Please find all the script I have used for the wisconsin dataset.
# assignment2
setwd("C:/Users/olgad/OneDrive/Desktop/CETM72R")
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(readr)
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.5.0 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.1
## ✔ purrr 1.0.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(forcats)
library(randomForest)
## randomForest 4.7-1.1
## Type rfNews() to see new features/changes/bug fixes.
##
## Attaching package: 'randomForest'
##
## The following object is masked from 'package:ggplot2':
##
## margin
##
## The following object is masked from 'package:dplyr':
##
## combine
library(caret) #these libraries need to be installed first before running
## Loading required package: lattice
##
## Attaching package: 'caret'
##
## The following object is masked from 'package:purrr':
##
## lift
library (corrplot)
## corrplot 0.92 loaded
# Load the dataset
wisconsin <- read_csv("wisconsin.csv", show_col_types = FALSE)
glimpse(wisconsin)
## Rows: 699
## Columns: 10
## $ Cl.thickness <dbl> 5, 5, 3, 6, 4, 8, 1, 2, 2, 4, 1, 2, 5, 1, 8, 7, 4, 4, …
## $ Cell.size <dbl> 1, 4, 1, 8, 1, 10, 1, 1, 1, 2, 1, 1, 3, 1, 7, 4, 1, 1,…
## $ Cell.shape <dbl> 1, 4, 1, 8, 1, 10, 1, 2, 1, 1, 1, 1, 3, 1, 5, 6, 1, 1,…
## $ Marg.adhesion <dbl> 1, 5, 1, 1, 3, 8, 1, 1, 1, 1, 1, 1, 3, 1, 10, 4, 1, 1,…
## $ Epith.c.size <dbl> 2, 7, 2, 3, 2, 7, 2, 2, 2, 2, 1, 2, 2, 2, 7, 6, 2, 2, …
## $ Bare.nuclei <dbl> 1, 10, 2, 4, 1, 10, 10, 1, 1, 1, 1, 1, 3, 3, 9, 1, 1, …
## $ Bl.cromatin <dbl> 3, 3, 3, 3, 3, 9, 3, 3, 1, 2, 3, 2, 4, 3, 5, 4, 2, 3, …
## $ Normal.nucleoli <dbl> 1, 2, 1, 7, 1, 7, 1, 1, 1, 1, 1, 1, 4, 1, 5, 3, 1, 1, …
## $ Mitoses <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 5, 1, 1, 1, 1, 1, 4, 1, 1, 1, …
## $ Class <chr> "benign", "benign", "benign", "benign", "benign", "mal…
wisconsin <- wisconsin %>%
mutate(Bare.nuclei = replace_na(Bare.nuclei, median(Bare.nuclei, na.rm = TRUE)))
wisconsin <- wisconsin %>%
mutate(Class = if_else(Class == "malignant", 1, 0))
summary(wisconsin)
## Cl.thickness Cell.size Cell.shape Marg.adhesion
## Min. : 1.000 Min. : 1.000 Min. : 1.000 Min. : 1.000
## 1st Qu.: 2.000 1st Qu.: 1.000 1st Qu.: 1.000 1st Qu.: 1.000
## Median : 4.000 Median : 1.000 Median : 1.000 Median : 1.000
## Mean : 4.418 Mean : 3.134 Mean : 3.207 Mean : 2.807
## 3rd Qu.: 6.000 3rd Qu.: 5.000 3rd Qu.: 5.000 3rd Qu.: 4.000
## Max. :10.000 Max. :10.000 Max. :10.000 Max. :10.000
## Epith.c.size Bare.nuclei Bl.cromatin Normal.nucleoli
## Min. : 1.000 Min. : 1.000 Min. : 1.000 Min. : 1.000
## 1st Qu.: 2.000 1st Qu.: 1.000 1st Qu.: 2.000 1st Qu.: 1.000
## Median : 2.000 Median : 1.000 Median : 3.000 Median : 1.000
## Mean : 3.216 Mean : 3.486 Mean : 3.438 Mean : 2.867
## 3rd Qu.: 4.000 3rd Qu.: 5.000 3rd Qu.: 5.000 3rd Qu.: 4.000
## Max. :10.000 Max. :10.000 Max. :10.000 Max. :10.000
## Mitoses Class
## Min. : 1.000 Min. :0.0000
## 1st Qu.: 1.000 1st Qu.:0.0000
## Median : 1.000 Median :0.0000
## Mean : 1.589 Mean :0.3448
## 3rd Qu.: 1.000 3rd Qu.:1.0000
## Max. :10.000 Max. :1.0000
# Splitting the data into training and testing sets for model validation
set.seed(123) # Ensuring reproducibility
training_indices <- createDataPartition(wisconsin$Class, p = 0.8, list = FALSE)
train_data <- wisconsin[training_indices, ]
test_data <- wisconsin[-training_indices, ]
# Building and training the Logistic Regression model
log_model <- glm(Class ~ ., data = train_data, family = "binomial")
# Ensure 'Class' is a factor
train_data$Class <- as.factor(train_data$Class)
# Check for NAs
sum(is.na(train_data))
## [1] 0
# Developing and training the Random Forest model
library(randomForest)
rf_model <- randomForest(Class ~ ., data = train_data)
train_data$Class <- as.factor(train_data$Class)
test_data$Class <- as.factor(test_data$Class)
library(randomForest)
rf_model <- randomForest(Class ~ ., data = train_data)
# Defining a function to calculate accuracy of the models
calculate_accuracy <- function(predictions, true_values) {
correct <- sum(predictions == true_values)
total <- length(true_values)
accuracy <- correct / total
return(accuracy)
}
# Evaluating Logistic Regression model accuracy
log_predictions <- predict(log_model, test_data, type = "response") > 0.5
log_accuracy <- calculate_accuracy(log_predictions, test_data$Class)
# Evaluating Random Forest model accuracy
rf_predictions <- predict(rf_model, test_data)
rf_accuracy <- calculate_accuracy(rf_predictions, test_data$Class)
# Outputting the comparison of model accuracies
print(paste("Logistic Regression accuracy:", log_accuracy))
## [1] "Logistic Regression accuracy: 0"
print(paste("Random Forest accuracy:", rf_accuracy))
## [1] "Random Forest accuracy: 0.97841726618705"
correlation_matrix <- cor(wisconsin[,-10]) # Exclude the response variable
print(correlation_matrix)
## Cl.thickness Cell.size Cell.shape Marg.adhesion Epith.c.size
## Cl.thickness 1.0000000 0.6449125 0.6545891 0.4863562 0.5218162
## Cell.size 0.6449125 1.0000000 0.9068819 0.7055818 0.7517991
## Cell.shape 0.6545891 0.9068819 1.0000000 0.6830792 0.7196684
## Marg.adhesion 0.4863562 0.7055818 0.6830792 1.0000000 0.5995991
## Epith.c.size 0.5218162 0.7517991 0.7196684 0.5995991 1.0000000
## Bare.nuclei 0.5900082 0.6866728 0.7074738 0.6669710 0.5837014
## Bl.cromatin 0.5584282 0.7557210 0.7359485 0.6667153 0.6161018
## Normal.nucleoli 0.5358345 0.7228648 0.7194463 0.6033524 0.6288807
## Mitoses 0.3500339 0.4586931 0.4389109 0.4176328 0.4791015
## Bare.nuclei Bl.cromatin Normal.nucleoli Mitoses
## Cl.thickness 0.5900082 0.5584282 0.5358345 0.3500339
## Cell.size 0.6866728 0.7557210 0.7228648 0.4586931
## Cell.shape 0.7074738 0.7359485 0.7194463 0.4389109
## Marg.adhesion 0.6669710 0.6667153 0.6033524 0.4176328
## Epith.c.size 0.5837014 0.6161018 0.6288807 0.4791015
## Bare.nuclei 1.0000000 0.6742147 0.5747781 0.3423971
## Bl.cromatin 0.6742147 1.0000000 0.6658778 0.3441695
## Normal.nucleoli 0.5747781 0.6658778 1.0000000 0.4283357
## Mitoses 0.3423971 0.3441695 0.4283357 1.0000000
summary(log_model)
##
## Call:
## glm(formula = Class ~ ., family = "binomial", data = train_data)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -9.0139 1.1056 -8.153 3.54e-16 ***
## Cl.thickness 0.5063 0.1591 3.182 0.00146 **
## Cell.size 0.1714 0.2253 0.761 0.44680
## Cell.shape 0.4846 0.2677 1.810 0.07030 .
## Marg.adhesion 0.1650 0.1362 1.211 0.22578
## Epith.c.size -0.2064 0.2042 -1.011 0.31216
## Bare.nuclei 0.4806 0.1114 4.315 1.60e-05 ***
## Bl.cromatin 0.3288 0.1815 1.812 0.07004 .
## Normal.nucleoli 0.1424 0.1225 1.163 0.24497
## Mitoses 0.4019 0.3139 1.280 0.20048
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 728.784 on 559 degrees of freedom
## Residual deviance: 89.265 on 550 degrees of freedom
## AIC: 109.26
##
## Number of Fisher Scoring iterations: 8
accuracy_conf_int <- binom.test(sum(rf_predictions == test_data$Class), length(rf_predictions))
print(accuracy_conf_int$conf.int)
## [1] 0.9382228 0.9955268
## attr(,"conf.level")
## [1] 0.95
# Prepare the data
model_accuracies <- data.frame(
Model = c("Logistic Regression", "Random Forest"),
Accuracy = c(0, 0.971223021582734)
)
# Plot the accuracies
library(ggplot2)
accuracy_plot <- ggplot(model_accuracies, aes(x = Model, y = Accuracy, fill = Model)) +
geom_bar(stat = "identity") +
geom_text(aes(label = scales::percent(Accuracy)), vjust = -0.3) +
labs(title = "Comparison of Model Accuracies", y = "Accuracy", x = "") +
ylim(0, 1) +
theme_minimal()
# Display the plot
print(accuracy_plot)
# Install if not already installed
if (!requireNamespace("corrplot", quietly = TRUE)) {
install.packages("corrplot")
}
wisconsin_numeric <- wisconsin[, sapply(wisconsin, is.numeric)]
# Load necessary library
library(corrplot)
# Calculate correlation matrix
cor_matrix <- cor(wisconsin_numeric)
# Plot the heatmap
corrplot(cor_matrix, method = "color", type = "upper", order = "hclust",
tl.col = "black", tl.srt = 45,
addCoef.col = "black", title = "Correlation Matrix Heatmap")