Everything is simple.
Start learning one language and focus on all the nuances of programming through the syntax of that language.
But still, it is difficult to do without some kind of general guide.
For this reason, I recommend paying attention to this article: Software Development Skills for Data Scientists: Amazing article about important soft skills for programming practice.
For example, I would advise you to pay attention to Python.
Firstly, it is perfect for beginners to learn, it has a relatively simple syntax.
Secondly, Python combines the demand for specialists and is multifunctional.
But if these statements don’t tell you anything, read more about it here: Python vs R.
Choosing the Best Tool for AI, ML & Data Science.
Time is a precious resource, so it’s better not to disintegrate at once and not just waste it.
So how to learn Python?If you don’t have any programming understanding, I recommend reading Automate the Boring Stuff With Python.
The book offers to explain practical programming for total beginners and teach from scratch.
Read Chapter 6, “String Manipulation,” and complete the practical tasks for this lesson.
That will be enough.
Here are some other great resources to explore:Codecademy — teaches good general syntaxLearn Python the Hard Way — a brilliant manual-like book that explains both basics and more complex applications.
Dataquest — this resource teaches syntax while also teaching data scienceThe Python Tutorial — official documentationAfter you learn the basics of Python, you need to spend time getting to know the main libraries.
Here is a list of recommendations for studying libraries.
Here I have divided all the necessary libraries for their intended purpose, and also provided all the necessary links for mastering (documentation and guides):Main libraries:Numpy — documentation — tutorialScipy — documentation — tutorialPandas — documentation — tutorialVisualization:Matplotlib — documentation — tutorialSeaborn — documentation — tutorialMachine learning and deep learning:SciKit-Learn — documentation — tutorialTensorFlow — documentation — tutorialTheano — documentation — tutorialKeras — documentation — tutorialNatural language processing:NLTK — documentation — tutorialWeb scraping:BeautifulSoup 4 — documentation — tutorialStep 3.
Machine LearningMachine learning allows you to train computers to act independently so that we do not have to write detailed instructions for performing certain tasks.
For this reason, machine learning is of great value for almost any area, but first of all, of course, it will work well where there is Data Science.
First thing or the first step in learning ML is its three main groups:1) Supervised Learning is now the most developed form of ML.
The idea here is that you have historical data with some notion of the output variable.
Output Variable is meant for recognizing how you can a good combination of several input variables and corresponding output values as historical data presented to you and then based on that you try to come up with a function which is able to predict an output given any input.
So, the key idea is that historical data is labeled.
Labeled means that you have a specific output value for every row of data, that is presented to it⠀PS.
in the case of the output variable, if the output variable is discreet, it is called CLASSIFICATION.
And if it is continuous it is called REGRESSION2) Unsupervised learning doesn’t have the luxury of having labeled historical data input-output.
Instead, we can only say that it has a whole bunch of input data, RAW INPUT DATA.
It allows us to identify what is known as patterns in the historical input data and interesting insights from the overall perspective.
So, the output here is absent and all you need to understand is that is there a pattern being visible in the unsupervised set of input.
The beauty of unsupervised learning is that it lends itself to numerous combinations of patterns, that’s why unsupervised algorithms are harder.
3) Reinforcement learning occurs when you present the algorithm with examples that lack labels, as in unsupervised learning.
However, you can accompany an example with positive or negative feedback according to the solution the algorithm proposes.
RL is connected to applications for which the algorithm must make decisions, and the decisions bear consequences.
It is just like learning by trial and error.
An interesting example of RL occurs when computers learn to play video games by themselves.
So okay, now you know the basics of ML.
After this, you obviously need to learn more.
Here are great resources to explore for this purpose:Supervised and Unsupervised Machine Learning Algorithms: Clear, concise explanations of the types of machine learning algorithms.
Visualization of Machine Learning: Excellent visualization that walks you through exactly how machine learning is used.
Data Mining and Data VisualizationData Mining is an important analytic process designed to explore data.
It is the process of analyzing hidden patterns of data according to different perspectives for categorization into useful information, which is collected and assembled in common areas, such as data warehouses, for efficient analysis, data mining algorithms, facilitating business decision making and other information requirements to ultimately cut costs and increase revenue.
Resources to master Data Mining:How data mining works — great video with the best explanation I found so far‘Janitor Work’ is Key Hurdle to Insights: Interesting article that goes into detail regarding the importance of data mining practices in the field of data science.
Data Visualization is a general term that describes an effort to help people understand the significance of data by placing it in a visual context.
Resources to master Data Visualization:Data visualization beginner’s guideWhat Makes a Good Data VisualizationStep 5.
Practical ExperienceStudying only the theory is not very interesting, you need to try your hand at practice.
Data Scientist’s beginner has a few good options for this:Use Kaggle, a website dedicated to Data Science.
It constantly hosts data analysis competitions in which you can take part.
There are also a large number of open data sets that you can analyze and publish your results.
In addition, you can watch scripts published by other participants (on Kaggle, such scripts are called Kernels) and learn from successful experience.
Qualification ConfirmationAfter you have studied everything you need to analyze the data and try your hand at open tasks and contests, then start looking for a job.
Of course, you will say only good things, but you have the right to doubt your words.
Then you will demonstrate independent confirmations, for example:Advanced profile on Kaggle.
Kaggle has a ranks system, you can go through the steps from beginner to grandmaster.
For successful participation in competitions, the publication of scripts and discussions, you can get points that allow you to raise the rating.
In addition, the site shows in what competitions you participated, and what are your results.
Data analysis programs can be published on GitHub or other open repositories, then all interested can get acquainted with them.
Including representatives of the employer, who will conduct an interview with you.
Final Advice: Don’t Be a Copy of a Copy, Find Your Own WayNow anyone can become Data Scientist.
There is everything you need for this in the public domain: online-courses, books, competitions for gaining practical experience and so on.
It’s good for the first glance, but you shouldn’t learn it just because of hype.
All we hear about Data Science it is unbelievably cool and it’s the sexiest job of the 21st century.
If these things are the main motivation for you, nothing ever will work.
Sad truth yes and maybe I’m exaggerating a little bit but that’s kind of how I feel about it.
What I’m going to say right now is becoming a self-taught Data Scientist is possible.
However, the key to your success is a high motivation to regularly find time to study data analysis and its practical application.
Most importantly, you have to learn to get satisfaction in the process of learning and working.
Think about it.
Good luck!Feel free to share your ideas and thoughts.
Check out my blog on Medium and Instagram.