https://github.com/danielwohlr/delivery_time_series

Time series forecasting of food delivery service data
https://github.com/danielwohlr/delivery_time_series

forecasting-time-series python scikit-learn

Last synced: 3 days ago
JSON representation

Time series forecasting of food delivery service data

• Host: GitHub
• URL: https://github.com/danielwohlr/delivery_time_series
• Owner: Danielwohlr
• Created: 2025-02-10T08:15:21.000Z (11 days ago)
• Default Branch: main
• Last Pushed: 2025-02-16T14:19:10.000Z (4 days ago)
• Last Synced: 2025-02-16T15:28:37.173Z (4 days ago)
• Topics: forecasting-time-series, python, scikit-learn
• Language: Python
• Homepage:
• Size: 260 KB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# food_delivery_ts



    



Presentation is in reports/presentation.pdf.

Installation instructions: 

Being in the root of this project, run

```conda env create -f environment.yml``` in your terminal to create a conda environment.

Then activate it and run, e.g. src/modeling/evaluate.py or src/modeling/qual_analysis.py, for running the experiments.

## Project Organization

```

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

├── data                <- The original, immutable data dump.

├── pyproject.toml     <- Project configuration file with package metadata for 

│                         food_delivery_ts and configuration for tools like black

│

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

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

│

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

    │

    ├── config.py               <- Store useful variables and configuration

    │

    ├── features.py             <- Code to create features for modeling

    └── plots.py                <- Code to create some visualizations

    ├── modeling                

    │   ├── __init__.py 

    │   ├── evaluate.py          <- Compute CrossValidation Losses

    │   └── qual_analysis.py            <- Qualitative Analysis, e.g. Analysis predicted values, Residual analysis, Feature Importance

    │

    ├── models                  <- Modules with all Prediction models definitions                

        ├── ewm.py              <- benchmark ewm

        ├── hgbr.py             <- Gradient Boosting Regression Tree

        ├── regression.py        <- All Implementations of Linear Regression Pipelines

```

--------