DEV Community: Spencer

Data Analysis 101: Concepts, Techniques, and Real-world Application

Spencer — Sun, 13 Sep 2026 09:33:05 +0000

Introduction

Data analysis is the process of collecting, cleaning, organizing,examining and interpreting data to find useful information and play a major role in decision making. As a data analyst, it means looking at numbers and information and trying to figure out what they are telling you

Steps in data analysis

Collect data-Whereby this is the collection of data from websites, databases, surveys, websites etc.
Clean Data - This is the process of fixing errors, removing duplicates, and handle missing information.
Organize Data- Putting information in a useful structure
Analyze Data- Use calculations, statistics, and patterns to understand it. 5 Visualize Data- Create charts, graphs and dashboards
Interpret and communicate - Explain what the result means and recommend actions.

Tools used in data analysis

Excel.
Power BI.
SQL.

EXCEL

Excel is one of the most beginner friendly tool used in data analysis. We can use excel in the following

Organize and clean data - where we use things like conditioning formating where the appearance of a cell are changed based on the defined conditions so increasind it's readability
Calculate totals, averages, percentages and growth - where we come across AVERAGEIFS, SUMIFS ; which only allows to calculate the averages or sums of a particular column if they have met a specific condition
Filter and sort large datasets - This is where we use the find and replace functions which enables the correction of errors from the wrong type to the required type.
Create chart and graphs - Creation of charts and graphs depends on the type of visualization you would wish to portray. A good example being the donut chart which we can use to portray six subjects at most in order to enable good readability, other examples include; column and area bar, line graph, clustered and stacked column charts etc.
Use formulas such as SUM, AVERAGE, IF, COUNTIF, and XLOOKUP- The formulas are used to find the desired result i.e. if you desire your answer to be in total, average or only count the cells that meet a specific requirement. In addition, we also have the VLOOKUP which checks for the desire request in a vertical arrangement and HLOOKUP which looks for the required search in a horizontal arrangement
Create PivotTables to summarize large amounts of data - In a case of Excel you open a new tab and click on any of the cells plus insert pivotable; Rows are used for grouping categories and columns are used to create comparison layers
Build reports and dashboards - A report is basically a submission of what your analysis findings and explanations whereas a dashboard is a visualized data in form of tables, a dashboard must have a title, Key performance indicators (KPIs)

Power Quary

Power Quary is an excel inbuilt tool that is used;

To clean data
To import data
To transform data
To combine data

Power BI.

Power BI helps to turn raw data into interactive reports, charts and dashboards so you can understand what is happening and make decisions. So, we can say power BI is used for visualization.

Dax

Dax analysis expression is a formulae language that power BI uses to create customs and calculations (it can create a calculated measure, column or table)

Categories of Dax functions

Aggregate/Mathematical/Statistical functions; which include sum, average, maximum, median, and count
Filter functions - help to modify the filter context
Logical conditions - evaluate logic in calculations, used to evaluate conditions and return if those conditions and true or false. These logical functions are used in decision making. Examples include ;

IF - when you have two or more conditions.
Nested IF - when you have more than two conditions.
NOT - opposes logic.

Text functions - where we use the cut and trim
Date and time functions - where we use functions like; DATEDIF where we can get the difference in time from two different dates 'NOW () which enables us to get the time at the moment, WEEKNUM which enables the counting of the numbers of weeks in an allocated timeframe

Conclusion

Data analysis is an important process that helps individuals and organizations turn data into useful information. Tools such as excel and power BI make data analysis easier by helping users perform calculations, create visualization and present information clearly.Therefore,developing data analysis skills is valuable in today's world because data plays an important role in business,education,research and everyday decions-making.

Building An Interactive Excel Dashboard For E-commerce Project Analysis

Spencer — Tue, 08 Sep 2026 22:53:20 +0000

INTRODUCTION

Data science and analysis is the process of using data to understand what is happening,find patterns,solve problems and make better decisions,In some cases most of the available data is usualy dirty, Excel and power Bi are some of the tools that can be used in data cleaning
Stick with me as I try to answer the following questions

Whether larger reviews are associated with more reviews
Whether highly rated products attract stronger engagements
Whether pricing and ratings move together
Which products perform best based on ratins
Which product may need a different pricing or marketing strategy

Initial data-quality audit

From the above picture we can see a number of issues with the data

The numbers have been kept in text form
The product colomn needs to be trimmed to get rid of the unnessesary spaces
Blanks and errors are visible in the dataset 4.Some of the words have been misspelled

Cleaning and preparation decisions

Inorder for our file to be cleaned the following need to be done

As highlited in the picture above elimination of the out 5 is neccesary to enable the conversion of the texts to decimal values
A trim is also needed in the product category to enable the elimination of unwanted and uncessary spacing

