Skip to content

ChaitanyaSaik/Intelligent-AutoML-Engine-for-End-to-End-Data-Analysis-Predictive-Modeling

Repository files navigation

Intelligent AutoML Engine for End-to-End Data Analysis & Predictive Modeling

Timeline: September 2024 – December 2024
Tech Stack: Streamlit · Python · Scikit-learn · TensorFlow/Keras · Pandas · NumPy · MongoDB

An end-to-end ML & DL workflow automation platform built with Streamlit that empowers users to train, evaluate, visualize, and deploy machine learning models seamlessly — without writing code. It supports classification, regression, and clustering tasks, making model experimentation and insight generation accessible for both technical and non-technical users.


🌟 Key Features

  • 🔧 Interactive Workflow UI via Streamlit
  • 🤖 Supports Classical ML (Scikit-learn) and Deep Learning (TensorFlow/Keras) models
  • 📊 Real-time Data Visualization and Metric Reports
  • 🧠 Train models for:
    • Classification (Logistic Regression, Random Forest, DNN)
    • Regression (Linear Regression, SVR, DNN)
    • Clustering (K-Means, DBSCAN)
  • 📁 Upload your dataset (CSV format)
  • 🔍 Data Preprocessing pipeline (null handling, encoding, scaling)
  • 📈 Model Evaluation (confusion matrix, accuracy, MSE, silhouette score, etc.)
  • 💾 MongoDB for storing model performance metadata & logs
  • 🚀 Model deployment-ready interface with experiment tracking

🚀 Getting Started

1. Clone the Repository

git clone https://github.com/your-username/automl-streamlit-app.git
cd automl-streamlit-app
  1. Install Dependencies
pip install -r requirements.txt
  1. Launch the App
streamlit run app.py

🛠️ ML/DL Models Used Task Algorithms Used Classification Logistic Regression, Random Forest, SVM, KNN, Deep Neural Network (Keras) Regression Linear Regression, Decision Tree Regressor, SVR, DNN Regressor (Keras) Clustering KMeans, DBSCAN, Hierarchical Clustering


💡 Sample Use Case Flow Upload Dataset

Data Preview & Clean

Choose ML/DL Task: Classification / Regression / Clustering

Train Model (customize hyperparameters)

Evaluate & Visualize Results

Save and Log Model Info in MongoDB


📦 MongoDB Integration Stores experiment metadata:

Model type

Accuracy / Loss

Hyperparameters

Timestamp

Easily retrieve past experiment logs for reproducibility and tracking

About

An end-to-end ML & DL workflow automation platform built with Streamlit that empowers users to train, evaluate, visualize, and deploy machine learning models seamlessly — without writing code. It supports classification, regression, and clustering tasks, making model experimentation etc

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages