---
title: "Project 2 Flexdashboard"
output:
flexdashboard::flex_dashboard:
orientation: rows
vertical_layout: scroll
theme:
version: 4
bootswatch: minty
source_code: embed
---
```{r echo = FALSE, results='axis', include=FALSE}
# PACKAGES ----------------------------------------------------------------
library(tidyverse)
library(tidymodels)
library(readr)
library(easystats)
library(randomForest)
library(vip)
library(car)
library(knitr)
library(ggplot2)
library(corrplot)
# DOWNLOAD DATA -----------------------------------------------------------
data <- read.csv("/Users/stephenvieno/Projects/hgen-612/data/Data_1993.csv") # Download data
### CLEAN DATA ###
data <- na.omit(data) # Remove missing values from data
# Remove single column with NA values
data$TreeNum <- as.numeric(data$TreeNum, na.rm = FALSE) # Convert TreeNum to numeric
```
MODEL 1
===============================================================================
Column
----------------------------------------------------------------------
### MODEL 1 :: BACKWARD STEPWISE REGRESSION LOOP FOR GAMMA LOG MODEL
Models 1-3 attempt to predict the minimum linear distance to the nearest brood tree using the total basal area of all infested trees within a given neighborhood. Model 1 is a gamma generalized linear model, with the log function as its link function. To achieve this, a loop was created in which one predictor was removed in each iteration. Since multiple predictors display high collinearity, model 1 removes the predictor with the highest variance inflation factor. If all predictors have a variance inflation factor less than four or if only two predictors remain, the loop then selects the predictor with the highest p-value to remove. Summary statistics, including estimates of coefficients and statistics, are reported for each iteration of the loop. Descriptions of the variables used are also provided in the flexdashboard.
### DESCRIPTION OF VARIABLES
OUTCOME VARIABLE
1. Dead Distance: Minimum linear distance to nearest brood tree
PREDICTOR VARIABLES
1. 1/20th-Acre: Basal area total for all infested trees within 1/20th-acre neighborhood
2. 1/4th-Acre: Basal area of infested trees within 1/4th-acre neighborhood of response tree
3. 1/2th-Acre: Basal area of infested trees within 1/2-acre neighborhood of response tree
4. 1-Acre: Basal area of infested trees within 1-acre neighborhood of response tree
5. 1.5-Acre: Basal area of infested trees within 1.5-acre neighborhood of response tree
Column {.tabset .tabset-fade}
-----------------------------------------------------------------------
### SUMMARY OF DATA
```{r}
# -------------------------------------------------------------------------
### SUMMMARY OF VARIABLES USED IN GLM ###
var <- c("DeadDist", # List of variables used in the following models
"BA_Inf_20th",
"bsadead1new",
"bsadead5new",
"bsadead15new",
"bsadead25new")
data |>
dplyr::select(var) |> # Select variables used in the following models
setNames(c("Dead Distance", # Rename variables to original names
"1/20th-Acre",
"1/4th-Acre",
"1/2th-Acre",
"1-Acre",
"1.5-Acre")) |>
report() |> # Create report of variables
kable() # Create table for report of variables
```
### CORRELATION PLOT OF OUTCOME AND PREDICTORS
```{r}
col <- colorRampPalette(c("#0072B2", "#56B4E9", "#FFFFFF","#E69F00","#D55E00")) # Set colors for correlation matrix plot
cor_data <- data |>
dplyr::select(var) |> # Select variables used in the following models
setNames(c("Dead Distance", # Rename variables to original names
"1/20th-Acre",
"1/4th-Acre",
"1/2th-Acre",
"1-Acre",
"1.5-Acre")) |>
cor() # Create correlation matrix
corrplot::corrplot(cor_data, # Set data as correlation matrix
method="color", # Set correlation plot style to color
col=col(200), # Set number of possible colors for correlation plot
type="upper", # Display only upper section of matrix
order="original", # Use original order of variables for correlation matrix
addCoef.col = "black", # Color of coefficients on the graph
tl.col="black", # Color of text label
tl.srt=45, # Rotation of labels
diag=FALSE) # Hide diagonal in correlation matrix
```
Column {data-height=800, data-width = 500}
-----------------------------------------------------------------------
### SUMMARY PLOT
```{r, fig.height=7, fig.width=12}
data_test_1 <- data |>
dplyr::select(var) |> # Select variables in the model
setNames(c("DeadDist", # Rename variables to original names
