{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 98,
   "id": "df9383b8-2de4-4e5a-8e1c-5bb47887bf1a",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import torch\n",
    "import torch.nn as nn\n",
    "from torch.utils.data import Dataset, DataLoader\n",
    "import numpy as np\n",
    "import os"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 99,
   "id": "f94c660f-4a3e-4a90-93e5-ad7a5152db4e",
   "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>CO_ID</th>\n",
       "      <th>Name</th>\n",
       "      <th>Year</th>\n",
       "      <th>Quarter</th>\n",
       "      <th>Sector</th>\n",
       "      <th>Return on Assets</th>\n",
       "      <th>Return on Capital\\t</th>\n",
       "      <th>Return on Equity</th>\n",
       "      <th>Return on Common Equity</th>\n",
       "      <th>Gross Profit Margin</th>\n",
       "      <th>EBITA Margin</th>\n",
       "      <th>EBIT Margin</th>\n",
       "      <th>Net Income Margin</th>\n",
       "      <th>Asset Turnover</th>\n",
       "      <th>Current Ratio</th>\n",
       "      <th>Debt / Equity</th>\n",
       "      <th>Long Term Debt / Captial</th>\n",
       "      <th>Book Value Per Share</th>\n",
       "      <th>Stock Return</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2030.0</td>\n",
       "      <td>SARCO</td>\n",
       "      <td>2015</td>\n",
       "      <td>1</td>\n",
       "      <td>Energy</td>\n",
       "      <td>1.25</td>\n",
       "      <td>1.28</td>\n",
       "      <td>1.96</td>\n",
       "      <td>1.24</td>\n",
       "      <td>100.0</td>\n",
       "      <td>55.26</td>\n",
       "      <td>55.26</td>\n",
       "      <td>50.65</td>\n",
       "      <td>0.03</td>\n",
       "      <td>3.39</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>19.19</td>\n",
       "      <td>-11.28</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2030.0</td>\n",
       "      <td>SARCO</td>\n",
       "      <td>2015</td>\n",
       "      <td>2</td>\n",
       "      <td>Energy</td>\n",
       "      <td>1.28</td>\n",
       "      <td>1.26</td>\n",
       "      <td>1.95</td>\n",
       "      <td>1.65</td>\n",
       "      <td>100.0</td>\n",
       "      <td>56.23</td>\n",
       "      <td>56.23</td>\n",
       "      <td>50.62</td>\n",
       "      <td>0.02</td>\n",
       "      <td>3.38</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>19.56</td>\n",
       "      <td>-7.48</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2030.0</td>\n",
       "      <td>SARCO</td>\n",
       "      <td>2015</td>\n",
       "      <td>3</td>\n",
       "      <td>Energy</td>\n",
       "      <td>1.26</td>\n",
       "      <td>1.27</td>\n",
       "      <td>1.96</td>\n",
       "      <td>-1.12</td>\n",
       "      <td>100.0</td>\n",
       "      <td>54.35</td>\n",
       "      <td>54.35</td>\n",
       "      <td>50.95</td>\n",
       "      <td>0.06</td>\n",
       "      <td>3.35</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>19.73</td>\n",
       "      <td>-29.31</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2030.0</td>\n",
       "      <td>SARCO</td>\n",
       "      <td>2015</td>\n",
       "      <td>4</td>\n",
       "      <td>Energy</td>\n",
       "      <td>1.27</td>\n",
       "      <td>1.29</td>\n",
       "      <td>1.93</td>\n",
       "      <td>-1.23</td>\n",
       "      <td>100.0</td>\n",
       "      <td>54.13</td>\n",
       "      <td>54.13</td>\n",
       "      <td>50.58</td>\n",
       "      <td>0.04</td>\n",
       "      <td>3.39</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>19.76</td>\n",
       "      <td>-5.51</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2030.0</td>\n",
       "      <td>SARCO</td>\n",
       "      <td>2016</td>\n",
       "      <td>1</td>\n",
       "      <td>Energy</td>\n",
       "      <td>1.52</td>\n",
       "      <td>0.86</td>\n",
       "      <td>1.24</td>\n",
       "      <td>2.65</td>\n",
       "      <td>100.0</td>\n",
       "      <td>292.49</td>\n",
       "      <td>292.49</td>\n",
       "      <td>272.96</td>\n",
       "      <td>-1.00</td>\n",
       "      <td>2.90</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>23.65</td>\n",
       "      <td>10.56</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    CO_ID   Name  Year  Quarter  Sector  Return on Assets  \\\n",
