Skip to content

Plotting

Uses matplotlib

https://pandas.pydata.org/docs/user_guide/visualization.html

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

plt.close("all")

df = pd.read_csv('penguins.csv')
plt.figure()
df["bill_length_mm"].plot(kind="hist")
plt.show()

plt.figure()
df["bill_length_mm"].plot(kind="line")
plt.show()

png

png

species_population = df.groupby("species").size()

index = species_population.index
display(list(index))
display(list(species_population.values))

plt.figure()
# x and height must be lists
plt.bar(x = species_population.index, height = species_population.values)
plt.show()
['Adelie', 'Chinstrap', 'Gentoo']



[152, 68, 124]

png

# Scatterplots

species = df.groupby("species")

plt.figure()
plt.xlabel("Bill length (mm)")
plt.ylabel("Body mass (grams)")
for n, grp in species:
    plt.scatter(x = grp['bill_length_mm'], y = grp['body_mass_g'])
plt.show()

png

# correlation between two columns
df.bill_length_mm.corr(df.body_mass_g)

# correlation matrix
df.corr()
bill_length_mm bill_depth_mm flipper_length_mm body_mass_g
bill_length_mm 1.000000 -0.235053 0.656181 0.595110
bill_depth_mm -0.235053 1.000000 -0.583851 -0.471916
flipper_length_mm 0.656181 -0.583851 1.000000 0.871202
body_mass_g 0.595110 -0.471916 0.871202 1.000000
plt.figure()
bill_length = df['bill_length_mm']
plt.hist(bill_length, bins=40)  # default bin #: 10
plt.show()

png


Last update: 2022-11-04