"1/20th-Acre",
"1/4th-Acre",
"1/2th-Acre",
"1-Acre",
"1.5-Acre")) |>
pivot_longer(cols = "1/20th-Acre":"1.5-Acre", # Pivot predictors into column
names_to = "variable", # Name of predictors variables
values_to = "values") |> # Values of predictor variables
mutate(variable = factor(variable, # Convert predictors variables to factor
levels = c("1/20th-Acre", # Order the predictor variables
"1/4th-Acre",
"1/2th-Acre",
"1-Acre",
"1.5-Acre")))
data_test_2 <- data |>
dplyr::select(var) |> # Select variables in the model
setNames(c("DeadDist", # Rename variables to original names
"1/20th-Acre",
"1/4th-Acre",
"1/2th-Acre",
"1-Acre",
"1.5-Acre")) |>
pivot_longer(cols = "1/20th-Acre":"1.5-Acre", # Pivot predictors into column
names_to = "variable", # Values of predictor variables
values_to = "values") |> # Values of predictor variables
dplyr::select(-variable) # Remove predictor name assignments
cbPalette <- c("#0072B2", "#56B4E9", "#009E73", "#F0E442","#E69F00", "#D55E00", "#CC79A7") # Use colorblind friendly colors
ggplot(data_test_1, aes(values, DeadDist)) + # Create scatter plot of DeadDist and predictors
geom_point(data = data_test_2, # Plot all data points for predictors
colour = "#999999", # Set color as grey for plots
alpha = 0.5) + # Set alpha to 0.5
geom_point(aes(colour = variable), # Set color to predictor
alpha = 0.5) + # Set alpha to 0.5
facet_wrap(~variable) + # Facet wrap on the basis of predictor variable
scale_color_manual(values=cbPalette) + # Set colors to colorblind friendly colors
theme_bw() + # Set theme to black and white theme
xlab("Basal area of total for all infested trees within neighborhood") + # Label x-axis
ylab("Minimum linear distance to nearest brood tree") + # Label y-axis
ggtitle("Scatter Plot of Dead Distance Variable and Predictor Variables") + # Label title
theme(legend.title = element_text(face = "bold"), # Bold legend theme
axis.title=element_text(size=15), # Size axis text
plot.title = element_text(size = 20)) + # Size plot title
labs(colour = "Basal Area") # Change legend title
```
Column {data-height=800, data-width = 500} {.tabset .tabset-fade}
-----------------------------------------------------------------------
```{r setup, include=FALSE}
### CREATE MODEL FOR EXPOTNETIAL DECAY :: GAMMA LOG GLM ###
log_mod <- linear_reg(mode = "regression") |> #Set model to linear regression model
set_engine("glm", # Set engine to generalized linear model
family = Gamma(link = "log")) # Set family to Gamma log model
rec <- recipe(DeadDist ~ BA_Inf_20th + bsadead1new + bsadead5new + bsadead15new + bsadead25new, # Set recipe for model
data = data) # Set data to data
vif_loop <- NULL # Set to NULL :: Remove any previous assignments to vector/data frame
loop_data <- NULL # Set to NULL :: Remove any previous assignments to vector/data frame
glance_lm <- NULL # Set to NULL :: Remove any previous assignments to vector/data frame
pred <- NULL # Set to NULL :: Remove any previous assignments to vector/data frame
loop_data <- list() # Create list to store coefficients and statistics for each loop
glance_lm <- list() # Create list to store fit statistics for each loop
vif_loop <- list() # Create list to store predictor VIF for each loop
pred <- list() # Create list to store predictions for each loop
# BACKWARD STEPWISE REGRESSION LOOP FOR GAMMA LOG MODEL
# IF VIF > 4 FOR ANY PREDICTOR AND NUMBER OF PREDICTORS > 2, THEN REMOVE VARIABLE WITH HIGHEST VIF
# IF VIF < 4 FOR ALL PREDICTORS OR ALL NUMBER OF PREDICTORS < 3, THEN REMOVE PREDICTOR WTH HIGHEST P-VALUE
for (i in 1:5) {
lm_workflow <- workflow() |> # Create workflow
add_model(log_mod) |> # Add gamma log glm model
add_recipe(rec) # Add recipe
glance_lm[[i]] <- lm_workflow |> # Create list to store fit statistics for each loop
fit(data = data) |> # Fit the data to the model
glance() # Use glance to create fit statistics for loop
fit_lm <- lm_workflow |> # Create summary statistics for coefficients in each loop
fit(data = data) |> # Fit the data to the model
tidy() |> # Create data frame of summary statistics for coefficients in each loop
dplyr::filter(term != "(Intercept)") |> # Remove intercept from data frame
arrange(desc(p.value)) # Arrange in order of descending p-values
loop <- print(rep( paste0("loop",i), 6-i)) # Create vector of loop 1-5 labels
loop_data[[i]] <- as.data.frame(bind_cols(loop, fit_lm)) # Label loop number for summary statistics for coefficients in each loop
