# Time series forecasting energy prices

![tsf](price_actual_over_time.png "Actual energy price")

With features representing energy generation of various sources (oil/biomass/hydro)

## Setup

### Prerequisites:

- Have a working version of `pip` preferably in Python 3.12

### Steps

1. Install `uv`

```bash
pip install uv
```

2. Create & activate virtual environment

```bash
uv venv .venv
# on Windows
.\.venv\Scripts\activate
# on Linux:
source .venv/bin/activate
```

3. Install the dependencies

```bash
uv pip install .
```

## Get hackin'

Look in `tsforecast.ipynb`

- Play around with some of the techniques
  - Seasonal decompose
  - SARIMA
  - XGBoost
  - LSTM
- Try to beat my MAE on test set of ~0.31 (I used LSTM)