Member-only story
Tackling the Data Wilderness of my Digital Grocery Basket
As I Clean and Explore Data
In the earlier post of this series of documenting my very first Personal Data Project — ‘Unpacking My Online Grocery Spend,’ I mentioned about the ‘Why’ and ‘What’ of it.
It’s time to dive into some pivotal aspects, now that I have a manual dataset growing over weeks and months.
Time to probe into the not so glamorous phases of a Data Project that not only strengthen the foundation of the problem identified and data collected but also bridge the gap between unrefined data and significant insights overhauling cluttered and messy figures into actionable awareness.
PHASE III — DATA CLEANING : THE NECESSARY CHORE OF POLISHING DATA
When I first embarked on tracking my online grocery spends manually row by row, I must say I naively assumed that cleaning this self — collected data would be a piece of cake. Because unlike downloading those heavily structured CSV files, the data I had gathered was purely human, with not much scope for inconsistencies.
Only to be proven wrong.
Although I believed that I was in full control of the data I had entered manually, reality struck me hard when I looked closely at the data.
