Visualizing datasets: correlation scatter plot and heatmaps

Get dataset

import pandas as pd

df = pd.read_csv('https://raw.githubusercontent.com/rasbt/'
                 'python-machine-learning-book-3rd-edition/'
                 'master/ch10/housing.data.txt',
                 header=None,
                 sep='\s+')

df.columns = ['CRIM', 'ZN', 'INDUS', 'CHAS', 
              'NOX', 'RM', 'AGE', 'DIS', 'RAD', 
              'TAX', 'PTRATIO', 'B', 'LSTAT', 'MEDV']
df.head()

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

Scatterplot matrix

Visuzalizing 2 variables at the time across all variables of the dataset.

import matplotlib.pyplot as plt
import seaborn as sns

cols = ['LSTAT', 'INDUS', 'NOX', 'RM', 'MEDV']

sns.pairplot(df[cols], height=2.5)
plt.tight_layout()
#plt.savefig('images/10_03.png', dpi=300)
plt.show()

png

Correlation matrix

import numpy as np

cm = np.corrcoef(df[cols].values.T)
hm = sns.heatmap(cm, cbar=True, annot=True, fmt='.2f', annot_kws={'size': 15},  yticklabels=cols, xticklabels=cols)
# plt.savefig('images/10_04.png', dpi=300)
plt.show()

png