\n",
       "      <td>0.308350</td>\n",
       "      <td>0.277842</td>\n",
       "      <td>0.282244</td>\n",
       "      <td>0.114917</td>\n",
       "      <td>0.853349</td>\n",
       "      <td>0.843725</td>\n",
       "      <td>0.214689</td>\n",
       "      <td>0.610619</td>\n",
       "      <td>0.723419</td>\n",
       "      <td>0.708522</td>\n",
       "      <td>0.521606</td>\n",
       "      <td>0.650974</td>\n",
       "      <td>0.442781</td>\n",
       "      <td>0.834749</td>\n",
       "      <td>0.356119</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>FGA</th>\n",
       "      <td>0.538190</td>\n",
       "      <td>0.914114</td>\n",
       "      <td>0.980013</td>\n",
       "      <td>0.979742</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.145322</td>\n",
       "      <td>0.382426</td>\n",
       "      <td>0.399330</td>\n",
       "      <td>0.202011</td>\n",
       "      <td>0.832288</td>\n",
       "      <td>0.807849</td>\n",
       "      <td>0.262776</td>\n",
       "      <td>0.514503</td>\n",
       "      <td>0.655417</td>\n",
       "      <td>0.627248</td>\n",
       "      <td>0.587837</td>\n",
       "      <td>0.689307</td>\n",
       "      <td>0.360720</td>\n",
       "      <td>0.848879</td>\n",
       "      <td>0.327988</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>FG%</th>\n",
       "      <td>0.311106</td>\n",
       "      <td>0.211973</td>\n",
       "      <td>0.272255</td>\n",
       "      <td>0.308350</td>\n",
       "      <td>0.145322</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.304532</td>\n",
       "      <td>-0.360298</td>\n",
       "      <td>-0.376032</td>\n",
       "      <td>0.267298</td>\n",
       "      <td>0.320679</td>\n",
       "      <td>-0.142038</td>\n",
       "      <td>0.527119</td>\n",
       "      <td>0.431919</td>\n",
       "      <td>0.484302</td>\n",
       "      <td>-0.130397</td>\n",
       "      <td>0.040709</td>\n",
       "      <td>0.414445</td>\n",
       "      <td>0.125793</td>\n",
       "      <td>0.252236</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3P Made</th>\n",
       "      <td>0.119768</td>\n",
       "      <td>0.390542</td>\n",
       "      <td>0.337452</td>\n",
       "      <td>0.277842</td>\n",
       "      <td>0.382426</td>\n",
       "      <td>-0.304532</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.982678</td>\n",
       "      <td>0.619991</td>\n",
       "      <td>0.157143</td>\n",
       "      <td>0.090530</td>\n",
       "      <td>0.310734</td>\n",
       "      <td>-0.221181</td>\n",
       "      <td>0.017703</td>\n",
       "      <td>-0.072795</td>\n",
       "      <td>0.415002</td>\n",
       "      <td>0.353963</td>\n",
       "      <td>-0.157557</td>\n",
       "      <td>0.269701</td>\n",
       "      <td>0.037159</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3PA</th>\n",
       "      <td>0.106866</td>\n",
       "      <td>0.398589</td>\n",
       "      <td>0.341765</td>\n",
       "      <td>0.282244</td>\n",
       "      <td>0.399330</td>\n",
       "      <td>-0.360298</td>\n",
       "      <td>0.982678</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.612823</td>\n",
       "      <td>0.165934</td>\n",
       "      <td>0.096702</td>\n",
       "      <td>0.321690</td>\n",
       "      <td>-0.237302</td>\n",
       "      <td>0.007024</td>\n",
       "      <td>-0.086081</td>\n",
       "      <td>0.444800</td>\n",
       "      <td>0.379792</td>\n",
       "      <td>-0.172752</td>\n",
       "      <td>0.290051</td>\n",
       "      <td>0.018759</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3P%</th>\n",
       "      <td>0.026659</td>\n",
       "      <td>0.169725</td>\n",
       "      <td>0.147124</td>\n",
       "      <td>0.114917</td>\n",
       "      <td>0.202011</td>\n",
       "      <td>-0.376032</td>\n",
       "      <td>0.619991</td>\n",
       "      <td>0.612823</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.018112</td>\n",
       "      <td>-0.048118</td>\n",
       "      <td>0.329070</td>\n",
       "      <td>-0.294037</td>\n",
       "      <td>-0.132653</td>\n",
       "      <td>-0.198723</td>\n",
       "      <td>0.296920</td>\n",
       "      <td>0.233972</td>\n",
       "      <td>-0.264620</td>\n",
       "      <td>0.111586</td>\n",
       "      <td>0.001285</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>FTM</th>\n",
       "      <td>0.503171</td>\n",
       "      <td>0.811353</td>\n",
       "      <td>0.899845</td>\n",
       "      <td>0.853349</td>\n",
       "      <td>0.832288</td>\n",
       "      <td>0.267298</td>\n",
       "      <td>0.157143</td>\n",
       "      <td>0.165934</td>\n",
       "      <td>0.018112</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.980388</td>\n",
       "      <td>0.236930</td>\n",
       "      <td>0.604364</td>\n",
       "      <td>0.686171</td>\n",
       "      <td>0.681736</td>\n",
       "      <td>0.473577</td>\n",
       "      <td>0.597443</td>\n",
       "      <td>0.462012</td>\n",
       "      <td>0.811781</td>\n",
       "      <td>0.333098</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>FTA</th>\n",
       "      <td>0.491696</td>\n",
       "      <td>0.795711</td>\n",
       "      <td>0.882502</td>\n",
       "      <td>0.843725</td>\n",
       "      <td>0.807849</td>\n",
       "      <td>0.320679</td>\n",
       "      <td>0.090530</td>\n",
       "      <td>0.096702</td>\n",
       "      <td>-0.048118</td>\n",
       "      <td>0.980388</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.092367</td>\n",
       "      <td>0.673121</td>\n",
       "      <td>0.731581</td>\n",
       "      <td>0.737864</td>\n",
       "      <td>0.419419</td>\n",
       "      <td>0.568765</td>\n",
       "      <td>0.521547</td>\n",
       "      <td>0.800064</td>\n",
       "      <td>0.334718</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>FT%</th>\n",
       "      <td>0.200386</td>\n",
       "      <td>0.241640</td>\n",
       "      <td>0.246680</td>\n",
       "      <td>0.214689</td>\n",
       "      <td>0.262776</td>\n",
       "      <td>-0.142038</td>\n",
       "      <td>0.310734</td>\n",
       "      <td>0.321690</td>\n",
       "      <td>0.329070</td>\n",
       "      <td>0.236930</td>\n",
       "      <td>0.092367</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.143924</td>\n",
       "      <td>-0.016600</td>\n",
       "      <td>-0.065965</td>\n",
       "      <td>0.308191</td>\n",
       "      <td>0.228524</td>\n",
       "      <td>-0.150065</td>\n",
       "      <td>0.197130</td>\n",
       "      <td>0.088597</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>OREB</th>\n",
       "      <td>0.416948</td>\n",
       "      <td>0.586255</td>\n",
       "      <td>0.590605</td>\n",
       "      <td>0.610619</td>\n",
       "      <td>0.514503</td>\n",
       "      <td>0.527119</td>\n",
       "      <td>-0.221181</td>\n",
       "      <td>-0.237302</td>\n",
       "      <td>-0.294037</td>\n",
       "      <td>0.604364</td>\n",
       "      <td>0.673121</td>\n",
       "      <td>-0.143924</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.847967</td>\n",
       "      <td>0.937130</td>\n",
       "      <td>-0.016893</td>\n",
       "      <td>0.275706</td>\n",
       "      <td>0.665600</td>\n",
       "      <td>0.434725</td>\n",
       "      <td>0.329306</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>DREB</th>\n",
       "      <td>0.479671</td>\n",
       "      <td>0.756072</td>\n",
