Manhattan distance

Q: How deeply does Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI cover Manhattan distance?

Defines the metric, contrasts it with Euclidean distance, and applies it to coordinates and nearest-neighbor queries.

As explained in Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI

Manhattan distance is the sum of the absolute coordinate differences between two points.

Manhattan distance measures how far two points are by adding the absolute differences of their coordinates. For Tokyo property data, it can turn proximity to the Imperial Palace into a machine-learning feature. section 7.1.3

Unlike Euclidean distance, which assumes a straight-line path, Manhattan distance reflects horizontal and vertical movement through a city. It is also called city block distance, taxicab distance, or the L1 norm. section 7.1.3

Choose the distance measure according to the movement or geometry represented by the feature:

Use Manhattan distance when street layouts and road networks make horizontal and vertical travel more realistic. section 7.1.3
Use Euclidean distance when direct physical distance between locations is the more appropriate interpretation. section 7.1.3

Tokyo property proximity

A geographical feature compares each Airbnb accommodation with the Imperial Palace by summing absolute latitude and longitude differences, converting the result to meters, and storing it as imperial_palace_distance. The closest displayed listing has a distance of 137.394271 meters. section 7.1.3

How Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI covers it

Cover of Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI

liveBook manning.com

Read Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI on liveBook Get the book at manning.com

Also explained in

liveBook manning.com

Classic Computer Science Problems in Swift: Essential techniques for practicing programmersManhattan distance is the sum of the absolute differences between corresponding coordinates of two points.
liveBook manning.com

Data Without LabelsManhattan distance is the sum of absolute coordinate differences between two points, corresponding to movement along perpendicular axes.
liveBook manning.com

Outlier Detection in PythonManhattan distance is the sum of the absolute coordinate-wise differences between two points.

Compare how 4 books explain Manhattan distance →

Related concepts

Euclidean distancecontrasts with · Euclidean distance is the straight-line distance between two points in Euclidean space, calculated as the square root of the sum of squared differences between corresponding coordinates.
minkowski distanceequivalent to · Minkowski distance is a parameterized metric between points based on a positive-order norm, including Manhattan and Euclidean distance as special cases.
distancecontrasts with · Distance is a measure of separation between points or entities in a defined space or context.
heuristickind of · A heuristic is a practical rule or approximate method for guiding judgment, search, or problem solving without guaranteeing an exact or optimal result.

This explainer was generated by Manning's knowledge graph from the text of Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI. The section links point to the parts of the book it draws on.