So, you already know about the types of machine learning. The next question is how to learn machine learning? What’s the tools to do machine learning? Here are the three things you need to know to learn machine learning (especially if you don’t have an IT background like me).
1. Python (Programming Language)
The first thing to do is learn a programming language. Programming language is like the first thing you need to know to start your machine learning journey. Programming language i highly recommend for machine learning is python. Python is a high-level programming language. That means python can be read easily and similar to a human language. Python also an open source language. This means that python package can be made from people all over the world. This makes python more rich in package about machine learning. The more people use python, the more people develop packages for any kind of programming, include machine learning. Python is one of the most popular programming language in the world.
There’s a lot of site or course you can take to learn python. I use udemy to learn python for the first time. I choose udemy because the course cost is not that expensive and the explanation is depth. A little tips to use udemy is you purchase udemy course when it’s discount. The discount is often occur.
2. Anaconda
To build your machine learning model, you need a place to code. My recommendation for a place to code is jupyter notebook. You can install jupyter notebook through anaconda. Anaconda is a free and open-source distribution of the Python programming languages for something like data science, machine learning applications, etc. Anaconda contain python, jupyter notebook, and many other application. So, Anaconda is a bundle of tools you need to start machine learning. You can download Anaconda from here.
3. Pandas and Matplotlib
Pandas is one of python library. Pandas is stands for Python Data Analysis Library. Pandas is useful for analyzed a data. Pandas can clean a data and give a statistical insight from data. When we build a machine learning model, we have to know about the data. When we know about the data, we can perfect our model. That way, the model can predict more accurately.
Matplotlib is one of python library. Matplotlib is useful to visualize the data. When we build a machine learning model, we have to know what the data insight is. Sometimes is better to look at graph than a table to know a data. That’s why we use Matplotlib to see the visualization of a data.
4. Scikit-learn
Scikit-learn is very powerful and widely use for machine learning python. When you want to build a model machine learning, you have to use scikit-learn. Scikit-learn is use to build the model. It can split the data, make a pipeline, and train a model. The depth explanation to use scikit-learn is in the next part. All you need to know is scikit-learn is very useful for machine learning python.
That’s it! That’s all you need to know to start machine learning.
If you like this kind of content, please let me know! You can find me on instagram @jeffsabarman.
