Instacart is a grocery delivery platform where customers can place a grocery order and have it delivered to them, similar to how Uber Eats and Door Dash work. This particular dataset was publicly released by Instacart in 2017 for a Kaggle competition.
In this Exploratory Data Analysis (EDA) project we'll clean up the data and prepare a report that gives insight into the shopping habits of Instacart customers.
- To clean up the data and prepare a report that gives insight into the shopping habits of Instacart customers.
- Provide a brief explanation of the results after answering each question.
- Make plots that communicate your results.
- Verify that the
'order_hour_of_day'
and'order_dow'
values in theorders
tables are sensible - What time of day do people shop for groceries?
- What day of the week do people shop for groceries?
- How long do people wait until placing another order?
- Is there a difference in
'order_hour_of_day'
distributions on Wednesdays and Saturdays? - What's the distribution for the number of orders per customer?
- What are the top 20 popular products?
- How many items do people typically buy in one order?
- What are the top 20 items that are reordered most frequently?
- What are the top 20 items that people put in their carts first?
pandas
numpy
matplotlib