Commit ⋅ hauselin/hausekeep

Showing 3 of 5 files from the diff.

0.00% 0.00% ø

R/fit_ezddm.R changed.

0.00% 0.00% ø

R/outliersZ.R changed.

0.00% 0.00% ø

R/se.R changed.

Other files ignored by Codecov

NAMESPACE has changed.

.DS_Store has changed.

@@ -27,7 +27,6 @@

#' @import data.table
#' @importFrom dplyr select
#' @importFrom dplyr left_join
#' @importFrom dtplyr tbl_dt
#' @importFrom dplyr %>%
#' @export
#'

@@ -61,7 +60,7 @@


  # message("Fits EZ-diffusion model (Wagenmaker et al., 2007, Psychonomic Bulletin & Review).\nResponses or choice must be coded as 0 (lower bound) or 1 (upper bound).")

  data <- tbl_dt(data)
  data <- data.table(data)

  # create new variables
  data$rtCol <- data[, get(rts)]

@@ -111,7 +110,7 @@

  ddmRt <- data[response_num == 1, .(rt = mean(rtCol, na.rm = T), rtVar = stats::var(rtCol, na.rm = T)), by = c(id, group)]

  # calculate responses for each subject, each condition
  ddmAcc <- tbl_dt(data[, .(acc = mean(response_num, na.rm = T), n = .N), by = c(id, group)])
  ddmAcc <- data.table(data[, .(acc = mean(response_num, na.rm = T), n = .N), by = c(id, group)])

  if (sum(ddmAcc[, acc] %in% c(0.5, 1)) > 0) {
    n_corrected <- sum(ddmAcc[, acc] %in% c(0.5, 1))

@@ -169,7 +168,7 @@

    resultsFinal$temporary_subject <- NULL
  }

  return(tbl_dt(resultsFinal))
  return(resultsFinal)

}


@@ -35,8 +35,9 @@


  # compute standard deviation (sample version n = n [not n-1])
  stdev <- sqrt(sum((x - mean(x, na.rm = T))^2, na.rm = T) / sum(!is.na(x)))
  # compute absolute Z values for each value
  absZ <- abs(x - mean(x, na.rm = T)) / stdev
  # compute Z values for each value
  Zvals <- (x - mean(x, na.rm = T)) / stdev
  absZ <- abs(Zvals)
  # subset data that has absZ greater than the zCutOff and replace them with replace
  # can also replace with other values (such as max/mean of data)
  x[absZ > zCutOff] <- replaceOutliersWith

@@ -45,7 +46,7 @@

  if (showZValues) {
    message("Showing absolute z-scores for each value.")
    message(paste0(outliers, " outliers detected."))
    return(round(absZ, digits)) # if values == TRUE, return z score for each value
    return(round(Zvals, digits)) # if values == TRUE, return z score for each value
  } else if (outlierIndices) {
    message("Showing indices of outliers.")
    return(which(is.na(x)))

@@ -24,7 +24,7 @@

stderror <- function(data = NULL, measurevar, groupvars = NULL, na.rm = TRUE, conf.interval = 0.95, tonumeric = TRUE) {

  # convert to datatable and tibble
  data <- data.table(data)
  data <- data.table::data.table(data)

  # function to compute N without NAs
  length2 <- function(x, na.rm = FALSE) {

@@ -93,7 +93,6 @@

#' @return a data.frame
#' @description normWithin norms the data within specified groups in a data frame
#' @importFrom dplyr left_join
#' @importFrom dtplyr tbl_dt
#' @import data.table
#' @examples
#' \dontrun{

@@ -105,12 +104,13 @@

  # specified by betweenvars.
  # norm data (this function will only be used by seWithin, and won't have to be called directly)

  data <- tbl_dt(data)
  data <- data.table::data.table(data)
  setkeyv(data, idvar) # sort by idvar

  data.subjMean <- data[, .(unlist(lapply(.SD, mean, na.rm = na.rm))), by = c(idvar, betweenvars), .SDcols = measurevar] # compute mean for each subject
  setnames(data.subjMean, c(idvar, betweenvars,'subjMean'))
  dataNew <- left_join(data, data.subjMean)
  dataNew <- data.table::data.table(dataNew)
  setkeyv(dataNew, c(idvar, betweenvars)) # sort

  measureNormedVar <- paste0(measurevar, "Normed")

@@ -157,7 +157,6 @@

#' @importFrom dplyr tbl_df
#' @importFrom dplyr left_join
#' @importFrom dplyr mutate_if
#' @importFrom dtplyr tbl_dt
#' @importFrom stats sd
#' @export
#' @seealso \code{\link{stderror}}

@@ -232,7 +231,7 @@

    nWithinGroups <- prod(vapply(ndatac[,withinvars, drop = FALSE], FUN = function(x) length(levels(x)), FUN.VALUE = numeric(1)))
    correctionFactor <- sqrt( nWithinGroups / (nWithinGroups-1) )

    ndatacTbl <- tbl_dt(ndatac)
    ndatacTbl <- data.table::data.table(ndatac)

    # Apply the correction factor
    # setnames(ndatacTbl, c("sd", "se"), c("stdev", "stderror"))

@@ -245,7 +244,7 @@

    merged <- left_join(datac, ndatacTbl)
    merged <- mutate_if(merged, is.factor, as.character) #if factor, convert to character
    merged[order( unlist((merged[, 1])), decreasing =  F), ] #arrange by first column
    merged <- tbl_dt(merged)
    merged <- data.table::data.table(merged)
    message("Factors have been converted to characters.")

