KDE con displot() —

• 0:00 min | Última modificación: Octubre 13, 2021 | [YouTube]

import matplotlib.pyplot as plt
import numpy as np
import seaborn as sns

penguins = sns.load_dataset("penguins")

display(
    penguins.head(),
    penguins.tail(),
    penguins.size,
)

	species	island	bill_length_mm	bill_depth_mm	flipper_length_mm	body_mass_g	sex
0	Adelie	Torgersen	39.1	18.7	181.0	3750.0	Male
1	Adelie	Torgersen	39.5	17.4	186.0	3800.0	Female
2	Adelie	Torgersen	40.3	18.0	195.0	3250.0	Female
3	Adelie	Torgersen	NaN	NaN	NaN	NaN	NaN
4	Adelie	Torgersen	36.7	19.3	193.0	3450.0	Female

	species	island	bill_length_mm	bill_depth_mm	flipper_length_mm	body_mass_g	sex
339	Gentoo	Biscoe	NaN	NaN	NaN	NaN	NaN
340	Gentoo	Biscoe	46.8	14.3	215.0	4850.0	Female
341	Gentoo	Biscoe	50.4	15.7	222.0	5750.0	Male
342	Gentoo	Biscoe	45.2	14.8	212.0	5200.0	Female
343	Gentoo	Biscoe	49.9	16.1	213.0	5400.0	Male

2408

#
# Estimación no paramétrica básica usando dissplot().
#
sns.displot(
    penguins,
    x="flipper_length_mm",
    kind="kde",
    color='tab:blue',
    fill=True,
    rug=True,
    cumulative=False,
)
plt.show()

#
# Modificación del ancho de banda para la estimación de los kernels.
#
sns.displot(
    penguins,
    x="flipper_length_mm",
    kind="kde",
    bw_adjust=0.25,
)
plt.show()

#
# Compare el resultado con el gráfico anterior.
#
sns.displot(
    penguins,
    x="flipper_length_mm",
    kind="kde",
    bw_adjust=2,
)
plt.show()

#
# kde por variable categórica.
#
sns.displot(
    penguins,
    x="flipper_length_mm",
    hue="species",
    kind="kde",
    fill=True,
)
plt.show()

#
# Efecto de apilamiento.
#
sns.displot(
    penguins,
    x="flipper_length_mm",
    hue="species",
    kind="kde",
    multiple="stack",
)
plt.show()

#
# kde acumulada usando displot().
#
sns.displot(
    penguins,
    x="flipper_length_mm",
    kind="kde",
    color='red',
    fill=True,
    cumulative=True,
)
plt.show()