Excel formulas and enrichment fields

In Excel formulae are used to calculate,analyze, and manipiulate data automatically and a formulae usually starts with an = sign

formulae and what it does

=sum, Adds numbers
=Average,finds the average
=Max,finds the largest value
=Min,find the smallest value
=count,counts numbers

PivotTable and analysis workflow

A pivotTable is an Excel tool used to summerize,organize,and analyze alarge amount of data quickly without changing the original data
In my case i got to use a number of pivot tables to summerize my data for easier understanding and communication,Example of pivot tables i learnt

Bar graph
Column chart
Pie chart, Donut chart
Area chart

an example of column and line chart

Dashboard design and slicer connections

The picture above is an example of a dashboard where the slicers are interconnected to the data presented

in the picture above it illustrates that in the occurrence of a price drop from 900 to 450, the reviews came down to

Key findings

Below are some of the findings that I found out

Power Query is a tool in excel that is easier to navigate and clean data with
The functions in excel are used to help to make your work easier during the process of handling data.ie VLOOKUP which handles data vertically and HLOOKUP which handles data horizontally
Logical functions which are used to automate decision making enabling dynamic instruction i.e IF,AND,OR . In a case where we are handling more data we use a nested "IF"

Business recommendations

Below are some of the recommendations from the above data

Promote the products that are rated 4.8-5.0, because they have stronger customer satisfaction

2.Review low rated products which are from 3.3-3.8 before increasing their promotion

3.Products with significant price reductions can be used to attract customers,but you should check whether the reduced price still provides a good profit margin

Limitations and lessons learned

Limitations

Ratings does not necessarily indicates the sales perfomance i,e a product with the highest ratings doesn't necessarily symbolizes that it is the best selling

-No time period provided, there is no clear indication of when the prices,discounts,reviews and ratings were recorded.Product perfomance may change over time

Lessons learnt

Customer ratings are usually useful for identifying product popularity
Discount can make a product more attractive
Low rated products need attention. Products with ratings such as 3.3-3.8 should be investigated to understand customer complaints and improve product quality
Price comparison is important cause it helps identify products with significant price reductions and can help evaluate pricing strategies
High ratings alone are not enough for decision making hence the need to combine ratings,reviews,discounts ,price,salesvolume and profit before deciding which products to promote

How I Learnt How To Push Data

Spencer — Sat, 22 Aug 2026 21:09:18 +0000

Introduction

DATA; data has become an essential key tool in the day to day running of the modern world which is consuming and producing data in large amount. Mobile applications, social media, and business transactions are some of the few ways that data is produced massively. However, collecting this data alone is not enough, organizations need a way to understand this data and today i begin to understand my way in the data world.

Undestanding Git and Github

Git is a software that I installed locally in my computer in order to enable to see what I changed, when I did make the change and allows me to go back in case something went wrong
_Gitub_is an online platform where git repositories are stored and shared, basically github stores a copy of your work online

Terminologies

Repository- A Repository is an online project being tracked by git
Clone- To clone is a process whereby lets say another researcher or writer sees your project then decides to actualy donwload it
Forking- to fork is actually making the changes on the project that you have downloaded from github and sending it back to the owner asking if they can also make the changes on their far end
Pushpush- To git push is actually moving your project from your local computer into the online platform called github
Gitpull- To gitpull is the process of taking your project from github into your local computer, it's actually privatisation of your project
Commit- is a saved checkpoint in a project history

linking git and github

As discussed earlier , git is a softer that we install in our local computer and githu is an online platform where the git repositories are stored so we link the two using a secure shell "SSH" hence enabling the pushing and pulling of projects from your github to your computer

Creating and preparing your file

In creating and preparation of my files below are some of the key commands I learnt

cd- change directory
Mkdir- make directory
Ls - list
Touch- make file
rm-r -remove command
cd.. - going back to the previous file
echo - to push data

Writing line of code,Block of data and Quotes

in writing a simple line of code we use the sign <> i.e
select* from kenya hospital.analysis
in writing a block of data we us the same icon but enclosed in a rectangle i.e

SELECT. patient. name 
FROM. kenyan hospital analysis
WHERE patient_disease "malaria"

Also during one of the sessions we where given a quote by stephen

I came, I saw , I conquered
by stephen

Generation of URL links

Below is a URL link to my article about my first week of onboarding
article on onboarding week https://dev.to/new

below is a picture of writing data

conclusion

My first week in Luxdev has been really educative and very motivating encouraging me to keep on going and increasing my urge to learn more in data science and analytics