edit in vignettes

DESCRIPTION

@@ -11,7 +11,7 @@ Imports:
     ggplot2,
     dplyr,
     nycflights13,
-    methods
+    methods,
 RoxygenNote: 7.3.2
 Encoding: UTF-8
 Suggests: 

R/predictive_modelling_flight_delay.R

-#' Predictive modeling of flight delays using ridgereg()
-#'
-#' Ridge Regression Reference Class
-#'
-#' This class implements ridge regression with methods for initialization, coefficient extraction,
-#' prediction, and printing the model summary.
-#'
-#' @field formula_string A character string representing the regression formula.
-#' @field data_string A character string representing the data frame used.
-#' @field formula A formula specifying the relationship between dependent and independent variables.
-#' @field data A data frame containing the variables specified in the formula.
-#' @field lambda A numeric value for the ridge penalty parameter.
-#' @field coefficients A matrix containing the estimated ridge regression coefficients.
-#' @field fitted_values A matrix of the fitted (predicted) values.
-#' @field residuals A matrix of the residuals (difference between actual and fitted values).
-#' @method initialize Initializes
-#' @param formula A formula specifying the model.
-#' @param data A data frame containing the variables in the formula.
-#' @param lambda The ridge penalty parameter.
-#'
-#' @method print Prints
-#'
-#' @method predict Predicts
-#' @param newdata A data frame for which to predict new values.
-#' @return A vector of predicted values.
-#'
-#' @method coef Extracts
-#' @return A named vector of the regression coefficients.
-#' @importFrom methods new
-#'
-#' @import dplyr
-#' @import ggplot2
-#' @import nycflights13
-#'
-#' Prepare Flight Data
-#'
-#'
-#' @return A preprocessed data frame for modeling.
-#'
-#' @examples
-#' flight_data <- prepare_flight_data()
-#'
-#'
-#' Split Flight Data
-#'
-#'
-#' @return A list containing `train_data`, `validation_data`, and `test_data` data frames.
-#'
-#' @examples
-#' split_data <- split_flight_data(flight_data)
-#'
-#' Train and Evaluate Ridge Regression Models
-#'
-#'
-#' @return The best lambda value and the test RMSE for the final model.
-#'
-#' @examples
-#' best_lambda <- train_and_evaluate_ridge_regression(train_data, validation_data, test_data)
-#'
-#' Train the Final Model and Evaluate on Test Set
-#' @examples
-#' final_rmse <- final_model_evaluation(best_lambda, train_data, validation_data, test_data)
-#'
-#' @export
-#' Ridge Regression Reference Class
-#'
-#' @field formula A formula object specifying the regression model.
-#' @field data A data frame containing the variables in the model.
-#' @field lambda A numeric value for the ridge penalty (lambda).
-#' @field coefficients A numeric vector of estimated coefficients for the predictors.
-#' @field intercept A numeric value for the intercept term.
-#'
-#' @description
-#' This class performs ridge regression using a provided formula, data, and lambda parameter.
-#' It normalizes covariates, calculates coefficients using linear algebra, and provides methods
-#' to display the model, make predictions, and retrieve coefficients.
-#'
-#' @examples
-#' # Example usage with mtcars dataset
-#' mod <- ridgereg$new(formula = mpg ~ cyl + disp, data = mtcars, lambda = 0.1)
-#' mod$show()
-#' mod$coef()
-#'
-#' mod <- ridgereg$new(formula = Sepal.Length ~ Sepal.Width + Petal.Length, data = iris, lambda = 0.1)
-#' mod$show()
-#' mod$coef()
-ridgereg <- setRefClass(
-  "ridgereg",
-  fields = list(
-    formula = "formula",
-    data = "data.frame",
-    lambda = "numeric",
-    coefficients = "numeric",
-    intercept = "numeric"
-  ),
-  methods = list(
-    #' Initialize the Ridge Regression Model
-    #'
-    #' @param formula A formula specifying the regression model.
-    #' @param data A data frame containing the variables in the model.
-    #' @param lambda A numeric value for the ridge penalty.
-    initialize = function(formula, data, lambda) {
-      formula <<- formula
-      data <<- data
-      lambda <<- lambda
-      X <- model.matrix(formula, data)
-      y <- data[[as.character(formula[[2]])]]
-      intercept_column <- X[, 1]
-      X_predictors <- X[, -1]
-      X_scaled <- scale(X_predictors, center = TRUE, scale = TRUE)
-      y_centered <- y - mean(y)
-      X_standardized <- cbind(Intercept = intercept_column, X_scaled)
-      I <- diag(ncol(X_standardized))
-      I[1, 1] <- 0
-      beta_ridge <- solve(t(X_standardized) %*% X_standardized + lambda * I) %*% t(X_standardized) %*% y_centered
-      beta_unscaled <- beta_ridge[-1] / attr(X_scaled, "scaled:scale")
-      intercept_adjusted <- mean(y) - sum(beta_unscaled * attr(X_scaled, "scaled:center"))
-      coefficients <<- as.numeric(beta_unscaled)
-      intercept <<- intercept_adjusted
-    },
-
-    #' Show the model coefficients
