xg_boost_model.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "8a55bf0c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting xgboost\n",
      "  Downloading xgboost-1.7.5-py3-none-macosx_10_15_x86_64.macosx_11_0_x86_64.macosx_12_0_x86_64.whl (1.8 MB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.8/1.8 MB\u001b[0m \u001b[31m7.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
      "\u001b[?25hRequirement already satisfied: numpy in ./env/lib/python3.10/site-packages (from xgboost) (1.23.3)\n",
      "Requirement already satisfied: scipy in ./env/lib/python3.10/site-packages (from xgboost) (1.10.1)\n",
      "Installing collected packages: xgboost\n",
      "Successfully installed xgboost-1.7.5\n"
     ]
    }
   ],
   "source": [
    "! pip install xgboost"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "c741d50a",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import time"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "c4688c16",
   "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>Date</th>\n",
       "      <th>S&amp;P500</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2012-10-22</td>\n",
       "      <td>1433.82</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2012-10-23</td>\n",
       "      <td>1413.11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2012-10-24</td>\n",
       "      <td>1408.75</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2012-10-25</td>\n",
       "      <td>1412.97</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2012-10-26</td>\n",
       "      <td>1411.94</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         Date   S&P500\n",
       "0  2012-10-22  1433.82\n",
       "1  2012-10-23  1413.11\n",
       "2  2012-10-24  1408.75\n",
       "3  2012-10-25  1412.97\n",
       "4  2012-10-26  1411.94"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv('sp500_index.csv')\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "d4d6906b",
   "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>S&amp;P500</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1433.82</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1413.11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1408.75</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1412.97</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1411.94</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    S&P500\n",
       "0  1433.82\n",
       "1  1413.11\n",
       "2  1408.75\n",
       "3  1412.97\n",
       "4  1411.94"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dates = df['Date']\n",
    "df = df[['S&P500']]\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "f01a6270",
   "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>S&amp;P500</th>\n",
       "      <th>Target</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1433.82</td>\n",
       "      <td>1413.11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1413.11</td>\n",
       "      <td>1408.75</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1408.75</td>\n",
       "      <td>1412.97</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1412.97</td>\n",
       "      <td>1411.94</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1411.94</td>\n",
       "      <td>1412.16</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    S&P500   Target\n",
       "0  1433.82  1413.11\n",
       "1  1413.11  1408.75\n",
       "2  1408.75  1412.97\n",
       "3  1412.97  1411.94\n",
       "4  1411.94  1412.16"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Target'] = df['S&P500'].shift(-1)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "c98c9be2",
   "metadata": {},
   "outputs": [],
   "source": [
    "def train_test(data, percent_test):\n",
    "    data = data.values\n",
    "    split = int(len(data) * (1-percent_test))\n",
    "    train, test = data[:split], data[split :]\n",
    "    return train, test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "9438656c",
   "metadata": {},
   "outputs": [],
   "source": [
    "train, test = train_test(df, .2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "883a546a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2517\n",
      "2013\n",
      "504\n"
     ]
    }
   ],
   "source": [
    "print(len(df))\n",
    "print(len(train))\n",
    "print(len(test))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "b3b21079",
   "metadata": {},
   "outputs": [],
   "source": [
    "X = train[:, : -1]\n",
    "y = train[:, -1 :]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "062e7dff",
   "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>XGBRegressor(base_score=None, booster=None, callbacks=None,\n",
       "             colsample_bylevel=None, colsample_bynode=None,\n",
       "             colsample_bytree=None, early_stopping_rounds=None,\n",
       "             enable_categorical=False, eval_metric=None, feature_types=None,\n",
       "             gamma=None, gpu_id=None, grow_policy=None, importance_type=None,\n",
       "             interaction_constraints=None, learning_rate=None, max_bin=None,\n",
