Recently Published
OPTICS algorithm hyper tuning process
xi hyper_tuning process in OPTICS algorithm.
Sampling the Imaginary: Using Bayesian Models for Understanding and Prediction
Intro to Quantitative Biology (BIOL 325)
February 16, 2024
Spring 2024
William & Mary
Data Science Project
Select one dataset (that you find interesting) from the “datasets” folder: datasets or if you have your research dataset you can use that too. But make sure your personal dataset contains
At least 2 numerical columns
One target column
Download it and move it to your working directory (or any directory you feel comfortable with) of R Studio.
Create a notebook file in R studio and load the dataset in a variable.
Write a few sentences to explain the dataset.
Identify numerical columns
Identify categorical columns
Identify the target variable (the last column is the target variable)
Remove all the categorical columns (not the target column) from the dataset. Now we will call all the numerical columns as features and the last column as target or class.
Use the ggplot2 library functions to plot the following and explain each figure in (2-3) sentences.
A scatter plot of 3 combinations of any two features where each class (target) should be represented with different colours.
Boxplot of all columns where each class (target) should be represented with different colours. If you have 5 features and 2 target categories, you will create 5 plots where each plot will contain 2 boxes.
Violin plot of all columns where each class (target) should be represented with different colours. If you have 5 features and 2 target categories, you will create 5 plots where each plot will contain 2 violins.