time-series-r

This repository contains examples, analysis, and tools for working with time series using the R programming language. It is designed for both beginners who want to learn about time series analysis and advanced users looking for practical resources and models.

---

Contents

The repository includes:

1. Introduction to Time Series:

   • Basic concepts: seasonality, trends, noise.
   • Data exploration and visualization.

2. Data Preprocessing:

   • Cleaning and transformation methods.
   • Handling missing data.
   • Time series decomposition.

3. Time Series Models:

   • ARIMA (AutoRegressive Integrated Moving Average).
   • SARIMA (Seasonal ARIMA).
   • Exponential Smoothing models.
   • Machine Learning-based methods (optional).

4. Model Evaluation:

   • Performance metrics such as MAE, RMSE, and MAPE.
   • Cross-validation for time series.

5. Practical Examples:

   • Financial data forecasting.
   • Sales time series analysis.
   • Real-world case studies.

---

Requirements

To use the scripts in this repository, you will need:

• R (version 4.0 or higher).
• RStudio (optional, but recommended).
• The following R packages:
  • forecast
  • ggplot2
  • tseries
  • dplyr
  • tidyr

Install the required packages by running:

 install.packages(c("forecast", "ggplot2", "tseries", "dplyr", "tidyr"))

---

Usage

1. Clone the repository:

   git clone https://github.com/Marta-Barea/time-series-analysis-r.git
   cd time-series-analysis-r

3. Open the scripts in RStudio to explore and execute the examples.
4. Follow the inline comments in the scripts to understand the analysis flow.

---

📜 License

This project is licensed under the GNU GENERAL PUBLIC License. See LICENSE for details.