https://github.com/gaurav0502/electricity-forecasting
Forecasting daily electricity consumption 💡 with Portuguese weather data on precipitation 🌧️ and temperature 🌡️
https://github.com/gaurav0502/electricity-forecasting
clustering facebook-prophet forecasting lstm python sarimax sklearn-metrics time-series tslearn
Last synced: about 1 month ago
JSON representation
Forecasting daily electricity consumption 💡 with Portuguese weather data on precipitation 🌧️ and temperature 🌡️
- Host: GitHub
- URL: https://github.com/gaurav0502/electricity-forecasting
- Owner: Gaurav0502
- Created: 2025-02-26T00:34:33.000Z (8 months ago)
- Default Branch: main
- Last Pushed: 2025-05-18T00:37:03.000Z (5 months ago)
- Last Synced: 2025-05-18T01:28:53.034Z (5 months ago)
- Topics: clustering, facebook-prophet, forecasting, lstm, python, sarimax, sklearn-metrics, time-series, tslearn
- Language: Jupyter Notebook
- Homepage:
- Size: 5.53 MB
- Stars: 1
- Watchers: 1
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- Contributing: .github/CONTRIBUTING.md
Awesome Lists containing this project
README
Daily Electricity Usage Forecasting
## Aim
To forecast the daily electricity consumption with weather data (daily temperature ranges and precipitation).
## Environment Setup
- Clone this repository.
```bash
git clone https://github.com/Gaurav0502/electricity-forecasting.git
```
- Install all packages in the ```requirements.txt``` file.
```bash
pip install -r requirements.txt
```
- Download and store all the three datasets from following sources:
1. Electricity dataset: https://archive.ics.uci.edu/dataset/321/electricityloaddiagrams20112014
2. Weather dataset: https://www.kaggle.com/datasets/gauravpendharkar/portuguese-weather-data-from-2011-to-2014
- Ensure the all the data and code files have the directory structure as follows:
```bash
.
├── README.md
├── clustering.ipynb
├── clusters.json
├── data
│ ├── LD2011_2014.txt
│ ├── lisbon_precip_2011-2014.csv
│ └── lisbon_temp_2011-2014.csv
├── eda.ipynb
├── model.py
├── modelling.ipynb
├── preprocess.py
└── requirements.txt
```
### References
Electricity: https://archive.ics.uci.edu/dataset/321/electricityloaddiagrams20112014
Weather: https://www.ipma.pt/en/oclima/series.longas/list.jsp