Skip to content

make prediction how many comodition per ton for one of kind food production in Yogyakarta.

License

Notifications You must be signed in to change notification settings

BangkitProjectYOG4/Yogyakarta-Food-Production-Prediction

Repository files navigation

Yogyakarta-Food-Production-Prediction

This Repository is about build Regression model to try predict values of Rice Production commodity in tons from Some years before (Respectively) using Keras(Tensorflow) Sequence modeling.

Dataset

We got the dataset from 'Produksi Pertanian Indonesia BPS'. From all dataset on that folder, we used Padi.csv (Rice Production dataset) as data to make regression model. The datset contains commodity values for rice and other commodity each year from 1993 until 2015, in all Province in Indonesia. Have 24 columns where 23 of them provide the commodity values from each year (in tons, as integer) and 1 column gives the info about their respective province (in string). The number of rows represent the number of provinces in Indonesia, which is 34.

Prerequisites

What things you need to install some python package before you run the notebook or python code

- Tensforflow Package
- Sklearn Package
- Numpy Package
- Pandas Package
- Matplotlib Package

Contents

  1. Folder data (it's contain dataset Indonesia food production from 1993 until 2015 provided by BPS such as Corn, Rice, Soy, and etc.)
  2. Folder model (it's contain Regression model with trained weights from modeling in Modeling notebook)
  3. Folder Plot (it's contain MAE and MSE result during train and validation process also Regression and Prediction graph of Rice Prodcution)
  4. Modeling Notebook
  5. Model Python file
*Note : 
- Modeling we used is [Final Model](https://github.com/BangkitProjectYOG4/Yogyakarta-Food-Production-Prediction/blob/master/Final_regression_model.ipynb)
- Model Python file (main.py) is same model and workflow as Final Model, but we not update it until final model like Final_regression_model.ipynb
- preprocessing.py is very necessery file to proceed raw dataset of Padi.csv (Rice Production dataset) to dataset that can be used to make regression model in modeling file. 

License

This project is licensed under the MIT License - see the LICENSE file for details

Authors

About

make prediction how many comodition per ton for one of kind food production in Yogyakarta.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 3

  •  
  •  
  •