Although both are rooted in statistics, Data Science or Data Mining and ML are very different fields even if they might share some concepts and methods.

I did different courses for each in University. Data Science is concerned with extracting patterns from existing data.

Like you have some papers for exam and you want to know if students cheated. Or you have the results from a poll about people hobbies, income etc and you want to correlate that with voting for party X. Or you want to correlate the race of canines with their abilities.

ML is also mostly about patterns but in a different way. You want something to tell how likely a comment is spam, if an article is positive towards a politician, if a picture is of a cat or dog.

So, to get to get a fundamental understanding you will need to learn statistics. Which in turn will require some calculus and algebra, but nothing too difficult.

Although I have the basic math knowledge and I have the basic knowledge of ML and Data Mining, I quit trying to do things in those fields because they are really vast, especially ML. Knowing the math and the basics of ML is required but far, far from enough to get good results. The people who work in the field are focused on it. I like ML but I like software architecture and development more, so I did my choice.

That being said, I still got some benefits from basic ML knowledge when I used ML libraries such as ML.NET in my day job. Knowing what a SVM or random forest is and how to tune parameters to improve my model was helpful. It was just a simple usage case like suggesting to customers what they might want to acquire based on their past purchases.

Honestly, I almost never need Statistics.

More than basic notations and explanatory parts of research papers, I never need even iota of Statistics.

When you need to learn something specific, like, say, KL divergence, if your math is solid, then you can pick it up in 10 minutes.