Machine Learning Algorithms - Second Edition

Linear regression with scikit-learn and higher dimensionality

The scikit-learn library offers the LinearRegression class, which works with n-dimensional spaces. For this purpose, we're going to use the Boston dataset:

from sklearn.datasets import load_bostonboston = load_boston()print(boston.data.shape)(506L, 13L)print(boston.target.shape)(506L,)

It has 506 samples with 13 input features and one output. In the following graph, there's a collection of the plots of the first 12 features:

The plot of the first 12 features of the Boston dataset

When working with datasets, it's useful to have a tabular view to manipulate data. Pandas is a perfect ...