       "      <td>0.716958</td>\n",
       "      <td>0.723419</td>\n",
       "      <td>0.655417</td>\n",
       "      <td>0.431919</td>\n",
       "      <td>0.017703</td>\n",
       "      <td>0.007024</td>\n",
       "      <td>-0.132653</td>\n",
       "      <td>0.686171</td>\n",
       "      <td>0.731581</td>\n",
       "      <td>-0.016600</td>\n",
       "      <td>0.847967</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.979235</td>\n",
       "      <td>0.193664</td>\n",
       "      <td>0.414556</td>\n",
       "      <td>0.712691</td>\n",
       "      <td>0.591945</td>\n",
       "      <td>0.323428</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>REB</th>\n",
       "      <td>0.473715</td>\n",
       "      <td>0.719870</td>\n",
       "      <td>0.696668</td>\n",
       "      <td>0.708522</td>\n",
       "      <td>0.627248</td>\n",
       "      <td>0.484302</td>\n",
       "      <td>-0.072795</td>\n",
       "      <td>-0.086081</td>\n",
       "      <td>-0.198723</td>\n",
       "      <td>0.681736</td>\n",
       "      <td>0.737864</td>\n",
       "      <td>-0.065965</td>\n",
       "      <td>0.937130</td>\n",
       "      <td>0.979235</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.121015</td>\n",
       "      <td>0.377460</td>\n",
       "      <td>0.720953</td>\n",
       "      <td>0.554782</td>\n",
       "      <td>0.338257</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>AST</th>\n",
       "      <td>0.362790</td>\n",
       "      <td>0.625946</td>\n",
       "      <td>0.546482</td>\n",
       "      <td>0.521606</td>\n",
       "      <td>0.587837</td>\n",
       "      <td>-0.130397</td>\n",
       "      <td>0.415002</td>\n",
       "      <td>0.444800</td>\n",
       "      <td>0.296920</td>\n",
       "      <td>0.473577</td>\n",
       "      <td>0.419419</td>\n",
       "      <td>0.308191</td>\n",
       "      <td>-0.016893</td>\n",
       "      <td>0.193664</td>\n",
       "      <td>0.121015</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.745087</td>\n",
       "      <td>-0.063675</td>\n",
       "      <td>0.736611</td>\n",
       "      <td>0.213621</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>STL</th>\n",
       "      <td>0.456121</td>\n",
       "      <td>0.766311</td>\n",
       "      <td>0.669969</td>\n",
       "      <td>0.650974</td>\n",
       "      <td>0.689307</td>\n",
       "      <td>0.040709</td>\n",
       "      <td>0.353963</td>\n",
       "      <td>0.379792</td>\n",
       "      <td>0.233972</td>\n",
       "      <td>0.597443</td>\n",
       "      <td>0.568765</td>\n",
       "      <td>0.228524</td>\n",
       "      <td>0.275706</td>\n",
       "      <td>0.414556</td>\n",
       "      <td>0.377460</td>\n",
       "      <td>0.745087</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.161667</td>\n",
       "      <td>0.718808</td>\n",
       "      <td>0.268398</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>BLK</th>\n",
       "      <td>0.303153</td>\n",
       "      <td>0.432429</td>\n",
       "      <td>0.433771</td>\n",
       "      <td>0.442781</td>\n",
       "      <td>0.360720</td>\n",
       "      <td>0.414445</td>\n",
       "      <td>-0.157557</td>\n",
       "      <td>-0.172752</td>\n",
       "      <td>-0.264620</td>\n",
       "      <td>0.462012</td>\n",
       "      <td>0.521547</td>\n",
       "      <td>-0.150065</td>\n",
       "      <td>0.665600</td>\n",
       "      <td>0.712691</td>\n",
       "      <td>0.720953</td>\n",
       "      <td>-0.063675</td>\n",
       "      <td>0.161667</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.333091</td>\n",
       "      <td>0.227312</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>TOV</th>\n",
       "      <td>0.523640</td>\n",
       "      <td>0.830394</td>\n",
       "      <td>0.853030</td>\n",
       "      <td>0.834749</td>\n",
       "      <td>0.848879</td>\n",
       "      <td>0.125793</td>\n",
       "      <td>0.269701</td>\n",
       "      <td>0.290051</td>\n",
       "      <td>0.111586</td>\n",
       "      <td>0.811781</td>\n",
       "      <td>0.800064</td>\n",
       "      <td>0.197130</td>\n",
       "      <td>0.434725</td>\n",
       "      <td>0.591945</td>\n",
       "      <td>0.554782</td>\n",
       "      <td>0.736611</td>\n",
       "      <td>0.718808</td>\n",
       "      <td>0.333091</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.314013</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Target</th>\n",
       "      <td>0.415001</td>\n",
       "      <td>0.354152</td>\n",
       "      <td>0.354192</td>\n",
       "      <td>0.356119</td>\n",
       "      <td>0.327988</td>\n",
       "      <td>0.252236</td>\n",
       "      <td>0.037159</td>\n",
       "      <td>0.018759</td>\n",
       "      <td>0.001285</td>\n",
       "      <td>0.333098</td>\n",
       "      <td>0.334718</td>\n",
       "      <td>0.088597</td>\n",
       "      <td>0.329306</td>\n",
       "      <td>0.323428</td>\n",
       "      <td>0.338257</td>\n",
       "      <td>0.213621</td>\n",
       "      <td>0.268398</td>\n",
       "      <td>0.227312</td>\n",
       "      <td>0.314013</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               GP       MIN       PTS       FGM       FGA       FG%   3P Made  \\\n",
       "GP       1.000000  0.597446  0.559332  0.562213  0.538190  0.311106  0.119768   \n",
       "MIN      0.597446  1.000000  0.918264  0.905489  0.914114  0.211973  0.390542   \n",
       "PTS      0.559332  0.918264  1.000000  0.991033  0.980013  0.272255  0.337452   \n",
       "FGM      0.562213  0.905489  0.991033  1.000000  0.979742  0.308350  0.277842   \n",
       "FGA      0.538190  0.914114  0.980013  0.979742  1.000000  0.145322  0.382426   \n",
       "FG%      0.311106  0.211973  0.272255  0.308350  0.145322  1.000000 -0.304532   \n",
       "3P Made  0.119768  0.390542  0.337452  0.277842  0.382426 -0.304532  1.000000   \n",
       "3PA      0.106866  0.398589  0.341765  0.282244  0.399330 -0.360298  0.982678   \n",
       "3P%      0.026659  0.169725  0.147124  0.114917  0.202011 -0.376032  0.619991   \n",
       "FTM      0.503171  0.811353  0.899845  0.853349  0.832288  0.267298  0.157143   \n",
       "FTA      0.491696  0.795711  0.882502  0.843725  0.807849  0.320679  0.090530   \n",
       "FT%      0.200386  0.241640  0.246680  0.214689  0.262776 -0.142038  0.310734   \n",
       "OREB     0.416948  0.586255  0.590605  0.610619  0.514503  0.527119 -0.221181   \n",
       "DREB     0.479671  0.756072  0.716958  0.723419  0.655417  0.431919  0.017703   \n",
       "REB      0.473715  0.719870  0.696668  0.708522  0.627248  0.484302 -0.072795   \n",
       "AST      0.362790  0.625946  0.546482  0.521606  0.587837 -0.130397  0.415002   \n",
       "STL      0.456121  0.766311  0.669969  0.650974  0.689307  0.040709  0.353963   \n",
       "BLK      0.303153  0.432429  0.433771  0.442781  0.360720  0.414445 -0.157557   \n",
       "TOV      0.523640  0.830394  0.853030  0.834749  0.848879  0.125793  0.269701   \n",
       "Target   0.415001  0.354152  0.354192  0.356119  0.327988  0.252236  0.037159   \n",
       "\n",
       "              3PA       3P%       FTM       FTA       FT%      OREB      DREB  \\\n",
       "GP       0.106866  0.026659  0.503171  0.491696  0.200386  0.416948  0.479671   \n",
       "MIN      0.398589  0.169725  0.811353  0.795711  0.241640  0.586255  0.756072   \n",
       "PTS      0.341765  0.147124  0.899845  0.882502  0.246680  0.590605  0.716958   \n",