lm_workflow <- lm_workflow |> fit(data = data) # Fit data to gamma log glm model
pred[[i]] <- predict(lm_workflow, new_data = data) # Create predictions using gamma log glm model
# If else statement::
# Create VIF for first loop or if more than two predictors are used
if (i == 1 || nrow(vif_lm) > 2) {
vif_lm <- lm_workflow |>
extract_recipe() |> # Extract recipe from workflow
lm(data = data) |> # Fit data to linear model
vif() |> # Extract VIF for predictors
as.data.frame() |> # Convert to data frame
rownames_to_column("Variables") |> # Convert row names to a column
rename(VIF = `vif(lm(extract_recipe(lm_workflow), data = data))`) |> # Rename column to VIF
arrange(desc(VIF)) # Arrage in descending order of VIF
vif_loop[[i]] <- as.data.frame(bind_cols(loop, vif_lm)) # Label loop number for VIF in each loop
} else {
print("no vif") # If unable to use VIF to analyse multi-collinearity, print no VIF
}
if(nrow(vif_lm) > 2 & vif_lm[1,2] > 5){ # Create
rec <- remove_role(rec, as.character(vif_lm[1,1]), old_role = "predictor") # If VIF available, remove predictor with highest VIF
} else {
rec <- remove_role(rec, as.character(fit_lm[1,1]), old_role = "predictor") # If no VIF available, removed predictor with highest p-value
}
}
lm_loop <- do.call(bind_rows, loop_data) # Create data frame to store coefficients and statistics for each loop
colnames(lm_loop)[1] <- "loop" # Rename column with loop assignment
glance_loop <- do.call(bind_rows, glance_lm) # Create data frame to store fit statistics for each loop
vif_loop <- do.call(bind_rows, vif_loop) # Create data frame to store predictor VIF for each loop
colnames(vif_loop)[1] <- "loop" # Rename column with loop assignment
pred_loop <- do.call(bind_cols, pred) # Create data frame to store predictions for each loop
colnames(pred_loop) <- c("loop1", "loop2", "loop3", "loop4", "loop5") # Rename columns by loop assignment
plot_data <- bind_cols(data, pred_loop) # Bind loop predictions to predictors
```
### LOOP 1
```{r, fig.height=7, fig.width=12}
### PLOT THE FITTED VALUES FOR THE LOOP 1
plot_data |> # Plot predicted values
dplyr::select(var, loop1:loop5) |> # Select predictors and prediction values
setNames(c("DeadDist", # Rename variables to original names
"1/20th-Acre",
"1/4th-Acre",
"1/2th-Acre",
"1-Acre",
"1.5-Acre",
"loop1",
"loop2",
"loop3",
"loop4",
"loop5")) |>
pivot_longer(cols = "1/20th-Acre":"1.5-Acre", # Pivot longer predictors
names_to = "predictors", # Convert column names to predictors
values_to = "variables_values") |>
mutate(predictors = factor(predictors, # Convert predictors variables to factor
levels = c("1/20th-Acre", # Order the predictor variables
"1/4th-Acre",
"1/2th-Acre",
"1-Acre",
"1.5-Acre"))) |> # Convert variables values to variables_values
ggplot(aes(y = DeadDist, # Plot actual values (DeadDist) vs Predictors
x = variables_values # Plot actual values (DeadDist) vs Predictors
)) +
geom_point(color = "#999999") + # Set color of actual values to grey
geom_point(aes(y = loop1, # Plot predicted values (DeadDist) vs Predictors
x = variables_values), # Plot predicted values (DeadDist) vs Predictors
alpha = 0.3, # Set alpha to 0.3
color = "#0072B2") + # Set color of predicted values to blue
facet_wrap(vars(predictors)) + # Facet wrap on predictors
theme_bw(base_size = 15) + # Set theme to black and white
xlab("Basal area of total for all infested trees within neighborhood") + # Title x-axis
ylab("Minimum linear distance to nearest brood tree") + # Title y-axis
ggtitle("Loop 1: Scatter plot of Fitted and Actual Values for the Dead Distance Variable", # Title
subtitle = "Fitted Values in Dark Blue & Actual Values in Grey") # Subtitle
```
### LOOP 2
```{r, fig.height=7, fig.width=12}
### PLOT THE FITTED VALUES FOR THE LOOP 2
plot_data |> # Plot predicted values
dplyr::select(var, loop1:loop5) |> # Select predictors and prediction values
setNames(c("DeadDist", # Rename variables to original names
"1/20th-Acre",
"1/4th-Acre",
"1/2th-Acre",
"1-Acre",
"1.5-Acre",
"loop1",
"loop2",
"loop3",
"loop4",
"loop5")) |>
pivot_longer(cols = "1/20th-Acre":"1.5-Acre", # Pivot longer predictors
names_to = "predictors", # Convert column names to predictors
values_to = "variables_values") |>
mutate(predictors = factor(predictors, # Convert predictors variables to factor
levels = c("1/20th-Acre", # Order the predictor variables
"1/4th-Acre",
"1/2th-Acre",
"1-Acre",
"1.5-Acre"))) |> # Convert variables values to variables_values
