---
title: "Ridge model"
output: rmarkdown::html_vignette
vignette: >
  %\VignetteIndexEntry{Ridge model}
  %\VignetteEngine{knitr::rmarkdown}
  %\VignetteEncoding{UTF-8}
---

```{r}
library(rvfl)
```

# Example 1: MPG Prediction (mtcars dataset)

## Load and prepare data
```{r}
data(mtcars)

set.seed(1243)
train_idx <- sample(nrow(mtcars), size = floor(0.8 * nrow(mtcars)))
train_data <- mtcars[train_idx, ]
test_data <- mtcars[-train_idx, -1]
```

## Fit models
```{r fig.size=7.5}
# Fit regular linear model
start <- proc.time()[3]
lm_model <- lm(mpg ~ ., data = train_data)
print(proc.time()[3] - start)
print(summary(lm_model))
print(confint(lm_model))

# Fit calibrated model 
start <- proc.time()[3]
ridge_model <- rvfl::calibmodel(lambda=10**seq(-10, 10, length.out=100), x = as.matrix(train_data[,-1]), y = train_data$mpg)
print(proc.time()[3] - start)
print(summary(ridge_model))
print(plot(ridge_model))
```

# Example 2: Boston Housing Price Prediction

## Load and prepare data
```{r}
library(MASS)
data(Boston)

set.seed(1243)
train_idx <- sample(nrow(Boston), size = floor(0.8 * nrow(Boston)))
train_data <- Boston[train_idx, ]
test_data <- Boston[-train_idx, -14]  # -14 removes 'medv' (target variable)
```

## Fit models
```{r fig.size=7.5}
# Fit regular linear model
start <- proc.time()[3]
lm_model <- lm(medv ~ ., data = train_data)
print(proc.time()[3] - start)
print(summary(lm_model))
print(confint(lm_model))

# Fit calibrated model 
start <- proc.time()[3]
ridge_model <- rvfl::calibmodel(lambda=10**seq(-10, 10, length.out=100), x = as.matrix(train_data[,-14]), y = train_data$medv)
print(proc.time()[3] - start)
print(summary(ridge_model))
print(plot(ridge_model))
```


# Example 3: Economic Indicators (Longley dataset)

## Load and prepare data
```{r}
data(longley)

set.seed(1243)
train_idx <- sample(nrow(longley), size = floor(0.8 * nrow(longley)))
train_data <- longley[train_idx, ]
test_data <- longley[-train_idx, -7]  # -7 removes 'Employed' (target variable)
```

## Fit models
```{r fig.size=7.5}
# Fit regular linear model
start <- proc.time()[3]
lm_model <- lm(Employed ~ ., data = train_data)
print(proc.time()[3] - start)
print(summary(lm_model))
print(confint(lm_model))

# Fit calibrated model 
start <- proc.time()[3]
ridge_model <- rvfl::calibmodel(lambda=10**seq(-10, 10, length.out=100), x = as.matrix(train_data[,-7]), y = train_data$Employed)
print(proc.time()[3] - start)
# print(summary(ridge_model))
print(plot(ridge_model))
```

# Example 4: US Crime Rate Analysis

## Load and prepare data
```{r}
data(UScrime)

set.seed(1243)
train_idx <- sample(nrow(UScrime), size = floor(0.8 * nrow(UScrime)))
train_data <- UScrime[train_idx, ]
test_data <- UScrime[-train_idx, -16]  # -16 removes 'y' (crime rate)
```

## Fit models
```{r fig.size=7.5}
# Fit regular linear model
start <- proc.time()[3]
lm_model <- lm(y ~ ., data = train_data)
print(proc.time()[3] - start)
print(summary(lm_model))
print(confint(lm_model))

# Fit calibrated model 
start <- proc.time()[3]
ridge_model <- rvfl::calibmodel(lambda=10**seq(-10, 10, length.out=100), x = as.matrix(train_data[,-16]), y = train_data$y)
print(proc.time()[3] - start)
print(summary(ridge_model))
print(plot(ridge_model))
```

# Example 5: Car Price Analysis (Cars93 dataset)

## Load and prepare data
```{r}
data(Cars93, package = "MASS")

# Remove rows with missing values
Cars93 <- na.omit(Cars93)

# Select numeric predictors and price as response
predictors <- c("MPG.city", "MPG.highway", "EngineSize", "Horsepower", 
                "RPM", "Rev.per.mile", "Fuel.tank.capacity", "Length", 
                "Wheelbase", "Width", "Turn.circle", "Weight")
car_data <- Cars93[, c(predictors, "Price")]

set.seed(1243)
train_idx <- sample(nrow(car_data), size = floor(0.8 * nrow(car_data)))
train_data <- car_data[train_idx, ]
test_data <- car_data[-train_idx, -which(names(car_data) == "Price")]
```

## Fit models
```{r fig.size=7.5}
# Fit regular linear model
start <- proc.time()[3]
lm_model <- lm(Price ~ ., data = train_data)
print(proc.time()[3] - start)
print(summary(lm_model))
print(confint(lm_model))

# Fit calibrated model 
start <- proc.time()[3]
ridge_model <- rvfl::calibmodel(lambda=10**seq(-10, 10, length.out=100), x = as.matrix(train_data[,-which(names(train_data) == "Price")]), 
                               y = train_data$Price)
print(proc.time()[3] - start)
print(summary(ridge_model))
print(plot(ridge_model))
```