mobility-covid-growth.py

# This code released under an MIT license. In notebook form with more explanation:
# https://github.com/nikhaldi/covid-notebooks/blob/master/Mobility%20vs%20COVID-19%20growth%20plot.ipynb
import numpy as np
import pandas as pd

us_counties = pd.read_csv(
    "https://raw.githubusercontent.com/nytimes/covid-19-data/master/us-counties.csv",
    dtype={"fips": str},
    parse_dates=["date"]
)
mobility = pd.read_csv(
    "https://raw.githubusercontent.com/descarteslabs/DL-COVID-19/master/DL-us-mobility-daterow.csv",
    dtype={'fips': str},
    parse_dates=['date']
)

us_counties_march_week4 = us_counties.set_index('date').loc["2020-03-23":"2020-03-29"]
mobility_march_week2 = mobility.set_index("date").loc["2020-03-09":"2020-03-15"]
us_counties_march_week4_ny = us_counties_march_week4[(us_counties_march_week4["state"] == "New York")]
mobility_march_week2_ny = mobility_march_week2[
    (mobility_march_week2["admin_level"] == 2) & (mobility_march_week2["admin1"] == "New York")
]

def mean_daily_growth(series):
    return np.mean(series / series.shift(1) - 1)

us_counties_march_week4_ny_mean_growth = us_counties_march_week4_ny[["fips", "cases"]].groupby("fips").aggregate(
    max_cases=pd.NamedAgg(column="cases", aggfunc=np.max),
    mean_daily_growth=pd.NamedAgg(column="cases", aggfunc=mean_daily_growth)
)
mobility_march_week2_ny_mean = mobility_march_week2_ny.groupby("fips").mean()

min_cases_threshold = 20
merged = pd.merge(
    us_counties_march_week4_ny_mean_growth[
        us_counties_march_week4_ny_mean_growth["max_cases"] >= min_cases_threshold
    ],
    mobility_march_week2_ny_mean["m50_index"],
    on="fips"
)

slope, intercept = np.polyfit(merged.m50_index, np.log(merged.mean_daily_growth), deg=1)
y_log_estimated = slope * merged.m50_index + intercept

ax = merged.plot.scatter(x="m50_index", y="mean_daily_growth", figsize=(10,10))
ax.plot(merged.m50_index, np.exp(y_log_estimated))