1. Data Science vs Data Analytics
1.1 Analytics and Science — Same Data, Different Questions
Data analytics answers what happened and why it looks like this with clear summaries, filters and charts. Data science (in the industry sense) often adds coding, reproducible notebooks and sometimes prediction. In this course we use the data-science toolkit (Python, pandas, viz) for analytics-depth work: clean → explore → visualise → tell a story. We do not train machine learning models here.
| Focus | Typical question | Tool you already know | Tool in this course |
|---|---|---|---|
| Analytics | Which city had the highest Diwali GMV? | Excel Pivot / Power BI | groupby + bar chart |
| Analytics | Why did cancels rise in Nashik last week? | Filters + charts | pandas filter + EDA |
| Science (later course) | Will this order cancel? | — | ML course (not here) |
Worked example. Ravindra Bagale (Pune city manager) asks: “Show Delivered GMV by city for Ganeshotsav week.” That is analytics. Asking “predict cancel risk for tonight’s orders” is ML — out of scope for this book.
Ravindra Bagale's Tip
Khup students Data Science mhanje fakt machine learning asa samajtat. Interview madhe pan “I only know models” mhanun analytics fundamentals skip kartat. Pehle clean data, EDA aani clear story – mag models. Ya course madhe ML nahi; paaya pakka kara. Dhyan rakho!
Practice task
Write three questions your future job might ask about quick-commerce orders. Mark each as analytics (what/why) or prediction (ML). Keep only analytics questions for this course.