       "FGM      0.282244  0.114917  0.853349  0.843725  0.214689  0.610619  0.723419   \n",
       "FGA      0.399330  0.202011  0.832288  0.807849  0.262776  0.514503  0.655417   \n",
       "FG%     -0.360298 -0.376032  0.267298  0.320679 -0.142038  0.527119  0.431919   \n",
       "3P Made  0.982678  0.619991  0.157143  0.090530  0.310734 -0.221181  0.017703   \n",
       "3PA      1.000000  0.612823  0.165934  0.096702  0.321690 -0.237302  0.007024   \n",
       "3P%      0.612823  1.000000  0.018112 -0.048118  0.329070 -0.294037 -0.132653   \n",
       "FTM      0.165934  0.018112  1.000000  0.980388  0.236930  0.604364  0.686171   \n",
       "FTA      0.096702 -0.048118  0.980388  1.000000  0.092367  0.673121  0.731581   \n",
       "FT%      0.321690  0.329070  0.236930  0.092367  1.000000 -0.143924 -0.016600   \n",
       "OREB    -0.237302 -0.294037  0.604364  0.673121 -0.143924  1.000000  0.847967   \n",
       "DREB     0.007024 -0.132653  0.686171  0.731581 -0.016600  0.847967  1.000000   \n",
       "REB     -0.086081 -0.198723  0.681736  0.737864 -0.065965  0.937130  0.979235   \n",
       "AST      0.444800  0.296920  0.473577  0.419419  0.308191 -0.016893  0.193664   \n",
       "STL      0.379792  0.233972  0.597443  0.568765  0.228524  0.275706  0.414556   \n",
       "BLK     -0.172752 -0.264620  0.462012  0.521547 -0.150065  0.665600  0.712691   \n",
       "TOV      0.290051  0.111586  0.811781  0.800064  0.197130  0.434725  0.591945   \n",
       "Target   0.018759  0.001285  0.333098  0.334718  0.088597  0.329306  0.323428   \n",
       "\n",
       "              REB       AST       STL       BLK       TOV    Target  \n",
       "GP       0.473715  0.362790  0.456121  0.303153  0.523640  0.415001  \n",
       "MIN      0.719870  0.625946  0.766311  0.432429  0.830394  0.354152  \n",
       "PTS      0.696668  0.546482  0.669969  0.433771  0.853030  0.354192  \n",
       "FGM      0.708522  0.521606  0.650974  0.442781  0.834749  0.356119  \n",
       "FGA      0.627248  0.587837  0.689307  0.360720  0.848879  0.327988  \n",
       "FG%      0.484302 -0.130397  0.040709  0.414445  0.125793  0.252236  \n",
       "3P Made -0.072795  0.415002  0.353963 -0.157557  0.269701  0.037159  \n",
       "3PA     -0.086081  0.444800  0.379792 -0.172752  0.290051  0.018759  \n",
       "3P%     -0.198723  0.296920  0.233972 -0.264620  0.111586  0.001285  \n",
       "FTM      0.681736  0.473577  0.597443  0.462012  0.811781  0.333098  \n",
       "FTA      0.737864  0.419419  0.568765  0.521547  0.800064  0.334718  \n",
       "FT%     -0.065965  0.308191  0.228524 -0.150065  0.197130  0.088597  \n",
       "OREB     0.937130 -0.016893  0.275706  0.665600  0.434725  0.329306  \n",
       "DREB     0.979235  0.193664  0.414556  0.712691  0.591945  0.323428  \n",
       "REB      1.000000  0.121015  0.377460  0.720953  0.554782  0.338257  \n",
       "AST      0.121015  1.000000  0.745087 -0.063675  0.736611  0.213621  \n",
       "STL      0.377460  0.745087  1.000000  0.161667  0.718808  0.268398  \n",
       "BLK      0.720953 -0.063675  0.161667  1.000000  0.333091  0.227312  \n",
       "TOV      0.554782  0.736611  0.718808  0.333091  1.000000  0.314013  \n",
       "Target   0.338257  0.213621  0.268398  0.227312  0.314013  1.000000  "
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_df.corr()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "From the correlation table above, we can see that GP, MIN, PTS, and FGM are the metrics that correlates well with career years played while the 3 point metrics correlate poorly.  \n",
    "\n",
    "We then visualize these below"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(target_0['GP'], target_0[\"Target\"], c='blue', edgecolors='black', marker='d', label='< 5years')\n",
    "plt.scatter(target_1['GP'], target_1[\"Target\"], c='orange', edgecolors='black', marker='d', label='>= 5 years')\n",
    "plt.xlabel(\"Total games played\")\n",
    "plt.ylabel(\"Longevity\")\n",
    "plt.title(\"Total games played vs Longevity\")\n",
    "plt.legend(loc=\"lower center\", ncol=2, bbox_to_anchor=(0.5, -0.25))\n",
    "plt.savefig(\"images/games_vs_target.png\");"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(target_0['MIN'], target_0[\"Target\"], c='blue', edgecolors='black', marker='d', label='< 5years')\n",
    "plt.scatter(target_1['MIN'], target_1[\"Target\"], c='orange', edgecolors='black', marker='d', label='>= 5 years')\n",
    "plt.xlabel(\"Average minutes played\")\n",
    "plt.ylabel(\"Longevity\")\n",
    "plt.title(\"Average minutes played vs Longevity\")\n",
    "plt.legend(loc=\"lower center\", ncol=2, bbox_to_anchor=(0.5, -0.25))\n",
    "plt.savefig(\"images/minutes_vs_target.png\");"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(target_0['FG%'], target_0[\"Target\"], c='blue', edgecolors='black', marker='d', label='< 5years')\n",
    "plt.scatter(target_1['FG%'], target_1[\"Target\"], c='orange', edgecolors='black', marker='d', label='>= 5 years')\n",
    "plt.xlabel(\"Total games played\")\n",
    "plt.ylabel(\"Longevity\")\n",
    "plt.title(\"Field goal % vs Longevity\")\n",
    "plt.legend(loc=\"lower center\", ncol=2, bbox_to_anchor=(0.5, -0.25))\n",
    "plt.savefig(\"images/fg%_vs_target.png\");"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAjcAAAHxCAYAAACRcZ2aAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjYuMCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy89olMNAAAACXBIWXMAAA9hAAAPYQGoP6dpAABZeUlEQVR4nO3dd3xT5f4H8E9G27RNF5S2jELZe0O5VRGVekEQRBwFEQoXxQEOuKjwQwUUhKuCoCiol6XIElQcXBCxRUUQZChDNmVUW6ilEzrz/f2R5pCkSUdIG3r4vF+vvMp5zjO+z5PT5svJyYlGRAREREREKqH1dABERERE7sTkhoiIiFSFyQ0RERGpCpMbIiIiUhUmN0RERKQqTG6IiIhIVZjcEBERkaowuSEiIiJVYXJDREREqsLkhugGEhUVhZEjR3o6DLpOaDQaTJs2zdNhELkdkxuiKnTo0CE88MADaNKkCfz8/BAaGopbb70VX331VYXaT5s2DRqNRnn4+fmhTZs2ePHFF5GVlVXF0dt67733sGzZsgrVFRFMnz4d9evXR1hYGJ599lkUFBTY1MnJyUH9+vWxcuXKKoi28hITE6HRaLBu3TpPh+IxP//8M6ZNm4aMjAxPh0J0TfSeDoBIzc6cOYPs7GzEx8ejXr16uHz5MtavX4+BAwfi/fffx5gxYyrUz8KFC2E0GpGTk4Nvv/0WM2fOxPfff4/t27dDo9FUOJ6jR49Cq3Xt/zTvvfceQkNDK3Tm55NPPsFrr72GF154Af7+/pg5cybCw8MxefJkpc7MmTMRFRWFhx56yKV46NpduXIFev3Vl4Gff/4Z06dPx8iRIxEcHOy5wIiuEZMboirUr18/9OvXz6Zs3Lhx6Nq1K+bOnVvh5Ob+++9HaGgoAODxxx/Hfffdh88++ww7d+5ETExMhePx8fGpePDX4Ouvv8awYcPwyiuvADC/iH755ZdKcnPy5EnMnz8fP/zwQ7XEQ44ZDAZPh0BUJfi2FFE10+l0iIyMvKZT/3fccQcA4PTp0wCA3Nxc/Pvf/0ZkZCR8fHzQsmVLvPnmmxARm3b219wsW7YMGo0G27dvx4QJE1CnTh34+/vj3nvvxcWLF23aHTp0CNu2bVPeIrvtttucxnflyhWEhIQo27Vq1cLly5eV7X//+98YMmQIunXrVqH5pqamQq/XY/r06aX2HT16FBqNBgsWLAAAFBYWYvr06WjevDkMBgNq166NW265BVu2bKnQWOU5deoUHnjgAdSqVQt+fn74xz/+gW+++camjuUtrrVr12LmzJlo0KABDAYDevfujRMnTpTq891330WTJk3g6+uL6Oho/Pjjj7jttttKrXF+fj6mTp2KZs2awcfHB5GRkXj++eeRn5+v1GnXrh1uv/32UmOYTCbUr18f999/v1Jmfc3NtGnT8NxzzwEAGjdurDzPSUlJ6NWrFzp27OhwPVq2bIk+ffpUaO2IqgvP3BBVg9zcXFy5cgWZmZn48ssv8b///Q9xcXEu93fy5EkAQO3atSEiGDhwIBISEjB69Gh06tQJmzdvxnPPPYfk5GS89dZb5fb31FNPISQkBFOnTkVSUhLmzZuHcePGYc2aNQCAefPm4amnnoLRaMSUKVMAAOHh4U776969O9577z088MAD8Pf3x/vvv4+bbroJALBlyxZ8//33OHbsWIXnGx4ejl69emHt2rWYOnWqzb41a9ZAp9PhgQceAGB+kZ41axYeeeQRREdHIysrC7/++iv27t2LO++8s8JjOpKamoqbbroJly9fxtNPP43atWtj+fLlGDhwINatW4d7773Xpv7s2bOh1WoxceJEZGZm4vXXX8ewYcPwyy+/KHUWLlyIcePGoWfPnhg/fjySkpIwaNAghISEoEGDBko9k8mEgQMH4qeffsKYMWPQunVrHDhwAG+99RaOHTuGL774AgAQFxeHadOmISUlBREREUr7n376CX/++SeGDBnicG6DBw/GsWPHsGrVKrz11lvKmcI6depg+PDhePTRR3Hw4EG0a9dOabN7924cO3YML7744jWtK5HbCRFVuccee0wACADRarVy//33S3p6erntpk6dKgDk6NGjcvHiRTl9+rS8//774uPjI+Hh4ZKbmytffPGFAJAZM2bYtL3//vtFo9HIiRMnlLJGjRpJfHy8sr106VIBILGxsWIymZTy8ePHi06nk4yMDKWsbdu20qtXrwrNNysrS2655RZlzm3btpXz589LYWGhtGnTRmbPnl2hfqy9//77AkAOHDhgU96mTRu54447lO2OHTtK//79K91/QkKCAJBPP/3UaZ1nn31WAMiPP/6olGVnZ0vjxo0lKipKiouLbfpq3bq15OfnK3Xnz59vM4f8/HypXbu2dO/eXQoLC5V6y5YtEwA26/3xxx+LVqu1GVtEZNGiRQJAtm/fLiIiR48eFQDyzjvv2NR78sknxWg0yuXLl5UyADJ16lRl+4033hAAcvr0aZu2GRkZYjAY5IUXXrApf/rpp8Xf319ycnKcrhmRJ/BtKaJq8Oyzz2LLli1Yvnw57rrrLhQXF5f69FBZWrZsiTp16qBx48Z47LHH0KxZM3zzzTfw8/PDxo0bodPp8PTTT9u0+fe//w0Rwf/+979y+x8zZozNhck9e/ZEcXExzpw5U/FJWgkICMC2bdtw6NAh7N+/H/v370f9+vXx3nvvIT8/H+PHj8fhw4dx++23o379+nj44YfL/fTX4MGDodfrlbNJAHDw4EEcPnzY5ixYcHAwDh06hOPHj7sUe1k2btyI6Oho3HLLLUqZ0WjEmDFjkJSUhMOHD9vUHzVqFLy9vZXtnj17AjC/tQUAv/76K/7++288+uijNhf2Dhs2zOZtPQD49NNP0bp1a7Rq1QppaWnKw/IWZUJCAgCgRYsW6NSpk806FRcXY926dRgwYAB8fX0rPe+goCDcc889WLVqlfJWZ3FxMdasWYNBgwbB39+/0n0SVSUmN0TVoFWrVoiNjcWIESPw9ddfIycnBwMGDCh1TYwz69evx5YtW5CYmIgTJ07g4MGD6Nq1KwDzJ7Lq1auHgIAAmzatW7dW9penYcOGNtuWF9ZLly5VKD5HtFot2rRpg44dO0Kv1yMtLQ3Tpk3Dm2++CY1Gg7vvvhvt27fHhg0bcPbsWTz11FNl9hcaGorevXtj7dq1StmaNWug1+sxePBgpeyVV15BRkYGWrRogfbt2+O5557D77//7vI8rJ05cwYtW7YsVe5srctbV0v9Zs2a2dTT6/WIioqyKTt+/DgOHTqEOnXq2DxatGgBALhw4YJSNy4uDtu3b0dycjIA8zVAFy5cuKa3QkeMGIGzZ8/ixx9/BAB89913SE1NxfDhw13uk6iqMLkh8oD7779fuV6hIm699VbExsaiV69eaNq0qdvj0el0DssrmnxVxEsvvYQuXbpg0KBB2LlzJ/766y+8/vrr6NatG6ZPn47Vq1fDZDKV2ceQIUNw7Ngx7N+/HwCwdu1a9O7dW7k+BDCv1cmTJ7FkyRK0a9cO//3vf9GlSxf897//ddtcKsqd62oymdC+fXts2bLF4ePJJ59U6sbFxUFE8OmnnwIwr1NQUBD69u3r2kQA9OnTB+Hh4VixYgUAYMWKFYiIiEBsbKzLfRJVFSY3RB5w5coVAEBmZuY199WoUSP8+eefyM7Otik/cuSIst8dKnM/HXu//fYblixZgnnz5gEA/vzzT4SEhCgfRa5Xrx4KCgpsPqHlyKBBg+Dt7Y01a9Zg//79OHbsmMMLZGvVqoVRo0Zh1apVOHfuHDp06OCWO/E2atQIR48eLVXu6lpb6tt/gqqoqAhJSUk2ZU2bNkV6ejp69+6N2NjYUg/rM0qNGzdGdHQ01qxZg6KiInz22WcYNGhQubcCKOs51ul0eOihh7Bu3TpcunQJX3zxBYYOHeo0gSPyJCY3RFXI+q0Ci8LCQnz00Ufw9fVFmzZtrnmMfv36obi4WPkotMVbb70FjUaDu+6665rHAAB/f3+XP77+zDPP4JFHHlE+aRMeHo6LFy8iPT0dAPDHH39Ar9fbnIFxJDg4GH369MHatWuxevVqeHt7Y9CgQTZ1/v77b5tto9GIZs2a2Xxc2lX9+vXDrl27sGPHDqUsNzcXH3zwAaKioir9fHbr1g21a9fGhx9+iKKiIqX8k08+KfWW4IMPPojk5GR8+OGHpfq5cuUKcnNzbcri4uKwc+dOLFmyBGlpaRV6S8py7Yyz53n48OG4dOkSHnvsMeTk5ODhhx8ut08iT+BHwYmq0GOPPYasrCzceuutqF+/PlJSUvDJJ5/gyJEjmDNnDoxG4zWPMWDAANx+++2YMmUKkpKS0LFjR3z77bfYsGEDnn32Wbe9jdW1a1csXLgQM2bMQLNmzRAWFqZczFqWTz/9FL///jvWr1+vlMXExCA8PBwPPPAABg8ejDfffBODBw+u0FmAuLg4PPzww3jvvffQp0+fUnfSbdOmDW677TZ07doVtWrVwq+//op169Zh3LhxFZrn+vXrlTMx1uLj4zFp0iSsWrUKd911F55++mnUqlULy5cvx+nTp7F+/fpK3/3Z29sb06ZNw1NPPYU77rgDDz74IJKSkrBs2TI0bdrU5kzK8OHDsXbtWjz++ONISEjAzTffjOLiYhw5cgRr167F5s2bbe4b9OCDD2LixImYOHEiatWqVaG3jyzXcU2ZMgVDhgyBl5cXBgwYoCQ9nTt3Rrt27ZSLm7t06VKp+RJVG09+VItI7VatWiWxsbESHh4uer1eQkJCJDY2VjZs2FCh9paPgl+8eLHMetnZ2TJ+/HipV6+eeHl5SfPmzeWNN96w+Xi3iPOPgu/evdumnuWjzAkJCUpZSkqK9O/fXwICAkp9TNmZy5cvS6NGjeTtt98utW/37t3SpUsXCQgIkAEDBsiFCxfK7U/E/DFzX19fASArVqwotX/GjBkSHR0twcHB4uvrK61atZKZM2dKQUFBmf1a5uzsYfkI9smTJ+X++++X4OBgMRgMEh0dLV9//bXDvuw/Vn769GkBIEuXLrUpf/vtt6VRo0bi4+Mj0dHRsn37dunatav07dvXpl5BQYH85z//kbZt24qPj4+EhIRI165dZfr06ZKZmVlqTjfffLMAkEceecThnGH3UXARkVdffVXq168vWq3W4cfCX3/9dQEgr732mrOlJPI4jYgbrxgkIqJrZjKZUKdOHQwePNjh21CeNH/+fOVmg/afBiO6XvCaGyIiD8rLyyv16amPPvoI6enpZX7FhSeICBYvXoxevXoxsaHrGq+5ISLyoJ07d2L8+PF44IEHULt2bezduxeLFy9Gu3btlK+U8LTc3Fx8+eWXSEhIwIEDB7BhwwZPh0RUJiY3REQeFBUVhcjISLz99ttIT09HrVq1MGLECMyePdvm7saedPHiRTz00EMIDg7G//3f/2HgwIGeDomoTLzmhoiIiFSF19wQERGRqjC5ISIiIlW54a65MZlM+PPPPxEQEHBNt5MnIiKi6iMiyM7ORr169cq9YeYNl9z8+eefiIyM9HQYRERE5IJz586hQYMGZda54ZKbgIAAAObFCQwM9HA0REREVBFZWVmIjIxUXsfLcsMlN5a3ogIDA5ncEBER1TAVuaSEFxQTERGRqjC5ISIiIlVhckNERESqwuSGiIiIVIXJDREREakKkxsiIiJSFSY3REREpCpMbtzMnV/pkJeXh6KiIpsy+217OTk5perbt7GuU1RUhLy8vFJ1U1JSyhzHUs/+Z1JSUqk6lvHsY7Gva70vLS1N2c7IyCg1/pEjR5T1ycvLQ15eHnJycpQy63kUFRUpMeTk5ChtioqKkJGRoczf8vPIkSM265KXl6fEYD2O5d+W/i3/tvSZkZGh1M3IyMD58+dLzTUpKUmpk5aWhrS0NJw/f17p2/LvDRs22LTLyclBRkaGsk6WeDIyMpCUlISMjAxlTEvdoqIiZQzruVkelv3Wa2Q5DqyfZ+vxrNfNst9627qt/b+dcXTMVsbBgwddbktE7nEtv8NuITeYzMxMASCZmZlu7xuAaABxx7LOmzdPtBqIr69Btm3bJiIiiYmJEhwcpGzbGzdunGgAefrpp5X6AUZ/MRr9lTbWdRITE8XP1yAaQJ566ikxGv0lwOgvjRs3Fg0gHTp0cDiOJY758+fb/KxVq5ZoAKlbt65S59577xUNIIMHD7aJJSIiwqauZext27ZJz549BYB46XXSs2dP0QBy3333KeMHBAQo66zX683rrjFvAxAfb28JMPpLkyZNlHqW+WgA0el0AkB0Oq2yf/DgwaLVQLy9vZX+LHFb+u7QoYPNc2x56HVapVyn1Sjl1vUs/65bt64yV8t6OerTvtzyM8Dob47Juq5GYzN/+4ezvixztsxXq9FcXdeSNdIA0qRJE+V5Nhr9xeDjXaqPt99+2+Z4evvtt0sds+Udv86O2crw9fUVDSC+vr6VbktE7lGR33VXVOb1m8mNm5hfEEpeGLTXluDk5uaKn8FL6at1q+aSm5srbVq3EADStk1LKSgosGmTkZEhXiXje+kgFy9elNatmptfxLWQNq1byMWLF23qtGjeRNmv10J5obPEr9dCzpw5YzNOQUGBEoclRutYLT+bNWlUqswyVtPGjWzKm0Q1FF3JdovmTUSngbJtXe/ixYuyZ88eh31afuo0V1+87esp9TXmuVqPYZm79dhaje0YWo15v2Wfozh1WogWZfQBx3Ozjt/R8+CsvnVMlm2Ngznar41luyLjWH76+uht+tNa7fMzeEnL5k2Vfb4GvWRkZCjHSpvWLZTj0dHxazm27I9ZR/Wc2blzp83v4M6dO137BSQil1m/Rjj7XXdVjUlutm3bJnfffbfUrVtXAMjnn39ebpuEhATp3LmzeHt7S9OmTWXp0qWVGrMqkxuNBrJ0zNWzCK4aOHBgqb4GDhwoWq1Glo6BaLUamTt3rk2btm3b2rQJDw8Xbcm2VnO1zL5fy37L/9I7NbKdh4+Pj804c+bMEa1WI0P+Yd5v+RnoW3r+ln9b6nRuBJszBdZ1LbFazjZoNaXbR0REOGyr0djOw3rsznbzGfIPx2OgZO72sTjt20mcWrv5aBz0Yd3Ger2tnwfLfkfral1fA9vn0f5skdZJ/FqrOWs0kHohzsfRaCBBvraxO3oeNXZ9t23bVjlmNRqrtg6OX+XYsjtmHdVzxp2/g0TkGstrRFm/666qMcnNxo0bZcqUKfLZZ59VKLk5deqU+Pn5yYQJE+Tw4cPyzjvviE6nk02bNlV4zKpIbiz/0xz3T4h8Ahl759X/MVfWnj17SvVl+R+4dVmA0U+Sk5NFRGTTpk0Oxx9569VtL23pPny8IMkLSv6tN5/N0WpK9zNjxgwREUlOThajv6+MvBViNED5eWc7x/PfM6MkVgNkZE9zWc8WtnUt5eP+aY7FW2eOxbovY0l7+3UY2dN89sFmTnpzPcvY9uvg72Oep/0YlufLUp68AOKtL923t87ct7M4H4y2nY+jcSzxWM/dZgy9ue2ATo7X9cEejuuPvdMcl1bjOD77tfHWmfsb0Ln8cbQa87o5et6cHU9ajbkPR+tgffxaji1/P0OpeP39DDb1nOnfv7/DOfTv37/Sv4NE5BrLa0RZv+vXosYkN9Yqktw8//zz0rZtW5uyuLg46dOnT4XHqYrkRqOB1PKHXPrA/ISmf2De1riQ3DRq1LBUXz56SIhdWZ0gnTw0dKiIiPj7+zkc//7oq9s6bekY6wRAHrrp6r999OaHs3kMHTJE6gTp5L5oSJ1AKD/1Osfzjwot6TvQHEstf/MLnnXd+6Kvbg+NgRi8zLFY91XbaG5vvw73RTtYl5J5WMYOsVsHg5d5v/0YISXztJQPjTGP66jvRqHO42xY+2pMQ2NK17F+XpzFb9Cbnxd/H8fr2rC24/rW83MWn/XaWNazIuM4WvuKHE8NazteB+vj13Js1TZqSq+FF2zqVcfvIBG5xvIaUdbv+rWozOt3jfq01I4dOxAbG2tT1qdPH+zYscNpm/z8fGRlZdk83Emj0UAEmPswEOxvLgvxB+YMM78HUJlPT82dOxdnzpy16Wt/EpBfBLxl1//rccVYuWoV7rnnHuTmXnY4/rpdQOJhYGkiUGwqHePrQ4GVPwO/nTH/O7/I/Nh/pvQ8GjdujFWrV+NfPYuxfhfwr1uB9buA+sFAUbHj+SelAct/AF4fYo6lY0PAZLVWCYfMfcx9GNiXBKzaAeQVAm88ZNvXmw+Z21uvg6VtqXUpmYdl7LlW67A/ydx/flHpMeaWzDO23dVY5gxz3PeZNMdxjr4NOPu3OSZLH/Z1LM/LWxudx59XZH5ecvMdr+vZv4F5/ytdf9m2q/Nzto6WtXlxrfnfnRqWP479MWj9vJV3PJ392/E6WI7fxMREJCQkYNXq1ZgzTEqvRSGUes74+vqW+Tvo6+vrtC0RuYfl9/iNIcVOf9erU41KblJSUhAeHm5TFh4ejqysLFy5csVhm1mzZiEoKEh5REZGuj2u2kbg4Vtsy4b3BGr5V66fhQsXlurro5+AOoGO+w8N1GLjxo1Oxw8NAJb/CCzc6jxGSx3Lv3305m37eSQlJaFOoBYpmeZ4LD8PJpc9/3e3XO3719O2da3n9tFPgI+X87nWMpr3W7cta07e+qtj1zaa5/TRT+b5OR3DH9h1ylwvNMB531qN4/2pmVdjKvN5CwDe+67sMYDy19W6vo/e3KePV9nrWNtoXpuPf3L8nDgax349ypub9fHkrTfH5uz4Xb58OT766KMy18LHC1i+fDmcycvLK3MO9h9NJyL3++ijj1AnUFvm73p1qlHJjSsmT56MzMxM5XHu3Dm3j/F3DrDiJ9uyj38E0nMr18/YsWNL9RXfE7iY5bj/tCwT7r77bqfjp2UDI28Fxt7pPEZLHcu/84vM2/bzaNy4MS5mmRARbI7H8rN9g7LnP+6fV/vu3sS2rvXc4nsC+YXO55qeY95v3basORUUXR377xzznOJ7mufndIxcoEcTc720bOd9m8Tx/oigqzGV+bxlm5+TssYAyl9X6/r5ReY+8wvLXse/c8xrM6Kn4+fE0Tj261He3KyPp4KSs4HOjt+RI0ciPj6+zLXILwRGjhwJZwwGQ5lz4JkboqoXHx+Pi1mmMn/Xq5Vb3ghzA1TgmpuePXvKM888Y1O2ZMkSCQwMrPA4VXLNDdx4zU1DF6658avANTcOrklw2zU3Dq7ncfmaGwfXw1iuufG+nq65cRKnO6+58XPlmpuSC4ydxefompuKjHPdX3Pjxt9BInINr7lxUUxMDLZu3WpTtmXLFsTExHgoIjMBkHkFeGmdefulT83b4kJfn33+eam+CouBLLuyvGIfvPHmmwCA9Z995nB8o+HqtlZTOsasPPO1EC99au7fJOax7Pt5dcYMAMCbc+bgSpE3AgzAlQIoP29v43j+658tibUAMPqYy25ubls3wOfq9pvDzDHYzzW/yNy+yG4dAnyArMt2c7pinoNl7Cy7ddBpHY+RVfJ8ZVnFkp3noI4Anz3rPM5/NLXtw76O9fMS4OM4DhPMz0vv1o7X9R/NHNd/6VNzXEXFjuPLybNdGymp09vJ82c9TmGxub2j583Z8VRYbO7D0TpYH7+WYyvP5FNqLXReBpt6zvTr39/hHPr1719uWyJyD8trRFm/69XGLemUi7Kzs2Xfvn2yb98+Acz3tNi3b59y47hJkybJ8OHDlfqWj4I/99xz8scff8i77757XXwUXOTqPTaWuPE+N9Z9We5zs6Sc+9xY2ljuc7PEwX1urPu17IfdfW4sdZzd5yau5N4zcXb3ubHvu6z73FjXtcQK2G47u8+NdVuNxnYe1mPbz8f+PjfW/Vjf58YSi9O+ncSptZuPxkEf1m2s47N+Hiz7Ha2rdX0NbJ9HR/e5cRS/s/vcOBrH/j43NrFa1dHY9W25z41lv9K2nPvcWB+zrtznxh2/g0TkGstrRFm/666qMR8FT0hIUP7gWj/i4+NFRCQ+Pl569epVqk2nTp3E29tbmjRpcl3dxK+q71Dctk1Lp3d9dHSHYstdIp3dobhli6t3lK3MHYotcfj5etn8tLlDcdOoUmWWsezvUNy0cSPeodgq/uv2DsWGsu9Q3KpFM2Wf5Q7FlmOlTesW5d611PrOprxDMVHNZP0accPeodgT+N1S/G4pfreU7Zwt8+V3SxGRO1wP3y2lERHBDSQrKwtBQUHIzMxEYGCg2/s33/fGPUual5cHvV4PvV6vlBUVFdls28vJyYHRaLSpD8CmjXUdyzcwGwwGm7opKSmIiIhwOo4lDvufSUlJiIqKsqljGc8+Fvu61vvS0tIQHBwMvV6PjIwMBAcH24x/5MgRREVFKWNbj2fpwzKP0NBQ5OXlwWg0IicnR5mrJTaDwQCDwYC8vDwYDAYcOXIEzZo1U9bF8g3YwcHByrdnW8awrgOYP7lj6dP6+bN8y3eDBg1s5pqUlITQ0FAlFsvzHhoaqnzDeGhoKDZv3oz+JdePWOpanrvg4GClT8s3g1vWKycnR9lvNBqVbzc3Go02cVv6zcjIUNbDMn5ERITN82z9fFmvm/3xZH+s2P+7rGPL+liorIMHD6Jdu3YutSUi96jI73plVeb1m8kNERERXfcq8/pdoz4tRURERFQeJjdERESkKkxuiIiISFWY3BAREZGqMLkhIiIiVWFyQ0RERKrC5IaIiIhUhckNERERqQqTGyIiIlIVJjdERESkKkxuiIiISFWY3BAREZGqMLkhIiIiVWFyQ0RERKrC5IaIiIhUhckNERERqQqTGyIiIlIVJjdERESkKkxuiIiISFWY3BAREZGqMLkhIiIiVWFyQ0RERKrC5IaIiIhUhckNERERqQqTGyIiIlIVJjdERESkKkxuiIiISFWY3BAREZGqMLkhIiIiVWFyQ0RERKrC5IaIiIhUhckNERERqQqTGyIiIlIVJjdERESkKkxuiIiISFWY3BAREZGqMLkhIiIiVWFyQ0RERKrC5IaIiIhUhckNERERqQqTGyIiIlIVJjdERESkKkxuiIiISFWY3BAREZGqMLkhIiIiVWFyQ0RERKrC5IaIiIhUhckNERERqQqTGyIiIlIVJjdERESkKkxuiIiISFWY3BAREZGqMLkhIiIiVWFyQ0RERKri8eTm3XffRVRUFAwGA3r06IFdu3aVWX/evHlo2bIlfH19ERkZifHjxyMvL6+aoiUiIqLrnUeTmzVr1mDChAmYOnUq9u7di44dO6JPnz64cOGCw/orV67EpEmTMHXqVPzxxx9YvHgx1qxZg//7v/+r5siJiIjoeuXR5Gbu3Ll49NFHMWrUKLRp0waLFi2Cn58flixZ4rD+zz//jJtvvhkPPfQQoqKi8M9//hNDhw4t92wPERER3Tg8ltwUFBRgz549iI2NvRqMVovY2Fjs2LHDYZubbroJe/bsUZKZU6dOYePGjejXr5/TcfLz85GVlWXzICIiIvXSe2rgtLQ0FBcXIzw83KY8PDwcR44ccdjmoYceQlpaGm655RaICIqKivD444+X+bbUrFmzMH36dLfGTkRERNcvj19QXBmJiYl47bXX8N5772Hv3r347LPP8M033+DVV1912mby5MnIzMxUHufOnavGiImIiKi6eezMTWhoKHQ6HVJTU23KU1NTERER4bDNSy+9hOHDh+ORRx4BALRv3x65ubkYM2YMpkyZAq22dK7m4+MDHx8f90+AiIiIrkseO3Pj7e2Nrl27YuvWrUqZyWTC1q1bERMT47DN5cuXSyUwOp0OACAiVRcsERER1RgeO3MDABMmTEB8fDy6deuG6OhozJs3D7m5uRg1ahQAYMSIEahfvz5mzZoFABgwYADmzp2Lzp07o0ePHjhx4gReeuklDBgwQElyiIiI6Mbm0eQmLi4OFy9exMsvv4yUlBR06tQJmzZtUi4yPnv2rM2ZmhdffBEajQYvvvgikpOTUadOHQwYMAAzZ8701BSIiIjoOqORG+z9nKysLAQFBSEzMxOBgYGeDoeIiIgqoDKv3zXq01JERERE5WFyQ0RERKrC5IaIiIhUhckNERERqQqTGyIiIlIVJjdERESkKkxuiIiISFWY3BAREZGqMLkhIiIiVWFyQ0RERKrC5IaIiIhUhckNERERqQqTGyIiIlIVJjdERESkKkxuiIiISFWY3BAREZGqMLkhIiIiVWFyQ0RERKrC5IaIiIhUhckNERERqQqTGyIiIlIVJjdERESkKkxuiIiISFWY3BAREZGqMLkhIiIiVWFyQ0RERKrC5IaIiIhUhckNERERqQqTGyIiIlIVJjdERESkKkxuiIiISFWY3BAREZGqMLkhIiIiVWFyQ0RERKrC5IaIiIhUhckNERERqQqTGyIiIlIVJjdERESkKkxuiIiISFWY3BAREZGqMLkhIiIiVWFyQ0RERKrC5IaIiIhUhckNERERqQqTGyIiIlIVJjdERESkKkxuiIiISFWY3BAREZGqMLkhIiIiVWFyQ0RERKrC5IaIiIhUhckNERERqQqTGyIiIlIVJjdERESkKkxuiIiISFWY3BAREZGqeDy5effddxEVFQWDwYAePXpg165dZdbPyMjA2LFjUbduXfj4+KBFixbYuHFjNUVLRERE1zu9Jwdfs2YNJkyYgEWLFqFHjx6YN28e+vTpg6NHjyIsLKxU/YKCAtx5550ICwvDunXrUL9+fZw5cwbBwcHVHzwRERFdlzQiIp4avEePHujevTsWLFgAADCZTIiMjMRTTz2FSZMmlaq/aNEivPHGGzhy5Ai8vLxcGjMrKwtBQUHIzMxEYGDgNcVPRERE1aMyr98ee1uqoKAAe/bsQWxs7NVgtFrExsZix44dDtt8+eWXiImJwdixYxEeHo527drhtddeQ3FxsdNx8vPzkZWVZfMgIiIi9fJYcpOWlobi4mKEh4fblIeHhyMlJcVhm1OnTmHdunUoLi7Gxo0b8dJLL2HOnDmYMWOG03FmzZqFoKAg5REZGenWeRAREdH1xeMXFFeGyWRCWFgYPvjgA3Tt2hVxcXGYMmUKFi1a5LTN5MmTkZmZqTzOnTtXjRETERFRdfPYBcWhoaHQ6XRITU21KU9NTUVERITDNnXr1oWXlxd0Op1S1rp1a6SkpKCgoADe3t6l2vj4+MDHx8e9wRMREdF1y6UzN0uXLsXly5evaWBvb2907doVW7duVcpMJhO2bt2KmJgYh21uvvlmnDhxAiaTSSk7duwY6tat6zCxISIiohuPS8nNpEmTEBERgdGjR+Pnn392efAJEybgww8/xPLly/HHH3/giSeeQG5uLkaNGgUAGDFiBCZPnqzUf+KJJ5Ceno5nnnkGx44dwzfffIPXXnsNY8eOdTkGIiIiUheX3pZKTk7GV199hWXLluG2225DkyZNMGrUKMTHxzt9S8mRuLg4XLx4ES+//DJSUlLQqVMnbNq0SbnI+OzZs9Bqr+ZfkZGR2Lx5M8aPH48OHTqgfv36eOaZZ/DCCy+4Mg0iIiJSoWu+z01qaipWrFiB5cuX48iRI+jbty9Gjx6NAQMG2CQm1wve54aIiKjmqdb73ISHh+OWW25BTEwMtFotDhw4gPj4eDRt2hSJiYnX2j0RERFRpbic3KSmpuLNN99E27ZtcdtttyErKwtff/01Tp8+jeTkZDz44IOIj493Z6xERERE5XLpbakBAwZg8+bNaNGiBR555BGMGDECtWrVsqlz4cIFRERE2Hyy6XrAt6WIiIhqnsq8frt0QXFYWBi2bdvm9CPbAFCnTh2cPn3ale6JiIiIXObS21K9evVCly5dSpUXFBTgo48+AgBoNBo0atTo2qIjIiIiqiSX3pbS6XT466+/EBYWZlP+999/IywsrMwvsvQ0vi1FRERU81T5p6VEBBqNplT5+fPnERQU5EqXRERERG5RqWtuOnfuDI1GA41Gg969e0Ovv9q8uLgYp0+fRt++fd0eJBEREVFFVSq5GTRoEABg//796NOnD4xGo7LP29sbUVFRuO+++9waIBEREVFlVCq5mTp1KgAgKioKcXFxMBgMVRIUERERkatc+ig4b85HRERE16sKJze1atXCsWPHEBoaipCQEIcXFFukp6e7JTgiIiKiyqpwcvPWW28hICBA+XdZyQ0RERGRp1zzt4LXNLzPDRERUc1T5fe5iY2NxbJly5CVleVSgERERERVxaXkpm3btpg8eTIiIiLwwAMPYMOGDSgsLHR3bERERESV5lJyM3/+fCQnJ+OLL76Av78/RowYgfDwcIwZMwbbtm1zd4xEREREFeaWa27y8vLw1VdfYebMmThw4AC/W4qIiIjcqjKv3y7d58ZaSkoKVq9ejRUrVuD3339HdHT0tXZJRERE5DKX3pbKysrC0qVLceeddyIyMhILFy7EwIEDcfz4cezcudPdMRIRERFVmEtnbsLDwxESEoK4uDjMmjUL3bp1c3dcRERERC5xKbn58ssv0bt3b2i1Lp34ISIiIqoyLmUnd955J0wmE7777ju8//77yM7OBgD8+eefyMnJcWuARERERJXh0pmbM2fOoG/fvjh79izy8/Nx5513IiAgAP/5z3+Qn5+PRYsWuTtOIiIiogpx6czNM888g27duuHSpUvw9fVVyu+9915s3brVbcERERERVZZLZ25+/PFH/Pzzz/D29rYpj4qKQnJyslsCIyIiInKFS2duTCaTwxv1nT9/XvnmcCIiIiJPcCm5+ec//4l58+Yp2xqNBjk5OZg6dSr69evnrtiIiIiIKs2lr184f/48+vTpAxHB8ePH0a1bNxw/fhyhoaH44YcfEBYWVhWxugW/foGIiKjmqczrt8vfLVVUVITVq1fj999/R05ODrp06YJhw4bZXGB8PWJyQ0REVPNUy3dL6fV6PPzww642JyIiIqoSLt+h2BGNRgODwYBmzZqhcePG1xQYERERkStcSm4GDRoEjUYD+3e0LGUajQa33HILvvjiC4SEhLglUCIiIqKKcOnTUlu2bEH37t2xZcsWZGZmIjMzE1u2bEGPHj3w9ddf44cffsDff/+NiRMnujteIiIiojK5dObmmWeewQcffICbbrpJKevduzcMBgPGjBmDQ4cOYd68efjXv/7ltkCJiIiIKsKlMzcnT550eKVyYGAgTp06BQBo3rw50tLSri06IiIiokpyKbnp2rUrnnvuOVy8eFEpu3jxIp5//nl0794dAHD8+HFERka6J0oiIiKiCnLpbanFixfjnnvuQYMGDZQE5ty5c2jSpAk2bNgAAMjJycGLL77ovkiJiIiIKsDlm/iZTCZ8++23OHbsGACgZcuWuPPOO6HVunQyqNrwJn5EREQ1T7XcobimYnJDRERU81TLHYq3bt2KrVu34sKFCzCZTDb7lixZ4mq3RERERNfEpeRm+vTpeOWVV9CtWzfUrVsXGo3G3XERERERucSl5GbRokVYtmwZhg8f7u54iIiIiK6JS1f/FhQU2NzAj4iIiOh64VJy88gjj2DlypXujoWIiIjomrn0tlReXh4++OADfPfdd+jQoQO8vLxs9s+dO9ctwRERERFVlkvJze+//45OnToBAA4ePGizjxcXExERkSe5lNwkJCS4Ow4iIiIit7jm2wmfP38e58+fd0csRERERNfMpeTGZDLhlVdeQVBQEBo1aoRGjRohODgYr776aqkb+hERERFVJ5felpoyZQoWL16M2bNn4+abbwYA/PTTT5g2bRry8vIwc+ZMtwZJREREVFEufbdUvXr1sGjRIgwcONCmfMOGDXjyySeRnJzstgDdjd8tRUREVPNU5vXbpbel0tPT0apVq1LlrVq1Qnp6uitdEhEREbmFS8lNx44dsWDBglLlCxYsQIcOHa45KCIiIiJXuXTNzeuvv47+/fvju+++Q0xMDABgx44dOHfuHDZu3OjWAImIiIgqw6UzN7169cKxY8dw7733IiMjAxkZGRg8eDAOHTqEjz/+2N0xEhEREVWYy/e5qVevHmbOnIn169dj/fr1mDFjBi5duoTFixdXuq93330XUVFRMBgM6NGjB3bt2lWhdqtXr4ZGo8GgQYMqPSYRERGp0zXfxO9arVmzBhMmTMDUqVOxd+9edOzYEX369MGFCxfKbJeUlISJEyeiZ8+e1RQpERER1QQeT27mzp2LRx99FKNGjUKbNm2waNEi+Pn5YcmSJU7bFBcXY9iwYZg+fTqaNGlSjdESERHR9c6jyU1BQQH27NmD2NhYpUyr1SI2NhY7duxw2u6VV15BWFgYRo8eXe4Y+fn5yMrKsnkQERGRelXq01KDBw8uc39GRkalBk9LS0NxcTHCw8NtysPDw3HkyBGHbX766ScsXrwY+/fvr9AYs2bNwvTp0ysVFxEREdVclUpugoKCyt0/YsSIawqoLNnZ2Rg+fDg+/PBDhIaGVqjN5MmTMWHCBGU7KysLkZGRVRUiEREReVilkpulS5e6dfDQ0FDodDqkpqbalKempiIiIqJU/ZMnTyIpKQkDBgxQyixf1KnX63H06FE0bdrUpo2Pjw98fHzcGjcRERFdvzx6zY23tze6du2KrVu3KmUmkwlbt25Vbg5orVWrVjhw4AD279+vPAYOHIjbb78d+/fv5xkZIiIicu0Oxe40YcIExMfHo1u3boiOjsa8efOQm5uLUaNGAQBGjBiB+vXrY9asWTAYDGjXrp1N++DgYAAoVU5EREQ3Jo8nN3Fxcbh48SJefvllpKSkoFOnTti0aZNykfHZs2eh1Xr8E+tERERUQ2hERDwdRHWqzFemExER0fWhMq/fPCVCREREqsLkhoiIiFSFyQ0RERGpCpMbIiIiUhUmN0RERKQqTG6IiIhIVZjcEBERkaowuSEiIiJVYXJDREREqsLkhoiIiFSFyQ0RERGpCpMbIiIiUhUmN0RERKQqTG6IiIhIVZjcEBERkaowuSEiIiJVYXJDREREqsLkhoiIiFSFyQ0RERGpCpMbIiIiUhUmN0RERKQqTG6IiIhIVZjcEBERkaowuSEiIiJVYXJDREREqsLkhoiIiFSFyQ0RERGpCpMbIiIiUhUmN0RERKQqTG6IiIhIVZjcEBERkaowuSEiIiJVYXJDREREqsLkhoiIiFSFyQ0RERGpCpMbIiIiUhUmN0RERKQqTG6IiIhIVZjcEBERkaowuSEiIiJVYXJDREREqsLkhoiIiFSFyQ0RERGpCpMbIiIiUhUmN0RERKQqTG6IiIhIVZjcEBERkaowuSEiIiJVYXJDREREqsLkhoiIiFSFyQ0RERGpCpMbIiIiUhUmN0RERKQqTG6IiIhIVZjcEBERkaowuSEiIiJVuS6Sm3fffRdRUVEwGAzo0aMHdu3a5bTuhx9+iJ49eyIkJAQhISGIjY0tsz4RERHdWDye3KxZswYTJkzA1KlTsXfvXnTs2BF9+vTBhQsXHNZPTEzE0KFDkZCQgB07diAyMhL//Oc/kZycXM2RExER0fVIIyLiyQB69OiB7t27Y8GCBQAAk8mEyMhIPPXUU5g0aVK57YuLixESEoIFCxZgxIgR5