[Renewal] First-time Python Machine Learning Bootcamp (Easy! Solving Real Kaggle Problems) [Data Analysis/Science Part2]

This lecture is currently being used as an official in-house Python machine learning training course by one of the actual Nekarakubae companies.

• Machine learning/AI technology is a very broad subject, as it has complex concepts and various techniques for applying to real-world problems.
• When you first learn it, you should learn the basics of machine learning, concepts that you absolutely must learn, and techniques that can be applied to real problems in an appropriate combination.
• If you get a feel for machine learning technology based on this, you can learn artificial intelligence technology based on this.
• The more theories and complex the technology, the more you need to build them up, focusing on the essential parts, to be able to utilize them.

• Rather than focusing too much on deep principles like math/statistics or listing out old techniques that you won't even use,
• It is structured so that you can learn the essential concepts and key techniques to apply to real-world problems by solving real-world problems.
• There are various techniques that can be applied to real-world problems. To help you learn them, we will learn various machine learning techniques through real-world problems.
• This is a famous problem with the most abundant data, and you will learn various techniques that can be applied in practice, and various techniques that can be considered when actually using machine learning.
• We will solve the entire machine learning process by downloading data, making predictions, and submitting the final data prediction problem from the Kaggle site, which is most famous for data prediction problems.

This is the part that the instructor was frustrated with a long time ago. First, learn how to apply machine learning techniques based on real problems.
Even if you understand the basic concepts of machine learning, the reason it is difficult to apply them to real-world problems is because there are various techniques used when applying them to real-world problems.
If you follow various techniques that can be applied to real problems at the code level and listen to explanations of related concepts that require understanding whenever needed, you can utilize the entire process lightly.

By familiarizing yourself with the relevant technologies, you can understand and even utilize the overall machine learning technology in a short period of time.

If you can only use Python, you can take the course. If you can use pandas and visualization techniques, you can.
For those who are not familiar with the relevant technology, we provide a data analysis/science roadmap to help you learn systematically, taking into account the level of difficulty.
In particular, if you take this course together with the Beginner Python Data Analysis course in the Data Analysis/Science Roadmap explained at the bottom of this page, you can sequentially learn techniques for handling data with Python.

The data field has various theories and technologies, so if you approach it wrong, it can be difficult to learn even if it takes a long time. I have failed many times. However, if you learn by focusing on core technologies, it can be easier than you think.

Divide the core data-related technologies into data collection, storage, analysis, and prediction tasks, and learn the related technologies sequentially. If you build knowledge of each business field (called domain knowledge), you can gain competitiveness. In this regard, we have created a data analysis/science roadmap so that you can learn the core data-related technologies sequentially with increasing difficulty. You can also check the related roadmap at the bottom of this page.

These are proven courses that many people have studied for years and have given very good feedback on.

If you can do Python, it's not difficult!
When learning machine learning for the first time, the most difficult part is studying mathematics, statistics, and probability to understand the related theory . Even if an instructor who has studied related technology for decades explains it easily, it takes a very long time for someone to learn it.

Rather than delving deep into related theories and deep mathematical principles, try to understand the concepts lightly and learn how to write machine learning codes with real problems. Rather than aiming for the top 1% from the beginning, first aim for the top 20% of data predictions and learn how to write codes and techniques that can be applied to real problems. If you understand the concepts enough to understand and actually apply machine learning codes, you will become familiar with it, and if you only learn the theory, you will be able to understand and utilize machine learning technology that was vague.

This lecture is also structured so that you can learn step by step by applying it one by one based on actual Kaggle problems and data.

• There is a big difference between learning how to use each machine learning method and the code and steps required to solve real problems.
• We will go through the steps of how to analyze, process, and predict real data.
• And we explain the technology that needs to be understood at each step. We even submit the prediction results.
• So, instead of getting tired of just learning the theory, I designed it so that you can also understand how to apply it in practice.

This course is for beginners, so we aim to cover the top 20% of essential skills!

This lecture serves as a starting point for those who are learning machine learning for the first time.
With on-the-job experience and well-organized materials and examples, even the instructor is learning it for the first time!
So that even beginners can apply machine learning technology to the top 20% in a short period of time!

It's fun to apply it to real problems, and it's really great when the prediction results are good! I hope to share the fun of machine learning with reasonable and good people.

There is an abundance of data and information.
After listening to the lecture, which explains in detail with a summary that allows you to understand only the essential parts,
After that, whenever you think, 'Oh! There was something like this?', you can immediately understand it by just looking at the data.

So that you can understand and utilize the relevant topic
Materials written concisely and with only the essential parts
And, actual problem machine learning application code files

• The test code is provided in a format that allows for code testing (Jupyter Notebook format), and the basic theory is provided as a PDF file.
• We provide PDF materials related to machine learning so that you can check them at any time like an ebook . (However, copying and downloading of related materials is restricted due to copyright issues.)