Hey, there!
Are you exhausted by writing lines of code for treating missing values? by searching and implementing packages in your code & finding algorithms to train your model?
Here’s something interesting which makes your work easily without any code...
Azure provides various tools for this, alongside its pre-built, pre-trained, customizable models. The Designer lets you work with your existing data with a set of visual design tools and drag-and-drop controls.
Configuring a machine learning workspace
Your workspace contains tools for developing and managing ML models, from design & training to managing the compute & storage. It also helps in labeling & valuing Training Data. You can:
Work with the Azure ML Python SDK in a Jupyter-style notebook
Use Azure ML’s automated training tools
Use the low-code drag-and-drop Designer surface.
Using Azure ML Designer to create a model
The Designer is the quickest way to start with custom ML, as it gives you access to a set of prebuilt modules that can be chained together to make an ML API that’s ready to use in your code.
Create a canvas for your ML pipeline
Setup the compute target for your pipeline
Using data in Azure ML Designer
Once data has been processed,
Start to choose the modules you want to train your model.
The tool provides a set of common algorithms and tools for splitting data sets, training, and testing.
The resulting models can be scored using another module once you run them through training.
Scores are passed to an evaluation module so you can see how well your algorithm operated.
You do need some statistical knowledge to interpret the results to understand the types of errors generated, though in practice, the smaller the error value, the better. You don’t need to use the prepared algorithms, as you can bring in your Python and R code, as needed.
Publish your pipelines(train/inference) to a REST pipeline endpoint to submit a new pipeline that runs with different parameters and datasets.
Deploy a real-time inference pipeline to a real-time endpoint to make predictions on new data in real-time.
To conclude, Azure ML Designer is a great No-code tool to work with data & build models, to deploy & use the trained models on new parameters. Take a look at the list of assets provided by the tool: Cheatsheet .
Comentários