Numbers do not speak for themselves!. We make them talk.
An essential part of data analysis is communication. We need to arrange information in a comfortable and digestible way to communicate, highlight and visualise critical areas.
Dashboards take your data visualisation to the next level. They connect different visualisation components and make a whole and integrated data visualisation stories. Web application Dashboards also allow users to interact with the data and the visualisation, offering them to see and adjust what they want or need.
It has never been easier to create a dashboard in Python. We have several dashboard tools…
Road accidents — a leading cause of all deaths globally — is a major problem around the globe. Can a Machine Learning model help us understand, classify and predict crash severity based on spatial data?
This will be a three-part series article. In this first article, I will train a baseline model for one city. We will use Pycaret, a convenient Low-code machine learning library.
In the next article, we will use Geospatial Feature Engineering to improve our base model. The final part will scale the process to train a model for the whole of USA country car accidents.
Machine learning(ML) is hard to learn; especially it’s algorithms, data preprocessing and training models.
It is not the case anymore!
With the rise and availability of both no-code and low-code machine learning libraries and platforms, there are fewer barriers to use and apply machine learning models on your applications.
Low-code/No-code platforms and libraries enable users to run machine learning models easily by providing a ready-to-use code and functions. You can access these functions either through a web interface or writing minimal code.
While no-code platforms are the easiest way to train a Machine Learning model through drag and drop interface…
GIS skills and education have changed over the past years. “I’ve been GIS. Now I’m geospatial.” writes Will Cadell in a recent article titled Geospatial Is Not GIS.
As a GIS person typically produces cartographic and analytical products using desktop software, Geospatial data scientist creates code and runs pipelines that produce analytical products and cartographic representations. The difference might seem subtle, but it requires a new set of tools and mindset.
The GIS skills are still relevant, but there are a lot of other skillsets necessary for geospatial data scientists to succeed, some obvious while others are less known. A…
The satellite-based earth observation data is increasing at a rapid base, thanks to technological development in remote sensing platforms, and breakthroughs in data collection and storage. Today, we have more than 768 earth observation satellites in orbit, compared with only 150 in 2018.
As a Geospatial or earth observation data scientist, you have a vast array of tools and resources to choose. In this article, I highlight the best open source tools in the market that are integrated into the data science ecosystem.
Your wish granted. GEE is all in one package. Google Earth Engine(GEE) is by far the complete…
Recently, I thought back to a few years ago, when I tried to process a large geospatial dataset with Python. You can only guess how it ended. My laptop refused to cooperate and froze spectacularly without failing.
Fast forward today, I was experimenting with RAPIDS AI Suite and came across the same dataset. I immediately knew what to do. So I jumped into coding.
The RAPIDS suite of open source software libraries and APIs gives you the ability to execute end-to-end data science and analytics pipelines entirely on GPUs.
In this tutorial, I will go through a complete…
Learning Programming for GIS and Geospatial data analysis can be overwhelming, especially learning from unorganized resources and tutorials.
I know that because I have made the transition from GIS to geospatial data science earlier. It took me many years to grapple with different resources and materials for data science without having a tailored Geospatial data science course.
That is why I have made this course to help you kickstart your geospatial data science career and learn the basics right.
I have structured the course to be beginner-friendly to make sure a smooth learning experience. …
Remote sensed data might contain noise and other deficiencies derived from the sensors onboard or radiative transfer processes. Therefore, we often conduct further preprocessing techniques to deal with such flaws. These different processing techniques are generally referred to as Image Processing.
Image processing is a method to perform some operations on an image, in order to get an enhanced image or to extract some useful information from it. It is a type of signal processing in which input is an image and output may be image or characteristics/features associated with that image — Digital Image Processing.
There are several Image…
The new Geopandas 0.9.0 release brings forth improvements, bug fixes, and additional features. Here are some of my favorite new features.
You can now use
GeoDataFrame.plot() to not only create static maps but also create any Pandas Chart. This is much more convenient than transitioning between Pandas and Geopandas when we want to plot non-geographic plots or use other libraries (i,e. matplotlib or seaborn)
Forexample, you can have side-by-side plots, including a map and nongeographic plot using Geopandas.
gdf = gpd.read_file(gpd.datasets.get_path(“naturalearth_lowres”))
fig, ax = plt.subplots(1,2, figsize=(12,10))
gdf.plot(“pop_est”, cmap=”Reds”, ax=ax)
gdf.sort_values(by=[‘pop_est’], ascending=False).head(10).plot(kind=”bar”, x=”name”, y=”gdp_md_est”, ax=ax)
In Geospatial data analysis, Spatial Proximity plays a key role. We create valuable insights using topological information relative to a location (Point, line, or areas) with Spatial proximity analysis.
Geographic data science