Learning R if You Already Know Statistics

By Ruben Winastwan, Data Science Enthusiast

An Introduction: My Background

It was in 2016 where I started my journey to pursue my Master'south Degree in Computational Mechanics straight away afterwards I finished my Available'due south Degree in Mechanical Engineering. Dorsum then, I had express programming knowledge, let alone knowing what data science and machine learning are.

The boot-start matter occurred when I got a classic Computer Vision project during my Chief's written report, where I need to build object detection and object tracking algorithm using Python, C++, and OpenCV. That project really forced me to learn nigh Python and C++ the hard way as well as how to write a clean lawmaking properly.

Long story short, I detect myself fascinated by the field of Calculator Vision later that leads me to this obsession: I desire to become a Computer Vision Engineer.

Just the high hopes turned into a dust afterward I read the task requirements of Computer Vision Engineer in all vacancies: They wait the candidates to know about Car Learning and Deep Learning, in particular Convolutional Neural Network (CNN).

Mutual task description for Calculator Vision Engineer

Back then, I didn't even know what motorcar learning is, let solitary CNN. Although my study programme did touch on the area of programming, math, and statistics, only we never talked about machine learning.

Afterwards some research, I found out that if you want to larn nearly CNN, you need to know almost Deep Neural Networks (DNN) in general showtime. If you want to know most DNN, you need to know about classical Neural Networks kickoff. If you want to know about Neural Networks, you need to know about automobile learning first. If y'all desire to know nigh auto learning in full general, you demand to know about the primal of data science first.

It'southward like a video game, I need to step up level-by-level until I accomplish the topics that I want. Plus, I'm a big fan of the bottom-to-top approach, hence I decided to acquire the fundamental of information science outset.

The question back and so: how can I learn about all of them when my study plan didn't offer courses related to them?

I need to learn all of them by myself.

And that's the first time I knew that Coursera existed.

Why Coursera, though?

First of all, I don't hateful to endorse Coursera in this commodity. I just observe that they are the best online learning platform for me every bit in that location are plenty of courses in data science and machine learning from reputable institutions. Plus, you lot have the choice to inspect the grade for costless and you'll notwithstanding get admission to the learning materials.

On top of that, if you really want to pursue the certificate for specialization, the overall cost for it is much cheaper compared to Udacity Nanodegree, peculiarly if you're still a educatee.

Okay, enough talk nearly information technology, let'due south bound into my learning pathway.

My Data Scientific discipline Learning Pathway

I retrieve we all agree that the hardest part of everything is ever in the starting time. Same as me when I wanted to get my hands dirty in data science. I kept asking a question: where practise I start?

After some enquiry, I finally came up with my online learning curriculum and here are the listing of courses or specializations that I took on Coursera in chronological order.

IBM Data Science

I decided that I want to start learning data science at a very basic level because I don't want to miss out some of import concepts. That's why I decided to have IBM Information Scientific discipline as my very first specialization.

You don't need to have any prior knowledge about data science, statistics, auto learning, or programming before taking this form. The very starting time course of this specialization is literally chosen'What is Data Science?'. I mean, you lot won't become any more basic than this, right?

At that place are 9 courses in this specialization. It starts with the concept and methodology of data science before delving into programming stuff with Python and SQL. Next, it introduces you to the meat of information science — Statistics, Data Analysis, Data Visualization, and Machine Learning.

Yous won't be an expert in information science after completing this specialization, every bit this specialization won't teach you each topic in peachy detail. However, information technology gave me a very good overview of information science and what should I learn adjacent.

Thanks to this specialization, I was able to create a roadmap for my data scientific discipline and machine learning online learning journey every bit follows:

• SQL
• Statistics
• Information Visualization
• Machine Learning
• Deep Learning

Which then leads me to the side by side specialization that I took.

Modern Big Data Analysis with SQL

This is a specialization offered past Cloudera which focused on utilizing SQL for Big Data analysis. In total, at that place are 3 courses in this specialization.

Every bit we already know, the amount of information nowadays is just also big to exist stored in traditional DBMS, hence knowledge and hands-on feel in dealing with data in distributed clusters are very of import. And this grade will teach you lot exactly that.

