Upload demo_files\stock_forecasting.ipynb with huggingface_hub

demo_files//stock_forecasting.ipynb

@@ -0,0 +1,130 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Stock Price Forecasting with ARIMA and LSTM\n",
+        "\n",
+        "## Objective\n",
+        "Build and compare time series forecasting models for stock price prediction.\n",
+        "\n",
+        "**Dataset**: Daily stock prices (5 years)\n",
+        "**Models**: ARIMA, SARIMA, LSTM\n",
+        "**Metrics**: RMSE, MAE, MAPE"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 1,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import pandas as pd\n",
+        "import numpy as np\n",
+        "import matplotlib.pyplot as plt\n",
+        "from statsmodels.tsa.arima.model import ARIMA\n",
+        "from statsmodels.tsa.stattools import adfuller, acf, pacf\n",
+        "from statsmodels.graphics.tsaplots import plot_acf, plot_pacf\n",
+        "from sklearn.metrics import mean_squared_error, mean_absolute_error\n",
+        "import warnings\n",
+        "warnings.filterwarnings('ignore')\n",
+        "\n",
+        "# Generate synthetic stock data\n",
+        "np.random.seed(42)\n",
+        "dates = pd.date_range('2019-01-01', '2024-01-01', freq='D')\n",
+        "n = len(dates)\n",
+        "\n",
+        "# Generate realistic stock price with trend, seasonality, and noise\n",
+        "trend = np.linspace(100, 200, n)\n",
+        "seasonal = 10 * np.sin(np.linspace(0, 10*np.pi, n))\n",
+        "noise = np.random.normal(0, 5, n)\n",
+        "prices = trend + seasonal + noise\n",
+        "prices = np.maximum(prices, 50)  # Ensure positive prices\n",
+        "\n",
+        "df = pd.DataFrame({\n",
+        "    'Date': dates,\n",
+        "    'Close': prices,\n",
+        "    'Volume': np.random.randint(1000000, 10000000, n)\n",
+        "})\n",
+        "df.set_index('Date', inplace=True)\n",
+        "\n",
+        "print(f'Dataset shape: {df.shape}')\n",
+        "print(f'Date range: {df.index.min()} to {df.index.max()}')\n",
+        "print(f'Mean price: ${df.Close.mean():.2f}')\n",
+        "print(f'Price volatility (std): ${df.Close.std():.2f}')"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 2,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Stationarity test\n",
+        "result = adfuller(df['Close'])\n",
+        "print('ADF Statistic:', result[0])\n",
+        "print('p-value:', result[1])\n",
+        "print('Critical Values:', result[4])\n",
+        "\n",
+        "if result[1] > 0.05:\n",
+        "    print('\\nSeries is NON-STATIONARY. Differencing required.')\n",
+        "    df['Close_diff'] = df['Close'].diff().dropna()\n",
+        "else:\n",
+        "    print('\\nSeries is STATIONARY.')\n",
+        "\n",
+        "# Calculate returns\n",
+        "df['Returns'] = df['Close'].pct_change() * 100\n",
+        "df['MA_7'] = df['Close'].rolling(window=7).mean()\n",
+        "df['MA_30'] = df['Close'].rolling(window=30).mean()\n",
+        "\n",
+        "print(f'\\nAverage daily return: {df.Returns.mean():.3f}%')\n",
+        "print(f'Return volatility: {df.Returns.std():.3f}%')"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 3,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Train-test split (80-20)\n",
+        "train_size = int(len(df) * 0.8)\n",
+        "train, test = df[:train_size], df[train_size:]\n",
+        "\n",
+        "print(f'Training set: {len(train)} days')\n",
+        "print(f'Test set: {len(test)} days')\n",
+        "\n",
+        "# Fit ARIMA model\n",
+        "model = ARIMA(train['Close'], order=(5,1,2))\n",
+        "model_fit = model.fit()\n",
+        "\n",
+        "print('\\nARIMA Model Summary:')\n",
+        "print(model_fit.summary())\n",
+        "\n",
+        "# Forecast\n",
+        "forecast = model_fit.forecast(steps=len(test))\n",
+        "test['Forecast'] = forecast.values\n",
+        "\n",
+        "# Calculate errors\n",
+        "rmse = np.sqrt(mean_squared_error(test['Close'], test['Forecast']))\n",
+        "mae = mean_absolute_error(test['Close'], test['Forecast'])\n",
+        "mape = np.mean(np.abs((test['Close'] - test['Forecast']) / test['Close'])) * 100\n",
+        "\n",
+        "print(f'\\nModel Performance:')\n",
+        "print(f'RMSE: ${rmse:.2f}')\n",
+        "print(f'MAE: ${mae:.2f}')\n",
+        "print(f'MAPE: {mape:.2f}%')"
+      ]
+    }
+  ],
+  "metadata": {
+    "kernelspec": {
+      "display_name": "Python 3",
+      "language": "python",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 4
+}