My Car Data Analysis
“Data is the new oil, I live in a country where nobody is drilling — Olarenwaju Oyinbooke”. Data Analysis involves the sourcing, cleaning and visualization of data to find insights or recommendations that help provide answers to business problems with data-driven decisions.
I have been following the 30 days of learning organized by Mr. Olarenwaju Oyinbooke. As a beginner in data analysis, I have to say the course is very detailed and easy to learn with the resources that have been made available. I put my skills to the test and worked on a project with Car Sales data.
Data Sourcing
I got the sample dataset from Kaggle. The data has one hundred thousand and one (100,001) rows and nine (9) columns. The columns included Car Name, Year of Model, Present price($), Selling Price ($), Fuel Type, Kilometres Driven, Seller Type, Transmission Type, and Number Of Previous Owners.
Data Transformation
After I loaded the raw data into Power Query, I meticulously combed through it making several transformations that included but were not limited to promoting headers to ensure they were more readable, changing data types to enable better analysis, replacing values that were incorrect or incomplete, and ultimately, renaming columns to make the data more informative.
Measures
Measures are a summarization of data. To extract better insights and meaning from the data, I needed to develop additional tools or methods to analyze it effectively, which involved creating new measures or metrics to help me better understand the information.
Data Visualization
I used Power Query to gather and organize the information I needed. Then, in the report view, I selected appropriate charts to display the specific information I was interested in seeing, so it would be easier to understand and analyze.
This is the link to the report tinyurl.com/carsalesreport. The report is interactive, so feel free to apply filters to get specific information of your choice :)
Findings
Some insights I got when I analyzed the data include:
At $55,464,701, Petrol had the highest loss and was $11,415, which was 60% higher than CNG, which had the lowest loss at $481,648. Petrol had the highest loss at $55,464,701, followed by Diesel at $14,326,446 and CNG at $481,648. Petrol accounted for 78.93% of the loss.
At $16,327,350, 2015 had the highest loss and was $9,646 which was 56% higher than 2003, which had the lowest loss at $167,519. 2015 accounted for 23.23% of the loss. Across all 16 Years, losses ranged from $167,519 to $16,327,350.
The loss for Manual transmission was $60,779,022 and was higher than Automatic’s $9,493,772. Manual transmission accounted for 86.49% of the Loss. The loss for Dealers was $46,182,182 was higher than for Individual $24,090,612. Dealers accounted for 65.72% of the Loss. Individuals had a $24,090,612 loss and Dealer had $46,182,182.
Conclusion
I am very grateful to Mr. Olarenwaju Oyinbooke and others who made out the time to make this course available for those who are interested in learning data analysis. Are you interested in data analysis too? Click here to get started.
