Projects
fetchr aims to swiftly and effectively calculate fetch lengths across numerous water grid cells. Traditionally, determining fetch lengths for multiple points in various directions has been slow and resource-intensive. fetchr addresses this challenge by significantly reducing the time required for thousands of fetch calculations.
R 📦 for fast and scalable wind fetch calculations
The goal of cdsspy is to provide functions that help Python users to navigate, explore, and make requests to the CDSS REST API web service.
The Colorado’s Decision Support Systems (CDSS) is a water management system created and developed by the Colorado Water Conservation Board (CWCB) and the Colorado Division of Water Resources (DWR).
cdsspy
Python 📦 for exploring and requesting resources from the CDSS REST API
The goal of cdssr is to provide functions that help R users to navigate, explore, and make requests to the CDSS REST API web service.
The Colorado’s Decision Support Systems (CDSS) is a water management system created and developed by the Colorado Water Conservation Board (CWCB) and the Colorado Division of Water Resources (DWR).
cdssr
R 📦 for exploring and requesting resources from the CDSS REST API
Interactive R Shiny dashboard that displays each inventoried low head dam and its scores across all interest domains. Explores summaries of the inventory using the maps, data table, or plots. Manipulates how composite scores are calculated to reflect preferences on domain importance.
R Shiny Dashboard for visualizing Low Head Dam scoring analysis.
Interactive R Shiny dashboard that implements a multiple linear regression approach to determine the optimal set of climate variables for predicting water shortages in each district. The dashboard allows users to visualize and analyze the relationship between climate variables and water shortages.
R Shiny dashboard to visualize model approaches using StateMOD water allocation modeling project data outputs
By leveraging historical data on NFL team's offensive and defensive performances, I sought to determine if accurate predictions could be made about their upcoming game outcomes. Using R, specifically the tidyverse and tidymodels ecosystems, I handled data ingestion, processing, analysis, and modeling.
Predicting NFL wins using Machine Learning