       "0  2030.0  SARCO  2015        1  Energy              1.25   \n",
       "1  2030.0  SARCO  2015        2  Energy              1.28   \n",
       "2  2030.0  SARCO  2015        3  Energy              1.26   \n",
       "3  2030.0  SARCO  2015        4  Energy              1.27   \n",
       "4  2030.0  SARCO  2016        1  Energy              1.52   \n",
       "\n",
       "   Return on Capital\\t Return on Equity  Return on Common Equity   \\\n",
       "0                 1.28             1.96                      1.24   \n",
       "1                 1.26             1.95                      1.65   \n",
       "2                 1.27             1.96                     -1.12   \n",
       "3                 1.29             1.93                     -1.23   \n",
       "4                 0.86             1.24                      2.65   \n",
       "\n",
       "   Gross Profit Margin  EBITA Margin  EBIT Margin  Net Income Margin  \\\n",
       "0                100.0         55.26        55.26              50.65   \n",
       "1                100.0         56.23        56.23              50.62   \n",
       "2                100.0         54.35        54.35              50.95   \n",
       "3                100.0         54.13        54.13              50.58   \n",
       "4                100.0        292.49       292.49             272.96   \n",
       "\n",
       "   Asset Turnover  Current Ratio  Debt / Equity  Long Term Debt / Captial  \\\n",
       "0            0.03           3.39           -1.0                      -1.0   \n",
       "1            0.02           3.38           -1.0                      -1.0   \n",
       "2            0.06           3.35           -1.0                      -1.0   \n",
       "3            0.04           3.39           -1.0                      -1.0   \n",
       "4           -1.00           2.90           -1.0                      -1.0   \n",
       "\n",
       "  Book Value Per Share  Stock Return  \n",
       "0                19.19        -11.28  \n",
       "1                19.56         -7.48  \n",
       "2                19.73        -29.31  \n",
       "3                19.76         -5.51  \n",
       "4                23.65         10.56  "
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "df = pd.read_csv('dataset52.csv')\n",
    "df.head()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "id": "18b8fe04-4687-4bb8-a7e9-e163c800b0f7",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Number of Rows: 2091\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "rows, columns = df.shape\n",
    "print(f\"Number of Rows: {rows}\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 101,
   "id": "c38184aa-b88e-4cdb-96e9-11ec5bc4d1f8",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Long Term Debt / Captial    286\n",
      "Debt / Equity               220\n",
      "Gross Profit Margin         166\n",
      "EBIT Margin                 160\n",
      "Asset Turnover              160\n",
      "EBITA Margin                156\n",
      "Net Income Margin           155\n",
      "Return on Common Equity     144\n",
      "Return on Equity            144\n",
      "Current Ratio               141\n",
      "Return on Assets            139\n",
      "Return on Capital\\t         135\n",
      "Book Value Per Share         63\n",
      "Stock Return                 16\n",
      "dtype: int64\n"
     ]
    }
   ],
   "source": [
    "missing = df.isnull().sum()\n",
    "missing = missing[missing > 0].sort_values(ascending=False)\n",
    "print(missing)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 102,
   "id": "fa610664-4f03-4f28-92b1-46b3ff7e4741",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Return on Assets            0\n",
       "Return on Capital           0\n",
       "Return on Equity            0\n",
       "Return on Common Equity     0\n",
       "Gross Profit Margin         0\n",
       "EBITA Margin                0\n",
       "EBIT Margin                 0\n",
       "Net Income Margin           0\n",
       "Asset Turnover              0\n",
       "Current Ratio               0\n",
       "Debt / Equity               0\n",
       "Long Term Debt / Captial    0\n",
       "Book Value Per Share        0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 102,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "\n",
