dfsummary: Summarize a Dataframe After Grouping Samples

In anwarbio/bioassays: Summarising Multi Well Plate Cellular Assay

Description

This function summarize the dataframe (based on a column). It has additional controls to group samples and to omit variables not needed.

Usage

 dfsummary(dataframe, y, grp_vector, rm_vector, nickname, rm="FALSE", param)

Arguments

dataframe	data in dataframe format
y	column name whose values has to be summarized (column elements need to be numeric)
grp_vector	a character vector of column names whose order indicate the order of grouping
rm_vector	a character vector of items that need to be omitted before summarizing
nickname	label name for the entries in output dataframe
rm	rm = “FALSE” if outliers not to be removed. rm = “TRUE” If outliers to be removed
param	a vector of parameters for more stringent outlier removal. param has to be entered in the format c(strict, cutoff, n). For details please refer rmodd_summary:.

Details

This function first remove 'rm_vector' elements from the 'dataframe'. Samples are grouped (each level of a 'grp_vector' element as separate group) and sorted (based on 'grp_vector' elements order). column 'y' is then summarized for each group (please refer rmodd_summary: for details).

Value

A dataframe. First columns are named as grp_vector elements. Followed by a 'label' column (element is 'nickname').This 'label' column will be useful when analyzing multiple plates. Summary statistics of 'y' appear as columns: N (number of samples/group), Mean (average/group), SD (standard deviation/group) and CV (percentage cv/group).

Author(s)

A.A Palakkan

Examples

## loading data
data(metafile384, rawdata384)
rawdata<-plate2df(data2plateformat(rawdata384,platetype = 384))
data_DF2<- dplyr::inner_join(rawdata,metafile384,by=c("row","col","position"))

## eg:1 summarising the 'value' after grouping samples and omitting blanks.
  # grouping order cell, compound, concentration and type.

result2 <- dfsummary(data_DF2,y = "value",
           grp_vector = c("cell","compound","concentration","type"),
           rm_vector = c("blank1","blank2","blank3","blank4"),
           nickname = "384well",
           rm = "FALSE",param = c(strict="FALSE",cutoff=40,n=12))

anwarbio/bioassays documentation built on Oct. 9, 2020, 10:35 p.m.