Optional Project Task: Start diagnosing your data

If you are completing the optional project for this course, you may have already prepared your data as part of the second round of exploratory analysis in Course 2.

To begin diagnosing and diving deeper into the data to find meaningful insights, you’ll need to identify which areas are worth investigating. As you saw earlier in the course, exploratory visualisations are one of the best ways to spot patterns in your data. Having prepared your data in SQLite, and exported this to a CSV file(s), we’ll briefly switch back to using Excel (or another spreadsheet tool) in order to create further exploratory visualisations.

By now, you may be familiar with importing the CSV files into Excel and, as you did previously, plotting charts to visualise your data. You may wish to revisit the charts you created during your analysis of the sample data, or create new charts depending on how you’ve structured the data.

As you review your charts, try to identify the key features.

• Did these match those in the sample data, or have these changes using more data?
• What do these features tell you about the data?
• Which areas would you investigate further if you were to continue the analysis?

Don’t forget to save your visualisations and continue making notes about your analysis.

Next, you’ll learn about the different types of relationships in data, specifically, direct and indirect relationships in regard to correlation.