Johns Hopkins COVID-19 Dataset in Pandas

COVID-19 is ravaging the globe. Let’s look at the excellent Johns Hopkins dataset using Pandas. This will serve both as a guideline for getting the data and exploring on your own, as well as an example of Pandas multi-indexing in an easy to understand situation. I am currently involved in science-responds.

My favorite links: worldometerarcGISProjections

A few more: COVID-19 dashnCoV201991-DIVOC

# Python 3.6+ required
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.dates as mdates
from urllib.error import HTTPError
plt.style.use('ggplot')

Anyway, now that we’ve made some basic imports, let’s write a function that can read in a datafile from GitHub:

def get_day(day: pd.Timestamp):

    # Read in a datafile from GitHub
    try:
        table = pd.read_csv(
            "https://raw.githubusercontent.com/CSSEGISandData/COVID-19/"
            "master/csse_covid_19_data/csse_covid_19_daily_reports/"
            f"{day:%m-%d-%Y}.csv",
        )
    except HTTPError:
        return pd.DataFrame()
    
    # Cleanup - sadly, the format has changed a bit over time - we can normalize that here
    table.columns = [
        f.replace("/", "_")
        .replace(" ", "_")
        .replace("Latitude", "Lat")
        .replace("Longitude", "Long_")
        for f in table.columns
    ]

    # This column is new in recent datasets
    if "Admin2" not in table.columns:
        table["Admin2"] = None

    # New datasets have these, but they are not very useful for now
    table.drop(
        columns=["FIPS", "Combined_Key", "Lat", "Long_"], errors="ignore", inplace=True
    )
    
    # If the last update time was useful, we would make this day only, rather than day + time
    #   table["Last_Update"] = pd.to_datetime(table["Last_Update"]).dt.normalize()
    #
    # However, last update is odd, let's just make this the current day
    table["Last_Update"] = day
    
    # Make sure indexes are not NaN, which causes later bits to not work. 0 isn't
    # perfect, but good enough.
    # Return as a multindex
    return table.fillna(0).set_index(
        ["Last_Update", "Country_Region", "Province_State", "Admin2"], drop=True
    )

Now let’s loop over all days and build a multi-index DataFrame with the whole dataset. We’ll be doing quite a bit of cleanup here as well. If you do this outside of a function, you should never modify an object in multiple cells; ideally you create an object like df, and make any modifications and replacements in the same cell. That way, running any cell again or running a cell multiple times will not cause unusual errors and problems to show up.

def get_all_days(end_day = None):

    # Assume current day - 1 is the latest dataset if no end given
    if end_day is None:
        end_day = pd.Timestamp.now().normalize()

    # Make a list of all dates
    date_range = pd.date_range("2020-01-22", end_day)
    
    # Create a generator that returns each day's dataframe
    day_gen = (get_day(day) for day in date_range)
    
    # Make a big dataframe, NaN is 0
    df = pd.concat(day_gen).fillna(0).astype(int)
    
    # Remove a few duplicate keys
    df = df.groupby(level=df.index.names).sum()
    
    # Sometimes active is not filled in; we can compute easily
    df["Active"] = np.clip(
        df["Confirmed"] - df["Deaths"] - df["Recovered"], 0, None
    )
    
    # Change in confirmed cases (placed in a pleasing location in the table)
    df.insert(
        1,
        "ΔConfirmed",
        df.groupby(level=("Country_Region", "Province_State", "Admin2"))["Confirmed"]
        .diff()
        .fillna(0)
        .astype(int),
    )
    
    # Change in deaths
    df.insert(
        3,
        "ΔDeaths",
        df.groupby(level=("Country_Region", "Province_State", "Admin2"))["Deaths"]
        .diff()
        .fillna(0)
        .astype(int),
    )
    
    return df

If this were a larger/real project, it would be time to bundle up the functions above and put them into a .py file - notebooks are for experimentation, teaching, and high level manipulation. Functions and classes should normally move to normal Python files when ready.