ggplot(aes(y = DeadDist, # Plot actual values (DeadDist) vs Predictors
x = variables_values # Plot actual values (DeadDist) vs Predictors
)) +
geom_point(color = "#999999") + # Set color of actual values to grey
geom_point(aes(y = loop2, # Plot predicted values (DeadDist) vs Predictors
x = variables_values), # Plot predicted values (DeadDist) vs Predictors
alpha = 0.3, # Set alpha to 0.3
color = "#56B4E9") + # Set color of predicted values to light blue
facet_wrap(vars(predictors)) + # Facet wrap on predictors
theme_bw(base_size = 15) + # Set theme to black and white
xlab("Basal area of total for all infested trees within neighborhood") + # Title x-axis
ylab("Minimum linear distance to nearest brood tree") + # Title y-axis
ggtitle("Loop 2: Scatter plot of Fitted and Actual Values for the Dead Distance Variable", # Title
subtitle = "Fitted Values in Light Blue & Actual Values in Grey") # Subtitle
```
### LOOP 3
```{r, fig.height=7, fig.width=12}
### PLOT THE FITTED VALUES FOR THE LOOP 3
plot_data |> # Plot predicted values
dplyr::select(var, loop1:loop5) |> # Select predictors and prediction values
setNames(c("DeadDist", # Rename variables to original names
"1/20th-Acre",
"1/4th-Acre",
"1/2th-Acre",
"1-Acre",
"1.5-Acre",
"loop1",
"loop2",
"loop3",
"loop4",
"loop5")) |>
pivot_longer(cols = "1/20th-Acre":"1.5-Acre", # Pivot longer predictors
names_to = "predictors", # Convert column names to predictors
values_to = "variables_values") |>
mutate(predictors = factor(predictors, # Convert predictors variables to factor
levels = c("1/20th-Acre", # Order the predictor variables
"1/4th-Acre",
"1/2th-Acre",
"1-Acre",
"1.5-Acre"))) |> # Convert variables values to variables_values
ggplot(aes(y = DeadDist, # Plot actual values (DeadDist) vs Predictors
x = variables_values # Plot actual values (DeadDist) vs Predictors
)) +
geom_point(color = "#999999") + # Set color of actual values to grey
geom_point(aes(y = loop3, # Plot predicted values (DeadDist) vs Predictors
x = variables_values # Plot predicted values (DeadDist) vs Predictors
), alpha = 0.3, color = "#009E73") + # Set color of predicted values to green
facet_wrap(vars(predictors)) + # Facet wrap on predictors
theme_bw(base_size = 15) + # Set theme to black and white
xlab("Basal area of total for all infested trees within neighborhood") + # Title x-axis
ylab("Minimum linear distance to nearest brood tree") + # Title y-axis
ggtitle("Loop 3: Scatter plot of Fitted and Actual Values for the Dead Distance Variable", # Title
subtitle = "Fitted Values in Green & Actual Values in Grey") # Subtitle
```
### LOOP 4
```{r, fig.height=7, fig.width=12}
### PLOT THE FITTED VALUES FOR THE LOOP 4
plot_data |> # Plot predicted values
dplyr::select(var, loop1:loop5) |> # Select predictors and prediction values
setNames(c("DeadDist", # Rename variables to original names
"1/20th-Acre",
"1/4th-Acre",
"1/2th-Acre",
"1-Acre",
"1.5-Acre",
"loop1",
"loop2",
"loop3",
"loop4",
"loop5")) |>
pivot_longer(cols = "1/20th-Acre":"1.5-Acre", # Pivot longer predictors
names_to = "predictors", # Convert column names to predictors
values_to = "variables_values") |>
mutate(predictors = factor(predictors, # Convert predictors variables to factor
levels = c("1/20th-Acre", # Order the predictor variables
"1/4th-Acre",
"1/2th-Acre",
"1-Acre",
"1.5-Acre"))) |> # Convert variables values to variables_values
ggplot(aes(y = DeadDist, # Plot actual values (DeadDist) vs Predictors
x = variables_values # Plot actual values (DeadDist) vs Predictors
)) +
geom_point(color = "#999999") + # Set color of actual values to grey
geom_point(aes(y = loop4, # Plot predicted values (DeadDist) vs Predictors
x = variables_values), # Plot predicted values (DeadDist) vs Predictors
alpha = 0.3, # Set alpha to 0.3
color = "#F0E442") + # Set color of predicted values to yellow
facet_wrap(vars(predictors)) + # Facet wrap on predictors
theme_bw(base_size = 15) + # Set theme to black and white
xlab("Basal area of total for all infested trees within neighborhood") + # Title x-axis
ylab("Minimum linear distance to nearest brood tree") + # Title y-axis
ggtitle("Loop 4: Scatter plot of Fitted and Actual Values for the Dead Distance Variable", # Title
subtitle = "Fitted Values in Yellow & Actual Values in Grey") # Subtitle
```
### LOOP 5
```{r, fig.height=7, fig.width=12}
### PLOT THE FITTED VALUES FOR THE LOOP 5
plot_data |> # Plot predicted values
dplyr::select(var, loop1:loop5) |> # Select predictors and prediction values
setNames(c("DeadDist", # Rename variables to original names
"1/20th-Acre",
"1/4th-Acre",
"1/2th-Acre",
"1-Acre",
"1.5-Acre",
"loop1",
"loop2",
"loop3",
"loop4",
"loop5")) |>
pivot_longer(cols = "1/20th-Acre":"1.5-Acre", # Pivot longer predictors
names_to = "predictors", # Convert column names to predictors
values_to = "variables_values") |>
mutate(predictors = factor(predictors, # Convert predictors variables to factor
levels = c("1/20th-Acre", # Order the predictor variables
"1/4th-Acre",
"1/2th-Acre",
"1-Acre",
"1.5-Acre"))) |> # Convert variables values to variables_values
ggplot(aes(y = DeadDist, # Plot actual values (DeadDist) vs Predictors
x = variables_values # Plot actual values (DeadDist) vs Predictors
)) +
geom_point(color = "#999999") + # Set color of actual values to grey
geom_point(aes(y = loop5, # Plot predicted values (DeadDist) vs Predictors
x = variables_values), # Plot predicted values (DeadDist) vs Predictors
alpha = 0.3, # Set alpha to 0.3
color = "#E69F00") + # Set color of predicted values to orange
facet_wrap(vars(predictors)) + # Facet wrap on predictors
theme_bw(base_size = 15) + # Set theme to black and white
xlab("Basal area of total for all infested trees within neighborhood") + # Title x-axis
ylab("Minimum linear distance to nearest brood tree") + # Title y-axis
ggtitle("Loop 5: Scatter plot of Fitted and Actual Values for the Dead Distance Variable", # Title
subtitle = "Fitted Values in Orange & Actual Values in Grey") # Subtitle
```
Row {data-height=400, data-width = 1000}
-----------------------------------------------------------------------
### ESTIMATED COEFFICIENT PLOT
```{r}
# Colorblind friendly colors
cbPalette <- c("#E69F00", "#56B4E9", "#009E73", "#F0E442", "#0072B2", "#D55E00", "#CC79A7")
### CREATE PLOT OF COEFFICENTS FOR EACH LOOP ###
lm_loop |>
mutate(loop = as.numeric(gsub("loop", "", lm_loop$loop)), # Create vector of number of loop
num_var = 6 - loop) |> # Create vector of number of predictors
ggplot(aes(x = num_var, # X-axis as number of predictors
y = estimate, # Y-axis as estimate of coefficient
group = term, # Group by predictors
color = term)) + # Color by predictors
geom_point(size = 3) + # Size of point
geom_line(alpha = 0.5, # Set alpha to 0.5
lwd = 2) + # Set line width to 2
geom_hline(yintercept = 0, # Set y-intercept to 0
color = "black", # Set line color to black
linetype = "dashed", # Set line type to dashed
size=1) + # Set line size to 1
geom_errorbar(width=0.1, # Set line width for error bars
aes(ymin=estimate-std.error, # Set lower error bar
ymax=estimate+std.error), # Set upper error bar
colour="black") + # Set color of error bars
theme_bw(base_size = 12) + # Set theme to black and white
labs(title = "Estimate of Coefficent for Each Loop", # Title
col = "Predictors") + # Title of legend
xlab("Number of Predictors") + # Title of of x-axis
ylab("Estimate of Coefficent") + # Title of y-axis
scale_colour_manual(values=cbPalette, # Set colors to colorblind friendly colors
labels = c("1/20th-Acre", # Labels for predictors
"1/4th-Acre",
"1/2th-Acre",
"1-Acre",
"1.5-Acre"))
```
### VARIANCE INFLATION FACTOR (VIF) PLOT
```{r}
### CREAT VIF PLOT FOR EACH LOOP ###
vif_loop |>
mutate(loop = as.numeric(gsub("loop", "", vif_loop$loop)), # Create vector of number of loop
num_var = 6 - loop) |> # Create vector of number of predictors
ggplot(aes(x = num_var, # Set x-axis as number of variables
y = VIF, # Set y-axis as VIF
group = Variables, # Group by predictors
col = Variables)) + # Group by predictors
geom_point(size = 3) + # Size points to 3
geom_line(alpha = 0.5, # Set alpha to 0.5
lwd = 2) + #
geom_hline(yintercept = 5,
color = "black",
linetype = "dashed", # Set line type to dashed
size=1) + # Set size of line to 1
theme(legend.title = element_text(face = "bold")) + # Create bold label
theme_bw(base_size = 12) + # Set size of text to 12
labs(title = "Variance Inflation Factor (VIF) for Each Loop", # Title
subtitle = "Dashed Line: Variance Inflation Factor = 4") + # Subtitle
xlab("Number of Variables") + # Title of x-axis
ylab("Variance Inflation Factor") + # Title of y-axis
scale_colour_manual(values=cbPalette, # Set colors to colorblind friendly colors
labels = c("1/20th-Acre", # Labels for predictors
"1/4th-Acre",
"1/2th-Acre",
"1-Acre",
"1.5-Acre"))
```
Row {data-height=400, data-width = 1000} {.tabset .tabset-fade}
