Learn how to repurpose machine learning code in R for new datasets in this comprehensive tutorial video. Explore the process of adapting existing R code to model a new dataset, specifically focusing on the DHFR (dihydrofolate reductase) data. Follow along as the instructor guides you through launching RStudio, loading and exploring the DHFR dataset, performing summary statistics, creating visualizations, and building a classification model. Gain practical skills in data understanding, feature analysis, and model building while learning how to effectively reuse and modify R code for different datasets.
Machine Learning in R - Repurpose Machine Learning Code for New Data
Overview
Syllabus
Launch RStudio or RStudio.cloud
Open iris-data-understanding.R file
Create a copy of iris-data-understanding.R
Save as dhfr-data-understanding.R
What is DHFR?
Load in DHFR data, type: librarydatasets and then datadhfr
Perform summary statistics
Use skimr package to explore the data
Make a scatter plot
Make a histogram
Make feature plots
Let's build the DHFR classification model
Load in the libraries
Set the seed for reproducibility
Build the training and CV models
Let's look at prediction results
Let's make Feature importance plots
Taught by
Data Professor
