In this repository, a forecasting model's API is created using the Facebook Prophet model for forecasting Dhaka's temperature. The model is trained using the Open-Meteo weather API. The model can predict the temperature in Dhaka, Bangladesh, for a given date.
Using the Weather API I am collecting data from 01 Jan 2023 to 31 May 2023. Here only temperature data is collecting at 120 meters above ground. The website can be found here.
Here I used a famous forecasting model named prophet. Prophet is a procedure for forecasting time series data based on an additive model where non-linear trends are fit with yearly, weekly, and daily seasonality, plus holiday effects. It works best with time series that have strong seasonal effects and several seasons of historical data. Prophet is robust to missing data and shifts in the trend, and typically handles outliers well.
Prophet is open source software released by Facebook's Core Data Science team. It is available for download on CRAN and PyPI. The models documentation can be found here.
First clone the github repo in your local or server machine by following:
git clone https://github.com/rahatkader/Dhaka-Weather-Forecasting.git
Change the working directory to project root directory. Use Pip to create a new environment and install dependencies from requirement.txt file. The following command will install the packages according to the configuration file requirement.txt.
pip install -r requirements.txt
Now run mlapi.py
python mlapi.py
After that open your browser and go to http://127.0.0.1:8000/docs link. Then follow the below steps:
