Machine Learning on Geographical Data Using Python: Introduction into Geodata with Applications and Use Cases

Table of Contents
About the Author
About the Technical Reviewer
Introduction
Part I: General Introduction
	Chapter 1: Introduction to Geodata
		Reading Guide for This Book
		Geodata Definitions
			Cartesian Coordinates
			Polar Coordinates and Degrees
			The Difference with Reality
		Geographic Information Systems and Common Tools
			What Are Geographic Information Systems
				ArcGIS
				QGIS and Other Open Source ArcGIS Alternatives
				Python/R Programming
		Standard Formats of Geodata
			Shapefile
			Google KML File
			GeoJSON
			TIFF/JPEG/PNG
			CSV/TXT/Excel
		Overview of Python Tools for Geodata
		Key Takeaways
	Chapter 2: Coordinate Systems and Projections
		Coordinate Systems
			Geographic Coordinate Systems
				Latitude and Longitude
				WGS 1984 Geographic Coordinate System
				Other Geographic Coordinate Systems
			Projected Coordinate Systems
				X and Y Coordinates
				Four Types of Projected Coordinate Systems
					Equal Area Projections
						Example 1: Mollweide Projection
						Example 2: Albers Equal Area Conic
					Conformal Projections
						Mercator
						Lambert Conformal Conic
					Equidistant Projections
						Azimuthal Equidistant Projection
						Equidistant Conic Projection
					True Direction or Azimuthal Projections
						Lambert Equal Area Azimuthal
						Two-Point Equidistant Projection
			Local Coordinate Systems
		Which Coordinate System to Choose
		Playing Around with Some Maps
			Example: Working with Own Data
				Step 1: Make Your Own Dataset on Google My Maps
				Step 2: Add Some Features on Your Map
				Step 3: Export Your Map As a .KML
				Step 4: Import the .KML in Python
				Step 5: Plot the Map
				Step 6: Change the Coordinate System
				Step 7: Plot the Map Again
		Key Takeaways
	Chapter 3: Geodata Data Types
		Vector vs. Raster Data
			Dealing with Attributes in Vector and Raster
		Points
			Definition of a Point
			Importing an Example Point Dataset in Python
			Some Basic Operations with Points
				Filter Morning vs. Afternoon
		Lines
			Definition of a Line
			An Example Line Dataset in Python
		Polygons
			Definition of a Polygon
			An Example Polygon Dataset in Python
			Some Simple Operations with Polygons
		Rasters/Grids
			Definition of a Grid or Raster
			Importing a Raster Dataset in Python
		Key Takeaways
	Chapter 4: Creating Maps
		Mapping Using Geopandas and Matplotlib
			Getting a Dataset into Python
			Making a Basic Plot
			Plot Title
			Plot Legend
			Mapping a Point Dataset with Geopandas and Matplotlib
			Concluding on Mapping with Geopandas and Matplotlib
		Making a Map with Cartopy
			Concluding on Mapping with Cartopy
		Making a Map with Plotly
			Concluding on Mapping with Plotly
		Making a Map with Folium
			Concluding on Mapping with Folium
		Key Takeaways
Part II: GIS Operations
	Chapter 5: Clipping and Intersecting
		What Is Clipping?
			A Schematic Example of Clipping
			What Happens in Practice When Clipping?
			Clipping in Python
		What Is Intersecting?
			What Happens in Practice When Intersecting?
			Conceptual Examples of Intersecting Geodata
		Intersecting in Python
			Difference Between Clipping and Intersecting
		Key Takeaways
	Chapter 6: Buffers
		What Are Buffers?
			A Schematic Example of Buffering
			What Happens in Practice When Buffering?
				Buffers for Point Data
				Buffers for Line Data
				Buffers for Polygon Data
		Creating Buffers in Python
			Creating Buffers Around Points in Python
			Creating Buffers Around Lines in Python
			Creating Buffers Around Polygons in Python
		Combining Buffers and Set Operations
		Key Takeaways
	Chapter 7: Merge and Dissolve
		The Merge Operation
			What Is a Merge?
			A Schematic Example of Merging
				Different Definitions of Merging
		Merging in Python
			Row-Wise Merging in Python
			Attribute Join in Python
			Spatial Join in Python
		The Dissolve Operation
			What Is the Dissolve Operation?
			Schematic Overview of the Dissolve Operation
			The Dissolve Operation in Python
		Key Takeaways
	Chapter 8: Erase
		The Erase Operation
			Schematic Overview of Spatially Erasing Points
			Schematic Overview of Spatially Erasing Lines
			Schematic Overview of Spatially Erasing Polygons
		Erase vs. Other Operations
			Erase vs. Deleting a Feature
			Erase vs. Clip
			Erase vs. Overlay
		Erasing in Python
			Erasing Portugal from Iberia to Obtain Spain
			Erasing Points in Portugal from the Dataset
			Cutting Lines to Be Only in Spain
		Key Takeaways
Part III: Machine Learning and Mathematics
	Chapter 9: Interpolation
		What Is Interpolation?
		Different Types of Interpolation
			Linear Interpolation
			Polynomial Interpolation
				Piecewise Polynomial or Spline
			Nearest Neighbor Interpolation
		From One-Dimensional to Spatial Interpolation
		Spatial Interpolation in Python
			Linear Interpolation Using Scipy Interp2d
		Kriging
			Linear Ordinary Kriging
			Gaussian Ordinary Kriging
			Exponential Ordinary Kriging
		Conclusion on Interpolation Methods
		Key Takeaways
	Chapter 10: Classification
		Quick Intro to Machine Learning
		Quick Intro to Classification
		Spatial Classification Use Case
			Feature Engineering with Additional Data
			Importing and Inspecting the Data
			Spatial Operations for Feature Engineering
			Reorganizing and Standardizing the Data
			Modeling
			Model Benchmarking
		Key Takeaways
	Chapter 11: Regression
		Introduction to Regression
		Spatial Regression Use Case
			Importing and Preparing Data
			Iteration 1 of Data Exploration
			Iteration 1 of the Model
				Interpretation of Iteration 1 Model
			Iteration 2 of Data Exploration
			Iteration 2 of the Model
			Iteration 3 of the Model
			Iteration 4 of the Model
			Interpretation of Iteration 4 Model
		Key Takeaways
	Chapter 12: Clustering
		Introduction to Unsupervised Modeling
		Introduction to Clustering
		Different Clustering Models
		Spatial Clustering Use Case
		Importing and Inspecting the Data
		Cluster Model for One Person
		Tuning the Clustering Model
		Applying the Model to All Data
		Key Takeaways
	Chapter 13: Conclusion
		What You Should Remember from This Book
			Recap of Chapter 1 – Introduction to Geodata
			Recap of Chapter 2 – Coordinate Systems and Projections
			Recap of Chapter 3 – Geodata Data Types
			Recap of Chapter 4 – Creating Maps
			Recap of Chapter 5 – Clipping and Intersecting
			Recap of Chapter 6 – Buffers
			Recap of Chapter 7 – Merge and Dissolve
			Recap of Chapter 8 – Erase
			Recap of Chapter 9 – Interpolation
			Recap of Chapter 10 – Classification
			Recap of Chapter 11 – Regression
			Recap of Chapter 12 – Clustering
		Further Learning Path
			Going into Specialized GIS
			Specializing in Machine Learning
			Remote Sensing and Image Treatment
			Other Specialties
		Key Takeaways
Index