What I really like about this specialization is how hands-on it was. With the Virtual Machine from Cloudera, we take a risk to use SQL query to remember or to store data with either Apache Hive, Apache Impala, MySQL, or PostgreSQL. You can always revisit the Virtual Car even after yous finished the specialization, so you will always able to revise your SQL skills and play effectually with the information.

Don't worry if you know cipher virtually SQL, as this specialization volition teach you lot from the basics.

From Data to Insights with Google Cloud Platform

I took this grade to complement the material that I've learned from the previous specialization from Cloudera. While the specialization from Cloudera focused more on applying SQL in distributed clusters, this specialization gave me access to utilise SQL on the cloud.

This specialization volition teach you near how to remember or to store data on Google Cloud Platform (GCP) in BigQuery. Yous'll go access to play around with Google public datasets like Google analytics and implement the SQL query past yourself.

Bated from that, what I like about this specialization is that you'll learn more than merely SQL and BigQuery. You lot'll besides learn almost how to use Google Data Studio to create an interactive data visualization dashboard and how to create a elementary regression or classification machine learning model directly in BigQuery.

After taking this specialization, I moved forward to larn most ane of, if not, the about important concept behind data science and machine learning, which is statistics.

Statistics with R

We can agree that statistics is the heart of data science. As I already know statistics before, I took this specialization with the expectation to refresh the fundamental theory of statistics. Simply in the finish, I got more I was expected.

The specialization really teaches you all you need to know nearly statistics, starting with the cardinal theory about probability, inferential statistics, and regression theory from both frequentist and Bayesian perspectives.

There are two things that I like about this specialization:

1. All of the final projects are portfolio-worthy, which means that you need to do the real statistical data analysis work and don't expect to cease them in i or ii hours. After yous end the specialization, you will take 3 or four portfolio-worthy projects that you can put in your resume.
2. You demand to utilise R to finish the projection in each course. This was good for me because I have never used R before. I retrieve learning a new programming language will be beneficial in the long run and R is definitely a nice data science and statistical toolbox to add in your skillset.

After finishing the specialization, I felt like I want to dig a little bit deeper near Bayesian statistics, in detail almost Markoff chain Monte Carlo. That's why I took one more course about statistics after this specialization, which was…

Bayesian Statistics: Techniques and Models

If you want to know the concept of Bayesian statistics in a comprehensive way, I think this volition be the right course for you. In this course, you'll learn about the concept regarding Markov chain Monte Carlo too every bit how to solve regression problems with the Bayesian concept.

What I really similar about this course is the balance between the theory and practical aspects.

For every textile, the theory will be covered first, and and then at that place will be a demonstration, in which the lecturer volition show you lot how to implement the theory yous've merely learned in a code. In this form, you'll learn how to implement Bayesian statistics in R and JAGS.

The final project for this class is as well portfolio-worthy and pretty much similar to Statistics with R specialization above. You will be asked to practise statistical assay work with Bayesian concepts in R.

Afterwards finishing the course, I decided to move forward to the next topic, which is data visualization.

Data Visualization with Tableau

I would normally use Python when it comes to visualizing data, either with the help of Matplotlib, Seaborn, or Plotly. Nonetheless, I wanted to acquire something new — I wanted to learn how to visualize the information using Business organisation Intelligence tools, either with PowerBI or Tableau. And then I found this specialization.

I would recommend this specialization if you are new to Tableau and want to learn to visualize the data with it.

There are 5 courses including a Capstone project in this specialization. The first three courses will requite yous a theoretical understanding of data visualization all-time practice and how to tell a story with your data. The fourth course is basically where you get your easily dirty with Tableau, equally you lot volition acquire how to create an interactive data visualization dashboard and story with Tableau.

What I really like about this specialization is that when you're enrolled in this specialization, you'll get free access to use Tableau Desktop for 6 months.

This means that you can explore a lot of functionality of Tableau on your local auto and create a lot of interesting visualizations with it. If the license is expired after six months, yous'll have a chance to extend information technology for farther 6 months.

Machine Learning

At this point, I take learned about the overview of data scientific discipline, Big Information analysis using SQL, statistics, and information visualization all-time practice. Next, it was finally the time for me to acquire well-nigh auto learning.

