AE 17: Forest classification

Application exercise

In this application exercise, we will

Split our data into testing and training
Fit logistic regression regression models to testing data to classify outcomes
Evaluate performance of models on testing data

We will use tidyverse and tidymodels for data exploration and modeling, respectively, and the forested package for the data.

library(tidyverse)
library(tidymodels)
library(forested)

Remember from the lecture that the forested dataset contains information on whether a plot is forested (Yes) or not (No) as well as numerical and categorical features of that plot.

glimpse(forested)

Rows: 7,107
Columns: 19
$ forested         <fct> Yes, Yes, No, Yes, Yes, Yes, Yes, Yes, Yes, Yes, Yes,…
$ year             <dbl> 2005, 2005, 2005, 2005, 2005, 2005, 2005, 2005, 2005,…
$ elevation        <dbl> 881, 113, 164, 299, 806, 736, 636, 224, 52, 2240, 104…
$ eastness         <dbl> 90, -25, -84, 93, 47, -27, -48, -65, -62, -67, 96, -4…
$ northness        <dbl> 43, 96, 53, 34, -88, -96, 87, -75, 78, -74, -26, 86, …
$ roughness        <dbl> 63, 30, 13, 6, 35, 53, 3, 9, 42, 99, 51, 190, 95, 212…
$ tree_no_tree     <fct> Tree, Tree, Tree, No tree, Tree, Tree, No tree, Tree,…
$ dew_temp         <dbl> 0.04, 6.40, 6.06, 4.43, 1.06, 1.35, 1.42, 6.39, 6.50,…
$ precip_annual    <dbl> 466, 1710, 1297, 2545, 609, 539, 702, 1195, 1312, 103…
$ temp_annual_mean <dbl> 6.42, 10.64, 10.07, 9.86, 7.72, 7.89, 7.61, 10.45, 10…
$ temp_annual_min  <dbl> -8.32, 1.40, 0.19, -1.20, -5.98, -6.00, -5.76, 1.11, …
$ temp_annual_max  <dbl> 12.91, 15.84, 14.42, 15.78, 13.84, 14.66, 14.23, 15.3…
$ temp_january_min <dbl> -0.08, 5.44, 5.72, 3.95, 1.60, 1.12, 0.99, 5.54, 6.20…
$ vapor_min        <dbl> 78, 34, 49, 67, 114, 67, 67, 31, 60, 79, 172, 162, 70…
$ vapor_max        <dbl> 1194, 938, 754, 1164, 1254, 1331, 1275, 944, 892, 549…
$ canopy_cover     <dbl> 50, 79, 47, 42, 59, 36, 14, 27, 82, 12, 74, 66, 83, 6…
$ lon              <dbl> -118.6865, -123.0825, -122.3468, -121.9144, -117.8841…
$ lat              <dbl> 48.69537, 47.07991, 48.77132, 45.80776, 48.07396, 48.…
$ land_type        <fct> Tree, Tree, Tree, Tree, Tree, Tree, Non-tree vegetati…

Spending your data

Split your data into testing and training in a reproducible manner and display the split object.

# add code here

What percent of the original forested data is allocated to training and what percent to testing? Compare your response to your neighbor’s. Are the percentages roughly consistent? What determines this in the initial_split()? How would the code need to be updated to allocate 80% of the data to training and the remaining 20% to testing?

# add code here

Add response here.

# add code here

Let’s stick with the default split and save our testing and training data.

# add code here

Exploratory data analysis

Create a visualization that explores the relationship between the outcome, one numerical predictor, and one categorical predictor. Then, describe, in a few sentences, what the visualization shows about the relationship between these variables.

Note: Pay attention to which dataset you use for your exploration.

# add code here

Add response here.

Model 1: Custom choice of predictors

Fit

Fit a model for classifying plots as forested or not based on a subset of predictors of your choice. Name the model forested_custom_fit and display a tidy output of the model.

# add code here

Predict

Predict for the testing data using this model.

# add code here

Evaluate

Calculate the false positive and false negative rates for the testing data using this model.

# add code here

Another commonly used display of this information is a confusion matrix. Create this using the conf_mat() function. You will need to review the documentation for the function to determine how to use it.

# add code here

Sensitivity, specificity, ROC curve

Calculate sensitivity and specificity and draw the ROC curve.

# add code here

Model 2: All predictors

Fit

Fit a model for classifying plots as forested or not based on all predictors available. Name the model forested_full_fit and display a tidy output of the model.

# add code here

Predict

Predict for the testing data using this model.

# add code here

Evaluate

Calculate the false positive and false negative rates for the testing data using this model.

# add code here

Sensitivity, specificity, ROC curve

Calculate sensitivity and specificity and draw the ROC curve.

# add code here

Model 1 vs. Model 2

Plot both ROC curves and articulate how you would use them to compare these models.

# add code here

Add response here.