Geospatial data analysis with python

Explore reading, writing, and visualizing geospatial data with the open source Python package, including data conversion, filtering, and vector geometry operations such as points, lines, polygons, and buffers.

Install geopandas in python and import the required geospatial libraries to set up a ready-to-use geospatial data analysis environment.

Learn to upload, read, and inspect vector data in Python, view attributes and results, and visualize geospatial datasets with map tools and database integration.

Explore the metadata of the data frame by counting records with len(df), checking the coordinate system, and confirming the geometry type as polygons.

Visualize vector data on a map, color features by a chosen column to reveal districts in different colors, and tailor output with package imports.

Write vector data from a geospatial data frame in Python, export to multiple formats with configurable drivers, encoding, and file paths for easy download and map visualization.

Learn to work with an attribute table by filtering data with conditions, selecting provinces, and visualizing results with maps, while adding and computing area and setting the coordinate system.

Learn to build geospatial data with Shapely by manually entering latitude and longitude to create point, line, and polygon geometries, assign a coordinate system, and export shapefiles.

Learn how to dissolve municipalities into districts using Python geospatial tools, filter and aggregate data by district, and create an area-based choropleth map for Nepal's 77 districts.

Merge the population file with the spatial file to create a new zip code name, aligning area, distinct name, registered voter, and total population for geospatial analysis in Python.

Load population geospatial data, create a data frame, and merge datasets on matching district columns with a left join, preserving geometry for visualization.

Log in or register to access Copernicus land cover datasets and download the 2001 Langkawi land cover grid via the CBS API using Python for analysis.

Install rasterio in a Python notebook, import rasterio successfully, and manage library versions (e.g., 1.2.6) to ensure compatibility during geospatial data analysis.

Read a raster dataset in Python by uploading the file to Google Colab, opening it with a one-line reader, and inspecting its data and metadata.

Learn to read raster metadata from a Palenque 2020 map, including dimensions, bands, data type, driver, size, and coordinate system, plus missing data handling and conversion to projected coordinates.

Visualize raster data by applying color maps and titles to maps in a notebook, experimenting with color maps such as mild winter, and interpreting land cover class frequencies in Nepal.

Create the output folder, prepare the input dataset, and specify driver, width, height, bands, series parameter, and data type to write a tiff file.

Learn to perform pixel-wise mathematical operations on raster data, including add, subtract, and divide, while handling unsigned 8-bit values and updating metadata for writing outputs.

Mask a tiff file with a shapefile using Python in geospatial data analysis, reading the shapefile, applying the mask, cropping the result, and writing the masked output with updated metadata.

This lecture demonstrates raster reclassification in python by reading data, applying conditional thresholds to group values into six land-cover classes, and producing a classified map with forest, grassland, and water.

Explore raster resampling in geospatial analysis, comparing upsampling and downsampling, and applying techniques like nearest neighbor and bilinear interpolation to adjust raster resolution.

Learn to reproject a raster to a new coordinate system, selecting a Nepal projected CRS, applying nearest neighbor resampling, updating metadata, and validating the transformation parameters.

Calculate NDVI in Python by uploading two datasets, selecting the red band locations, applying the normalized difference formula, and visualizing results with red and green color mapping.

Fix small issues in the NDVI calculation by manually setting the data type to 64 to improve color mapping. This yields the exact NBPA map.

Generate interactive maps in python with geopandas, reading shapefiles, plotting choropleth maps with matplotlib, and customizing colors, legends, and axes for Nepal's districts and provinces.

Learn to compute zonal statistics on raster data with the raster state package. The tutorial covers mean, max, standard deviation, and area calculations for land use classes, including categorical rasters.

Learn to add or remove bands from sentinel-2 imagery using rasterio in python, including rgb extraction, ndvi computation, and saving a seven-band raster.

Download Google's building footprint dataset for your area of interest in shapefile or GeoJSON. Learn to convert large CSV exports to geospatial formats using geopandas and dask.