    "#dataset\n",
    "df = pd.read_csv(\"dataset13.csv\")\n",
    "\n",
    "#Fix column names\n",
    "df.columns = df.columns.str.strip().str.replace('\\t', '')\n",
    "\n",
    "#Convert types\n",
    "df['Return on Equity'] = pd.to_numeric(df['Return on Equity'], errors='coerce')\n",
    "\n",
    "#Sort by company and time\n",
    "df = df.sort_values(by=['CO_ID', 'Year', 'Quarter'])\n",
    "\n",
    "#Select features and target\n",
    "features = [\n",
    "    'Return on Assets', 'Return on Capital', 'Return on Equity',\n",
    "    'Return on Common Equity', 'Gross Profit Margin', 'EBITA Margin',\n",
    "    'EBIT Margin', 'Net Income Margin', 'Asset Turnover', 'Current Ratio',\n",
    "    'Debt / Equity', 'Long Term Debt / Captial', 'Book Value Per Share'\n",
    "]\n",
    "\n",
    "target = 'Stock Return'\n",
    "\n",
    "#Fill missing values per company\n",
    "df[features] = df.groupby('CO_ID')[features].transform(lambda g: g.ffill().bfill())\n",
    "\n",
    "# Normalize\n",
    "scaler = StandardScaler()\n",
    "df[features] = scaler.fit_transform(df[features])\n",
    "\n",
    "# Check if missing values remain\n",
    "df[features].isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 103,
   "id": "e7ccf182-d78d-4ec6-b1d3-efab4ddc1f63",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Series([], dtype: int64)\n"
     ]
    }
   ],
   "source": [
    "missing = df.isnull().sum()\n",
    "missing = missing[missing > 0].sort_values(ascending=False)\n",
    "print(missing)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "id": "2962ae06-130a-47c4-a294-24f0e4361264",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_all, y_all = [], []\n",
    "window_size = 20\n",
    "target_offset = 1\n",
    "\n",
    "for _, group in df.groupby('CO_ID'):\n",
    "    X = group[features].values\n",
    "    y = group[target].values\n",
    "    for i in range(len(X) - window_size - target_offset + 1):\n",
    "        X_all.append(X[i:i+window_size])\n",
    "        y_all.append(y[i+window_size+target_offset-1])\n",
    "\n",
    "import torch\n",
    "X_tensor = torch.tensor(np.array(X_all), dtype=torch.float32)\n",
    "y_tensor = torch.tensor(np.array(y_all), dtype=torch.float32).view(-1, 1)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "id": "0a18e1fc-000c-4795-8156-11ce7c1d02e7",
   "metadata": {},
   "outputs": [],
   "source": [
    "from torch.utils.data import Dataset, DataLoader\n",
    "\n",
    "class FinancialDataset(Dataset):\n",
    "    def __init__(self, X, y):\n",
    "        self.X = X\n",
    "        self.y = y\n",
    "\n",
    "    def __len__(self):\n",
    "        return len(self.X)\n",
    "\n",
    "    def __getitem__(self, idx):\n",
    "        return self.X[idx], self.y[idx]\n",
    "\n",
    "dataset = FinancialDataset(X_tensor, y_tensor)\n",
    "train_loader = DataLoader(dataset, batch_size=16, shuffle=True)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "id": "76798dfa-5e5f-4e76-b3d2-b9461112b4fa",
   "metadata": {},
   "outputs": [],
   "source": [
    "from torch.utils.data import random_split, DataLoader\n",
    "\n",
    "# Step 1: Split into training and validation sets\n",
    "total_size = len(dataset)\n",
    "train_size = int(0.8 * total_size)\n",
    "val_size = total_size - train_size\n",
    "\n",
    "train_dataset, val_dataset = random_split(dataset, [train_size, val_size])\n",
    "\n",
    "# Step 2: Create DataLoaders\n",
    "train_loader = DataLoader(train_dataset, batch_size=16, shuffle=True)\n",
    "val_loader = DataLoader(val_dataset, batch_size=16, shuffle=False)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "id": "22a5a2ea-ddc8-4483-a658-c268f98ac62a",
   "metadata": {},
   "outputs": [],
   "source": [
    "# --------------------------\n",
    "# HYPERPARAMETERS\n",
    "# --------------------------\n",
    "input_dim = 13         # Number of input features\n",
    "hidden_dim = 64        # LSTM hidden size\n",
    "num_layers = 2         # Number of LSTM layers\n",
    "dropout = 0.4          # Dropout rate\n",
    "learning_rate = 0.0005 # ← Try reducing from 0.001\n",
    "batch_size = 128        # Batch size for training\n",
    "num_epochs = 50        # Number of training epochs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "id": "ad3fe157-a5dc-40e1-9bf8-cd5a1cfc7607",