-----------------------------------------------------------------------
### LOOP 1 STATISTICS
```{r}
colnames(vif_loop)[2] <- "term" # Rename column to term
loop_stat <- lm_loop |>
dplyr::inner_join(vif_loop, # Inner join summary statistics with VIF
by = c("loop", "term")) |> # Inner join by term and loop
dplyr::filter(loop == "loop1") # Filter loop 1
colnames(loop_stat)[2] <- "predictor" # Reassign name of term to predictor
loop_stat |>
mutate(predictor = dplyr::recode(predictor, # Rename the predictor to correct names
"BA_Inf_20th" = "1/20th-Acre",
"bsadead1new"="1/4th-Acre",
"bsadead5new"="1/2th-Acre",
"bsadead15new"="1-Acre",
"bsadead25new"="1.5-Acre"),
estimate = round(estimate,3), # Round to 3 decimals
std.error = round(std.error,3), # Round to 3 decimals
statistic = round(statistic,3), # Round to 3 decimals
p.value = round(p.value,3), # Round to 3 decimals
VIF = round(VIF,3)) |> # Round to 3 decimals
kable() # Create table
```
### LOOP 2 STATISTICS
```{r}
colnames(vif_loop)[2] <- "term" # Rename column to term
loop_stat <- lm_loop |>
dplyr::inner_join(vif_loop, # Inner join summary statistics with VIF
by = c("loop", "term")) |> # Inner join by term and loop
dplyr::filter(loop == "loop2") # Filter loop 2
colnames(loop_stat)[2] <- "predictor" # Reassign name of term to predictor
loop_stat |>
mutate(predictor = dplyr::recode(predictor, # Rename the predictor to correct names
"BA_Inf_20th" = "1/20th-Acre",
"bsadead1new"="1/4th-Acre",
"bsadead5new"="1/2th-Acre",
"bsadead15new"="1-Acre",
"bsadead25new"="1.5-Acre"),
estimate = round(estimate,3), # Round to 3 decimals
std.error = round(std.error,3), # Round to 3 decimals
statistic = round(statistic,3), # Round to 3 decimals
p.value = round(p.value,3), # Round to 3 decimals
VIF = round(VIF,3)) |> # Round to 3 decimals
kable() # Create table
```
### LOOP 3 STATISTICS
```{r}
colnames(vif_loop)[2] <- "term" # Rename column to term
loop_stat <- lm_loop |>
dplyr::inner_join(vif_loop, # Inner join summary statistics with VIF
by = c("loop", "term")) |> # Inner join by term and loop
dplyr::filter(loop == "loop3") # Filter loop 3
colnames(loop_stat)[2] <- "predictor" # Reassign name of term to predictor
loop_stat |>
mutate(predictor = dplyr::recode(predictor, # Rename the predictor to correct names
"BA_Inf_20th" = "1/20th-Acre",
"bsadead1new"="1/4th-Acre",
"bsadead5new"="1/2th-Acre",
"bsadead15new"="1-Acre",
"bsadead25new"="1.5-Acre"),
estimate = round(estimate,3), # Round to 3 decimals
std.error = round(std.error,3), # Round to 3 decimals
statistic = round(statistic,3), # Round to 3 decimals
p.value = round(p.value,3), # Round to 3 decimals
VIF = round(VIF,3)) |> # Round to 3 decimals
kable() # Create table
```
### LOOP 4 STATISTICS
```{r}
colnames(vif_loop)[2] <- "term" # Rename column to term
loop_stat <- lm_loop |>
dplyr::inner_join(vif_loop, # Inner join summary statistics with VIF
by = c("loop", "term")) |> # Inner join by term and loop
dplyr::filter(loop == "loop4") # Filter loop 4
colnames(loop_stat)[2] <- "predictor" # Reassign name of term to predictor
loop_stat |>
mutate(predictor = dplyr::recode(predictor, # Rename the predictor to correct names
"BA_Inf_20th" = "1/20th-Acre",
"bsadead1new"="1/4th-Acre",
"bsadead5new"="1/2th-Acre",
"bsadead15new"="1-Acre",
"bsadead25new"="1.5-Acre"),
estimate = round(estimate,3), # Round to 3 decimals
std.error = round(std.error,3), # Round to 3 decimals
statistic = round(statistic,3), # Round to 3 decimals
p.value = round(p.value,3), # Round to 3 decimals
VIF = round(VIF,3)) |> # Round to 3 decimals
kable() # Create table
```
### LOOP 5 STATISTICS
```{r}
colnames(vif_loop)[2] <- "term" # Rename column to term
loop_stat <- lm_loop |>
dplyr::filter(loop == "loop5") # Filter loop 5
colnames(loop_stat)[2] <- "predictor" # Reassign name of term to predictor
loop_stat |>
mutate(predictor = dplyr::recode(predictor, # Rename the predictor to correct names
"BA_Inf_20th" = "1/20th-Acre",
"bsadead1new"="1/4th-Acre",
"bsadead5new"="1/2th-Acre",
"bsadead15new"="1-Acre",
"bsadead25new"="1.5-Acre"),
estimate = round(estimate,3), # Round to 3 decimals
std.error = round(std.error,3), # Round to 3 decimals
statistic = round(statistic,3), # Round to 3 decimals
p.value = round(p.value,3)) |> # Round to 3 decimals
kable() # Create table
```
### GOODNESS-OF-FIT STATISTICS FOR EACH LOOP
```{r}
### LOG LIKELIHOOD TEST ###
# LOG LIKELIHOOD TEST FOR REMOVAL OF ONE PREDICTOR COMPARED TO THE PREVIOUS MODEL
for (i in 1:4){
