# ====================================================================
# Week 10: Unsupervised Learning
# Kmex Consult - R Data Science Course
# Open in RStudio and run each block with Ctrl+Enter (Cmd+Enter on Mac).
# ====================================================================

# Finding patterns and structure in unlabeled data

# ====================================================================
# WEEK 10 OVERVIEW
# ====================================================================
# Unsupervised Learning = Learning WITHOUT labels
# USE CASES:
# - Customer Segmentation: Divide into groups
# - Anomaly Detection: Find unusual records
# - Data Exploration: Discover structure
# - Dimension Reduction: Simplify data
# - Recommendation: Find similar users
# TWO MAIN APPROACHES:
# 1. CLUSTERING: Group similar observations
# - K-means
# - Hierarchical clustering
# - DBSCAN
# 2. DIMENSIONALITY REDUCTION: Reduce variables
# - PCA (Principal Component Analysis)
# - t-SNE (visualization)
# CHALLENGES:
# - No "right answer" - hard to validate
# - Must decide number of clusters/dimensions
# - Result quality depends on preprocessing
# - Can find spurious patterns
# THIS WEEK YOU'LL LEARN:
# ✓ K-means clustering
# ✓ Hierarchical clustering and dendrograms
# ✓ DBSCAN for density-based clustering
# ✓ Cluster evaluation (silhouette, Davies-Bouldin)
# ✓ Principal Component Analysis (PCA)
# ✓ t-SNE for visualization
# ✓ Choosing number of clusters
# ✓ Interpreting cluster solutions

# ====================================================================
# SESSION 1: K-MEANS CLUSTERING
# ====================================================================

# --- Duration: 2 hours ---

# --- 1.1 K-Means and Cluster Evaluation ---
# K-MEANS CLUSTERING - MOST POPULAR:
# Algorithm:
# 1. Choose k (number clusters)
# 2. Randomly assign points to clusters
# 3. Calculate center of each cluster
# 4. Assign points to nearest center
# 5. Repeat until converged


library(ggplot2)

# Generate sample data
set.seed(42)
data <- tibble(
x = c(rnorm(30, mean=2, sd=0.5), rnorm(30, mean=8, sd=0.5)),
y = c(rnorm(30, mean=2, sd=0.5), rnorm(30, mean=8, sd=0.5))
)

# K-means with 2 clusters
km <- kmeans(data, centers=2, nstart=25)

# Add cluster assignments
data$cluster <- factor(km$cluster)

# Visualize
ggplot(data, aes(x, y, color=cluster)) +
geom_point(size=3) +
geom_point(data=tibble(x=km$centers[, 1], y=km$centers[, 2]),
size=5, shape=8, color="black") +
labs(title="K-Means Clustering (k=2)")

# CHOOSING K - THE ELBOW METHOD:


# Calculate within-cluster sum of squares for k=1 to 10
wss <- vector("numeric", 10)
for (k in 1:10) {
km <- kmeans(data, centers=k, nstart=25)
wss[k] <- km$tot.withinss
}

# Plot
plot(1:10, wss, type="b", main="Elbow Plot",
xlab="Number of Clusters", ylab="Within-cluster SS")

# Look for "elbow" - point where improvement drops
# Often k=2 or k=3 in this example

# The "silhouette" method (more formal)
library(cluster)
silhouette_scores <- vector("numeric", 10)
for (k in 2:10) {
km <- kmeans(data, centers=k, nstart=25)
sil <- silhouette(km$cluster, dist(data))
silhouette_scores[k] <- mean(sil[, 3])
}

plot(2:10, silhouette_scores[2:10], type="b",
main="Silhouette Scores",
xlab="Number of Clusters", ylab="Average Silhouette")

# Higher silhouette = better separation

# EVALUATING CLUSTERS:


# Silhouette coefficient: -1 to 1
# Close to 1 = well-separated
# Close to 0 = overlapping
# Negative = probably wrong cluster

library(cluster)
km <- kmeans(data, centers=2, nstart=25)
sil <- silhouette(km$cluster, dist(data))
mean(sil[, 3]) # Average silhouette (higher is better)

# Visualize silhouette
plot(sil, main="Silhouette Plot")

# Davies-Bouldin Index: Lower is better
library(clusterSim)
index.DB(data, km$cluster)

# HIERARCHICAL CLUSTERING - DENDROGRAM:


# Builds tree of clusters (easy visualization)

hc <- hclust(dist(data), method="complete")

# Dendrogram
plot(hc, main="Hierarchical Clustering Dendrogram")

# Cut dendrogram at height 2
cluster_assignment <- cutree(hc, h=2)

# Or specify k
cluster_assignment <- cutree(hc, k=2)

# PCA - DIMENSIONALITY REDUCTION:


# Compress data to main patterns

# Standardize data first
data_scaled <- scale(data)

# PCA
pca <- prcomp(data_scaled)

# Variance explained
summary(pca)
# PC1 explains 70% of variance
# PC2 explains 30%
# Together = 100%

# Plot in PC space
plot(pca$x[, 1], pca$x[, 2],
main="PCA Projection",
xlab="PC1", ylab="PC2")

# Biplot (shows variables)
biplot(pca)

# T-SNE FOR VISUALIZATION:


library(tsne)

# t-SNE reduces to 2D for visualization
tsne_result <- tsne(data_scaled, k=2, initial_dims=ncol(data_scaled))

plot(tsne_result, main="t-SNE Visualization")

# PRACTICAL WORKFLOW:


# Customer segmentation example
customers <- read_csv("customers.csv")

# 1. Prepare data
features <- customers |>
select(age, income, purchases, tenure) |>
scale()

# 2. Find optimal k
wss <- vector("numeric", 10)
for (k in 1:10) {
km <- kmeans(features, centers=k, nstart=25)
wss[k] <- km$tot.withinss
}
plot(wss) # Look for elbow

# 3. Fit final model with chosen k
k_final <- 3
km_final <- kmeans(features, centers=k_final, nstart=25)

# 4. Add to original data
customers$segment <- km_final$cluster

# 5. Profile segments
customers |>
group_by(segment) |>
summarize(
avg_age = mean(age),
avg_income = mean(income),
avg_purchases = mean(purchases),
count = n()
)

# 6. Name segments
customers$segment_name <- case_when(
customers$segment == 1 ~ "Young Budget",
customers$segment == 2 ~ "Established Rich",
customers$segment == 3 ~ "Mature Moderate"
)