NEURAL NETWORK

library(ggplot2)
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(neuralnet)

## 
## Attaching package: 'neuralnet'

## The following object is masked from 'package:dplyr':
## 
##     compute

library(plotly)

## 
## Attaching package: 'plotly'

## The following object is masked from 'package:ggplot2':
## 
##     last_plot

## The following object is masked from 'package:stats':
## 
##     filter

## The following object is masked from 'package:graphics':
## 
##     layout

library(caret)

## Loading required package: lattice

#loading dataset
haberman_survival<-read.csv("C:\\Users\\sanan\\Downloads\\haberman.data",header=FALSE,col.names=c("Age","Op_year","Axil_nodes","Surv_status"))
View(haberman_survival)

#convert to numeric
haberman_survival<-haberman_survival%>%
  mutate(Age=as.numeric(Age),
         Op_year=as.numeric(Op_year),
         Axil_nodes=as.numeric(Axil_nodes),
         Surv_status=as.factor(Surv_status))

# Check for NA values and remove rows with NA values
sum(is.na(haberman_survival))

## [1] 0

haberman_survival <- haberman_survival[complete.cases(haberman_survival), ]
View(haberman_survival)
summary(haberman_survival)

##       Age           Op_year        Axil_nodes     Surv_status
##  Min.   :30.00   Min.   :58.00   Min.   : 0.000   1:225      
##  1st Qu.:44.00   1st Qu.:60.00   1st Qu.: 0.000   2: 81      
##  Median :52.00   Median :63.00   Median : 1.000              
##  Mean   :52.46   Mean   :62.85   Mean   : 4.026              
##  3rd Qu.:60.75   3rd Qu.:65.75   3rd Qu.: 4.000              
##  Max.   :83.00   Max.   :69.00   Max.   :52.000

# Distribution of Age (continuous)
ggplot(haberman_survival, aes(x = Age)) + 
  geom_histogram(binwidth = 5, fill = "green", color = "red") + 
  labs(title = "Age Dist", x = "Age", y = "Frequency")

# Distribution of Axillary Nodes (continuous)
ggplot(haberman_survival, aes(x = Axil_nodes)) + 
  geom_histogram(binwidth = 5, fill = "yellow", color = "blue") + 
  labs(title = "Axillary Nodes Dist", x = "No of Nodes", y = "Frequency")

# Distribution of Operation Year (discrete, so we use geom_bar)
ggplot(haberman_survival, aes(x = as.factor(Op_year))) + 
  geom_bar(fill = "cyan", color = "white") + 
  labs(title = "Operation Year Dist", x = "Year of Operation", y = "Frequency")

# Survival status distribution (discrete, use geom_bar)
ggplot(haberman_survival, aes(x = Surv_status)) + 
  geom_bar(fill = "pink", color = "brown") + 
  labs(title = "Survival Status Dist", x = "Survival Status", y = "Frequency")

# Scatter plots
pairs(
  haberman_survival[,1:3], 
  col = ifelse(haberman_survival$Surv_status == 1, "pink", "orange"), 
  main = "Pairwise Scatter Plots", 
  pch = 19
)

#NORMALISATION
# Normalization function
normalize <- function(x) {
  return ((x - min(x)) / (max(x) - min(x)))
}

# Normalize the numeric columns
haberman_norm <- as.data.frame(lapply(haberman_survival[,1:3], normalize))
haberman_norm$Surv_status <- as.numeric(haberman_survival$Surv_status) - 1  # Convert factor to numeric (0 and 1)

# Check for NA values after normalization
sum(is.na(haberman_norm))

## [1] 0

# Handle NA values by removing rows with NA
haberman_norm <- haberman_norm[complete.cases(haberman_norm), ]

# Load the neural network library
library(neuralnet)

# Split the data
set.seed(123)
index <- sample(1:nrow(haberman_norm), round(0.80 * nrow(haberman_norm)))
trainset <- haberman_norm[index,]
testset <- haberman_norm[-index,]

# Train the neural network
nn <- neuralnet(Surv_status ~ Age + Op_year + Axil_nodes, 
                data = trainset, hidden = 3, 
                linear.output = FALSE, 
                act.fct = "tanh", 
                err.fct = "ce", 
                likelihood = TRUE)

## Warning in log(x): NaNs produced

## Warning: 'err.fct' does not fit 'data' or 'act.fct'

# Save the neural network plot as PDF
pdf("neuralnet_plot.pdf", width = 8, height = 6)
plot(nn)
dev.off()

## png 
##   2

# Save the neural network plot as PNG
png("neuralnet_plot.png", width = 800, height = 600)
plot(nn)
dev.off()

## png 
##   2

# Predict on test data
predicted <- compute(nn, testset[,1:3])$net.result
predicted <- ifelse(predicted > 0.5, 1, 0)

# Convert predicted to factor for comparison with Surv_status
predicted <- factor(predicted, levels = c(0, 1))

# Confusion matrix
confusion_matrix <- table(predicted, testset$Surv_status)
print(confusion_matrix)

##          
## predicted  0  1
##         0 43 18
##         1  0  0

# Calculate accuracy
accuracy <- sum(diag(confusion_matrix)) / sum(confusion_matrix)
print(paste("Accuracy:", round(accuracy, 2)))

## [1] "Accuracy: 0.7"

# Calculate MSE
mse <- mean((as.numeric(predicted) - 1 - testset$Surv_status)^2)
print(paste("MSE:",round(mse,2)))

## [1] "MSE: 0.3"