Let’s look at a few lines of this DataFrame to see what we have:

df = get_all_days()
df
Confirmed ΔConfirmed Deaths ΔDeaths Recovered Active Incidence_Rate Case-Fatality_Ratio
Last_Update Country_Region Province_State Admin2
2020-01-22 Hong Kong Hong Kong 0 0 0 0 0 0 0 0 0
Japan 0 0 2 0 0 0 0 2 0 0
Macau Macau 0 1 0 0 0 0 1 0 0
Mainland China Anhui 0 1 0 0 0 0 1 0 0
Beijing 0 14 0 0 0 0 14 0 0
... ... ... ... ... ... ... ... ... ... ... ...
2020-08-02 West Bank and Gaza 0 0 12297 137 84 1 5390 6823 241 0
Western Sahara 0 0 10 0 1 0 8 1 1 10
Yemen 0 0 1734 4 497 3 862 375 5 28
Zambia 0 0 6347 119 170 5 4493 1684 34 2
Zimbabwe 0 0 3921 262 70 1 1016 2835 26 1

472457 rows × 8 columns

The benefit of doing this all at once, in one DataFrame, should quickly become apparent. We can now use simple selection and grouping to “ask” almost anything about our dataset.

As an example, let’s look at just the US portion of the dataset. We’ll use the pandas selection .xs:

us = df.xs("US", level="Country_Region")
us
Confirmed ΔConfirmed Deaths ΔDeaths Recovered Active Incidence_Rate Case-Fatality_Ratio
Last_Update Province_State Admin2
2020-01-22 Washington 0 1 0 0 0 0 1 0 0
2020-01-23 Washington 0 1 0 0 0 0 1 0 0
2020-01-24 Chicago 0 1 0 0 0 0 1 0 0
Washington 0 1 0 0 0 0 1 0 0
2020-01-25 Illinois 0 1 0 0 0 0 1 0 0
... ... ... ... ... ... ... ... ... ... ...
2020-08-02 Wyoming Teton 354 6 0 0 0 354 1508 0
Uinta 262 3 0 0 0 262 1295 0
Unassigned 0 0 25 0 0 0 0 0
Washakie 49 0 0 0 0 49 627 0
Weston 5 0 0 0 0 5 72 0

403587 rows × 8 columns

Notice we have counties (early datasets just have one “county” called "0"). If we were only interested in states, we can group by the remaining levels and sum out the "Admin2" (county and similar) dimension:

by_state = us.groupby(level=("Last_Update", "Province_State")).sum()
by_state
Confirmed ΔConfirmed Deaths ΔDeaths Recovered Active Incidence_Rate Case-Fatality_Ratio
Last_Update Province_State
2020-01-22 Washington 1 0 0 0 0 1 0 0
2020-01-23 Washington 1 0 0 0 0 1 0 0
2020-01-24 Chicago 1 0 0 0 0 1 0 0
Washington 1 0 0 0 0 1 0 0
2020-01-25 Illinois 1 0 0 0 0 1 0 0
... ... ... ... ... ... ... ... ... ...
2020-08-02 Virginia 91782 981 2218 3 0 89564 121815 270
Washington 58173 632 1596 4 0 56577 27855 63
West Virginia 6858 120 117 1 0 6741 16571 73
Wisconsin 54924 922 948 1 0 53976 38015 84
Wyoming 2808 39 26 0 0 2807 10048 4

9340 rows × 8 columns

Using the same selector as before, we can pick out North Carolina:

by_state.xs("North Carolina", level="Province_State")
Confirmed ΔConfirmed Deaths ΔDeaths Recovered Active Incidence_Rate Case-Fatality_Ratio
Last_Update
2020-03-10 7 0 0 0 0 7 0 0
2020-03-11 7 0 0 0 0 7 0 0
2020-03-12 15 8 0 0 0 15 0 0
2020-03-13 17 2 0 0 0 17 0 0
2020-03-14 24 7 0 0 0 24 0 0
... ... ... ... ... ... ... ... ...
2020-07-29 118387 1687 1888 28 0 116499 100790 133
2020-07-30 120532 2145 1922 34 0 118610 102691 131
2020-07-31 122298 1766 1942 20 0 120356 104227 127
2020-08-01 124006 1708 1979 37 0 122027 105917 128
2020-08-02 125330 1324 1983 4 0 123347 107315 126

