R/tests_norm.R
In oislen/BuenaVista: Functions for Everyday Data Science Tasks
#' @title Performs a variety of Normality Tests on a given dataset
#'
#' @description Performs a variety of normality tests on the numeric variables on a given dataset.
#' Note the function also evaluates numeric vectors as well.
#' The tests include; the shapiro wilk test, the anderson darling test, the cramer-von Mises test, the lillie (kolmogorov-smirnov) test, pearson chi-square test and the shapiro-francia test.
#' The results can be saved to a specified directory.
#'
#' @param dataset A dataset to be tested
#'
#' @param test The type of normlity test used.
#' One of six; "shapiro-wilk", "anderson-darling", "cramer-von mises", "lillie", "pearson" and "shapiro-francia".
#' Default is "shapiro-wilk".
#'
#' @param file_name A character object indicating the file name when saving the data frame.
#' The default is NULL.
#' The name must include the .csv suffixs.
#'
#' @param directory A character object specifying the directory where the data frame is to be saved as a .csv file.
#'
#' @return Outputs a dataframe of the normality tests
#'
#' @import nortest
#'
#' @export
#'
#' @seealso \code{\link{tests_chisq}}, \code{\link{tests_cors}}, \code{\link{tests_ks}}, \code{\link{tests_proptest}}, \code{\link{tests_t}}, \code{\link{tests_var}}, \code{\link{tests_wilcoxon}}
#'
#' @keywords Normality Tests, Shapiro-Wilk, Anderson-Darling, Cramer-Von Mises, Lillie, Pearson, Shapiro-Francia
#'
#' @examples
#' # Example House Price Dataset
#' tests_norm(dataset = house_prices, test = "anderson-darling")
#'
tests_norm <- function(dataset,
test = c("shapiro-wilk", "anderson-darling", "cramer-von mises", "lillie", "pearson", "shapiro-francia"),
file_name = NULL,
directory = NULL)
{
#-------------------------------------------------------------------------------#
# When dataset = data frame #
#-------------------------------------------------------------------------------#
if(is.data.frame(dataset)){
# Make sure the datset is converted to a data frame
dataset <- as.data.frame(x = dataset)
# Confirm correct choice for test
test <- match.arg(test)
# First create a dataframe to store the relevent normality test data
normtestdf <- as.data.frame(matrix(nrow = 1,
ncol = 4))
# rename the columns of the data frame
colnames(normtestdf) <- c("X", "test",
"Statistic", "P-Value")
# Create a row index to populate the data frame with
r = 1
for (i in 1:ncol(dataset)) {
if (is.numeric(dataset[,i])){
if(test == "shapiro-wilk"){
# Fill in the Variable Name
normtestdf[r, 1] <- colnames(dataset)[i]
# Fill in the test
normtestdf[r, 2] <- test
# Perform the Shapiro Wilk Test
SWT <- shapiro.test(x = dataset[,i])
# Fill in the Shapiro Wilk Test Statistic
normtestdf[r, 3] <- round(SWT$statistic,
digits = 4)
# Fill in the Shapiro Wilk P-Value
normtestdf[r, 4] <- round(SWT$p.value,
digits = 4)
# update r index
r = r + 1
} else if(test == "anderson-darling"){
# Fill in the Variable Name
normtestdf[r, 1] <- colnames(dataset)[i]
# Fill in the test
normtestdf[r, 2] <- test
# Perform the Anderson Darling Test
ADT <- ad.test(x = dataset[,i])
# Fill in the Anderson Darling Test Statistic
normtestdf[r, 3] <- round(ADT$statistic,
digits = 4)
# Fill in the Anderson Darling P-Value
normtestdf[r, 4] <- round(ADT$p.value,
digits = 4)
# update r index
r = r + 1
} else if(test == "cramer-von mises"){
# Fill in the Variable Name
normtestdf[r, 1] <- colnames(dataset)[i]
# Fill in the test
normtestdf[r, 2] <- test
# Perform the Cramer-von Mises Test
CVMT <- cvm.test(x = dataset[,i])
# Fill in the Cramer-von Mises Test Statistic
normtestdf[r, 3] <- round(CVMT$statistic,
digits = 4)
# Fill in the Cramer-von Mises P-Value
normtestdf[r, 4] <- round(CVMT$p.value,
digits = 4)
# update r index
r = r + 1
} else if(test == "lillie"){
# Fill in the Variable Name
normtestdf[r, 1] <- colnames(dataset)[i]
# Fill in the test
normtestdf[r, 2] <- test
# Perform the Lillie (Kolomogrov-Smirnov) Test
LT <- lillie.test(x = dataset[,i])
# Fill in the Lillie Test Statistic
normtestdf[r, 3] <- round(LT$statistic,
digits = 4)
# Fill in the Lillie P-Value
normtestdf[r, 4] <- round(LT$p.value,
digits = 4)
# update r index
r = r + 1
} else if(test == "pearson"){
# Fill in the Variable Name
normtestdf[r, 1] <- colnames(dataset)[i]
# Fill in the test
normtestdf[r, 2] <- test
# Perform the Pearson chi-square Test
PT <- pearson.test(x = dataset[,i])
# Fill in the Pearson chi-square Test Statistic
normtestdf[r, 3] <- round(PT$statistic,
digits = 4)
# Fill in the Pearson chi-square P-Value
normtestdf[r, 4] <- round(PT$p.value,
digits = 4)
# update r index
r = r + 1
} else if(test == "shapiro-francia"){
# Fill in the Variable Name
normtestdf[r, 1] <- colnames(dataset)[i]
# Fill in the test
normtestdf[r, 2] <- test
# Perform the Shapiro-Francia Test
SFT <- sf.test(x = dataset[,i])
# Fill in the Shapiro-Francia Test Statistic
normtestdf[r, 3] <- round(SFT$statistic,
digits = 4)
# Fill in the Shapiro-Francia P-Value
normtestdf[r, 4] <- round(SFT$p.value,
digits = 4)
# update r index
r = r + 1
}
}
}
#-------------------------------------------------------------------------------#
# When dataset = vector #
#-------------------------------------------------------------------------------#
} else if(is.vector(dataset)){
# First create a dataframe to store the relevent normality test data
normtestdf <- as.data.frame(matrix(nrow = 1,
ncol = 4))
# rename the columns of the data frame
colnames(normtestdf) <- c("X", "test",
"Statistic", "P-Value")
# Confirm correct choice for test
test <- match.arg(test)
if(test == "shapiro-wilk"){
# Fill in the Variable Name
normtestdf[1, 1] <- deparse(substitute(dataset))
# Fill in the test
normtestdf[1, 2] <- test
# Perform the Shapiro Wilk Test
SWT <- shapiro.test(x = dataset)
# Fill in the Shapiro Wilk Test Statistic
normtestdf[1, 3] <- round(SWT$statistic,
digits = 4)
# Fill in the Shapiro Wilk P-Value
normtestdf[1, 4] <- round(SWT$p.value,
digits = 4)
} else if(test == "anderson-darling"){
# Fill in the Variable Name
normtestdf[1, 1] <- deparse(substitute(dataset))
# Fill in the test
normtestdf[1, 2] <- test
# Perform the Anderson Darling Test
ADT <- ad.test(x = dataset)
# Fill in the Anderson Darling Test Statistic
normtestdf[1, 3] <- round(ADT$statistic,
digits = 4)
# Fill in the Anderson Darling P-Value
normtestdf[1, 4] <- round(ADT$p.value,
digits = 4)
} else if(test == "cramer-von mises"){
# Fill in the Variable Name
normtestdf[1, 1] <- deparse(substitute(dataset))
# Fill in the test
normtestdf[1, 2] <- test
# Perform the Cramer-von Mises Test
CVMT <- cvm.test(x = dataset)
# Fill in the Cramer-von Mises Test Statistic
normtestdf[1, 3] <- round(CVMT$statistic,
digits = 4)
# Fill in the Cramer-von Mises P-Value
normtestdf[1, 4] <- round(CVMT$p.value,
digits = 4)
} else if(test == "lillie"){
# Fill in the Variable Name
normtestdf[1, 1] <- deparse(substitute(dataset))
# Fill in the test
normtestdf[1, 2] <- test
# Perform the Lillie (Kolomogrov-Smirnov) Test
LT <- ad.test(x = dataset)
# Fill in the Lillie Test Statistic
normtestdf[1, 3] <- round(LT$statistic,
digits = 4)
# Fill in the Lillie P-Value
normtestdf[1, 4] <- round(LT$p.value,
digits = 4)
} else if(test == "pearson"){
# Fill in the Variable Name
normtestdf[1, 1] <- deparse(substitute(dataset))
# Fill in the test
normtestdf[1, 2] <- test
# Perform the Pearson chi-square Test
PT <- pearson.test(x = dataset)
# Fill in the Pearson chi-square Test Statistic
normtestdf[1, 3] <- round(PT$statistic,
digits = 4)
# Fill in the Pearson chi-square P-Value
normtestdf[1, 4] <- round(PT$p.value,
digits = 4)
} else if(test == "shapiro-francia"){
# Fill in the Variable Name
normtestdf[1, 1] <- colnames(dataset)
# Fill in the test
normtestdf[1, 2] <- test
# Perform the Shapiro-Francia Test
SFT <- sf.test(x = dataset)
# Fill in the Shapiro-Francia Test Statistic
normtestdf[1, 3] <- round(SFT$statistic,
digits = 4)
# Fill in the Shapiro-Francia P-Value
normtestdf[1, 4] <- round(SFT$p.value,
digits = 4)
}
}
# Write the data frame to the specified directory
if(!is.null(directory)) {
write.csv(x = normtestdf,
file = paste(directory, "/", file_name, sep = ""),
row.names = F)
}
# return the chisqtestdf
return(normtestdf)
}
oislen/BuenaVista documentation built on May 16, 2019, 8:12 p.m.
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
#' @title Performs a variety of Normality Tests on a given dataset
#'
#' @description Performs a variety of normality tests on the numeric variables on a given dataset.
#' Note the function also evaluates numeric vectors as well.
#' The tests include; the shapiro wilk test, the anderson darling test, the cramer-von Mises test, the lillie (kolmogorov-smirnov) test, pearson chi-square test and the shapiro-francia test.
#' The results can be saved to a specified directory.
#'
#' @param dataset A dataset to be tested
#'
#' @param test The type of normlity test used.
#' One of six; "shapiro-wilk", "anderson-darling", "cramer-von mises", "lillie", "pearson" and "shapiro-francia".
#' Default is "shapiro-wilk".
#'
#' @param file_name A character object indicating the file name when saving the data frame.
#' The default is NULL.
#' The name must include the .csv suffixs.
#'
#' @param directory A character object specifying the directory where the data frame is to be saved as a .csv file.
#'
#' @return Outputs a dataframe of the normality tests
#'
#' @import nortest
#'
#' @export
#'
#' @seealso \code{\link{tests_chisq}}, \code{\link{tests_cors}}, \code{\link{tests_ks}}, \code{\link{tests_proptest}}, \code{\link{tests_t}}, \code{\link{tests_var}}, \code{\link{tests_wilcoxon}}
#'
#' @keywords Normality Tests, Shapiro-Wilk, Anderson-Darling, Cramer-Von Mises, Lillie, Pearson, Shapiro-Francia
#'
#' @examples
#' # Example House Price Dataset
#' tests_norm(dataset = house_prices, test = "anderson-darling")
#'
tests_norm <- function(dataset,
test = c("shapiro-wilk", "anderson-darling", "cramer-von mises", "lillie", "pearson", "shapiro-francia"),
file_name = NULL,
directory = NULL)
{
#-------------------------------------------------------------------------------#
# When dataset = data frame #
#-------------------------------------------------------------------------------#
if(is.data.frame(dataset)){
# Make sure the datset is converted to a data frame
dataset <- as.data.frame(x = dataset)
# Confirm correct choice for test
test <- match.arg(test)
# First create a dataframe to store the relevent normality test data
normtestdf <- as.data.frame(matrix(nrow = 1,
ncol = 4))
# rename the columns of the data frame
colnames(normtestdf) <- c("X", "test",
"Statistic", "P-Value")
# Create a row index to populate the data frame with
r = 1
for (i in 1:ncol(dataset)) {
if (is.numeric(dataset[,i])){
if(test == "shapiro-wilk"){
# Fill in the Variable Name
normtestdf[r, 1] <- colnames(dataset)[i]
# Fill in the test
normtestdf[r, 2] <- test
# Perform the Shapiro Wilk Test
SWT <- shapiro.test(x = dataset[,i])
# Fill in the Shapiro Wilk Test Statistic
normtestdf[r, 3] <- round(SWT$statistic,
digits = 4)
# Fill in the Shapiro Wilk P-Value
normtestdf[r, 4] <- round(SWT$p.value,
digits = 4)
# update r index
r = r + 1
} else if(test == "anderson-darling"){
# Fill in the Variable Name
normtestdf[r, 1] <- colnames(dataset)[i]
# Fill in the test
normtestdf[r, 2] <- test
# Perform the Anderson Darling Test
ADT <- ad.test(x = dataset[,i])
# Fill in the Anderson Darling Test Statistic
normtestdf[r, 3] <- round(ADT$statistic,
digits = 4)
# Fill in the Anderson Darling P-Value
normtestdf[r, 4] <- round(ADT$p.value,
digits = 4)
# update r index
r = r + 1
} else if(test == "cramer-von mises"){
# Fill in the Variable Name
normtestdf[r, 1] <- colnames(dataset)[i]
# Fill in the test
normtestdf[r, 2] <- test
# Perform the Cramer-von Mises Test
CVMT <- cvm.test(x = dataset[,i])
# Fill in the Cramer-von Mises Test Statistic
normtestdf[r, 3] <- round(CVMT$statistic,
digits = 4)
# Fill in the Cramer-von Mises P-Value
normtestdf[r, 4] <- round(CVMT$p.value,
digits = 4)
# update r index
r = r + 1
} else if(test == "lillie"){
# Fill in the Variable Name
normtestdf[r, 1] <- colnames(dataset)[i]
# Fill in the test
normtestdf[r, 2] <- test
# Perform the Lillie (Kolomogrov-Smirnov) Test
LT <- lillie.test(x = dataset[,i])
# Fill in the Lillie Test Statistic
normtestdf[r, 3] <- round(LT$statistic,
digits = 4)
# Fill in the Lillie P-Value
normtestdf[r, 4] <- round(LT$p.value,
digits = 4)
# update r index
r = r + 1
} else if(test == "pearson"){
# Fill in the Variable Name
normtestdf[r, 1] <- colnames(dataset)[i]
# Fill in the test
normtestdf[r, 2] <- test
# Perform the Pearson chi-square Test
PT <- pearson.test(x = dataset[,i])
# Fill in the Pearson chi-square Test Statistic
normtestdf[r, 3] <- round(PT$statistic,
digits = 4)
# Fill in the Pearson chi-square P-Value
normtestdf[r, 4] <- round(PT$p.value,
digits = 4)
# update r index
r = r + 1
} else if(test == "shapiro-francia"){
# Fill in the Variable Name
normtestdf[r, 1] <- colnames(dataset)[i]
# Fill in the test
normtestdf[r, 2] <- test
# Perform the Shapiro-Francia Test
SFT <- sf.test(x = dataset[,i])
# Fill in the Shapiro-Francia Test Statistic
normtestdf[r, 3] <- round(SFT$statistic,
digits = 4)
# Fill in the Shapiro-Francia P-Value
normtestdf[r, 4] <- round(SFT$p.value,
digits = 4)
# update r index
r = r + 1
}
}
}
#-------------------------------------------------------------------------------#
# When dataset = vector #
#-------------------------------------------------------------------------------#
} else if(is.vector(dataset)){
# First create a dataframe to store the relevent normality test data
normtestdf <- as.data.frame(matrix(nrow = 1,
ncol = 4))
# rename the columns of the data frame
colnames(normtestdf) <- c("X", "test",
"Statistic", "P-Value")
# Confirm correct choice for test
test <- match.arg(test)
if(test == "shapiro-wilk"){
# Fill in the Variable Name
normtestdf[1, 1] <- deparse(substitute(dataset))
# Fill in the test
normtestdf[1, 2] <- test
# Perform the Shapiro Wilk Test
SWT <- shapiro.test(x = dataset)
# Fill in the Shapiro Wilk Test Statistic
normtestdf[1, 3] <- round(SWT$statistic,
digits = 4)
# Fill in the Shapiro Wilk P-Value
normtestdf[1, 4] <- round(SWT$p.value,
digits = 4)
} else if(test == "anderson-darling"){
# Fill in the Variable Name
normtestdf[1, 1] <- deparse(substitute(dataset))
# Fill in the test
normtestdf[1, 2] <- test
# Perform the Anderson Darling Test
ADT <- ad.test(x = dataset)
# Fill in the Anderson Darling Test Statistic
normtestdf[1, 3] <- round(ADT$statistic,
digits = 4)
# Fill in the Anderson Darling P-Value
normtestdf[1, 4] <- round(ADT$p.value,
digits = 4)
} else if(test == "cramer-von mises"){
# Fill in the Variable Name
normtestdf[1, 1] <- deparse(substitute(dataset))
# Fill in the test
normtestdf[1, 2] <- test
# Perform the Cramer-von Mises Test
CVMT <- cvm.test(x = dataset)
# Fill in the Cramer-von Mises Test Statistic
normtestdf[1, 3] <- round(CVMT$statistic,
digits = 4)
# Fill in the Cramer-von Mises P-Value
normtestdf[1, 4] <- round(CVMT$p.value,
digits = 4)
} else if(test == "lillie"){
# Fill in the Variable Name
normtestdf[1, 1] <- deparse(substitute(dataset))
# Fill in the test
normtestdf[1, 2] <- test
# Perform the Lillie (Kolomogrov-Smirnov) Test
LT <- ad.test(x = dataset)
# Fill in the Lillie Test Statistic
normtestdf[1, 3] <- round(LT$statistic,
digits = 4)
# Fill in the Lillie P-Value
normtestdf[1, 4] <- round(LT$p.value,
digits = 4)
} else if(test == "pearson"){
# Fill in the Variable Name
normtestdf[1, 1] <- deparse(substitute(dataset))
# Fill in the test
normtestdf[1, 2] <- test
# Perform the Pearson chi-square Test
PT <- pearson.test(x = dataset)
# Fill in the Pearson chi-square Test Statistic
normtestdf[1, 3] <- round(PT$statistic,
digits = 4)
# Fill in the Pearson chi-square P-Value
normtestdf[1, 4] <- round(PT$p.value,
digits = 4)
} else if(test == "shapiro-francia"){
# Fill in the Variable Name
normtestdf[1, 1] <- colnames(dataset)
# Fill in the test
normtestdf[1, 2] <- test
# Perform the Shapiro-Francia Test
SFT <- sf.test(x = dataset)
# Fill in the Shapiro-Francia Test Statistic
normtestdf[1, 3] <- round(SFT$statistic,
digits = 4)
# Fill in the Shapiro-Francia P-Value
normtestdf[1, 4] <- round(SFT$p.value,
digits = 4)
}
}
# Write the data frame to the specified directory
if(!is.null(directory)) {
write.csv(x = normtestdf,
file = paste(directory, "/", file_name, sep = ""),
row.names = F)
}
# return the chisqtestdf
return(normtestdf)
}
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
Embedding an R snippet on your website
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.