dpirrott/BlocklyML

BlocklyML is a simple visual programming Tool for python and ML. 🧩 🖥️

Blockly ML

BlocklyML is a No Code training ground for python and Machine Learning. This tool is designed to simplify standard machine learning implementation. This tool can assist anyone who wants to start with Machine Learning or python. This is a forked project from Blockly and adapted for machine learning and Data analytics use-cases. 🧠

For a sample run go to sampleLayouts folder upload and try it out 😃

Read the for further info

In the Example given below we will train a random forest for Iris Dataset

blocklyML_demo.mp4

Table of contents

• Table of contents
• Installing as BlocklyML App
  • Flask Method
• UI Features
  • Shortcuts
  • Dataframe Viewer
  • Download Code
• Contribute
  • This repo welcomes any kind of contributions 🙏
• License
• Thanks to

Installing as BlocklyML App

First clone this repo

git clone https://github.com/chekoduadarsh/BlocklyML

After cloning the repo you can either follow the Flask Method

Running the App Using Docker

If you've cloned the project and want to build the image, follow these steps:

1.Open your terminal and navigate to the project directory.

2.Run the following command to build the Docker image:

docker build . -t blocklyml/demo

Once the image is built, you can launch the app by executing the following command:

docker run -ti -p5000:5000 blockly_ml/demo

This will start the app, and you'll be able to access it by opening your web browser and navigating to http://localhost:5000

Flask Method

Install the requirements from requirements.txt with the following command

pip install -r requirements.txt 

then you can run the application by

python app.py

Simple as that 🤷‍♂️

UI Features

Shortcuts

You can find these buttons in the top right corner of the application. Their functionality as follows

1. Download XML Layout
2. Upload XML layout
3. Copy Code
4. Launch Google Colab
5. Delete
6. Run (Not Supported Yet!!)

Dataframe Viewer

Blockly support complete html view of the DataFrame. This can be accessed by view option in the navigation bar

Download Code

Blockly support both .py and .ipynb formats. You can download the code from the download option in the navigation bar

Contribute

If you find any error or need support please raise a issue. If you think you can add a feature, or help solve a bug please raise a PR

This repo welcomes any kind of contributions 🙏

Feel free to adapt it criticize it and support it the way you like!!

Read : CONTRIBUTING.md

License

Apache License, Version 2.0

Thanks to