Spatial data is rapidly transforming data science, enabling nuanced insights across disciplines from environmental monitoring to urban planning. This chapter is one of the most unique in this book because it focuses on spatial data, a topic rarely covered in data science references. While many data science resources exist, few explore spatial data's unique aspects. Nowadays, most data includes location information, which can greatly enhance data science and decision-making. In this chapter, we’ll explore how spatial data is represented and structured and how it’s collected, stored, managed, analyzed, and visualized, as well as its various applications. We’ll also discuss how to assess the uncertainty in spatial data, and we’ll conclude with an explanation of common sources of error in spatial data, such as human, environmental, and instrument-related factors. In the next part of this chapter, we will practice working with the two main types of spatial data: vector and raster. Using Japan as our study case, we’ll join population data (in CSV format) with Japan’s prefecture-level administrative boundaries (in shapefile format). We’ll then create population change data through simple calculations and visualize the results using static and dynamic maps. Furthermore, we’ll work with earth observation satellite imageries to calculate the NDVI and create a land use land cover map using a machine learning algorithm and supervised method. We will also practice with the Nighttime Light (NTL) imagery of Black Marble datasets to visualize the changes in the NTL radiance image. We’ll also practice extracting annual data from NTL and plotting it using bar plots in RStudio.