Add-LSTM

[Erennn7]

PR: LSTM Time Series Forecasting in R

This PR introduces a fully documented implementation of a Long Short-Term Memory (LSTM) neural network in R for time series prediction and forecasting.
The implementation leverages the keras and tensorflow packages to build, train, and evaluate LSTM models capable of learning temporal dependencies in sequential data.

Overview

The provided LSTM workflow covers:

• Data Preprocessing:

  • Normalization of time series data to [0,1] range
  • Sequence creation for supervised learning (input sequences and target values)

• Model Architecture:

  • Single-layer LSTM network with configurable units and dropout
  • Dense output layer for regression tasks
  • Compilation with Adam optimizer and Mean Squared Error loss

• Training and Evaluation:

  • Training with configurable epochs and batch size
  • Validation split and monitoring of training history
  • Evaluation on test data with metrics: MSE, RMSE, MAE, and R-squared

• Prediction Capabilities:

  • Single-step and multi-step ahead predictions
  • Denormalization of predictions for interpretation
  • Visualization of actual vs. predicted series using ggplot2

• Best Practices:

  • Sequence length selection based on temporal dependencies
  • Dropout regularization to prevent overfitting
  • Early stopping, model checkpointing, and hyperparameter tuning

This LSTM implementation is suitable for:

• Synthetic or real-world time series (e.g., sine waves, stock prices, sensor data)
• Forecasting applications requiring learning of sequential patterns
• Multi-step ahead prediction and analysis of temporal trends

Complexity

• Training Complexity: O(n_samples × seq_length × lstm_units) per epoch
• Inference Complexity: O(n_samples × seq_length × lstm_units)

The approach demonstrates how LSTMs can model sequential dependencies more effectively than traditional regression or moving-average methods.

[Copilot]

Pull Request Overview

This PR introduces a comprehensive implementation of Long Short-Term Memory (LSTM) neural networks for time series forecasting in R, providing a complete workflow from data preprocessing to prediction visualization.

• Implements LSTM model architecture with configurable parameters for time series prediction
• Provides comprehensive data preprocessing including normalization and sequence generation
• Includes evaluation metrics, visualization capabilities, and multi-step ahead prediction functionality

[Erennn7]

LSTM script improvements:
• Fixed train/test split to maintain temporal order for time series (sequential split instead of random sampling).
• Updated geom_line() in ggplot2 to use linewidth instead of deprecated size argument.
• Added optional note about using tidyr::pivot_longer() instead of reshape2::melt() for modern, dependency-safe data reshaping.
• Minor formatting and readability improvements in plotting and metrics sections.

All changes maintain original functionality; the model workflow and outputs remain the same.

[Erennn7]

@siriak please have a look

[Copilot]

Pull Request Overview

Copilot reviewed 1 out of 1 changed files in this pull request and generated 1 comment.

[Copilot]

Pull Request Overview

Copilot reviewed 1 out of 1 changed files in this pull request and generated 1 comment.

[Copilot]

The error message references only 'tidyr' in the install command, but the message states both packages are options. Consider clarifying: stop(\"Please install 'tidyr' or 'reshape2' to create the plot: install.packages('tidyr') or install.packages('reshape2')\") to avoid confusion.

Suggested change

	stop("Please install 'tidyr' or 'reshape2' to create the plot (install.packages('tidyr')).")
	stop("Please install 'tidyr' or 'reshape2' to create the plot: install.packages('tidyr') or install.packages('reshape2').")

[siriak]

Looks good, thanks!