-    #'
-    #' Prints the intercept and coefficients for the ridge regression model.
-    show = function() {
-      cat("Ridge Regression Coefficients:\n")
-      cat("Intercept:", intercept, "\n")
-      cat("Coefficients:\n")
-      print(coefficients)
-    },
-
-    #' Predict using the Ridge Regression Model
-    #'
-    #' @param newdata Optional data frame for making predictions. If NULL, predictions are made on the training data.
-    #' @return Predicted values as a numeric vector.
-    predict = function(newdata = NULL) {
-      if (is.null(newdata)) {
-        X <- model.matrix(formula, data)
-      } else {
-        X <- model.matrix(formula, newdata)
-      }
-      X %*% c(intercept, coefficients)
-    },
-
-    #' Get the Coefficients
-    #'
-    #' @return A named numeric vector of the intercept and coefficients.
-    coef = function() {
-      c(Intercept = intercept, coefficients)
-    }
-  )
-)
-
-
-#' Prepare Flight Data
-#'
-#' @description
-#' Preprocesses the `flights` and `weather` data from the `nycflights13` package.
-#' The function merges, filters, and transforms the data, creating interaction terms.
-#' It removes any rows with NA values.
-#'
-#' @return A preprocessed data frame for modeling.
-#'
-#' @examples
-#' flight_data <- prepare_flight_data()
-prepare_flight_data <- function() {
-  # Merge flights and weather data on common columns (year, month, day, hour, origin)
-  flight_data <- nycflights13::flights %>%
-    dplyr::inner_join(nycflights13::weather, by = c("year", "month", "day", "hour", "origin")) %>%
-    dplyr::filter(!is.na(dep_delay)) %>%
-    dplyr::select(dep_delay, origin, month, day, hour, temp, dewp, humid, wind_speed, precip, visib) %>%
-    dplyr::mutate(
-      temp_wind_interaction = temp * wind_speed,  # Example of an interaction term
-      humid_precip_interaction = humid * precip
-    ) %>%
-    dplyr::select(-origin) %>%  # Remove categorical column to keep numeric features
-    na.omit()  # Remove any rows with NA values
-
-  return(flight_data)
-}
-
-
-# Prepare the data
-flight_data <- prepare_flight_data()
-
-
-#' Split Flight Data
-#'
-#' @description
-#' Splits the flight data into training, validation, and test sets. The training set contains
-#' 80% of the data, while the validation and test sets contain 15% and 5%, respectively.
-#'
-#' @return A list containing `train_data`, `validation_data`, and `test_data` data frames.
-#'
-#' @examples
-#' split_data <- split_flight_data(flight_data)
-set.seed(123)
-trainIndex <- caret::createDataPartition(flight_data$dep_delay, p = 0.8, list = FALSE)
-train_data <- flight_data[trainIndex, ]
-temp_data <- flight_data[-trainIndex, ]
-
-# Further split temp_data into validation (15%) and test (5%)
-validationIndex <- caret::createDataPartition(temp_data$dep_delay, p = 0.75, list = FALSE)
-validation_data <- temp_data[validationIndex, ]
-test_data <- temp_data[-validationIndex, ]
-
-
-#' Train and Evaluate Ridge Regression Models
-#'
-#' @description
-#' Trains ridge regression models with different lambda values and evaluates them on a validation set.
-#' The best lambda is chosen based on the lowest RMSE on the validation set.
-#'
-#' @return The best lambda value and the test RMSE for the final model.
-#'
-#' @examples
-#' best_lambda <- train_and_evaluate_ridge_regression(train_data, validation_data, test_data)
-lambdas <- c(0.1, 1, 10, 100)  # Set of lambda values to try
-validation_rmse <- numeric(length(lambdas))
-
-for (i in seq_along(lambdas)) {
-  # Train a ridgereg model on the training data
-  model <- ridgereg$new(dep_delay ~ ., data = train_data, lambda = lambdas[i])
-
-  # Predict on validation data
-  predictions <- model$predict(validation_data)
-
-  # Calculate RMSE on validation set
-  validation_rmse[i] <- sqrt(mean((validation_data$dep_delay - predictions)^2))
-}
-
-# Choose the best lambda based on lowest RMSE
-best_lambda <- lambdas[which.min(validation_rmse)]
-
-#' Train the Final Model and Evaluate on Test Set
-#'
-#' @description
-#' Trains the final ridge regression model using the best lambda value on the combined
-#' training and validation data. Evaluates the model on the test set and calculates the RMSE.
-#'
-#' @examples
-#' final_rmse <- final_model_evaluation(best_lambda, train_data, validation_data, test_data)
-final_model <- ridgereg$new(dep_delay ~ ., data = rbind(train_data, validation_data), lambda = best_lambda)
-test_predictions <- final_model$predict(test_data)
-test_rmse <- sqrt(mean((test_data$dep_delay - test_predictions)^2))
-
-# Print the test RMSE
-cat("Best lambda:", best_lambda, "\n")
-cat("Test RMSE:", test_rmse, "\n")

vignettes/group5labbonus.Rmd

@@ -95,4 +95,3 @@ This function visualizes the mean flight delay at each origin airport in the nyc
 ```{r}
 visualize_airport_delays()
 ```
-