Reid Falconer's repositories
landcover_classification
Determine land use and land cover classification based on Sentinel-2 satellite images with state-of-the-art performance π°
landcover_segmentation
Automatic categorization and segmentation of land cover πΊ(U-NET FastAI library)
rl_automated_trading
In this project, we apply a deep Q-learning approach to algorithmic trading where our algorithmic trader determines when to buy, sell or hold based on the current and historical market data. π€π
aws_dashboard_deployment
Blog post: Steps to deploy a flexdashboard or shiny app using AWS and R-Shiny and RStudio Servers
super_resolution
Sattelite Image Super-Resolution using Convolution Neural Networks and Auto-encoders π
text_mining_jobs
A basic introduction to text mining in R using the tidytext package on career24 job descriptions
14D001_spatial_cv
Cross-Validation for Model Assessment and Model Selection with Geospatial Data ππ
14D002_programming_projects
In this project, we analyse two algorithms, the Edit distance to calculate the least number of edit operations that are necessary to modify one string into another and Huffman codes to construct the optimal prefix code given input text.
14D004_computing_assignment
14D004 Computing Assignment: EDA of Traffic Accidents in the United Kingdom Between 2005-2015 π
14D004_scraping_project
14D004 Scraping Project: Scrape all the available courses on datacamp.com and scape all job posts on jobsinbarcelona.es using scrapy
15D019_exercise
Basic Demand Estimation Exercise - Estimating the demand elasticities of Kraft and Hellman's mayonnaise in the broader Chicago market
15D019_final_project
15D019 Final Project: When it Hurts: demand estimation in the market for over the counter (OTC) analgesics using a nested logit model.
balena-sense-hat-python-starter
A starter project with Python3 and Sense-HAT library ready to go
customer_churn
The goal is to estimate usersβ long-term (30 days later) engagement (engaged vs churned) with the news site based on their interactions with the site in the short term.
line_search_methods
The Algorithmic Showdown: Gradient Descent vs Newton's Method
predicting-poverty
Combining satellite imagery and machine learning to predict poverty
satisfaction_xgboost
In this project we build a xgboost model to classify individuals life satisfaction using the variables in the National Income Dynamic Studies (NIDS) database.
spatial_plots
Spatial plotting in R: an example using IEC voting data in South Africa.
text-mining
Class Folder for Text Mining for the Social Sciences @BGSE