glance_loop$chisq[1] <- NA # If last loop, set as NA
glance_loop$p_value[1] <- NA # If last loop, set as NA
nested <- glance_loop$logLik[i+1] # Log Likelihood for Nested Model
complex <- glance_loop$logLik[i] # Log Likelihood for Complex Model
glance_loop$chisq[i+1] <- (-2 * (nested-complex)) # 2 Log Likelihood
glance_loop$p_value[i+1] <- pchisq(glance_loop$chisq[i+1], df = 1, lower.tail = FALSE) # Calculate p-value for Log Likelihood Test
}
glance_loop$loop <- c("loop 1", "loop 2", "loop 3", "loop 4", "loop 5") # Label the loop
glance_loop |>
mutate(chisq = round(chisq,3), # Round to 3 decimal points
p_value = round(p_value, 3)) |> # Round to 3 decimal points
as.data.frame() |> # Covert to data frame
t() |> # Transpose data frame
as.data.frame() |> # Covert to data frame
row_to_colnames(11) |> # Convert loop to column names
kable() # Table for fit statistics
```
Row {data-height=400, data-width = 1000}
-----------------------------------------------------------------------
### FIT STATISTICS FOR EACH LOOP
```{r, fig.width=10}
cbPalette <- c("#E69F00", "#56B4E9", "#009E73", "#F0E442", "#0072B2", "#D55E00", "#CC79A7") # Use colorblind friendly colors
glance_loop$var_num <- c(5:1) # Create List of number of variables
glance_loop |>
pivot_longer(cols = c("AIC", "BIC", "logLik", "p_value"), # Pivot longer fit statistics
names_to = "Statistic", # Name of statistics
values_to = "values") |> # Values of statistics
ggplot(aes(x = var_num, # Set x-axis as number of variables
y = values, # Set y-axis as statistics values
group = Statistic, # Group by Statistic
col = Statistic)) + # Color by Statistic
geom_line(alpha = 0.5, # Set alpha to 0.5
lwd = 1.2) + # Set line width to 1.2
geom_point(size = 3) + # Set point size to 3
theme_bw() + # Set theme to black and white
facet_wrap(vars(Statistic), scales ="free") + # Facet wrap on Statistic with free scales
scale_color_manual(values=cbPalette, # Set colors to colorblind friendly colors
labels = c("AIC", # Label statistics in legend
"BIC",
"Log Likelihood",
"p-value ")) +
xlab("Number of Variables in Each Loop") + # Title of of x-axis
ylab("Value of Fit Statistic") + # Title of y-axis
theme_bw(base_size = 12) + # Set theme to black and white
theme(legend.title = element_text(face = "bold")) # Change legend to bold
```
MODEL 2 & 3
================================================================================
Column
----------------------------------------------------------------------
### MODEL 2 & 3 :: LASSO AND RANDOM FOREST REGRESSION
Models 2 and 3 use the same predictors to predict the minimum linear distance to the nearest brood tree. However, model two is a Lasso regression, while model three is a random forest regression. Unlike model one, both models were trained and tested on a 75/25 split. Summary statistics were reported for the cross-validation, indicating how well the models fit the test data.
```{r}
# Download data
data <- readxl::read_excel("/Users/stephenvieno/Projects/hgen-612/data/Data_1993.xlsx") |> na.omit() # Remove NAs
data <- data |>
dplyr::select(DeadDist, # Select outcome and predictor variables
"BA_Inf_20th",
"BA_Infest_1/4th",
"BA_Infest_1/2th",
"BA_Infest_1",
"BA_Infest_1.5")
names(data)[2:6] <- c("BA0.05", "BA0.25", "BA0.5", "BA1", "BA1.5") # Rename variables
```
```{r}
set.seed(4595) # Set seed
data_split <- initial_split(data, strata = "DeadDist",# Split data
prop = 0.75) # Split data with 0.75/0.25 split
data_train <- training(data_split) # Training data
data_test <- testing(data_split) # Testing data
### LASSO MODEL ### REGULARIZATION REGRESSION ###
norm_recipe <- recipe(DeadDist ~ ., # Set recipe with outcome and predictors
data = data_train ) |> # Use training data
step_center(all_predictors()) |> # Center all predictors
step_scale(all_predictors()) |> # Scale all predictors
step_log(DeadDist, base = 10) |> # Log transform DeadDist
prep(training = data_train, # Prep with training data
retain = TRUE)
glmn_fit <- linear_reg(penalty = 0.001, # Set regularization penalty
mixture = 1) |> # Set as Lasso Model
set_engine("glmnet") |> # Set engine as glmnet
fit(DeadDist ~ ., # Fit with outcome and all predictors
data = bake(norm_recipe, new_data = NULL)) # Bake with training data
# First, get the processed version of the test set predictors:
test_normalized <- bake(norm_recipe, # Use normalized (centered and scaled) recipe