dbPyspCUFAQMjMzERgYeM3xExERUdWrzOu3R8/cFBQUYM+ePYiNjVXKtFotYmNjsWPHjgr1cfnyZRQWFqJWrVpVFSYRERHVIHpPDp6Wlobi4mKEh4fblIeHh+PIkSMV6uOFF15AvXr1bBIka/n5+cjPz1e2s7KyXA+YiIiIrnsev+bmWsyePRurV6/G559/DoPB4LDOrFmzEBQUpDwiIyOrOUoiIiKqTh5NbkJDQ6HT6ZCammpTnpqaioiIiDLbvvnmm5g9eza+/fZbdOjQwWm9yZMnIzMzU3mcO3fOLbETERHR9cmjyY23tze6du2KrVu3KmUmkwlbt25FTEyM03avv/46Xn31VWzatAndunUrcwwfHx8EBgbaPIiIiEi9PHrNDQBMmDAB8fHx6NatG6KjozFv3jzk5uZi1KhRAIARI0agfv36mDVrFgDgP//5D15++WWsXLkSUVFRSElJAQAYjUYYjUaPzYOIiIiuDx5PbuLi4nDx4kW8/PLLSElJQadOnbBp0yblIuOzZ89Cq716gmnhwoUoKCjA/fffb9PP1KlTMW3atOoMnYiIiK5DHr/PTXXjfW6IiIhqnhpznxsiIiIid2NyQ0RERKrC5IaIiIhUhckNERERqQqTGyIiIlIVJjdERESkKkxuiIiISFWY3BAREZGqMLkhIiIiVWFyQ0RERKrC5IaIiIhUhckNERERqQqTGyIiIlIVJjdERESkKkxuiIiISFWY3BAREZGqMLkhIiIiVWFyQ0RERKrC5IaIiIhUhckNERERqQqTGyIiIlIVJjdERESkKkxuiIiISFWY3BAREZGqMLkhIiIiVWFyQ0RERKrC5IaIiIhUhckNERERqQqTGyIiIlIVJjdERESkKkxuiIiISFWY3BAREZGqMLkhIiIiVWFyQ0RERKrC5IaIiIhUhckNERERqQqTGyIiIlIVJjdERESkKkxuiIiISFWY3BAREZGqMLkhIiIiVWFyQ0RERKrC5IaIiIhUhckNERERqQqTGyIiIlIVJjdERESkKkxuiIiISFWY3BAREZGqMLkhIiIiVWFyQ0RERKrC5IaIiIhUhckNERERqQqTGyIiIlIVJjdERESkKnpPB6A2Go0GhYWF0Ottl7aoqKhUWXlcbQPAaTv7/UVFRcjJyUFwcLBNvYyMDKWsqKgIRUVFMBgMpfqylFv6zcnJgdFoVPZb2ljmYt3v+fPnERERAb1er7Sz1MvJyYHBYEBeXp4Sq3VfBw8eRKdOnVBUVKTUMRgMSElJQWhoKPR6PYqKipCRkYHQ0FAlvoyMDBiNRps48/LylDUxGo04ePAgmjVrpvSh1+uRlpYGg8GgtLXMPTg4WGlfVFQEo9GItLQ0ZS4AlDrWa25x/vx5JV5L25ycHERERNisdUpKCho0aKCsaU5OjtKf5aflebSONSkpCQ0aNFDW0nq98vLyEBoairS0NGU8S2zWMVofS9ZzsKyL5fks75gv79h01MYVeXl5pY5VIrrByA0mMzNTAEhmZqbb+wYggEYAyLZt25TyxMRECQoKtikrj6tt/P0DxN/f6LCdeb9R/P0DZNu2bZKYmCh6vbcAGrnvvvuUevfee69SlpiYKAaDnwAaefvtt236Mhh8BdDKU089Jf7+RtHp9AJoRKfTibe3twBaefvtt5W59OzZU+m3cePGAmhEo9HK4MGDBdDI4MGDJSgoWNnWarXKelrGT0xMVLb1en3JOObtunXrKu3mz58vOp1OAI106NBB/P2NotXqbZ6jq4+rY1jaAFDWxrqORqN10Id9f6X7te/HcR1H5aW3NRpH/TmLx/xvy5o6bmNeI8vx4+3tY9Pe29tbDAY/5biyPJ/t27cvWW+dckw5O37tjz13HfP25s2bpxx3RKQulXn9ZnLjJuYXAr3Nz4KCAikoKJAWLdoIAGnZsq0UFBSU25erbZo3b10yvk5atGhj0+7qfp0AkObNW0uTJi2UbUAvFy9elIsXL9rMo3Hj5kqfer2v5ObmSkFBgTRr1sqqnpeD+WtLEgRfq7is9+uUfu3XzfFPjej1vlK3bqSD/TqH9W3329fRlcToqK31T20Z+6z7tfSntevX2diOyrUO+qxMzNZttU7Kna9xVFSzcsbRSfPmrZ08n1COOfvjNzc31+bYsz82XT3m7eXm5oqXl58AEC8vP8nNza10H0R0/apxyc2CBQukUaNG4uPjI9HR0fLLL7+UWX/t2rXSsmVL8fHxkXbt2sk333xT4bGqNrnRCLBULP8jnjt3rsyZM6fkf/tLRaPRyty5c8vty9U25hekpSU/NTbtzPs1VnUs/2u/uh0RESHh4eGl5nG1T8g999xT0lfp+TpuZxljSBn7rct1dttDxPZMhKNxtAJ0KiMe+zZDlPnYjmEfY325etbFUuZonKtrfrVP+3W2HtsyD63dWI7KrWO3HiPQQcxau7Hsy+3nZz9v2NXXiuM101qNb7vf0TE/cOBAuzUpfUy7cszbuzqOOaZ77rmn0n0Q0fWrRiU3q1evFm9vb1myZIkcOnRIHn30UQkODpbU1FSH9bdv3y46nU5ef/11OXz4sLz44ovi5eUlBw4cqNB4VZHcXP3f7jgBRICxYvlfqsHgb1Pu5xcgycnJTvtKTk4WX19jpdvYjwP4iMHgL8nJySX7/QTwKamTLOazLT52bbQO5uFTUt/yb414efk4me9Iu+1NJW1GCmB00O8eBzHY9xNQsm19NsO+flu78pFW28kOxrDu88GS2BzFqCtZJ0f9Ol8fwLuMOv5O1t6S1PlUYDzLma/KrKu3AH5O1sF6PT5xMq6xZK10AtzpYL+5D4PBv+RYs5+b7Zr4+hqVY9qVY97enj17HB4be/bsqfgvMhFd12pUchMdHS1jx45VtouLi6VevXoya9Ysh/UffPBB6d+/v01Zjx495LHHHqvQeFWT3GgEqCXApZI/rOkl2xrRaGrblOt0dWTo0Iec9jVkyFDR6epUuo39OEAdAQwydOhDMmTIUAEMJWWXBBha8uJXx66NjwAhDvp5yOrflrc4HM33frttY0mb+xyMVUeAKAfl9v3UKdmuVeY625bfZ7U91MnYlj4blhFjSMmaOOq3rPVx9FxY6hicrH1ISds6FRhPV1Lf2bo2cvLcOurrfrv10DsZt3bJWlnqODpOLH0YHMzNtkyjqa0c064c8/YaNmzk8Nho2DCq4r/IRHRdqzHJTX5+vuh0Ovn8889tykeMGCEDBw502CYyMlLeeustm7KXX35ZOnTo4LB+Xl6eZGZmKo9z585VeHEq4upbCctK/qhaHkut9pUuT0hIKNXX999/X2ZfrrSxfSwT4HtxHHN5/STY9VlWPRHg+ZLtF5zUf76C/Vi2O5VTv7ODeZQ3J8tbRM5itI6lMuvzgpM6cyuwfpa2FY29vH4q0tcLdj/Lqtu0gn0lONhXumzu3Lll9ufomLd39W1Sx33Y/70gopqpxiQ3ycnJAkB+/vlnm/LnnntOoqOjHbbx8vKSlStX2pS9++67EhYW5rD+1KlTrf5gX324N7mpLUCR3R/WIjH/T9I+uSkSrTZURo4cWaqvkSNHilZbx2FfZbUBQp2MHyrm/7Frxfw/6yIxv+XgY7VtqT/SQZl1PyNL/q0tY76WeiJAfEm9eCf9xlewH8u2vpx11juYR3lzalpOjNaxVHR9apX056hOMydrLw7aljVerZLYK9JPRZ7beKuftUqeY2f9asp53ix9jXSwz76stjRr1qzSx7y9Zs2alXlsNGvWzC2/60TkWZVJblR/E7/JkycjMzNTeZw7d64KRvkbwAq7so8BpDuo+zFMpjSMHDmy1J74+HiYTBcd9lVWGyDNyfhpAPIBmABY+o0vKbMfJ95BmXU/I0v+bYLz+VrqAUBESb0IJ/1a9pfXj2W7fRn10wF0cDCP8uYUXU6M1rFUdH3SAdR1UmcsHK+99TwsbcsaL70k9or0U15faTDP3/IzHebn2Fm/TVH282bpa6SDffZlf2Ps2LGVPubtjR07toyY0jFu3Lhy+yAilamGZMup6nhbyh6vubkkzq+58Rb3XnPjL2Vfc9PIQXlNv+bGcmbLWR13XHOjFdeuuXF2nQyvuSGi61+NeVtKxHxB8bhx45Tt4uJiqV+/fpkXFN999902ZTExMR6+oJifluKnpfhpKX5aioiqUo1KblavXi0+Pj6ybNkyOXz4sIwZM0aCg4MlJSVFRESGDx8ukyZNUupv375d9Hq9vPnmm/LHH3/I1KlTPf5RcBFLgqMRYIk4vs/NEhfuc1O5NubkZImUf5+bqzFab9ve58a6jqVPR/e5sa7nqJ1ljLgy9luX6+y2nd3nxn4OncqIx76N/X1u4ux+WupZ3+fGUuZonKtrfrVP+3W2HtsyD+s69ZyUW8fu6D43cXb7rceyL7efn6P73FjX14rjNbO+z43tfkfHvO19bpZI2fe5qfgxb+/qOOaYeJ8bInWpUcmNiMg777wjDRs2FG9vb4mOjpadO3cq+3r16iXx8fE29deuXSstWrQQb29vadu27XV0Ez/Hdyhu2bKtAJW727ArbSx3eHV2h2Lz/qt3KG7atKVcPSPi+A7F5rsYm/u0vkOx+Y6z1X+H4nr1GjrY7+juu+XdoZd3KLb/aX036rLuUHz1OHN+h2Lr4zc3N9fm2HN2h+LKHvP2eIdiInWrcclNdeJ3S/G7pRyfCYISu2Wb3y1l3sfvliKi60FlXr81IiK4gWRlZSEoKAiZmZkIDAx0e//8VnB+Kzi/FRw2day3HdUrq40r+K3gROpUmddvJjdERER03avM67fq73NDRERENxYmN0RERKQqTG6IiIhIVZjcEBERkaowuSEiIiJVYXJDREREqsLkhoiIiFTl2u6WVQNZbuuTlZXl4UiIiIiooiyv2xW5Pd8Nl9xkZ2cDACIjIz0cCREREVVWdnY2goKCyqxzw92h2GQy4c8//0RAQAA0Go1b+87KykJkZCTOnTvHux9XIa5z9eA6Vw+uc/XhWlePqlpnEUF2djbq1asHrbbsq2puuDM3Wq0WDRo0qNIxAgMD+YtTDbjO1YPrXD24ztWHa109qmKdyztjY8ELiomIiEhVmNwQERGRqjC5cSMfHx9MnToVPj4+ng5F1bjO1YPrXD24ztWHa109rod1vuEuKCYiIiJ145kbIiIiUhUmN0RERKQqTG6IiIhIVZjcEBERkaowuXGTd999F1FRUTAYDOjRowd27drl6ZBqtFmzZqF79+4ICAhAWFgYBg0ahKNHj9rUycvLw9ixY1G7dm0YjUbcd999SE1N9VDE6jB79mxoNBo8++yzShnX2X2Sk5Px8MMPo3bt2vD19UX79u3x66+/KvtFBC+//DLq1q0LX19fxMbG4vjx4x6MuOYpLi7GSy+9hMaNG8PX1xdNmzbFq6++avN9RFznyvvhhx8wYMAA1KtXDxqNBl988YXN/oqsaXp6OoYNG4bAwEAEBwdj9OjRyMnJqZqAha7Z6tWrxdvbW5YsWSKHDh2SRx99VIKDgyU1NdXTodVYffr0kaVLl8rBgwdl//790q9fP2nYsKHk5OQodR5//HGJjIyUrVu3yq+//ir/+Mc/5KabbvJg1DXbrl27JCoqSjp06CDPPPOMUs51do/09HRp1KiRjBw5Un755Rc5deqUbN68WU6cOKHUmT17tgQFBckXX3whv/32mwwcOFAaN24sV65c8WDkNcvMmTOldu3a8vXXX8vp06fl008/FaPRKPPnz1fqcJ0rb+PGjTJlyhT57LPPBIB8/vnnNvsrsqZ9+/aVjh07ys6dO+XHH3+UZs2aydChQ6skXiY3bhAdHS1jx45VtouLi6VevXoya9YsD0alLhcuXBAAsm3bNhERycjIEC8vL/n000+VOn/88YcAkB07dngqzBorOztbmjdvLlu2bJFevXopyQ3X2X1eeOEFueWWW5zuN5lMEhERIW+88YZSlpGRIT4+PrJq1arqCFEV+vfvL//6179sygYPHizDhg0TEa6zO9gnNxVZ08OHDwsA2b17t1Lnf//7n2g0GklOTnZ7jHxb6hoVFBRgz549iI2NVcq0Wi1iY2OxY8cOD0amLpmZmQCAWrVqAQD27NmDwsJCm3Vv1aoVGjZsyHV3wdixY9G/f3+b9QS4zu705Zdfolu3bnjggQcQFhaGzp0748MPP1T2nz59GikpKTZrHRQUhB49enCtK+Gmm27C1q1bcezYMQDAb7/9hp9++gl33XUXAK5zVajImu7YsQPBwcHo1q2bUic2NhZarRa//PKL22O64b44093S0tJQXFyM8PBwm/Lw8HAcOXLEQ1Gpi8lkwrPPPoubb74Z7dq1AwCkpKTA29sbwcHBNnXDw8ORkpLigShrrtWrV2Pv3r3YvXt3qX1cZ/c5deoUFi5ciAkTJuD//u//sHv3bjz99NPw9vZGfHy8sp6O/pZwrStu0qRJyMrKQqtWraDT6VBcXIyZM2di2LBhAMB1rgIVWdOUlBSEhYXZ7Nfr9ahVq1aVrDuTG7rujR07FgcPHsRPP/3k6VBU59y5c3jmmWewZcsWGAwGT4ejaiaTCd26dcNrr70GAOjcuTMOHjyIRYsWIT4+3sPRqcfatWvxySefYOXKlWjbti3279+PZ599FvXq1eM630D4ttQ1Cg0NhU6nK/XpkdTUVERERHgoKvUYN24cvv76ayQkJKBBgwZKeUREBAoKCpCRkWFTn+teOXv27MGFCxfQpUsX6PV66PV6bNu2DW+//Tb0ej3Cw8O5zm5St25dtGnTxqasdevWOHv2LAAo68m/Jdfmueeew6RJkzBkyBC0b98ew4cPx/jx4zFr1iwAXOeqUJE1jYiIwIULF2z2FxUVIT09vUrWncnNNfL29kbXrl2xdetWpcxkMmHr1q2IiYnxYGQ1m4hg3Lhx+Pzzz/H999+jcePGNvu7du0KLy8vm3U/evQozp49y3WvhN69e+PAgQPYv3+/8ujWrRuGDRum/Jvr7B4333xzqdsZHDt2DI0aNQIANG7cGBERETZrnZWVhV9++YVrXQmXL1+GVmv70qbT6WAymQBwnatCRdY0JiYGGRkZ2LNnj1Ln+++/h8lkQo8ePdwflNsvUb4BrV69Wnx8fGTZsmVy+PBhGTNmjAQHB0tKSoqnQ6uxnnjiCQkKCpLExET566+/lMfly5eVOo8//rg0bNhQvv/+e/n1118lJiZGYmJiPBi1Olh/WkqE6+wuu3btEr1eLzNnzpTjx4/LJ598In5+frJixQqlzuzZsyU4OFg2bNggv//+u9xzzz38iHIlxcfHS/369ZWPgn/22WcSGhoqzz//vFKH61x52dnZsm/fPtm3b58AkLlz58q+ffvkzJkzIlKxNe3bt6907txZfvnlF/npp5+kefPm/Cj49e6dd96Rhg0bire3t0RHR8vOnTs9HVKNBsDhY+nSpUqdK1euyJNPPikhISHi5+cn9957r/z111+eC1ol7JMbrrP7fPXVV9KuXTvx8fGRVq1ayQcffGCz32QyyUsvvSTh4eHi4+MjvXv3lqNHj3oo2popKytLnnnmGWnYsKEYDAZp0qSJTJkyRfLz85U6XOfKS0hIcPg3OT4+XkQqtqZ///23DB06VIxGowQGBsqoUaMkOzu7SuLViFjdtpGIiIiohuM1N0RERKQqTG6IiIhIVZjcEBERkaowuSEiIiJVYXJDREREqsLkhoiIiFSFyQ0RERGpCpMbIlKFxMREaDSaUt+DRUQ3HiY3ROR2CxcuRIcOHRAYGIjAwEDExMTgf//7X5ltpk2bBo1GA41GA71ej6ioKIwfPx45OTkVGvOmm27CX3/9haCgoArHOXLkSAwaNKjcep988gkiIyMREhKCCRMm2OxLSkpCixYtkJWVVeFxiahq6T0dABGpT4MGDTB79mw0b94cIoLly5fjnnvuwb59+9C2bVun7dq2bYvvvvsORUVF2L59O/71r3/h8uXLeP/998sd09vbu0q+XTgtLQ2PPPIIli1bhiZNmqB///644447cPfddwMAnnzyScyePRuBgYFuH5uIXMMzN0TkdgMGDEC/fv3QvHlztGjRAjNnzoTRaMTOnTvLbKfX6xEREYEGDRogLi4Ow4YNw5dffgkAyM/Px9NPP42wsDAYDAbccsst2L17t9LW/m2pZcuWITg4GJs3b0br1q1hNBrRt29f/PXXXwDMZ4qWL1+ODRs2KGeMEhMTS8V06tQpBAUFIS4uDt27d8ftt9+OP/74AwCwatUqeHl5YfDgwW5YNSJyFyY3RFSliouLsXr1auTm5iImJqZSbX19fVFQUAAAeP7557F+/XosX74ce/fuRbNmzdCnTx+kp6c7bX/58mW8+eab+Pjjj/HDDz/g7NmzmDhxIgBg4sSJePDBB5WE56+//sJNN91Uqo/mzZvj8uXL2LdvH9LT07F792506NABly5dwksvvYQFCxZUak5EVPWY3BBRlThw4ACMRiN8fHzw+OOP4/PPP0ebNm0q3H7Pnj1YuXIl7rjjDuTm5mLhwoV44403cNddd6FNmzb48MMP4evri8WLFzvto7CwEIsWLUK3bt3QpUsXjBs3Dlu3bgUAGI1G+Pr6wsfHBxEREYiIiIC3t3epPkJCQrB8+XKMGDEC0dHRGDFiBPr06YOJEydi3LhxOH36NDp37ox27dph3bp1lV8oInI7XnNDRFWiZcuW2L9/PzIzM7Fu3TrEx8dj27ZtZSY4loSouLgYBQUF6N+/PxYsWICTJ0+isLAQN998s1LXy8sL0dHRyltEjvj5+aFp06bKdt26dXHhwoVKz+Xee+/Fvffeq2xv27YNv//+O9555x00a9YMq1atQkREBKKjo3HrrbciLCys0mMQkfswuSGiKuHt7Y1mzZoBALp27Yrdu3dj/vz5ZV4c3LJlS3z55ZfQ6/WoV6+eciYlNTXVpRi8vLxstjUaDUTEpb4s8vPz8eSTT+Ljjz/GiRMnUFRUhF69egEAWrRogV9++QUDBgy4pjGI6NrwbSkiqhYmkwn5+fll1rEkRFFRUTZvETVt2hTe3t7Yvn27UlZYWIjdu3dX6q0uR+MVFxdXqs2MGTPQt29fdOnSBcXFxSgqKrKJqbL9EZH78cwNEbnd5MmTcdddd6Fhw4bIzs7GypUrkZiYiM2bN7vUn7+/P5544gk899xzqFWrFho2bIjXX38dly9fxujRo12OMyoqCps3b8bRo0dRu3ZtBAUFlTrbY+3w4cNYs2YN9u3bBwBo1aoVtFotFi9ejIiICBw5cgTdu3d3OR4icg8mN0TkdhcuXMCIESOUm+p16NABmzdvxp133ulyn7Nnz4bJZMLw4cORnZ2Nbt26YfPmzQgJCXG5z0cffRSJiYno1q0bcnJykJCQgNtuu81hXRHBmDFjMHfuXPj7+wMwf5pr2bJlGDt2LPLz87FgwQLUr1/f5XiIyD00cq1vQBMRERFdR3jNDREREakKkxsiIiJSFSY3REREpCpMboiIiEhVmNwQERGRqjC5ISIiIlVhckNERESqwuSGiIiIVIXJDREREakKkxsiIiJSFSY3REREpCpMboiIiEhVmNwQERGRqjC5ISIiIlVhckNERESqwuSGiIiIVIXJDREREakKkxsiIiJSFb2nAyCqCsXFxSgsLPR0GERUzby8vKDT6TwdBnkYkxtSFRFBSkoKMjIyPB0KEXlIcHAwIiIioNFoPB0KeQiTG1IVS2ITFhYGPz8//nEjuoGICC5fvowLFy4AAOrWrevhiMhTmNyQahQXFyuJTe3atT0dDhF5gK+vLwDgwoULCAsL41tUNyheUEyqYbnGxs/Pz8OREJEnWf4G8Lq7GxeTG1IdvhVFdGPj3wBickNERESqwuSGyImioiJPh0DXAR4HRDUPkxsiB7Zt24bQ0Dr44YcfPB1KuaZNmwaNRmPzaNWqlafDUoVt27ahTp3QGnEcVFZUVFSp42b27NmeDovILfhpKSI7hYWFGDPmSWRmZmDMmCdx4MA+eHl5eSyeS5cuwcvLC0aj0Wmdtm3b4rvvvlO29XrP/2oXFBTA29vb02G4rLCwEE8+MQYZGZl48okx2Lf/QJUeB3/++SfCwsKq9bl75ZVX8OijjyrbAQEB1TZ2RdX044g8g2duiOy88847OH78CIClOHbsDyxYsKDaYygqKsI333yDBx54AHXr1sXJkyfLrK/X6xEREaE8QkNDlX3/+te/cPfdd9vULywsRFhYGBYvXgwAMJlMmDVrFho3bgxfX1907NgR69atU+oXFxdj9OjRyv6WLVti/vz5Nn2OHDkSgwYNwsyZM1GvXj20bNkSAPDee++hefPmMBgMCA8Px/33339Na1Nd3nnnHRw5ehxLxwB/HDlW5cfBhx9+iAYNGmDixIk4cOBAlY5lERAQYHPc+Pv7O63L44hqFCFSiStXrsjhw4flypUrLveRnJwsvr5GAcYJIAKMFT+/AElOTnZjpM79/vvvMmHCBAkPD5datWrJE088IT///HOZbaZOnSp+fn5St25dady4sTz00ENy5swZZf/27dtFp9PJn3/+qZR99tln4u/vL9nZ2SIiMmPGDGnVqpVs2rRJTp48KUuXLhUfHx9JTEwUEZGCggJ5+eWXZffu3XLq1ClZsWKF+Pn5yZo1a5Q+4+PjxWg0yvDhw+XgwYNy8OBB2b17t+h0Olm5cqUkJSXJ3r17Zf78+e5csiqRnJwsRn9fGfdPiHwCGXsnJMDoV6XHwZUrV2T16tXSr18/0ev10rlzZ5k/f75cuHDBYf02bdqIv7+/00ffvn3LHK9Ro0bKcdapUyd5/fXXpbCw0Gn9mnQcueNvAdVsTG5INdzxB23IkKGi09UR4FJJcpMuOl0dGTr0ITdGaistLU3mzZsnnTt3Fm9vbxk0aJCsX79e8vPzK9R+48aNsnbtWvntt99k06ZNEhMTIw0bNpSsrCylTps2beQ///mPsj1gwAAZOXKkiIjk5eWJn59fqSRq9OjRMnToUKfjjh07Vu677z5lOz4+XsLDw23iXr9+vQQGBtrEUhMMHTJE6gTp5NIH5uQm/QNInSCdPFTGerhTamqqvPXWW9K5c2fx8vKSe+65Rz777DOb5CMpKUmOHz/u9HH+/Pkyx5gzZ44kJCTIb7/9JgsXLpTg4GAZP358mW1qynHE5IaY3JBqXOsftO+//14ACLCsJLGxPJYKAElISHBvwCWmTp0qAKRnz55y9uzZa+7v0qVLEhgYKP/973+Vsrlz50qrVq1ERCQlJUX0er388MMPIiJy8OBBAVDqf/5eXl4SHR2t9LFgwQLp0qWLhIaGKvu7d++u7I+Pj5fY2FibWLKysqR9+/YSGhoqDz/8sKxYsUJyc3OveY5VyXIcLHvMnNhYHkvHoEqPA2c2btwoYWFhAkD27dtXZeMsXrxY9Hq95OXlOa1TU44jJjfEa26ISnz00UfQausAeNhuz3BotaFYvnx5lYw7ZswYvPrqq0hJSUHbtm0xatQofP/99zCZTC71FxwcjBYtWuDEiRNK2YgRI3Dq1Cns2LEDK1asQOPGjdGzZ08AQE5ODgDgm2++wf79+5XH4cOHleslVq9ejYkTJ2L06NH49ttvsX//fowaNQoFBQU2Y9tfsxEQEIC9e/di1apVqFu3Ll5++WV07Njxuv5i048++gh1ArV4+Bbb8uE9gdBAbZUdB9ays7OxdOlS3HHHHRgwYADatWuH5cuXo02bNkqdtm3bwmg0On3cddddlRqzR48eKCoqQlJSktM6PI6oxvB0dkXkLtf6v7WEhIQyz9xYrhuoStu3b5cxY8ZIUFCQNGjQQF544QU5ePBgpfrIzs6WkJCQUtckPPjgg/Loo49Ku3bt5LXXXlPKs7KyxMfHRz766COnfY4bN07uuOMOm7LevXtLx44dle34+Hi55557yowtJydH9Hq9rF+/vuITqmaW48DZmZuqOg6Kiopk48aNMnToUPH19ZUWLVrIjBkzbK6fsnatb0vZW7FihWi1WklPTy+zXk04jnjmhpjckGrU1GtuHLly5YqsWrVK+vTpIzqdTn7//Xendf/9739LYmKinD59WrZv3y6xsbESGhpa6kLUb7/9Vry9vUWn05W6MHbKlClSu3ZtWbZsmZw4cUL27Nkjb7/9tixbtkxERObPny+BgYGyadMmOXr0qLz44osSGBhY7ovSV199JfPnz5d9+/ZJUlKSvPfee6LVaiudsFU3T1xz88orr0hQUJCMGTNGtm/fXmXjiIj8/PPP8tZbb8n+/fvl5MmTsmLFCqlTp46MGDGi3LY14ThickNMbkg11PBpKWcxZWZmOt0fFxcndevWFW9vb6lfv77ExcXJiRMnStUzmUzSqFEj6devn8N98+bNk5YtW4qXl5fUqVNH+vTpI9u2bRMR88WiI0eOlKCgIAkODpYnnnhCJk2aVO6L0o8//ii9evWSkJAQ8fX1lQ4dOth8MuZ65YlPS50+fbraXoz37NkjPXr0kKCgIDEYDNK6dWt57bXXyrzexqImHEdMbojJDamGu/6gzZkzRzQarQBLRKPRyty5c90UoWdlZ2dLYGDgdf2W0PVkzpw5otVqZMkYiFarUc1xcK1qwnHE5IY0IiKeveqHyD3y8vJw+vRpNG7cGAaDweV+CgsL0b59Zxw9eggtW7b1+B2Kr5XJZEJaWhrmzJmD1atX4+TJk9fFHYyvd4WFhejcqT0OHT6Ktm1aVvkdiq93Nek4ctffAqq5+GkpIjteXl54//13ERQUjA8+eK/Gv6CdPXsW4eHhWLlyJZYsWXLdviBdb7y8vPDue+8jODgI7y38oMYfB9eKxxHVJDxzQ6rh7v+tFRUV8Q848TiogXjmhnjmhsgJvqARwOOAqCZickOqw5ORRDc2/g0gJjekGpZrIi5fvuzhSIjIkyx/A27066RuZDzfSqqh0+kQHByMCxcuAAD8/Pyg0Wg8HBURVRcRweXLl3HhwgUEBwdDp9N5OiTyEF5QTKoiIkhJSeF3zhDdwIKDgxEREcH/3NzAmNyQKhUXF6OwsNDTYRBRNfPy8uIZG2JyQ0REROrCC4qJiIhIVZjcEBERkaowuSEiIiJVYXJDREREqsLkhoiIiFSFyQ0RERGpCpMbIiIiUpX/B7fqRK0qBiaPAAAAAElFTkSuQmCC",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(target_0['3P%'], target_0[\"Target\"], c='blue', edgecolors='black', marker='d', label='< 5years')\n",
    "plt.scatter(target_1['3P%'], target_1[\"Target\"], c='orange', edgecolors='black', marker='d', label='>= 5 years')\n",
    "plt.xlabel(\"3 Point %\")\n",
    "plt.ylabel(\"Longevity\")\n",
    "plt.title(\"3 Point % vs Longevity\")\n",
    "plt.legend(loc=\"lower center\", ncol=2, bbox_to_anchor=(0.5, -0.25))\n",
    "plt.savefig(\"images/3p%_vs_target.png\");"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Step 3: splitting and standardizing the training data\n",
    "\n",
    "The Target column will be the target while the rest will be the features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.series.Series'>\n",
      "RangeIndex: 1101 entries, 0 to 1100\n",
      "Series name: Target\n",
      "Non-Null Count  Dtype   \n",
      "--------------  -----   \n",
      "1101 non-null   category\n",
      "dtypes: category(1)\n",
      "memory usage: 1.3 KB\n"
     ]
    }
   ],
   "source": [
    "# cast Target as categories\n",
    "train_df['Target'] = train_df[\"Target\"].astype('category')\n",
    "train_df[\"Target\"].info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 1101 entries, 0 to 1100\n",
      "Data columns (total 19 columns):\n",
      " #   Column   Non-Null Count  Dtype  \n",
      "---  ------   --------------  -----  \n",
      " 0   GP       1101 non-null   int32  \n",
      " 1   MIN      1101 non-null   float64\n",
      " 2   PTS      1101 non-null   float64\n",
      " 3   FGM      1101 non-null   float64\n",
      " 4   FGA      1101 non-null   float64\n",
      " 5   FG%      1101 non-null   float64\n",
      " 6   3P Made  1101 non-null   float64\n",
      " 7   3PA      1101 non-null   float64\n",
      " 8   3P%      1101 non-null   float64\n",
      " 9   FTM      1101 non-null   float64\n",
      " 10  FTA      1101 non-null   float64\n",
      " 11  FT%      1101 non-null   float64\n",
      " 12  OREB     1101 non-null   float64\n",
