Skip to main content

What is Data? And What is Data Science Process?

The Beginner’s Guide to Data & Data Science Process

  • About Data:

In our First Video today we talked about Data and how the Cambridge English Dictionary and Wikipedia defines Data, then we looked on few forms of Data that are:


  •  Population census data (Here is the US census website and some tools to help you examine it, but if you aren’t from the US, I urge you to check out your home country’s census bureau (if available) and look at some of the data there!)
  • Electronic medical records (EMR), other large databases
  • Geographic information system (GIS) data (mapping)
  • Image analysis and image extrapolation (A fun example you can play with is the DeepDream software that was originally designed to detect faces in an image, but has since moved on to more artistic pursuits.)
  • Language and translations
  • Website traffic
  • Personal/Ad data (e.g.: Facebook, Netflix predictions, etc.)

These data forms need a lot of preprocessing and cleaning after which these are used to answer a lot of questions and to make informed decisions.



Here is our video, if you haven’t watched it yet, watch now!

  • Data Science Process:

In our second video today, we discussed The Data Science Process So what is Data Science Process?

Here is our video on Data science Process.


The data science process is a structured approach to solving data-related problems. It involves several stages, from problem definition to model deployment. Here is a brief overview of the data science process in R:



1. Define the problem: The first step is to clearly define the problem you are trying to solve. This involves understanding the business problem, identifying the stakeholders, and specifying the data requirements.

2. Collect the data: Once you have defined the problem, the next step is to collect the data. This may involve obtaining data from various sources such as databases, APIs, or web scraping.

3. Explore the data: After collecting the data, the next step is to explore and analyze the data. This involves cleaning the data, summarizing the data using descriptive statistics, and visualizing the data using graphs and charts.

4. Prepare the data: Once the data is explored, the next step is to prepare the data for analysis. This involves transforming the data into a format that is suitable for analysis, such as reshaping the data, creating new variables, and filtering out irrelevant data.

5. Build the model: With the data prepared, the next step is to build the model. This involves selecting a modeling technique that is appropriate for the problem at hand and using R to develop the model.

6. Evaluate the model: Once the model is built, the next step is to evaluate its performance. This involves testing the model on a holdout dataset and assessing its accuracy and robustness.

7. Deploy the model: Finally, if the model is deemed satisfactory, the next step is to deploy the model. This may involve integrating the model into a production system, creating a user interface, or providing documentation for end-users.


R is a popular programming language for data science because it provides a wide range of tools for data manipulation, visualization, and statistical modeling. R also has a large community of users and a wealth of resources, such as packages and tutorials, that can be used throughout the data science process.


We also discussed an example that follows Data Science Process in R, "Predicting House Prices using Regression Models: A Case Study in R"

Please Subscribe our YouTube channel, if you haven't subscribed yet, so you don't miss on latest updates.

Thanks for reading our Blog!
Labels:

Comments

  1. Anonymous3 March 2023 at 23:45

    Really enjoyed reading, how well you explained complete Data Science Process, great Resource of learning Data science!

    ReplyDelete

Post a Comment

Type your comment here.
However, Comments for this blog are held for moderation before they are published to blog.
Thanks!

Popular posts from this blog

Mastering Data Science Experimental Design: From Hypothesis to Results

The Beginner’s Guide to Data Science Experimental Design: Now that we’ve looked at the different types of data science questions, we are going to spend some time looking at experimental design concepts, in our last lesson of our first Course "The Data Science Toolbox" in our Data Science Specialization using R Programming. As a data scientist, you are a  scientist  and as such, need to have the ability to design proper experiments to best answer your data science questions! Previous lesson, if you haven't watched! What does experimental design mean? Experimental design is organizing an experiment so that you have the correct data (and enough of it!) to clearly and effectively answer your data science question. This process involves clearly formulating your question in advance of any data collection, designing the best set-up possible to gather the data to answer your question, identifying problems or sources of error in your design, and only then, collecting the app...
Post a Comment
Read more

The Evolution of R: From S-Inspired Language to Statistical Powerhouse

The Beginner’s Guide to the History of R Programming: R Programming is basically the dialect of S Programming. S History: The S programming language was first developed in the late 1970s by John Chambers and his colleagues at Bell Laboratories. It was initially used for data analysis and graphics, and it served as the basis for the commercial software package S-PLUS, which was released in the early 1990s. While S-PLUS was popular in the statistical community for many years, it has since been largely replaced by the open-source software environment R, which was inspired by S and developed by some of the same people who worked on S-PLUS. As for the current version of S, it's not as widely used as R, and there are several different implementations of the S language that are still available today, including: S-PLUS: This is the commercial implementation of S that was developed by TIBCO Software Inc. It is still in use today, although it has been largely supplanted by R in the statisti...
Post a Comment
Read more

Streamlining Your Workflow: Linking Git/GitHub with R Studio for Efficient Version Control

The Beginner’s Guide Linking Git/GitHub with R Studio: Now that we have both R Studio and Git set-up on your computer and a GitHub account, it’s time to link them together so that you can maximize the benefits of using R Studio in your version control pipelines. First we will link R studio and Git and then we will link R Studio and GitHub. We will also link an existing Project with Git and GitHub. Linking R Studio and Git In R Studio, go to Tools > Global Options > Git/SVN Use the Global Options menu to tell R Studio you are using Git as your version control system Sometimes the default path to the Git executable is not correct. Confirm that git.exe resides in the directory that R Studio has specified; if not, change the directory to the correct path. Otherwise, click OK or Apply. Confirm that the directory R Studio points to for the Git executable is correct R Studio and Git are now linked. Linking R Studio and GitHub In that same R Studio option window, clic...
Post a Comment
Read more