Geospatial Data Science Quick Start Guide

图书信息

作者	Abdishakur Hassan
出版社	Packt Publishing
ISBN	9781789809336
出版时间	2019-05-31
字数	16.6万
分类	进口书,外文原版书,电脑,网络

读书简介

Discover the power of location data to build effective, intelligent data models with Geospatial ecosystems Key Features * Manipulate location-based data and create intelligent geospatial data models * Build effective location recommendation systems used by popular companies such as Uber * A hands-on guide to help you consume spatial data and parallelize GIS operations effectively Book Description Data scientists, who have access to vast data streams, are a bit myopic when it comes to intrinsic and extrinsic location-based data and are missing out on the intelligence it can provide to their models. This book demonstrates effective techniques for using the power of data science and geospatial intelligence to build effective, intelligent data models that make use of location-based data to give useful predictions and analyses. This book begins with a quick overview of the fundamentals of location-based data and how techniques such as Exploratory Data Analysis can be applied to it. We then delve into spatial operations such as computing distances, areas, extents, centroids, buffer polygons, intersecting geometries, geocoding, and more, which adds additional context to location data. Moving ahead, you will learn how to quickly build and deploy a geo-fencing system using Python. Lastly, you will learn how to leverage geospatial analysis techniques in popular recommendation systems such as collaborative filtering and location-based recommendations, and more. By the end of the book, you will be a rockstar when it comes to performing geospatial analysis with ease. What you will learn * Learn how companies now use location data * Set up your Python environment and install Python geospatial packages * Visualize spatial data as graphs * Extract geometry from spatial data * Perform spatial regression from scratch * Build web applications which dynamically references geospatial data Who this book is for Data Scientists who would like to leverage location-based data and want to use location-based intelligence in their data models will find this book useful. This book is also for GIS developers who wish to incorporate data analysis in their projects. Knowledge of Python programming and some basic understanding of data analysis are all you need to get the most out of this book.

目录

Dedication

About Packt

Why subscribe?

Packt.com

Contributors

About the authors

About the reviewers

Packt is searching for authors like you

Preface

Who this book is for

What this book covers

To get the most out of this book

Download the example code files

Download the color images

Conventions used

Get in touch

Reviews

Introducing Location Intelligence

Location data

Understanding location data from various perspectives

From a business perspective

From a technical perspective

From a data perspective

Types of location data

Location data intelligence

Application of location data intelligence

User or customer perspective

Venue or business perspective

Location data science versus data science

Data science

Location (spatial) data science

A primer on Google Colaboratory and Jupyter Notebooks

Summary

Consuming Location Data Like a Data Scientist

Exploratory data analysis

Handling missing values

Handling time values

Time values as a feature

Handling unrelated data

Spatial data processing

Taxi zones in New York

Visualization of taxi zones

Spatial joins

Calculating distances

Haversine distance

Manhattan distance

Error metric

Interpreting errors

Building the model

Validation data and error metrics

Summary

Performing Spatial Operations Like a Pro

GeoDataFrames and geometries

Geographic coordinates and geometries

Accessing the data

Geometry

Coordinate reference systems

GeoDataFrames

Spatial operations

Projections

Buffer analysis

Spatial joins

Location data visualization

Summary

Making Sense of Humongous Location Datasets

K-means clustering

The crime dataset

Cleaning data

Converting into a GeoDataFrame

K-means clustering with scikit-learn

Density-Based Spatial Clustering Applications with Noise

Detecting outliers

Detecting clusters

Spatial autocorrelation

Points in a polygon

Global spatial autocorrelation

The choropleth map

Spatial similarity and spatial weights

Global spatial autocorrelation

Local spatial autocorrelation

Summary

Nudging Check-Ins with Geofences

Geofencing

Geofencing applications

Marketing and geofencing

Geometry and topology (lines and polygons)

Line geometries

Polygon geometries

Topology – points in a polygon

Geofencing with Plotly

Masking

Plotly interactive maps

Summary

Let's Build a Routing Engine

Fundamentals of graph data structure

Directional graphs

Weighted graphs

Shortest path analysis on a simple graph

Dijkstra's algorithm

Calculating Dijkstra's shortest path

Calculating Dijkstra shortest path length

Calculating single source Dijkstra path length

Turning a simple DataFrame into graphs

Building a graph based on a road network

Open Street Maps data

Exploring the road data

Creating a graph from a DataFrame

Reading and exploding the geometry

Calculating the distance of edges

Finding a proxy for maximum speed

Accounting for directionality

Calculating drivetime

Building the graph

Shortest path analyses on the road network graph

Dijkstra's shortest path analysis

Dijkstra's shortest path cost

Single source Dijkstra's shortest path cost

Concept of isochrones

Constructing an isochrone

Summary

Getting Location Recommender Systems

Exploratory data analysis

Rating data

Restaurants data

Recommender systems

KNNWithMeans

SVDpp

Comparison and interpretations

Location-based recommenders

Summary

Other Books You May Enjoy

Leave a review - let other readers know what you think