TensorFlow 2.0 Quick Start Guide

The Boston housing dataset

Next, we will apply a similar regression technique to the Boston housing dataset.

The main difference between this and our previous artificial dataset, which had just one feature, is that the Boston housing dataset is real data and has 13 features. This is a regression problem because house prices—the label—we take as being continuously valued.

Again, we start with our imports, as follows:

import tensorflow as tffrom sklearn.datasets import load_bostonfrom sklearn.preprocessing import scaleimport numpy as np

And our important constants are shown as follows:

learning_rate = 0.01epochs = 10000display_epoch = epochs//20n_train = 300n_valid = 100

Next, we load our dataset and split it into training, validation, and ...