https://github.com/wgierke/informaticup2018

Predicting the optimal strategy for fueling for a given route
https://github.com/wgierke/informaticup2018

convolutional-neural-networks fbprophet forcasting informaticup machine-learning prediction recurrent-neural-networks tensorflow timeseries-analysis

Last synced: 7 days ago
JSON representation

Predicting the optimal strategy for fueling for a given route

• Host: GitHub
• URL: https://github.com/wgierke/informaticup2018
• Owner: WGierke
• License: mit
• Created: 2017-11-24T08:03:53.000Z (about 7 years ago)
• Default Branch: master
• Last Pushed: 2022-12-07T23:45:21.000Z (about 2 years ago)
• Last Synced: 2024-10-29T09:54:38.605Z (2 months ago)
• Topics: convolutional-neural-networks, fbprophet, forcasting, informaticup, machine-learning, prediction, recurrent-neural-networks, tensorflow, timeseries-analysis
• Language: Jupyter Notebook
• Homepage: http://tofill.dyndns.info:7080
• Size: 17.3 MB
• Stars: 1
• Watchers: 4
• Forks: 1
• Open Issues: 36
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
informatiCup2018 [![CircleCI](https://circleci.com/gh/WGierke/informatiCup2018.svg?style=svg&circle-token=00f4e65f31b3192e58b793d0282ba0af8c009b44)](https://circleci.com/gh/WGierke/informatiCup2018)

==============================

Predicting the optimal strategy for fueling for a given route ([task description](https://github.com/WGierke/informatiCup2018/blob/master/references/Intellitank.pdf)).

[Report](https://github.com/WGierke/informatiCup2018/blob/master/reports/informaticup2018.pdf)  

[Routes](https://github.com/WGierke/informatiCup2018/tree/master/routes)

Project Organization

------------

    ├── LICENSE

    ├── README.md          <- The top-level README for developers using this project.

    ├── data

    │   ├── external       <- Data from third party sources.

    │   ├── processed      <- The final, canonical data sets for modeling.

    │   └── raw            <- The original, immutable data dump.

    │

    ├── models             <- Trained and serialized models, model predictions, or model summaries

    │

    ├── notebooks          <- Jupyter notebooks. Naming convention is a number (for ordering),

    │                         the creator's initials, and a short `-` delimited description, e.g.

    │                         `1.0-jqp-initial-data-exploration`.

    │

    ├── references         <- Data dictionaries, manuals, and all other explanatory materials.

    │

    ├── reports            <- Generated analysis as HTML, PDF, LaTeX, etc.

    │   └── figures        <- Generated graphics and figures to be used in reporting

    │

    ├── requirements.txt   <- The requirements file for reproducing the analysis environment, e.g.

    │                         generated with `pip freeze > requirements.txt`

    │

    └── src                <- Source code for use in this project.

        ├── __init__.py    <- Makes src a Python module

        │

        ├── features       <- Scripts to turn raw data into features for modeling

        │   └── build_features.py

        │

        ├── models         <- Scripts to train models and then use trained models to make

        │   │                 predictions

        │   ├── predict_model.py

        │   └── train_model.py

        │

        └── visualization  <- Scripts to create exploratory and results oriented visualizations

            └── visualize.py

--------

### Setup

- Clone the repository including submodules (to include the challenge data as well):  

`git clone --recursive [email protected]:WGierke/informatiCup2018.git`  

However, if you already downloaded the [InformatiCup2018 repository](https://github.com/InformatiCup/InformatiCup2018), you can also create a symbolic link that shows from `data/raw/input_data` to the informatiCup2018 repository. A sanity check would be that `data/raw/input_data/Eingabedaten/Fahrzeugrouten/Bertha\ Benz\ Memorial\ Route.csv` is accessible.

- Install all dependencies  

`pip3 install -r requirements.txt`  

### Usage

- To start the server:  

`python3 src/serving/server.py`  

- To predict the gas prices given using training data up to a specified point in time for a given point in time:  

`python3 src/serving/price_prediction.py --input PATH_TO_PREDICTION_POINTS.CSV`

- To predict an optimal route given the path to an input file:  

`python3 src/serving/route_prediction.py --input PATH_TO_ROUTE.CSV`

### Credits

[Materialize](http://materializecss.com/)  

[bootstrap-material-datetimepicker](https://github.com/T00rk/bootstrap-material-datetimepicker)