new_data = data_test, # Bake with test data
all_predictors()) # Use all predictors
test_results_glmn_fit <- predict(glmn_fit, # Used glmnet model to predict the
new_data = test_normalized) |> # Predict with normalized test data
rename(glmnet = .pred) |> # Rename prediction with glmnet
bind_cols(data_test) # Bind predictions with testing data
```
```{r, echo = FALSE, warning=FALSE, include=FALSE}
### RANDOM FORREST MODEL ###
set.seed(123) # Set seed
rf_defaults <- rand_forest(mode = "regression") # Set model as random forest regression model
predictors <- data |>
dplyr::select(-DeadDist) |> # Remove DeadDist
colnames() # Get predictors names from column names
rf_defaults <-
rand_forest(mode = "regression", # Regression model
mtry = 3, # Number of predictors that will be sampled
trees = 1000) |> # Number of trees
set_engine("randomForest") |> # Set engine as Random Forest
fit_xy(
x = data_train[, predictors], # Used predictors from training data
y = log10(data_train$DeadDist)) # Log Transform DeadDist
test_results <- data_test |>
dplyr::select(DeadDist) |> # Select DeadDist from test data
mutate(DeadDist = log10(DeadDist)) |> # Log Transform DeadDist
bind_cols(predict(rf_defaults, # Bind prediction to actual values
new_data = model.matrix(~., data_test))) # Create predictions with test data
```
Row {data-height=1000, data-width = 500}
-------------------------------------
```{r}
glmnet <- metrics(test_results_glmn_fit, truth = DeadDist, estimate = glmnet) # Use prediction from glmnet
forest <- metrics(test_results, truth = DeadDist, estimate = .pred) # Use prediction from random forest
table_fit <- bind_rows(glmnet,forest) |> # Bind together prediction fit statistics
dplyr::select(.metric, .estimate) |> # Select columns of interest
setNames(c("Statistic", "Estimate")) |> # Rename columns
mutate(Estimate= round(Estimate, 3), # Round statistics
Model = c(rep("Glmnet", 3), rep("Forest", 3))) |> # Create labels for model type
pivot_wider(names_from = Statistic, values_from = Estimate) |> # Pivot wider
column_to_rownames("Model") # Model to rownames
```
### PLOTS OF ACTUAL VERSUS FITTED VALUES
```{r, echo=FALSE, fig.width=10, fig.height=7}
test_results <-
test_results |>
rename("random forest" = .pred) |> # Rename prediction from random forest
bind_cols(test_results_glmn_fit) # Bind to other prediction
colnames(test_results)[1] <- "DeadDist_Log10" # Rename variables
colnames(test_results)[2] <- "forest" # Rename variables
colnames(test_results)[4] <- "DeadDist" # Rename variables
test_results |>
mutate(forest = 10^forest, # Log Transform predictions
glmnet = 10^glmnet) |> # Log Transform predictions
dplyr::select(-DeadDist_Log10) |> # Remove Log to actual values
pivot_longer(cols = forest:glmnet, # Pivot longer model predictions
names_to = "model", # Names to model type
values_to = "prediction") |> # Values to prediction values
ggplot(aes(x = prediction, # Plot predictions versus actual values
y = DeadDist)) +
geom_point(alpha = 0.4) + # Set alpha to 0.4
geom_abline(col = "#56B4E9", # Set color to colorblind friendly colors
lty = 2, # Set line to dashed line
size =1) + # Set line size to 1
facet_wrap(~model, scales = "free") + # Facet wrap based on model
ylab("Actual minimum linear distance to nearest brood tree") + # Title y-axis
xlab("Predicted minimum linear distance to nearest brood tree") + # Tile x-axis
ggtitle("Scatter Plot of Actual versus Predicted Values for Random Forest and Lasso Models") + # Title
theme_bw() # Set black and white theme
```
Column
-------------------------------------
### GOODNESS-OF-FIT METRICS FOR LASSO AND RANDOM FOREST MODELS
```{r}
knitr::kable(table_fit) # Create table
```
### R-Squared for Lasso Regression
```{r}
library(flexdashboard)
rate <- as.vector(glmnet[2,3]) # R-Squared for Lasso Model
gauge(rate$.estimate * 100, # R-Squared for Lasso Model
min = 0, # Minimum of 0
max = 100, # Maximum of 100
symbol = '%', # Percentage symbol
gaugeSectors(success = c(80, 100), # Set success, warning, danger thresholds
warning = c(40, 79),
danger = c(0, 39)))
```
### R-Squared for Random Forest
```{r}
rate <- as.vector(forest[2,3]) # R-Squared for Random Forest
gauge(rate$.estimate * 100, # R-Squared for Random Forest
min = 0, # Minimum of 0
max = 100, # Maximum of 100
symbol = '%', # Percentage symbol
gaugeSectors(success = c(80, 100), # Set success, warning, danger thresholds
warning = c(40, 79),
danger = c(0, 39)))
```