How to get started with Data Science the right way

Original article was published on Deep Learning on Medium

How to get started with Data Science the right way

This blog tells you how to get started with data science the right way. Just follow these steps and at the end you will learn how to build machine learning and deep learning models. You will also learn how to deploy these models using docker, and then finally deploy them on the web using Heroku.

Step 1

Do an an introductory ml course like IBM data science specialization. after this you will learn how to collect data, data cleaning, data pre-processing and making machine learning models.

Step 2 : Deploying model

After completing the basic course and learning how to build machine learning models watch this complete playlist. after watching this playlist you will be able to deploy a machine learning model using flask inside a docker container.

Step 3 : Deploy the model on the web

After learning how to deploy model in a docker container, watch this video to learn how to deploy this model to the web.

What’s next?

Till now you should be able to build an end to end machine learning app.

Now all you need to do is refine your knowledge and gain a deeper understanding of how machine learning and deep learning works. Here are the stuff you can do which will take you to the next level.

Take Deep Learning Specialization

This specialization will teach you machine learning from the zeroth level, you will be able to understand why models work.

Take Advanced Machine Learning Specialization

Do this specialization to learn how professionals approach to a problem. You will learn lots of great techniques for a data science project.

Participate in Kaggle competitions

Participating in data science competitions will allow you to test your knowledge.

Implement Research papers.

It is one of the better ideas for personal projects, you can take a research paper and then replicate it.

That’s it, after following this path not only you will know how to make machine learning or deep learning models but also how to deploy them on the web.