      " 13  DREB     1101 non-null   float64\n",
      " 14  REB      1101 non-null   float64\n",
      " 15  AST      1101 non-null   float64\n",
      " 16  STL      1101 non-null   float64\n",
      " 17  BLK      1101 non-null   float64\n",
      " 18  TOV      1101 non-null   float64\n",
      "dtypes: float64(18), int32(1)\n",
      "memory usage: 159.3 KB\n",
      "None\n",
      "<class 'pandas.core.series.Series'>\n",
      "RangeIndex: 1101 entries, 0 to 1100\n",
      "Series name: Target\n",
      "Non-Null Count  Dtype   \n",
      "--------------  -----   \n",
      "1101 non-null   category\n",
      "dtypes: category(1)\n",
      "memory usage: 1.3 KB\n"
     ]
    }
   ],
   "source": [
    "## training features\n",
    "x = train_df.drop(columns=['Target'])\n",
    "print(x.info())\n",
    "\n",
    "# target to predict\n",
    "y = train_df[\"Target\"]\n",
    "y.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### NOTE\n",
    "\n",
    "The cell below was used to standardize the dataset. However, the accuracy is worse after standardization and was highest an K = 1.  \n",
    "You can uncomment it to see the effect on the accuracy plot.  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "# standardize the data\n",
    "\n",
    "# # instantiate the transformer\n",
    "# std_scaler = StandardScaler()\n",
    "# std_scaler.fit(x)\n",
    "\n",
    "# # transform using the scaler\n",
    "# X = std_scaler.transform(x)\n",
    "# X = pd.DataFrame(X, columns=x.columns)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(990, 19) (111, 19)\n",
      "(990,) (111,)\n"
     ]
    }
   ],
   "source": [
    "# split the data\n",
    "X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.1, random_state=4)\n",
    "\n",
    "print(X_train.shape, X_test.shape)\n",
    "print(y_train.shape, y_test.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Step 4: train the model\n",
    "\n",
    "Using the KNeighborsClassifier from sklearn"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Maximum accuracy: 0.7837837837837838 at K=3\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# iterate to find the best k value\n",
    "acc = []\n",
    "ks = []\n",
    "for i in range(1, 40):\n",
    "  ks.append(i)\n",
    "  knn = KNeighborsClassifier(n_neighbors=i)\n",
    "  knn.fit(X_train, y_train)\n",
    "  y_pred = knn.predict(X_test)\n",
    "  acc.append(accuracy_score(y_test, y_pred))\n",
    "\n",
    "plt.figure(figsize=(10, 6))\n",
    "plt.plot(range(1, 40), acc, color='orange', linestyle='dashed', marker='o', markerfacecolor='blue')\n",
    "plt.xlabel('K value')\n",
    "plt.ylabel(\"Accuracy\")\n",
    "plt.title(\"Accuracy vs K values\")\n",
    "\n",
    "max_acc, idx = max(acc), acc.index(max(acc))\n",
    "print(f\"Maximum accuracy: {max(acc)} at K={ks[idx]}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-1 {color: black;background-color: white;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>KNeighborsClassifier(n_neighbors=3)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">KNeighborsClassifier</label><div class=\"sk-toggleable__content\"><pre>KNeighborsClassifier(n_neighbors=3)</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "KNeighborsClassifier(n_neighbors=3)"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# set the number of neighbors\n",
    "k = 3 # gave the highest accuracy from the iteration above\n",
    "\n",
    "# instantiate the model\n",
    "model = KNeighborsClassifier(n_neighbors=k)\n",
    "\n",
    "# fit the model to the training data\n",
    "model.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "# confirm the model is fitted\n",
    "check_is_fitted(model)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Step 5: evaluate with test split data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 0, 0, 0, 0], dtype=int64)"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# obtain predictions using the test split data for comparison\n",
    "y_pred = model.predict(X_test)\n",
    "y_pred[:5]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.73      0.89      0.80        55\n",
      "           1       0.86      0.68      0.76        56\n",
      "\n",
      "    accuracy                           0.78       111\n",
      "   macro avg       0.80      0.78      0.78       111\n",
      "weighted avg       0.80      0.78      0.78       111\n",
      "\n",
      "Mean accuracy of the model: 0.7837837837837838\n"
     ]
    }
   ],
   "source": [
    "# print the classification report\n",
    "print(classification_report(y_test, y_pred))\n",
    "\n",
    "# print the mean accuracy of the model for the test split\n",
    "acc = model.score(X_test, y_test)\n",
    "print(f\"Mean accuracy of the model: {acc}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The report showed high accuracy with slightly lower recall especiall for those >= 5 career years. The model performance seems optimal"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Step 6: obtain predictions for the test data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 555 entries, 0 to 554\n",
      "Data columns (total 19 columns):\n",
      " #   Column   Non-Null Count  Dtype  \n",
      "---  ------   --------------  -----  \n",
      " 0   GP       555 non-null    int32  \n",
      " 1   MIN      555 non-null    float64\n",
      " 2   PTS      555 non-null    float64\n",
      " 3   FGM      555 non-null    float64\n",
      " 4   FGA      555 non-null    float64\n",
      " 5   FG%      555 non-null    float64\n",
      " 6   3P Made  555 non-null    float64\n",
      " 7   3PA      555 non-null    float64\n",
      " 8   3P%      555 non-null    float64\n",
      " 9   FTM      555 non-null    float64\n",
      " 10  FTA      555 non-null    float64\n",
      " 11  FT%      555 non-null    float64\n",
      " 12  OREB     555 non-null    float64\n",
      " 13  DREB     555 non-null    float64\n",
      " 14  REB      555 non-null    float64\n",
      " 15  AST      555 non-null    float64\n",
      " 16  STL      555 non-null    float64\n",
      " 17  BLK      555 non-null    float64\n",
      " 18  TOV      555 non-null    float64\n",
      "dtypes: float64(18), int32(1)\n",
      "memory usage: 80.3 KB\n"
     ]
    }
   ],
   "source": [
    "# read test dataset\n",
    "test_df = pd.read_csv(\"data/Test_data.csv\")\n",
    "test_df[\"GP\"] = test_df[\"GP\"].astype(int)\n",
    "test_df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1, 0, 0, 0, 1], dtype=int64)"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# obtain predications\n",
    "test_pred = model.predict(test_df)\n",
    "test_pred[:5]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "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>prediction</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   prediction\n",
       "0           1\n",
       "1           0\n",
       "2           0\n",
       "3           0\n",
       "4           1"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# convert prediction to a df\n",
    "pred_df = pd.DataFrame.from_dict({\"prediction\": test_pred})\n",
    "pred_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Save the complete test predictions to a file\n",
    "pred_df.to_csv(\"predications.csv\", index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.9.5 64-bit",
   "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": "3.9.5"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "2926e492272a7651263caa9ef5c18f3618a334d6aa06687da9c34bcae52be579"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}