{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Recurrent Neural Networks (RNNs) with TensorFlow\n",
    "\n",
    "<!--\n",
    "Project: TensorFlow Deep Learning\n",
    "Author: RSK World\n",
    "Website: https://rskworld.in\n",
    "Email: help@rskworld.in\n",
    "Phone: +91 93305 39277\n",
    "-->\n",
    "\n",
    "This notebook demonstrates RNN, LSTM, and GRU implementations for sequence modeling."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import sys\n",
    "import os\n",
    "sys.path.append(os.path.join(os.path.dirname(os.getcwd()), 'src'))\n",
    "\n",
    "import tensorflow as tf\n",
    "from tensorflow import keras\n",
    "from tensorflow.keras import layers\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "from rnns import (\n",
    "    create_simple_rnn,\n",
    "    create_lstm_model,\n",
    "    create_gru_model,\n",
    "    create_bidirectional_lstm,\n",
    "    generate_sequence_data\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Generate Sequence Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Generate synthetic sequence data\n",
    "X_train, y_train = generate_sequence_data(\n",
    "    num_samples=800,\n",
    "    sequence_length=50,\n",
    "    num_features=10,\n",
    "    num_classes=3\n",
    ")\n",
    "\n",
    "X_test, y_test = generate_sequence_data(\n",
    "    num_samples=200,\n",
    "    sequence_length=50,\n",
    "    num_features=10,\n",
    "    num_classes=3\n",
    ")\n",
    "\n",
    "print(f\"Training samples: {X_train.shape[0]}\")\n",
    "print(f\"Test samples: {X_test.shape[0]}\")\n",
    "print(f\"Sequence shape: {X_train.shape[1:]}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Create LSTM Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create LSTM model\n",
    "lstm_model = create_lstm_model(\n",
    "    input_shape=(50, 10),\n",
    "    num_classes=3,\n",
    "    lstm_units=128,\n",
    "    num_layers=2\n",
    ")\n",
    "\n",
    "lstm_model.summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Train LSTM Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Train model\n",
    "history = lstm_model.fit(\n",
    "    X_train, y_train,\n",
    "    batch_size=32,\n",
    "    epochs=10,\n",
    "    validation_data=(X_test, y_test),\n",
    "    verbose=1\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Create GRU Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create GRU model\n",
    "gru_model = create_gru_model(\n",
    "    input_shape=(50, 10),\n",
    "    num_classes=3,\n",
    "    gru_units=128,\n",
    "    num_layers=2\n",
    ")\n",
    "\n",
    "gru_model.summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Create Bidirectional LSTM"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create bidirectional LSTM\n",
    "bidirectional_model = create_bidirectional_lstm(\n",
    "    input_shape=(50, 10),\n",
    "    num_classes=3,\n",
    "    lstm_units=128\n",
    ")\n",
    "\n",
    "bidirectional_model.summary()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "name": "python",
   "version": "3.8.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}