count.column.R

#' Counts by 2 grouping varaibles
#' @description This function simply groups by two factors and returns the frequency. Can be passed to "use.prop.test" to test proportions.
#' @param df Data frame, in this case meta data of a corresponding gene
#' @param factor_one Character - first grouping factor, a column name of the data frame
#' @param factor_two Character - second grouping factor, a column name of the data frame
#' @importFrom magrittr %>%
#' @examples
#' df <- data.frame(case_id = c(1,2,3,4,5,6), group = c("one","one","two","one","two","three"), primary_diagnosis = c("Squamous cell carcinoma, NOS", "Adenocarcinoma, NOS", "Adenocarcinoma with mixed subtypes", "Squamous cell carcinoma, NOS", "Squamous cell carcinoma, NOS", "Squamous cell carcinoma, NOS"))
#' diagnosis_counts <- count.column(df, factor_one = "group", factor_two = "primary_diagnosis")
#' @return Returns a data frame

count.column <- function(df, factor_one = "group", factor_two  = "primary_diagnosis") {
  countFactor <- single_data_frame %>% dplyr::group_by_(factor_one, factor_two) %>%      #summarize count of patients grouped by group and diagnosis
  dplyr::summarize(sum.patients = n()) %>% tidyr::spread(., factor_two, "sum.patients", fill = 0)  #spread the df to wide format
  return(countFactor)
}