Day 11 of 14 35 minrolling()shift()pct_change()
Analyse how numbers change over time. Use a date index, smooth noisy data with rolling averages, compare each period with the one before using shift() and diff(), measure growth with pct_change(), and build running totals.
By the end of today you can
- Set up a DataFrame with a DatetimeIndex and select date ranges
- Smooth daily noise with rolling() averages
- Compare periods with shift() and diff()
- Measure growth with pct_change(), including month over month and year over year
- Build running totals with cumsum() and running maximums with cummax()
What's inside
- 6 sections
- 3 diagrams and mind maps
- 6 code examples you can run
- 5-question quiz
- 1A date index
- 2rolling(): smooth out the noise
- 3shift() and diff(): compare with the previous period
- 4pct_change(): growth rates
- 5Running totals: cumsum() and cummax()
- 6Putting it together: resample, then compare
Sign in free to read this lesson
Get the full lesson with diagrams, runnable code and the quiz. Your progress is saved across devices.
Sign in free