As a total beginner in machine learning, I decided to take Andrew Ng'southward Machine Learning course knowing that this class is the nigh well-known grade on Coursera regarding motorcar learning.

And it is totally justified. I believe I couldn't detect a better machine learning course for a beginner than this one.

The course will teach you about the concept of classical supervised and unsupervised machine learning algorithms like Linear Regression, Logistic Regression, SVM, Grand-means clustering, too as artificial neural networks. Not only that, Andrew besides gave us tips and tricks for applying auto learning system in practice.

Basically, I liked everything about this form.

I liked how passionate Andrew Ng in teaching us nigh unlike types of car learning algorithms. I liked how piece of cake it was for him to explain and simplify difficult machine learning concepts to u.s.. I besides liked the programming assignment and how nosotros had the opportunity to implement Neural Networks algorithms from scratch.

If you're new to automobile learning, for me this is the best grade that you should take to get you started.

Deep Learning

Finally, I was getting closer and closer to attain my initial goal — to acquire about the concept of Convolutional Neural Networks.

I still remember how excited I was when I find out that Andrew Ng is the teacher of this Deep Learning specialization. Information technology was not a difficult decision for me to have this specialization right later on I finished the Machine Learning grade.

The specialization is very well structured. The offset course will teach yous about the concept of Deep Neural Networks afterward you learned almost the classic Neural Networks in the previous Machine Learning form. Next, it gives the important concepts of Convolutional Neural Networks and Sequence Models.

Andrew Ng equally usual is perfect in teaching difficult concepts regarding deep learning algorithms. The programming assignments are interesting, which permit y'all to implement various deep learning algorithms with TensorFlow, one of the almost used deep learning frameworks in the industry right now.

However, most of the programming assignments in this specialization are withal implemented in TensorFlow i, which is pretty much outdated now.

DeepLearning.AI TensorFlow Programmer Professional Certificate

I believe that this specialization was calledTensorFlow in Practise before DeepLearning.AI inverse its name toTensorFlow Developer Professional person Certificate.

Anyway, the main reason I took this specialization direct away later finishing Deep Learning specialization is that I wanted to learn how to implement TensorFlow 2 for various deep learning algorithms. And this specialization totally delivered that.

This specialization is a pure easily-on exercise. You lot won't observe any theory regarding deep learning in it as its focus is to implement deep learning algorithm with the help of TensorFlow. Thus, information technology is suggested that you already know most deep learning concepts before taking this specialization.

It gives you hands-on experience on how to build deep learning models for image classification, sentiment analysis, poetry generation, and time serial forecasting.

As a bonus, if you want to take the TensorFlow Developer Document in the future, this specialization would also exist the best source for yous to prepare for information technology. I recently took the certification and I tin can say that this specialization is the best source for the preparation. If y'all're interested in my experience of taking the certification, you lot tin can read it in the link below.

My Story of Taking the TensorFlow Developer Certification Examination
My overall experience of taking the exam, how I prepared for information technology, and what I would've done differently if I had to take…

Closing Remarks

I would assume that you already know that taking data science and automobile learning courses lonely wouldn't be plenty to reach your goal, whether information technology is to get a data science job or to primary certain data scientific discipline concepts. Same equally me, having taken courses related to CNN doesn't hateful that I mastered information technology already.

These courses are a great source to give you lot the foundational cognition of whatever topics you are interested in. Taking the course is just a starting betoken and whatever happens adjacent is totally up to you.

Put the knowledge you've got from a grade into practice to really solidify your new skill. Do some pet projects while or after taking these courses, upload the lawmaking on GitHub, and share the projects or the learning textile that you've learned to other people with a blogpost.

All the all-time for your data science learning journey!

Bio: Ruben Winastwan is a data science enthusiast, with interests in machine learning and computer vision.

Original. Reposted with permission.

Related:

• Free From MIT: Intro to Computational Thinking and Data Science
• The Online Courses You Must Have to be a Better Data Scientist
• x All-time Automobile Learning Courses in 2020

segurafitiong.blogspot.com

Source: https://www.kdnuggets.com/2020/11/data-science-online-learning-journey-coursera.html

Share this post