This Streamlit app simplifies your ML workflow by combining automated EDA with Pandas Profiling, interactive visualizations through Pygwalker, and AutoML-based classification modeling using PyCaret - all in one place.

Clone the repository.

Install the required packages by running the following command:

Note: It is recommended to create a virtual environment before installing the dependencies.

Upload your CSV dataset in the "Generate Report" section.

Use the sidebar navigation to switch between different functionalities:

Click on the Generate Report option in the sidebar.

Upload your dataset (CSV format) using the file uploader. The uploaded data will be displayed.

Click the Generate Profile Report button.

A progress indicator will show the status while the automated EDA report is generated using ydata-profiling.

The comprehensive report will be displayed within the app once completed.

Select the Visualization option in the sidebar.

If a dataset has been uploaded, an interactive Pygwalker interface will appear, allowing you to create various visualizations by dragging and dropping fields.

The visualization interface utilizes the full page width for a better experience.

Select the Model Builder option in the sidebar.

If a dataset has been uploaded, you can perform automated machine learning for classification tasks using PyCaret.

Select the target variable (the column you want to predict) from the dropdown menu.

Click the Train Models button. PyCaret will automatically:

The results and the name of the best model (.pkl file) will be displayed.

A Download Best Model button will become active, allowing you to save the trained model file locally.

Note: Make sure to replace "logo.png" with your own logo file in the app.py code if desired.

This project can be deployed using Streamlit, a powerful Python library for building interactive web applications. Follow the steps below to deploy the project on a server or cloud platform.

To find more information about deploying an app, click here.