       "             max_cat_threshold=None, max_cat_to_onehot=None,\n",
       "             max_delta_step=None, max_depth=None, max_leaves=None,\n",
       "             min_child_weight=None, missing=nan, monotone_constraints=None,\n",
       "             n_estimators=1000, n_jobs=None, num_parallel_tree=None,\n",
       "             predictor=None, random_state=None, ...)</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\">XGBRegressor</label><div class=\"sk-toggleable__content\"><pre>XGBRegressor(base_score=None, booster=None, callbacks=None,\n",
       "             colsample_bylevel=None, colsample_bynode=None,\n",
       "             colsample_bytree=None, early_stopping_rounds=None,\n",
       "             enable_categorical=False, eval_metric=None, feature_types=None,\n",
       "             gamma=None, gpu_id=None, grow_policy=None, importance_type=None,\n",
       "             interaction_constraints=None, learning_rate=None, max_bin=None,\n",
       "             max_cat_threshold=None, max_cat_to_onehot=None,\n",
       "             max_delta_step=None, max_depth=None, max_leaves=None,\n",
       "             min_child_weight=None, missing=nan, monotone_constraints=None,\n",
       "             n_estimators=1000, n_jobs=None, num_parallel_tree=None,\n",
       "             predictor=None, random_state=None, ...)</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "XGBRegressor(base_score=None, booster=None, callbacks=None,\n",
       "             colsample_bylevel=None, colsample_bynode=None,\n",
       "             colsample_bytree=None, early_stopping_rounds=None,\n",
       "             enable_categorical=False, eval_metric=None, feature_types=None,\n",
       "             gamma=None, gpu_id=None, grow_policy=None, importance_type=None,\n",
       "             interaction_constraints=None, learning_rate=None, max_bin=None,\n",
       "             max_cat_threshold=None, max_cat_to_onehot=None,\n",
       "             max_delta_step=None, max_depth=None, max_leaves=None,\n",
       "             min_child_weight=None, missing=nan, monotone_constraints=None,\n",
       "             n_estimators=1000, n_jobs=None, num_parallel_tree=None,\n",
       "             predictor=None, random_state=None, ...)"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from xgboost import XGBRegressor\n",
    "model = XGBRegressor(objective='reg:squarederror', n_estimators=1000)\n",
    "model.fit(X, y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "21d12eea",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([3453.49, 3465.39])"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "7ac267d7",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "3427.4727\n"
     ]
    }
   ],
   "source": [
    "val = np.array(test[0, 0]).reshape(1, -1)\n",
    "pred = model.predict(val)\n",
    "print(pred[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "ed38bc36",
   "metadata": {},
   "outputs": [],
   "source": [
    "def xgb_predict(train, val):\n",
    "    train = np.array(train)\n",
    "    X = train[:, : -1]\n",
    "    y = train[:, -1 :]\n",
    "    model = XGBRegressor(objective='reg:squarederror', n_estimators=1000)\n",
    "    model.fit(X, y)\n",
    "    val = np.array(test[0, 0]).reshape(1, -1)\n",
    "    pred = model.predict(val)\n",
    "    return pred[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "f1d02cc5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "3427.4727"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "xgb_predict(train, test[0, 0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "f76d1d38",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.metrics import mean_squared_error\n",
    "\n",
    "def validate(data, percent):\n",
    "    predictions = []\n",
    "    \n",
    "    train, test = train_test(data, percent)\n",
    "    \n",
    "    history = [x for x in train]\n",
    "    \n",
    "    for i in range(len(test)):\n",
    "        test_X, test_y = test[i, : -1], test[i, -1:]\n",
    "        pred = xgb_predict(history, test_X[0])\n",
    "        predictions.append(pred)\n",
    "        history.append(test[i])\n",
    "    error = mean_squared_error(test[:, : -1], predictions, squared=False)\n",
    "    return error, test[:, -1:], predictions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "0c02d085",
   "metadata": {},
   "outputs": [],
   "source": [
    "error, test, predictions = validate(df, .2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "08638763",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[<matplotlib.lines.Line2D at 0x7f848784ea70>]"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.plot(predictions)\n",
    "plt.plot(test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "1092ae57",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "770.2362458653216"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "error"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0cb207b5",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}