This is example code for topic modeling from https://ladal.edu.au/topicmodels.html#Topic_distributions

This is example code from Simon’s AI workshop which explores NLP and its reseaerch uses.

This document provides an example workflow for producing PDPs and grouping them by a categorical variable. This uses the Ames Housing dataset along with Pakistan Conflict data.

This document is to practice using the tidyverse package using the code in the Guide to R book (https://bookdown.org/yih_huynh/Guide-to-R-Book/ifelse.html).

This is a consolidated document containing the data cleaning steps for HMA conflict research.

This code below works through the iml package. The code and examples are from cran’s website. I added additional code related to partial dependency plots and visualizing surrogate model trees.

This code contains the initial data cleaning steps and model runs for an analysis of conflict in High Mountain Asia.

This is an interactive map where users can examine 5,669 observed conflict events in Israeli and Palestinian territories.

This document uses a self organizing map and random forest to examine conflict in Pakistan.

This document outlines the procedures for building a district/year long data frame for Pakistan. It includes the following features/variables: Seasonal temperature (t2m) and precipitation (tp), SPEI, deprivation index, built, total conflict, and conflict by event type. This document also contains useful scripts for NetCDF processing, raster processing, zonal statistics, point data, and GIS functions.

This document introduces self-organized maps - an unsupervised machine learning method. This method is demonstrated with data from the GapMinder project as well as a California housing dataset. GEOG6160 - Lab 10.

This document demonstrates the use of pipelines in the mlr3 package using credit and sonar datasets. GEOG6160 - Lab 9

This document introduces regression and classification neural networks using the mlr3 package in R. Examples of both approaches are presented using cereal and credit score data. GEOG6160-Lab 8.

This lab explores ensemble tree machine learning methods using Pinyon Pine tree and sonar datasets. This lab examines CART, Random Forests, and Boosted Regression Trees. GEOG6160 - Lab 7.

This document introduces the mlr3 package and its use in machine learning. This uses a California housing data set as an example. GEOG6160 - Lab 6

This project is an exploration of climate change and conflict in Pakistan. This project uses the following datasets: Pakistan Conflict Data - Acquired from the Armed Conflict Location and Event Data Project (ACLED) on 21SEP2022. See https://acleddata.com/terms-of-use/ Regional Climate Data - ERA5 Dataset with monthly averaged temperature and precipitation data for January and July beginning in 2010 and ending in 2022. The spatial resolution is approximately 9 kilometers. Temperature data is calculated at 2m above the land surface. Precipitation data is total precipitation between forecast steps (monthly). Reanalysis model. See https://cds.climate.copernicus.eu/cdsapp#!/dataset/reanalysis-era5-land-monthly-means?tab=overview Log Gross National Income Per Capital Variable - From: https://globaldatalab.org/shdi/metadata/lgnic/ Population Data acquired on 07NOV2022 from: https://datacommons.org/place/country/PAK?utm_medium=explore&mprop=count&popt=Person&hl=en Pakistan Gross Domestic Product acquired on 07NOV2022 from: https://data.worldbank.org/indicator/NY.GDP.MKTP.CD?end=2021&locations=PK&start=2010

This document provides example code for examining point patterns and processes using quadrant counts, kernel density, distance functions, marked point processes, and point process models. GEOG6000 lab 14.

This document outlines kriging with external drift, regression kriging, indicator kriging, and geostatistical simulations. These methods are explored using a Swiss precipitation and midwestern US ozone data set. GEOG6000 - Lab 13

This document outlines variograms and the basics of spatial interpolation using ordinary kriging. GEOG6000 - Lab 12

This document walks through the steps for testing for spatial autocorrelation and building spatial models. The initial portion walks through spatial filtering, geographically weighted regression, and spatial hierarchical models. GEOG6000 - Lab 10

This document is a basic introduction to spatial regression models. Statistical tests include the Moran's I and Getis Ord. Models include spatial lag, spatial error, and spatial durbin. GEOG-6000 lab 9.

This document is a basic guide for using tmap and mapview. It also highlights different code to adjust the elements and legend of the map. Please see the links at the beginning of the page for additional resources. GEOG 6000 - Lab 8b

This document is a basic walkthrough of using spatial data using simple features (sf) and raster packages in R. There are some example visualizations and basic statistical analysis using spatial data as well. GEOG 6000 - Lab 8

This document outlines the procedures to perform hierarchical clustering, k-means clustering, and principle component analysis. This code uses climate and housing data. Additionally, this document explores some basic mapping features for spatial data. GEOG6000 - Lab 7

This document contains examples of several visualization techniques using ggplot and plotly.

This document introduces generalized linear models using both binomial and poisson families of data. This document also includes an example of combining boxplots into one figure for better visualization. GEOG6000 - Lab 5

This page uses basic linear modeling techniques to explore basic datasets. There are also methods to compare between models as well. GEOG6000 - Lab 4

This document explores basic plotting techniques using base R. There are some basic ggplot examples in this document as well. GEOG6000 - Lab 3

This document explores hierarchical linear models, generalized hierarchical models, and generalized additive models. This is a great basic overview of using different mixed effects model approaches. Additionally, this uses ggplot and ggplotly to produce interactive figures. GEOG6000 - Lab 6