# ====================================================================
# Week 9: Classification and Machine Learning
# Kmex Consult - R Data Science Course
# Open in RStudio and run each block with Ctrl+Enter (Cmd+Enter on Mac).
# ====================================================================

# Building predictive models for categorical outcomes

# ====================================================================
# WEEK 9 OVERVIEW
# ====================================================================
# Classification = Predicting categories (Yes/No, Class A/B/C, etc.)
# REAL EXAMPLES:
# - Email: Spam or Not Spam
# - Credit: Approve or Deny
# - Disease: Has cancer or Doesn't
# - Loan: Default or Repay
# - Customer: Will churn or Stay
# WORKFLOW:
# 1. Prepare data (train/test split)
# 2. Build models (multiple types)
# 3. Evaluate performance
# 4. Tune hyperparameters
# 5. Select best model
# 6. Deploy and monitor
# KEY ALGORITHMS THIS WEEK:
# ✓ Logistic Regression
# ✓ Decision Trees
# ✓ Random Forests
# ✓ Naive Bayes
# ✓ K-Nearest Neighbors (KNN)
# ✓ Support Vector Machines (SVM)
# ✓ Ensemble methods
# EVALUATION METRICS:
# ✓ Accuracy (% correct)
# ✓ Precision (of predicted positive)
# ✓ Recall (of actual positive)
# ✓ F1 Score (balance precision/recall)
# ✓ ROC-AUC (overall performance)
# ✓ Confusion Matrix (detailed breakdown)
# IMPORTANT:
# Accuracy alone is NOT enough!
# - Imbalanced data: Class A = 95%, Class B = 5%
# - Accuracy of 95% possible by predicting Class A always!
# - Need precision, recall, F1, or ROC-AUC instead

# ====================================================================
# SESSION 1: CLASSIFICATION FUNDAMENTALS AND LOGISTIC REGRESSION
# ====================================================================

# --- Duration: 2 hours ---

# --- 1.1 Train-Test Split and Logistic Regression ---
# TRAIN-TEST SPLIT - FUNDAMENTAL REQUIREMENT:
# Never evaluate on data used for training!


library(caret)
library(dplyr)

# Load data
data <- read_csv("customer_data.csv") # 1000 rows

# Split: 80% train, 20% test
set.seed(42)
index <- createDataPartition(data$churn, p=0.8, list=FALSE)
train_data <- data[index, ]
test_data <- data[-index, ]

print(paste("Train:", nrow(train_data), "rows")) # 800
print(paste("Test:", nrow(test_data), "rows")) # 200

# Alternative simple method
train_size <- 0.8 * nrow(data)
train_index <- sample(nrow(data), train_size)
train_data <- data[train_index, ]
test_data <- data[-train_index, ]

# LOGISTIC REGRESSION - BASELINE MODEL:
# Despite name, used for CLASSIFICATION, not regression


# Example data
df <- tibble(
age = c(20, 25, 30, 35, 40, 45, 50),
approved = c(0, 0, 1, 1, 1, 1, 1) # Binary outcome
)

# Logistic regression
model <- glm(approved ~ age, family=binomial, data=df)

summary(model)

# Output:
# Coefficients:
# Estimate Std. Error z value Pr(>|z|)
# (Intercept) -2.7081 2.5054 -1.081 0.280
# age 0.1018 0.0717 1.420 0.156

# Interpretation:
# Coefficient = log-odds change
# Positive = increases probability
# Each year of age → log-odds increase by 0.10

# Predict probabilities
predictions <- predict(model, df, type="response")
# [1] 0.063 0.104 0.163 0.243 0.337 0.438 0.531

# Interpretation: P(approved=1|age)
# Age 20 → 6% approval chance
# Age 50 → 53% approval chance

# Convert to binary predictions (threshold = 0.5)
pred_binary <- ifelse(predictions > 0.5, 1, 0)
# [1] 0 0 0 0 0 0 1

# DECISION TREES - INTERPRETABLE MODELS:


library(rpart)
library(rpart.plot)

# Simple tree
tree_model <- rpart(Species ~ ., data=iris, method="class")

# Plot tree
rpart.plot(tree_model)

# Predictions
predict(tree_model, iris[1:5, ], type="class")

# Tree interpretation (very human-readable):
# If Petal.Length <= 2.4: Setosa
# Else if Petal.Length <= 4.8: Versicolor
# Else: Virginica

# RANDOM FORESTS - ENSEMBLE METHOD:


library(randomForest)

# Train
rf_model <- randomForest(Species ~ .,
data=iris,
ntree=100,
mtry=2)

# Predictions
pred <- predict(rf_model, iris)

# Feature importance
importance(rf_model)
# Shows which variables matter most

# Visualize importance
plot(importance(rf_model))

# MODEL EVALUATION - CRITICAL STEP:


library(caret)

# Confusion matrix
predictions <- predict(model, test_data, type="response")
pred_binary <- ifelse(predictions > 0.5, "Yes", "No")

confusion <- table(test_data$churn, pred_binary)
# No Yes
# No 140 10
# Yes 20 30

# Interpretation:
# True Negatives (TN) = 140
# False Positives (FP) = 10
# False Negatives (FN) = 20
# True Positives (TP) = 30

# Calculate metrics
accuracy <- (TP + TN) / (TP + TN + FP + FN) # (140+30)/200 = 0.85
precision <- TP / (TP + FP) # 30/40 = 0.75
recall <- TP / (TP + FN) # 30/50 = 0.60
f1 <- 2 * (precision * recall) / (precision + recall) # 0.67

# Automatic calculation
confusionMatrix(factor(pred_binary), test_data$churn)

# ROC-AUC: Best overall metric
library(pROC)
roc_obj <- roc(test_data$churn, predictions)
auc(roc_obj) # AUC = 0.72

plot(roc_obj, main="ROC Curve")

# HYPERPARAMETER TUNING:


# Grid search for best parameters
library(caret)

# Define parameter grid
grid <- expand.grid(
mtry = c(2, 3, 4), # Variables per split
splitrule = "gini",
min.node.size = c(5, 10, 15)
)

# Train with cross-validation
train_control <- trainControl(
method = "cv", # 10-fold cross-validation
number = 10,
classProbs = TRUE,
summaryFunction = twoClassSummary
)

# Tune model
tune_model <- train(
churn ~ .,
data = train_data,
method = "ranger",
trControl = train_control,
tuneGrid = grid,
metric = "ROC"
)

# Best parameters
tune_model$bestTune

# Final model with best parameters
final_model <- tune_model$finalModel

# CROSS-VALIDATION - ROBUST EVALUATION:


library(caret)

# 5-fold cross-validation
folds <- createFolds(data$outcome, k=5)

results <- lapply(folds, function(i) {
train <- data[-i, ]
test <- data[i, ]

model <- glm(outcome ~ ., data=train, family=binomial)
pred <- predict(model, test, type="response")
pred_binary <- ifelse(pred > 0.5, 1, 0)

accuracy <- mean(pred_binary == test$outcome)
return(accuracy)
})

mean(unlist(results)) # Average across folds