Stacked bar charts¶

import pandas

df = pandas.read_csv('US_cities.csv', index_col="AccentCity")
df[:5]

states_pop = df[["Population", "Region"]].groupby(by=["Region"]).sum()
states_pop[:5]

states_pop.plot.bar()
plt.show()

largest_cities_idx = df.groupby(by=["Region"], sort=False)["Population"].transform(max) == df["Population"]
df[largest_cities_idx][:5]

def max2(cities):
    return nth_largest(cities, 2)
def max3(cities):
    return nth_largest(cities, 3)
def nth_largest(cities, n):
    nlargest = cities.nlargest(n)
    if len(nlargest) < n:
        return None
    return nlargest[n-1]
second_largest_idx = df.groupby(by=["Region"], sort=False)["Population"].transform(max2) == df["Population"]
third_largest_idx = df.groupby(by=["Region"], sort=False)["Population"].transform(max3) == df["Population"]
df[second_largest_idx][:5]

smaller_cities = df[~largest_cities_idx & ~second_largest_idx & ~third_largest_idx].copy()

smaller_cities[["Population", "Region"]].groupby(by=["Region"]).sum().plot.bar(stacked=True)
df[largest_cities_idx][["Population", "Region"]].groupby(by=["Region"]).sum().plot.bar(stacked=True)
# df[second_largest_idx].plot.bar()
# df[third_largest_idx].plot.bar()
plt.show()

df