Skip to content

OneMetric+ project for analytical tool on demand forecast and outlier detection

License

Notifications You must be signed in to change notification settings

jpcadena/onemetric-plus

Repository files navigation

onemetric-plus


Logo

Onemetric plus

Onemetric plus
Explore the docs »

Table of Contents
  1. About The Project
  2. Getting Started
  3. Usage
  4. Testing
  5. Contributing
  6. Security
  7. Code of Conduct
  8. License
  9. Contact

Project

About the Project

This project is dedicated to developing a sophisticated analytical tool for "ABC" to dynamically monitor and forecast store credit demands. This state-of-the-art system harnesses the power of machine learning and real-time streaming to identify and analyze unusual sales peaks, seasonal outliers, unforeseen events, and store-specific outliers.

The project encompasses several pivotal stages:

  • Real-time Data Streaming: Capturing data in real-time to transform each moment into actionable insights.
  • Data Processing: Incorporating continuous data, refining it for subsequent stages.
  • Anomaly Detection: Identifying unusual peaks in sales and other outliers which significantly affect the store credit demand.
  • Seasonality Analysis: Recognizing patterns corresponding to holidays, festivals, or peak shopping periods.
  • Event Recognition: Discerning unexpected external events such as concerts or sports that could influence credit demand.
  • Store-specific Analysis: Zoning in on specific store behavior that can provide a wealth of localized insights.

Crafted with precision, this system offers invaluable information about successful sales initiatives, allowing "ABC" and its affiliate stores to replicate and innovate their credit management strategies. The solution emphasizes adaptability, ensuring that the stores can promptly cater to increased demand, especially during unforeseen events or peak periods.

With its strategic blend of modern technology and analytical prowess, this project is a beacon for retailers, data analysts, and organizations aiming to transform raw data into meaningful, actionable strategies. Its holistic approach reaffirms its adaptability across multiple domains, making it an epitome of innovation and efficiency in the world of data analytics.

(back to top)

Built with

Python Pandas TensorFlow PyTorch numpy scikit-learn Pydantic Pytest isort Black Ruff MyPypre-commit GitHub Actions Pycharm Visual Studio Code Markdown License: MIT

(back to top)

Getting started

Prerequisites

  1. Clone the repository
    git clone https://github.com/jpcadena/onemetric-plus.git
    
  2. Change the directory to root project
    cd onemetric-plus
    
  3. Install Poetry package manager
    pip install poetry
    
  4. Install the project's dependencies
    poetry install
    
  5. Activate the environment
    poetry shell
    

(back to top)

Usage

  1. Setting up environment variables:

    If you find a .env.sample in the project directory, make a copy of it and rename to .env.

    cp .env.sample .env
    
  2. Configuring your credentials:

    Open the .env file in a text editor and replace the placeholder values with your actual credentials.

    # .env file
    POSTGRES_USER=your_database_user
    SECRET_KEY=your_api_key
    
  3. Execute with console

    python main.py
    

(back to top)

Testing

  1. Running tests:

    To run all tests, you can simply run the following command in the root directory of the project:

    pytest
    
  2. Running a specific test:

    If you want to run a specific test, you can do so by specifying the file and test name. For example, the following command will only run the test_get_users test in the test_main.py file:

    pytest tests/test_main.py::test_get_users
    
  3. Understanding test results:

    Pytest will provide a summary of the test results in the console. It will tell you how many tests passed and how many failed. For each failed test, Pytest will provide a detailed error message that can help you identify what went wrong.

  4. Writing new tests:

    When you add new features to the application, you should also write corresponding test cases. Each test case should be a function that starts with the word 'test'. Inside the function, you can use assert statements to check that your code is working as expected. For example:

    def test_add_user():
        user = add_user("testuser", "testpass")
        assert user.name == "testuser"
        assert user.password == "testpass"

    This function tests that the add_user function correctly creates a new user with the given name and password.

Remember to update your tests whenever you update your code. Maintaining a comprehensive test suite will help ensure the reliability and robustness of your application.

(back to top)

Contributing

GitHub

Please read our contributing guide for details on our code of conduct, and the process for submitting pull requests to us.

(back to top)

Security

For security considerations and best practices, please refer to our Security Guide for a detailed guide.

(back to top)

Code of Conduct

We enforce a code of conduct for all maintainers and contributors. Please read our Code of Conduct to understand the expectations before making any contributions.

(back to top)

License

Distributed under the MIT License. See LICENSE for more information.

(back to top)

Contact

  • LinkedIn

  • Outlook

(back to top)