Time Series Descompositions in Bitcoin

Description

This project focuses on the decomposition of time series of Bitcoin prices. Time series decomposition divides the data into seasonal, trend, and noise components, allowing for better understanding and prediction of patterns in Bitcoin prices over time.

Contents

• data/: Folder containng the datasest used in analysis.
• notebooks/: Jupyter Notebooks with the code and analysis.
• scripts/: Python script for data processing and time series descomposition.
• results/: Results and graphs generated by the analysis.
• README.md: This file.

Requirments

• Python 3.8+
• Python libraries:
  • pandas
  • numpy
  • matplotlib
  • statsmodels
  • seaborn
  • jupyter

You can install the necessary libraries with:

pip install pandas numpy matplotlib statsmodels seaborn jupyter

Usage

The generated results and graphs will be stored in the results/. folder. You can review these files to better understand the componentency of your time series.

1. Prepare the data

Place your time series data in the data/ folder in a compatible format (e.g., CSV).

2. Run the analysis

Open and run the notebooks in the notebooks/ folder to perform the decomposition and analysis of the time series. You can start with time_series_decomposition.ipynb.

3. Review the results

The generated results and graphs will be stored in the results/ folder. You can review these files to better understand the components of your time series.

Example

An example of time series decomposition usage can be found in the notebooks/time_series_decomposition_example.ipynb notebook, which uses sample data to illustrate the process.

Contribution

Contributions are welcome. Please open an issue or submit a pull request for any improvements or corrections.

License

This project is licensed under the MIT License. See the LICENSE file for more details..