Description
In the Computing $R_t$ section of the COVID spread notebook, the displayed equation has the earlier four-day total in the numerator and the most recent four-day total in the denominator:
R_t = (I_{t-7} + I_{t-6} + I_{t-5} + I_{t-4})
/ (I_{t-3} + I_{t-2} + I_{t-1} + I_t)
This is inverted relative to the interpretation that values above 1 indicate growth.
The code immediately below the equation computes the ratio in the other direction:
df["Rt"] = df["ninfected"].rolling(8).apply(
lambda x: x[4:].sum() / x[:4].sum()
)Within the chronological eight-day window, x[:4] is the earlier period and x[4:] is the recent period, so the implementation is consistent with:
R_t = (I_{t-3} + I_{t-2} + I_{t-1} + I_t)
/ (I_{t-7} + I_{t-6} + I_{t-5} + I_{t-4})
For example, if daily infections increase from 10 in each of the earlier four days to 20 in each of the recent four days, the displayed equation gives 0.5, while the code gives 2.
Suggested change
Swap the numerator and denominator in the Markdown equation so that it matches the code and the surrounding explanation.
File: 2-Working-With-Data/07-python/notebook-covidspread.ipynb
Description
In the Computing$R_t$ section of the COVID spread notebook, the displayed equation has the earlier four-day total in the numerator and the most recent four-day total in the denominator:
This is inverted relative to the interpretation that values above 1 indicate growth.
The code immediately below the equation computes the ratio in the other direction:
Within the chronological eight-day window,
x[:4]is the earlier period andx[4:]is the recent period, so the implementation is consistent with:For example, if daily infections increase from 10 in each of the earlier four days to 20 in each of the recent four days, the displayed equation gives
0.5, while the code gives2.Suggested change
Swap the numerator and denominator in the Markdown equation so that it matches the code and the surrounding explanation.
File:
2-Working-With-Data/07-python/notebook-covidspread.ipynb