https://github.com/nullhawk/dps-munich-ai-challenge
https://github.com/nullhawk/dps-munich-ai-challenge
machine-learning python sarima time-series-prediction
Last synced: about 2 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/nullhawk/dps-munich-ai-challenge
- Owner: nullHawk
- Created: 2024-12-11T09:16:38.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-12-12T13:17:00.000Z (over 1 year ago)
- Last Synced: 2025-06-02T12:36:05.150Z (about 1 year ago)
- Topics: machine-learning, python, sarima, time-series-prediction
- Language: Jupyter Notebook
- Homepage: https://dps-munich-ai-challenge.onrender.com/
- Size: 12.4 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# DPS AI Challenge
## Introduction
This repository contains the code s for the DPS AI Challenge.
**Goal**: Given the Dataset about traffic accidents, You need to predict total number of traffic accidents on the given month of a year.
## Aproach:
- At first I tried to use LSTM model for Time Sequence Prediction of accidents, but the model failed to predict the number of accidents properly,
- Used SARIMA model, since the the Time Sequence is Sesional
## Installation
To get started with the project, clone the repository and install the necessary dependencies:
```bash
git clone https://github.com/nullHawk/dps-munich-ai-challenge
cd dps_ai_challenge
pip install -r requirements.txt
```
## Usage
To run the project, use the following command:
```bash
python app.py
```
The application will start running at `http://localhost:8080`
**Using API**
to get a prediction from the API, send a POST request to http://localhost:8080/prediction with the following JSON payload:
```
{
"year": 2024,
"month": 1
}
```