Podcast Summary

Podcast: New Books Network

Host: Devika Jain
Guest: Dr. Milan Janosov
Book Discussed: Geospatial Data Science Essentials: 101 Practical Python Tips and Tricks (2024)
Date: September 6, 2025

Episode Overview

This episode features an engaging conversation between host Devika Jain and Dr. Milan Janosov, discussing his new book, Geospatial Data Science Essentials: 101 Practical Python Tips and Tricks. The book caters to those aspiring to master geospatial analytics with Python, whether they're data science veterans, GIS professionals, total newcomers, or simply map enthusiasts. The discussion covers the book’s genesis, its practical approach, essential tools and libraries, and the evolving landscape of geospatial data science.

Key Discussion Points & Insights

Origins & Audience of the Book

• Accidental Beginnings:
  • Milan explains the book started as a personal cheat sheet compiling Python snippets and tips he used frequently in geospatial data work. Over time, as the list grew and explanations were added, it naturally evolved into a book.

    “So, long story short, it was not planned, it was merely an accident that I wrote this book.” — Milan (04:50)

• Target Readers:
  • Initially, there was no clear audience, but Milan realized it’s the book he wished he'd had at the start of his own journey.

    “So to answer the question very quickly, the audience was whoever wants to learn geospatial data science in Python, or want to upgrade their skills or fill all the gaps at the foundational parts…” — Milan (06:11)

Content & Structure of the Book

• Data-Driven Compilation:
  • Milan ran a Python script over his old notebooks to identify the most-used libraries and code patterns, shaping the book’s content.
    • Main topics include vector data, raster data, OpenStreetMap, and practical tools.
• Practical First Approach:
  • The book focuses on actionable tips and code rather than deep, abstract theory.

    “Let's write something which is really straight to the point and like a quick shortcut to get there.” — Milan (08:34)

  • Emphasizes relevance for those who need to get projects done quickly in real-world settings.

Why Spatial Data Science Now?

• Timely Field:
  • Geospatial data science is rapidly evolving, with better tools, greater data availability, and major AI-driven advancements.

    “...now, of course, we are in this AI era… just during the past month there was at least one major GeoAI announcement per week.” — Milan (10:22)

Core Toolkits & Libraries

• Must-Know Libraries for Beginners:
  • GeoPandas:

    “GeoPandas is like, I think that the Swiss knife of spatial data science... 80% or maybe 95% of the datasets or vector data can be very well handled with GeoPandas.” — Milan (12:33)

  • Rasterio: For raster data (image-like grid data).
  • Shapely: Under-the-hood geometry creation and manipulation.
• Examples in the Book:
  • Projects span basic reading and manipulation, visualization, and network analysis, often inspired by Milan’s own urban planning and academic work.

Fundamentals: Geometry, CRS, and Map Projections

• Emphasis on Foundations:
  • Milan highlights the importance of understanding geometries, coordinate systems, and projections for data accuracy and troubleshooting.

    “I think it's really worth spending two hours on reviewing it from scratch… especially if we are iterating between platforms, GIS platforms and Python…” — Milan (15:36)

• Real-World Lessons:
  • Many spatial data issues stem from a lack of understanding of these fundamentals; “better to learn it through the book than… the hard way!” (17:47)

Vector vs. Raster Data

• Key Distinctions:
  • Vector: Points, lines, polygons; scale-independent shapes.
  • Raster: Gridded, pixel-based images.
  • Skills include reading, processing, cleaning, reprojection, and visualization.

Open Data & OpenStreetMap

• Role of Open & Crowdsourced Data:
  • OpenStreetMap (OSM) is a favored data source for its richness and accessibility.

    “Whatever data project I work on, OSM is one of the first sources I check out… we have like a complete digital twin of the whole planet in decent vector and raster formats.” — Milan (21:07)

• Future Trends:
  • Quality of open data is catching up to proprietary sources, democratizing access and research.

Advanced Topics: Spatial Networks & Machine Learning

• Advanced Glimpses:
  • Intro-level exposure to advanced topics, e.g., spatial network analysis, machine learning.
  • Practical example: Calculating accessibility in urban settings (e.g., 15-minute cities).

