https://github.com/bwconrad/weather-description-generator
Weather description generator using real-time images
https://github.com/bwconrad/weather-description-generator
data-science machine-learning neural-network python3 weather
Last synced: about 2 months ago
JSON representation
Weather description generator using real-time images
- Host: GitHub
- URL: https://github.com/bwconrad/weather-description-generator
- Owner: bwconrad
- Created: 2018-01-12T04:20:21.000Z (over 8 years ago)
- Default Branch: master
- Last Pushed: 2018-01-12T04:27:00.000Z (over 8 years ago)
- Last Synced: 2025-01-24T19:17:02.894Z (over 1 year ago)
- Topics: data-science, machine-learning, neural-network, python3, weather
- Language: Python
- Homepage:
- Size: 303 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Weather Description Neural Network
Neural network to create weather descriptions given an image and current weather measurements.
### Data Sets:
* Images: Kat Kam (private)
* Weather Data: GHCN YVR Airport
### Dependencies:
* Python 3
* Numpy
* Pandas
* Scikit Learn
* OpenCV
### How to run:
1. Clone the repo.
```
git clone https://github.com/bwconrad/Weather-Description-Generator.git
```
2. In the project directory run the program with the arguments [images directoy] [weather data directory] [output CSV].
```
python3 weather_imgs.py Data\katkam-scaled Data\yvr-weather results.csv
```
3. The program will output the accuracy on the testing data and the predictions are saved as the inputted CSV filename.
## Results
Network achieves 70% accuracy using a 75:25 data split and training for 3000 epoches.