Example code snippet for Naive Bayes fundamentals article, part [1]

bayes_import_visualise.py

import pandas as pd
import matplotlib.pyplot as plt

# [1] import and visualise our data
dataset = pd.read_csv('adult.csv')  # import data
# from Kaggle's 'Adult Census Income' dataset

# lets visualise the data, we classify by income (>$50k or not)
# based on number of years in education and hours worked per week
plt.figure(figsize=(12, 8))
sns.scatterplot(data=dataset, x='education.num', y='hours.per.week',
                hue='income', s=250, alpha=0.025, palette={
                        '<=50K': '#02AD6D',
                        '>50K': '#FF00FF'})
plt.show()  # visualise the data