Data, Data, Everywhere

designed in Canva by me

Last week, I worked on the first course in the Google Data Analytics Certification program. I decided to share my notes with the world while waiting for Coursera’s financial aid for the second course.

‘Hello, World!’ I am training to be a data analyst.

The course has been meticulously crafted and requires no prior knowledge of the concepts. There are learning logs for self-reflection, glossary sheets that clarify terms used in chapters, and quizzes, as expected. I’ll be sharing ideas, lessons, and takeaways from the course throughout this article. I hope you find it enjoyable.

I vividly recall teachings from my junior high school (JHS) ICT class: Data is a collection of raw facts and figures which are meaningless, and information is processed data. I’ll let the pundits decide if these concepts are still relevant in today’s tech world.

The first week started with definitions and the essence of data being the new oil. Let me share a few of them here:

1. Data analytics is the science of data.
2. Data is a collection of facts and information. ( I need to set up a meeting with my JHS ICT tutor after this post. :P)
3. Data analysis shows how much data can be leveraged for decision-making. To draw conclusions, make predictions, and drive informed decision-making, we collect, organize, and transform data. Data analytics uses math and statistics to derive meaning from data.
4. Data analysts sort out data to bring out information and also to explore ambiguity.

designed in Canva by me

Workflow of a Data Analyst

1. Ask: Specify the scope of the project and what constitutes success.
2. Prepare (take-off): Establish project timeframes. Specify the methodology, what data will be gathered, who will collect it, and how it will be collected. The tools required for the specific problem are also specified.
3. Process: at this stage, data is collected.
4. Analyze: insights are gleaned from the data collected.
5. Share: Insight is shared with stakeholders.
6. Act: Based on the insights offered, actions are taken.

During the sharing phase, domain experts are interviewed; these are persons who have an extensive understanding of the problem being handled. As a result, during the sharing stage, it is recommended that the data analyst runs their insights by domain experts to verify and validate their results.

Analytical Skills and Qualities

These are the attributes and characteristics involved in using data to solve problems. Analytical thinking entails identifying, defining, and solving an issue step by step.

These are the traits that recruiters look for in anyone looking to build a career in data analytics:

1. Curiosity: The ability to learn new things and a desire to discover new things within one’s field of interest.
2. Understanding context: Context is defined as the set of conditions that surround an occurrence. The capacity to categorize information is required for understanding concepts.
3. Technical mindset: A technical mentality is capable of breaking things down into small chunks in a logical and organized manner.
4. Data Design is focused on the structuring of information. Consider how you regularly save contacts in your phonebook and the pattern you use.
5. Data strategy: Data strategy is the administration of the people, processes, and tools involved in data analysis.

There are other concepts and even tools that would help to spice up the analytical thinking process. They enrich the elements and simplify certain facets of the analytical thinking process. They are as follows:

• the graphical representation of information — Visualisation
• a strategic mentality to remain focused on the objectives at hand — Strategy
• the ability to recognize, describe and fix problems — problem-oriented
• determining the link between bits of data — correlation
• being able to perceive the overall picture as well as the smallest details — Big Picture and Detail-oriented thinking

NB: To achieve the final attribute, the analyst must identify the root causes (why a problem occurs). This may be accomplished by asking “why” five times — a notion known commonly as “5 whys.” They also need to perform some gap analysis and thus evaluate current circumstances to get to their future selves.

This is when I realized how correlation does not imply causation. It essentially means that just because two sets of data have the same directional trend does not imply that they are connected.

Data Phases and Tools

The entire course is centered on data analytics. The ability to collect data has proved to be a valuable skill; but, what happens to the data once insights have been gleaned? Have you ever considered what happens to the data gathered by banks, hospitals, and other organizations?

It turns out that data has a lifespan. The cycle begins with planning and concludes with the destruction of the obtained data. I’ll go over the full cycle shortly here.

1. Planning: Planning entails determining what type of data is required, who will be responsible for it, and how it will be maintained.
2. Capture: During this step, we gather data from many sources. Data might be generated or collected through online surveys and organizational databases.
3. Manage: Management includes taking care of the data, where and how it will be kept, and the tools that would be utilized.
4. Analyze: At this level, the data is utilized to solve problems.
5. Archive: This is where the data is kept in a safe place. It may never be used again.
6. Destroy: Delete shared copies of data and erase data from storage.

My favorite task was distinguishing the data life cycle from data analysis. You could consider it and share your comments.

Query languages (SQL), spreadsheets (Microsoft Excel, Google Sheets), and visualization tools (Tableau, Power BI) are critical abilities to succeed as a data analyst. Following that, learners were introduced to the many skills that are required. I’ll include some notes from SQL codes and spreadsheet formulae that I wrote.

1. SQL queries databases. The following code chooses the column or columns of interest from the table that contains those columns. The author applies filters to the searches using the WHERE keyword.

SELECT column
FROM table
WHERE conditions

2. The spreadsheet lectures covered definitions of columns, rows, cells, observations, attributes, and so on. There was a hands-on tutorial on visualizing a given dataset in Microsoft Excel. I derived the information from my gym routine and how much I had to pay on particular days.

visualization in Microsoft Excel.

Planning a Data Visualisation

The graphical depiction of information is known as data visualization. Although spreadsheets and databases have visualization features built in, software such as Tableau integrates data into a dashboard-style display. Python and R have visualization libraries too. Data analysts have a variety of tools at their disposal. Stay inquisitive and get your hands dirty. To plan a data visualization project, you need to:

1. Explore the data for patterns.
2. Plan the visuals — refine the data and present the results of your analysis.
3. Create the visuals.

I recall filling out a form detailing my interests and why I opted to begin the course. That session ended with me “promising” to finish the full program. :D

Until I finish the second course, Ask Questions to make Data-Driven Decisions…byee!

Resources

1. All the concepts shared here are my excerpts from the Google Data Analytics Professional Certification: Foundations, Data, Data Everywhere.
2. The pictures, unless specified, were designed by me using Canva.