Visualizing Covid-19 Case Infection Rates across US States — July 2020

Determining relative Covid-19 rates by US State and County

What is Covid-19?

Reported Covid-19 Cases and Deaths

Why analyze Covid-19?

Covid 19 Case Data Sources

Covid Data Format

Simple Schema — Rows of Case Counts by State and County (“Admin2”)

Questions we’re answering

Questions we’re not answering (no public data)

“Flattening the Curve”

Inhibiting new infections to reduce the number of cases at any given time — known as “flattening the curve” — allows healthcare services to better manage the same volume of patients. — Wikipedia

Decreasing Cases ‘S’ curve

Manhattan’s New York County in Cornflower Blue
Chicago’s Cook County in Baby Blue

States with Increasing Cases

Maricopa county in light Green.
Harris, Dallas counties with growing cases.
Los Angeles county in light pink.

How do we compare rates across States?

y = slice_df.head(14)['cases']
lastY = y[0] # cases seen at start of period
x = np.arange(0, len(y))
polynomialDegree = 1
res = np.polyfit(x, y, polynomialDegree)
# y = res[0] * X + res[1] <---- res[0]=slope and res[1]=intercept

Detailed Example of Numpy PolyFit

Rough m=Slope Calculation: y=mx + b

Normalized Case Growth over Time

Normalize by Percentage Change

On March 10 (n=150) there were 74 times more than on March 3 (n=2)

Rank States by Flattening or Growing Curve

Rank States by % Change over last N days

Root Awaking

County-level Growth Rates

States without Lockdowns

Conclusion and Take-aways

Predictive Models

Next Article — Grading the Results

Data Enthusiast