Adedoyin Samuel's repositories
geospatial-de-pipeline
This repository contains FarmWatch, an innovative pipeline for monitoring agricultural lands using satellite imagery and geospatial data processing. It integrates OpenStreetMap (OSM) to extract updated farmland data and analyzes vegetation indices from satellite imagery, providing updates every 5 days for real-time agricultural insights.
geoai-ground-level-no2-estimation-challenge
This repository focuses on GeoAI-based ground-level NO₂ estimation, developing machine learning models to predict surface NO₂ concentrations using only public remote sensing data as predictor variables.
airbnb-spatial-analysis
This repository contains a spatial analysis of Airbnb data, exploring its relationship with housing prices and the short-let market using geospatial data science techniques such as hotspot analysis, spatial autocorrelation, and regression modeling.
airflow-forex-etl-pipeline
This project demonstrates the implementation of an ETL (Extract, Transform, Load) pipeline using Apache Airflow and Docker. The pipeline extracts data from a Forex API, processes it, and loads it into a PostgreSQL database.
dsn-meta-geospatial-hackathon
This project evaluates healthcare accessibility in Zamfara State, Nigeria, using spatial and non-spatial data. It analyzes population coverage within a 500m radius of existing facilities, identifies areas suitable for new facilities, and highlights regions with low healthcare access.
matto-grosso-soc-prediction
This repository focuses on predicting Soil Organic Carbon (SOC) values using spatial data analysis and machine learning techniques. It integrates geospatial datasets, applies predictive modeling, and leverages spatial interpolation to enhance SOC estimation accuracy.
scrape-property-listing-for-london
This repository contains a comprehensive dataset of listed properties across Greater London, extracted and blended from multiple sources. The goal is to create a unified property dataset to support informed decision-making in property selection, valuation, and market analysis.
spatial-analysis-with-duck-db
This repository is designed for learning spatial GIS processing with DuckDB, featuring practical examples on geospatial data handling, querying, and analysis.
arcgis_connector
This project is an ETL pipeline that extracts data from an ArcGIS Feature Service, transforms it into formats like JSON and GeoDataFrame, and loads it into storage destinations such as PostgreSQL, CSV, Shapefile, or GeoJSON.
cng_streamlit_app
This repository contains the code for a Streamlit application designed to visualize and analyze geospatial data using Leaflet. The app provides interactive features such as filtering and metrics for geospatial data related to a specific dataset.
data-engineer-handbook
This is a repo with links to everything you'd ever want to learn about data engineering
data-engineering-with-data-build-tool-dbt-4458303
This is a code repository for the course Data Engineering with Data Build Tool (DBT).
dec-hackathon-team-1-solution
This project involves building a simple yet robust data pipeline that extracts country-related information from a public REST API, transforms and cleans the data, and stores it in a database for efficient retrieval and analysis.
GIS-Community-Resources
A repository of GIS books, tools, datasets, and tutorials for all skill levels. Explore resources on spatial analysis, webgis, remote sensing, and mapping. Perfect for beginners and experts alike!
mbtiles_style
This repository contains styles and configurations for rendering MBTiles, enabling seamless visualization of tiled geospatial data in mapping applications.
mini_project
A repository of side projects I'm currently working on, exploring various topics through hands-on learning and practical implementation.
ml-flood-prediction
This project develops a machine learning model that predicts the likelihood of flooding in a given area using data sourced from various APIs. The model analyzes topographical and environmental factors to generate predictions, aiding in flood risk assessment and mitigation.
ny_taxi_ride_zoocamp_dbt
This repository focuses on learning database management using the NYC Taxi Ride dataset, following the Data Engineering Zoomcamp framework. It covers data ingestion, transformation, and storage, applying best practices in database optimization and query performance.
perth-poi-etl
This repository contains a script for ingesting geospatial data from various sources, such as schools, police facilities, and hospitals. The data is extracted using multiple APIs and libraries, transformed into a suitable format, and loaded into a PostgreSQL database.
Realtime-Data-Streaming-End-To-End-Data-Engineering-Project
This repository provides a hands-on tutorial for building a data engineering pipeline using the RandomUser API. It demonstrates real-time data streaming with Apache Kafka, data processing with Apache Spark, and storage in Cassandra and PostgreSQL. The workflow is orchestrated with Apache Airflow, and the entire system is containerized using Docker
Realtime-Voting-System-End-to-End-Data-Engineering-Project
This repository is designed for learning data engineering by simulating a real-time voting process. It covers data ingestion, processing, and storage, demonstrating key concepts such as streaming data pipelines, database management, and real-time analytics.
sammygis.github.io
This repository contains the source code for my personal portfolio website, showcasing my work, projects, and expertise in geospatial data science, geospatial data engineering, machine learning, and GIS.
scrape-medifind
This repository contains a two layer data scrapping scripts where the first scripts gets the link to the doctors profile and the second scripts extract all the doctors profile based on different medical conditions from a healthcare website.
streamlit-app
his repository contains a Streamlit app designed to visualize data using dynamic choropleth maps. The project serves as a learning tool for building interactive dashboards with Streamlit, incorporating real-time data updates, user input, and geospatial visualizations.
uber-data-analytics-and-etl
This project aims to conduct comprehensive data analytics on Uber data using a robust stack of tools and technologies, including Google Cloud Platform (GCP), Python, Compute Instance, Mage Data Pipeline Tool, BigQuery, and Looker Studio.