https://github.com/OthmanMohammad/ML-AutoTrainer-Engine

ML AutoTrainer Engine, developed using Streamlit, is an advanced app designed to automate the machine learning workflow. It provides a user-friendly platform for data processing, model training, and prediction, enabling a seamless, code-free interaction for machine learning tasks.
https://github.com/OthmanMohammad/ML-AutoTrainer-Engine

auto-ml machine-learning-pipelines python streamlit web-app

Last synced: 11 months ago
JSON representation

ML AutoTrainer Engine, developed using Streamlit, is an advanced app designed to automate the machine learning workflow. It provides a user-friendly platform for data processing, model training, and prediction, enabling a seamless, code-free interaction for machine learning tasks.

• Host: GitHub
• URL: https://github.com/OthmanMohammad/ML-AutoTrainer-Engine
• Owner: OthmanMohammad
• Created: 2023-11-07T07:34:02.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2023-12-05T11:35:16.000Z (over 2 years ago)
• Last Synced: 2024-08-08T01:56:41.772Z (almost 2 years ago)
• Topics: auto-ml, machine-learning-pipelines, python, streamlit, web-app
• Language: Python
• Homepage:
• Size: 319 KB
• Stars: 2
• Watchers: 3
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# ML AutoTrainer Engine

## Introduction

ML AutoTrainer Engine, developed using Streamlit, is an advanced app designed to automate the machine learning workflow. It provides a user-friendly platform for data processing, model training, and prediction, enabling a seamless, code-free interaction for machine learning tasks.

## Core Features

- **Model Predictions with Streamlit Integration**: Employs Streamlit's interactive environment for effortless model predictions. This feature includes a robust error-handling framework and a CSV download option for prediction results.

- **Data Processing Pipeline Design**: Implements `DataProcessingPipeline`, a highly modular and configurable class that addresses a wide range of data preprocessing needs. This design ensures scalability and ease of maintenance.

- **Persistent Model State Management**: Offers mechanisms for saving and loading machine learning models, enhancing model management and reducing the frequency of retraining.

- **Dynamic Project Infrastructure**: Manages project-specific data and resources in isolated environments, facilitating an organized and scalable framework.

- **Model Export Capabilities**: Enables the export of trained models in a universal format (.pkl), aiding in model sharing and deployment across various platforms.

- **Advanced Feature Extraction Techniques**: Integrates sophisticated feature extraction methods, including PCA, ICA, and LDA, to boost analytical capabilities and improve model accuracy.

- **Versatile Model Training Framework**: Supports an extensive range of machine learning algorithms for both classification and regression tasks, complete with a detailed evaluation of performance metrics. This approach allows for flexible algorithm selection and effective performance analysis.

- **Enhanced Data Filtering System**: Features a comprehensive data filtering mechanism, allowing for the definition of intricate filtering conditions to ensure precise and effective data analysis.

## Screenshots

### 1. Creating and Selecting Projects

![Creating and Selecting Projects](screenshots/Creating%20and%20Selecting%20a%20Project.png)

### 2. Uploading Data

![Uploading Data](screenshots/Uploading%20Data.png)

### 3. Core Functions of the App

![Core Functions - Data Processing, Training Models, Predictions](screenshots/Core%20Functions.png)