146 rows × 8 columns

We can look at all of US, as well:

all_states = by_state.groupby(level="Last_Update").sum()
all_states
Confirmed ΔConfirmed Deaths ΔDeaths Recovered Active Incidence_Rate Case-Fatality_Ratio
Last_Update
2020-01-22 1 0 0 0 0 1 0 0
2020-01-23 1 0 0 0 0 1 0 0
2020-01-24 2 0 0 0 0 2 0 0
2020-01-25 2 0 0 0 0 2 0 0
2020-01-26 5 0 0 0 0 5 0 0
... ... ... ... ... ... ... ... ...
2020-07-29 4426982 70776 150713 1403 1389425 4276775 2925370 7113
2020-07-30 4495015 68033 152055 1342 1414155 4343474 2985971 7054
2020-07-31 4562038 67023 153314 1259 1438160 4409123 3043308 7049
2020-08-01 4620444 58406 154447 1133 1461885 4466481 3097350 6983
2020-08-02 4667955 47511 154860 413 1468689 4513552 3137175 6824

194 rows × 8 columns

US total cases

Let’s try a simple plot first; this is the one you see quite often.

plt.figure(figsize=(10,5))
all_states.Confirmed.plot(logy=True, style='o');

png

Italy, new cases per day

As another example, let’s view the new cases per day for Italy. We will add a rolling mean, just to help guide the eye through the fluctuations - it is not a fit or anything fancy.

interesting = df.xs("Italy", level="Country_Region").groupby(level="Last_Update").sum()

plt.figure(figsize=(10,5))
interesting.ΔConfirmed.rolling(5, center=True).mean().plot(style='-', label='Rolling mean')
interesting.ΔConfirmed.plot(style='o', label="Data")
plt.ylabel("New cases per day")
plt.legend();

png

Italy, transmission rate

It’s more interesting to instead look at the transmission rate per day, which is new cases / active cases. The colors in the plot start changing when Italy implemented a lockdown on the 11th, and change over 14 days, which is roughly 1x the time to first symptoms. The lockdown make take longer than that to take full effect. There were several partial steps taken before the full lockdown on the 4th and 9th. Notice the transmission is slowing noticeably!

interesting = df.xs("Italy", level="Country_Region").groupby(level="Last_Update").sum()
growth = interesting.ΔConfirmed / interesting.Active
growth = growth['2020-02-24':]

# Color based on lockdown (which happened in 3 stages, 4th, 9th, and 11th)
lockdown = growth.index - pd.Timestamp('2020-03-11')
lockdown = np.clip(lockdown.days, 0, 14) / 14

fix, ax = plt.subplots(figsize=(10,5))
ax.scatter(growth.index, growth, cmap='cool', c=lockdown)

ax.set_ylabel("new cases / active cases")

#set ticks every week
ax.xaxis.set_major_locator(mdates.WeekdayLocator())
#set major ticks format
ax.xaxis.set_major_formatter(mdates.DateFormatter('%b %d'))

png

US, transmission rate

Same plot for the US. The colors in the plot start changing when the US started the 15 plan to slow the spread, and change over 14 days, which is roughly 1x the time to first symptoms. Each state has implemented different guidelines, so the effect will be spread out even futher. Again, we are see the effect of the lockdown!

interesting = df.xs("US", level="Country_Region").groupby(level="Last_Update").sum()
growth = interesting.ΔConfirmed / interesting.Active
growth = growth['2020-03-01':]

# Not really a full lockdown, just a distancing guideline + local lockdowns later
lockdown = growth.index - pd.Timestamp('2020-03-15')
lockdown = np.clip(lockdown.days, 0, 14) / 14

fix, ax = plt.subplots(figsize=(10,5))
ax.scatter(growth.index, growth, cmap='cool', c=lockdown)

ax.set_ylabel("new cases / active cases")

#set ticks every week
ax.xaxis.set_major_locator(mdates.WeekdayLocator())
#set major ticks format
ax.xaxis.set_major_formatter(mdates.DateFormatter('%b %d'))

png

comments powered by Disqus