   "metadata": {},
   "outputs": [],
   "source": [
    "import torch.nn as nn\n",
    "\n",
    "class LSTMRegressor(nn.Module):\n",
    "    def __init__(self, input_dim, hidden_dim, num_layers, dropout):\n",
    "        super().__init__()\n",
    "        self.lstm = nn.LSTM(input_dim, hidden_dim, num_layers, dropout=dropout, batch_first=True)\n",
    "        self.fc = nn.Linear(hidden_dim, 1)\n",
    "\n",
    "    def forward(self, x):\n",
    "        out, _ = self.lstm(x)\n",
    "        return self.fc(out[:, -1, :])  # last time step\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "id": "9da0dc75-e612-468a-b9e4-04d7deb98764",
   "metadata": {},
   "outputs": [],
   "source": [
    "model = LSTMRegressor(input_dim, hidden_dim, num_layers, dropout)\n",
    "criterion = nn.MSELoss()\n",
    "optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "id": "7ce96327-7f8c-4b6a-8932-747ed8ba99c7",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 70: Train Loss = 391.4414, Val Loss = 320.0146, Val MAE = 12.5624\n"
     ]
    }
   ],
   "source": [
    "# Training and validation\n",
    "for epoch in range(num_epochs):\n",
    "    model.train()\n",
    "    train_loss = 0\n",
    "    for X_batch, y_batch in train_loader:\n",
    "        optimizer.zero_grad()\n",
    "        y_pred = model(X_batch)\n",
    "        loss = criterion(y_pred, y_batch)\n",
    "        loss.backward()\n",
    "        optimizer.step()\n",
    "        train_loss += loss.item()\n",
    "\n",
    "\n",
    "# Validation\n",
    "    model.eval()\n",
    "    val_loss = 0\n",
    "    with torch.no_grad():\n",
    "        for X_val, y_val in val_loader:\n",
    "            y_val_pred = model(X_val)\n",
    "            val_loss += criterion(y_val_pred, y_val).item()\n",
    "\n",
    "#Average losses\n",
    "    train_loss /= len(train_loader)\n",
    "    val_loss /= len(val_loader)\n",
    "\n",
    "val_mae = 0\n",
    "with torch.no_grad():\n",
    "    for X_val, y_val in val_loader:\n",
    "        y_val_pred = model(X_val)\n",
    "        val_loss += criterion(y_val_pred, y_val).item()\n",
    "        \n",
    "        \n",
    "        val_mae += nn.L1Loss()(y_val_pred, y_val).item()\n",
    "\n",
    "# Average both\n",
    "val_loss /= len(val_loader)\n",
    "val_mae /= len(val_loader)\n",
    "\n",
    "print(f\"Epoch {epoch+1}: Train Loss = {train_loss:.4f}, Val Loss = {val_loss:.4f}, Val MAE = {val_mae:.4f}\")\n",
    "\n",
    "\n",
    "#print(f\"Epoch {epoch+1}: Train Loss = {train_loss:.4f}, Val Loss = {val_loss:.4f}\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 96,
   "id": "971c60ae-5e3a-4dac-b333-82220f216a41",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "📊 Validation MAE: 11.6773\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "# Switch model to evaluation mode\n",
    "model.eval()\n",
    "actuals, predictions = [], []\n",
    "\n",
    "# Get predictions on the validation set\n",
    "with torch.no_grad():\n",
    "    for X_val, y_val in val_loader:\n",
    "        y_pred = model(X_val)\n",
    "        actuals.extend(y_val.view(-1).tolist())\n",
    "        predictions.extend(y_pred.view(-1).tolist())\n",
    "\n",
    "# Convert to NumPy arrays\n",
    "actuals = np.array(actuals)\n",
    "predictions = np.array(predictions)\n",
    "\n",
    "# Compute MAE\n",
    "mae = np.mean(np.abs(actuals - predictions))\n",
    "\n",
    "# Compute MAPE with epsilon to avoid division by 0\n",
    "mape = np.mean(np.abs((actuals - predictions) / (actuals + 1e-8))) * 100\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "print(f\"\\n📊 Validation MAE: {mae:.4f}\")\n",
    "#print(f\"📈 Validation MAPE: {mape:.2f}%\")\n",
    "\n",
    "# Optional: plot actual vs predicted\n",
    "plt.figure(figsize=(10, 5))\n",
    "plt.plot(actuals, label='Actual')\n",
    "plt.plot(predictions, label='Predicted')\n",
    "plt.title('LSTM Evaluation')\n",
    "plt.xlabel('Sample Index')\n",
    "plt.ylabel('Stock Return')\n",
    "plt.legend()\n",
    "plt.grid(True)\n",
    "plt.tight_layout()\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8acbeb9a-bed6-43c7-bc36-30e17ef5f286",
   "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": "3.12.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}