Skip to main content

Kaggle's informative Tutorial

By
Greetings,

I would like to declare that this is just an Informative post. No promotion of site or any of its partner is done here. Would share this kind of platforms regularly with everyone so one can code online & learn. 

Today we will see how to use kaggle.

What is kaggle? Well it is an site where MNCs host competitions to find solutions of their problems based on ML & AI. Also it is one of the best platforms to learn Python, R, Machine Learning & many more stuffs. It has its own coding environment like Jupyter Notebooks, Which is known as Kernel. This kernel supports both R & Python. In this kernels you can code freely and develop your own code & run it there itself as it gives 14gb RAM & 5.2gb GPU for each session.

Let's see how we can leverage power of kaggle for learning.

You need to make account first which only require an active E-Mail id. Then after signing in. You will see dashboard like this.

My Kaggle Newsfeed

Competitions

Many competitions in kaggle gives Money Prices, Some are for knowledge & some may also result in recruiting. But most of the time we get to learn things from other Data scientiests. I would suggest you to enter competitions which are focused on knowledge. 

How to take part in it?

If you want to take part in one of them. Then click it read the description & then if you find it interesting then join it. Then after you can download dataset and work on it.   

Tips & Tricks

If you are new to this, then first go to discussion forum of that competition & study the blog posts by users for that competition. They share the basic understanding of dataset, few codes, guides etc. It will be beneficial to use those helps & carve your way out.

Datasets 

Kaggle is one of the sites where you can find datasets for your machine learning projects. Generally they are in csv formate but one can also get other formates too. I personally use kaggle datasets frequently. 
 

Kaggle datasets. Almost 14k datsets including images, text corpuses, etc.
You can find & use your desired datsets from here for free. It has a very reach library for it. 

Kernels

Kernels are the place where you will code. This part of blog is important because of kernel's high performance & better results. Plus its FREE!!!

Well it looks like this 


Output Look of kernel after running. This will be seen by other users.

The real interactive session of kernel. Looks same like jupyter notebook environment. Also it is version controlled.
This kernel will run on cloud & process the output until 6 hours. Then session will be closed. 

Learning

Kaggle also provides free learning courses solely on its cloud. One can learn about subjects listed in its site. All we need is to go in learn menu & start learning. 

Kaggle Learn Dashboard

Its free of cost & i would recommend everyone to take part in it & start learning. 

That's all for now. See you later.!!


 

Comments

Post a Comment

Popular posts from this blog

How to choose Machine Learning model for your problem ??

By
Greetings fellas, Here we will discuss the above mentioned question.   Machine learning is part art and part science. When you look at machine learning algorithms, there is no one solution or one approach that fits all. There are several factors that can affect your decision to choose a machine learning algorithm. Some problems are very specific and require a unique approach. E.g. if you look at a recommender system, it’s a very common type of machine learning algorithm and it solves a very specific kind of problem. While some other problems are very open and need a trial & error approach. Supervised learning, classification and regression etc. are very open. They could be used in anomaly detection, or they could be used to build more general sorts of predictive models. Understand Your Data The type and kind of data we have plays a key role in deciding which algorithm to use. Some algorithms can work with smaller sample sets while others require ton
1 comment
Read more

Requirements for learning ML

By
Greetings guys, Recently we saw that what is machine learning & why we need it this days. Well we would like to know now that how to start coding & using ML for learning & business purposes. Here in this post we will learn basic requirements for learning ML. For starters we will require Python & Mathematics. But here we will focus on Python because not everyone wants to learn math in beginning. Tho one needs to have math background for better understanding. Yet i will have some lectures where in we will cover math but one can skip them if they don't want to do it. I would highly recommend that they see math irrespective of time. This is my GitHub link :- Basics of Python This file contains basics necessary to get used to with Python. If you want to test or practice code then download file & use Jupyter Notebook to run it. We will be using 2 different IDEs. Jupyter Notebooks Spyder Why 2 IDEs?? Because both have different environments. Jupyter Note
Post a Comment
Read more