# usual imports
import pandas
import matplotlib.pyplot as plt
import seaborn as sns
import calendar
# Read the oldest people dataset, parsing their birth and death dates as datetime
# Print the dataframe to see the results
df = pandas.read_csv("~/Downloads/oldest-people.csv", parse_dates=[2, 3])
df
# Extract the month they died
df['died_month'] = df.Died.dt.month
# Lookin at the dataset, we know that the only death which occured in soutern hemisphere
# was in South Africa, so let us remove that
df = df[df["Deathplace"] != "South Africa"]
# Get the count of people, for each month
deaths_in_month_count = df['died_month'].value_counts().sort_index()
deaths_in_month_count
# Display the chart
# Show the winter months in red, and others in Cyan
plt.figure(figsize=(16,8))
palette=["red"] * 3 +["cyan"] * 8 + ["red"]
sns.barplot([el for el in calendar.month_name if el], deaths_in_month_count.values, palette=palette, saturation=0.6)
It doesn't look like that there is any statistically sigificant higher excess winter mortality
amongst the oldest people.