    “...using spatial networks, we can compute for every single point in our neighborhood, how many minutes does it take to reach, for example by walk, the nearest doctor's office?” — Milan (23:41)

“Prep and Go” Philosophy

• Who Should Use the Book:
  • Anyone suddenly facing geospatial data—data scientists, analysts, or professionals encountering coordinates, shapefiles, or geoJSONs in their work.

    “...we can just grab this book and start figuring out how we want to analyze the data. Because this book...will help to read the data, turn it into a data frame, explore the basic features, create visualizations…” — Milan (26:19)

  • Not only for “spatial data scientists” but for “data scientists working with spatial data.” (28:01)

Visualization: More Than an Afterthought

• Maps as Communication:
  • The book covers tools like matplotlib, plotly, pydeck for map creation and data visualization.
  • Milan observes that visually compelling maps attract more attention—important even in academic contexts.

    “It seems to me that having the right visual language for even the most academic paper is probably a must just because now we need to be seen because there is just so much stuff out there competing for our attention.” — Milan (30:41)

Takeaway Advice

• Most Important Lesson:
  • Get your data right—ensure the spatial data is valid and properly described before anything else.

    “So what's the crs, what's the spatial coverage? Whether the geometry component is accurate and all the geometries are valid...the most important part is to learn how to make sure that the spatial data set we have is in a good shape.” — Milan (31:31)

• Quick Map Visual:
  • A quick map plot is often the best first check for spatial data sanity.

What’s Next from Milan?

• Upcoming Projects:
  • Milan is developing a linked series of courses on LinkedIn Learning and Udemy, forming a coherent learning journey on geospatial data science (“mini program”).
  • The book offers a quick-start, while the courses go deeper and slower; both complement each other.

Notable Quotes & Memorable Moments

• On the Unplanned Origins:

  • “It was not planned, it was merely an accident that I wrote this book.” — Milan (04:50)

• On Audience:

  • “The audience was whoever wants to learn geospatial data science in Python, or want to upgrade their skills or like fill all the gaps at the foundational parts...” — Milan (06:11)

• On the Value of Practical Guides:

  • “Let's write something which is really straight to the point and like a quick shortcut...” — Milan (08:34)

• On OpenStreetMap:

  • “Whatever data project I work on, OSM is one of the first sources I check out and I think that we are moving to a direction where open source spatial data will be... just as good in quality as propriety data without all those restrictions...” — Milan (21:07)

• On Visualization:

  • “It seems to me that having the right visual language for even the most academic paper is probably a must...” — Milan (30:41)

• On the Book’s Purpose:

  • “This book is not for spatial data scientists, but for data scientists working with spatial data.” — Milan (28:01)

• On the Most Important Skill:

  • “The most important part is to learn how to make sure that the spatial data set we have is in a good shape.” — Milan (31:31)

Timestamps for Important Segments

• Introduction & Book Origins: [01:36–05:19]
• Audience & Content: [05:19–07:43]
• Practical First Approach: [07:43–09:14]
• Why Geospatial Now: [09:14–11:12]
• Key Tools (GeoPandas, etc.): [11:12–13:49]
• Fundamentals (Geometry & Projections): [14:57–16:58]
• Vector vs Raster, Examples: [18:11–19:54]
• Open Data & OpenStreetMap: [19:54–22:00]
• Advanced Topics (Networks, ML): [22:52–25:19]
• “Prep and Go” Approach: [25:57–27:14]
• Visualization & Map Design: [29:09–30:53]
• Takeaway Key Advice: [31:31–32:26]
• Future Projects/Courses: [32:55–34:32]

Overall Tone

The conversation is practical, friendly, and highly encouraging—Milan’s passion for democratizing geospatial data science is infectious, making the topic and his book approachable for a broad audience.

Recommended for:

• Anyone working with geospatial data, regardless of prior GIS experience
• Data scientists who suddenly encounter spatial datasets in their workflows
• Map enthusiasts and GIS beginners
• Professionals needing a pragmatic, hands-on Python reference for spatial data tasks

Summary prepared for listeners who want deep insights and actionable takeaways from the episode without the need to listen to all 35 minutes.