dataprep (version 0.1.5)

descdata: Fast descriptive statistics

Description

It describes data using R basic functions, without calling other packages to avoid redundant calculations, which is faster.

Usage

descdata(data, start = NULL, end = NULL, stats= 1:9, first = "variables")

Arguments

data

A data frame to describe, from the column start to the column end.

start

The column number of the first variable to describe.

end

The column number of the last variable to describe.

stats

Selecting or rearranging the items from the 9 statistics, i.e., n, na, mean, sd, median, trimmed, min, max, and IQR. It can be a vector or a single value, in 'character' or 'numeric' class.

first

The name of the first column of the output. It is the general name of the items (variables).

Value

A data frame of descriptive statistics:

size

default general name of items (variables). Users can define it via the parameter first.

n

number of valid cases

na

number of invalid cases

mean

mean of each item

sd

standard deviation

median

median of each item

trimmed

trimmed mean (with trim defaulting to .1)

min

minimum of each item

max

maximum of each item

IQR

interquartile range of each item

Details

This function can be used for different types of data, as long as the variables are numeric. Because it describes the data frame from the column start to the column end, the variables need to be linked together instead of being scattered.

References

1. Example data is from https://smear.avaa.csc.fi/download. It includes particle number concentrations in SMEAR I Varrio forest.

See Also

dataprep::descplot

Examples

# NOT RUN {
# Variable names are essentially numeric
descdata(data,5,65)
# Use numbers to select statistics
descdata(data,5,65,c(2,7:9))
# Use characters to select statistics
descdata(data,5,65,c('na','min','max','IQR'))

# When type of variable names is character
descdata(data1,3,7)
# Use numbers to select statistics
descdata(data1,3,7,c(2,7:9))
# Use characters to select statistics
descdata(data1,3,7,c('na','min','max','IQR'))
# }