    # convert columns to numeric class if possible, else, leave as character

Files		•	•	•	Coverage
R	1,123	45	0	1,078	4.01%
Project Totals (11 files)	1,123	45	0	1,078	4.01%

View CI Build

comment: false

coverage:
  status:
    project:
      default:
        target: auto
        threshold: 1%
    patch:
      default:
        target: auto
        threshold: 1%

Read the docs

Interact now

The inner-most circle is the entire project, moving away from the center are folders then, finally, a single file. The size and color of each slice is representing the number of statements and the coverage, respectively.

SVG

The top section represents the entire project. Proceeding with folders and finally individual files. The size and color of each slice is representing the number of statements and the coverage, respectively.

SVG

Each block represents a single file in the project. The size and color of each block is represented by the number of statements and the coverage, respectively.

SVG

Learn more about the coverage sunburst graph

61	60
62	61		# message("Fits EZ-diffusion model (Wagenmaker et al., 2007, Psychonomic Bulletin & Review).\nResponses or choice must be coded as 0 (lower bound) or 1 (upper bound).")
63	62
64		-	data <- tbl_dt(data)
	63	+	data <- data.table(data)
65	64
66	65		# create new variables
67	66		data$rtCol <- data[, get(rts)]

111	110		ddmRt <- data[response_num == 1, .(rt = mean(rtCol, na.rm = T), rtVar = stats::var(rtCol, na.rm = T)), by = c(id, group)]
112	111
113	112		# calculate responses for each subject, each condition
114		-	ddmAcc <- tbl_dt(data[, .(acc = mean(response_num, na.rm = T), n = .N), by = c(id, group)])
	113	+	ddmAcc <- data.table(data[, .(acc = mean(response_num, na.rm = T), n = .N), by = c(id, group)])
115	114
116	115		if (sum(ddmAcc[, acc] %in% c(0.5, 1)) > 0) {
117	116		n_corrected <- sum(ddmAcc[, acc] %in% c(0.5, 1))

169	168		resultsFinal$temporary_subject <- NULL
170	169		}
171	170
172		-	return(tbl_dt(resultsFinal))
	171	+	return(resultsFinal)
173	172
174	173		}
175	174

35	35
36	36		# compute standard deviation (sample version n = n [not n-1])
37	37		stdev <- sqrt(sum((x - mean(x, na.rm = T))^2, na.rm = T) / sum(!is.na(x)))
38		-	# compute absolute Z values for each value
39		-	absZ <- abs(x - mean(x, na.rm = T)) / stdev
	38	+	# compute Z values for each value
	39	+	Zvals <- (x - mean(x, na.rm = T)) / stdev
	40	+	absZ <- abs(Zvals)
40	41		# subset data that has absZ greater than the zCutOff and replace them with replace
41	42		# can also replace with other values (such as max/mean of data)
42	43		x[absZ > zCutOff] <- replaceOutliersWith

157	157		#' @importFrom dplyr tbl_df
158	158		#' @importFrom dplyr left_join
159	159		#' @importFrom dplyr mutate_if
160		-	#' @importFrom dtplyr tbl_dt
161	160		#' @importFrom stats sd
162	161		#' @export
163	162		#' @seealso \code{\link{stderror}}

27	27		#' @import data.table
28	28		#' @importFrom dplyr select
29	29		#' @importFrom dplyr left_join
30		-	#' @importFrom dtplyr tbl_dt
31	30		#' @importFrom dplyr %>%
32	31		#' @export
33	32		#'

45	46		if (showZValues) {
46	47		message("Showing absolute z-scores for each value.")
47	48		message(paste0(outliers, " outliers detected."))
48		-	return(round(absZ, digits)) # if values == TRUE, return z score for each value
	49	+	return(round(Zvals, digits)) # if values == TRUE, return z score for each value
49	50		} else if (outlierIndices) {
50	51		message("Showing indices of outliers.")
51	52		return(which(is.na(x)))

24	24		stderror <- function(data = NULL, measurevar, groupvars = NULL, na.rm = TRUE, conf.interval = 0.95, tonumeric = TRUE) {
25	25
26	26		# convert to datatable and tibble
27		-	data <- data.table(data)
	27	+	data <- data.table::data.table(data)
28	28
29	29		# function to compute N without NAs
30	30		length2 <- function(x, na.rm = FALSE) {

93	93		#' @return a data.frame
94	94		#' @description normWithin norms the data within specified groups in a data frame
95	95		#' @importFrom dplyr left_join
96		-	#' @importFrom dtplyr tbl_dt
97	96		#' @import data.table
98	97		#' @examples
99	98		#' \dontrun{

105	104		# specified by betweenvars.
106	105		# norm data (this function will only be used by seWithin, and won't have to be called directly)
107	106
108		-	data <- tbl_dt(data)
	107	+	data <- data.table::data.table(data)
109	108		setkeyv(data, idvar) # sort by idvar
110	109
111	110		data.subjMean <- data[, .(unlist(lapply(.SD, mean, na.rm = na.rm))), by = c(idvar, betweenvars), .SDcols = measurevar] # compute mean for each subject
112	111		setnames(data.subjMean, c(idvar, betweenvars,'subjMean'))
113	112		dataNew <- left_join(data, data.subjMean)
	113	+	dataNew <- data.table::data.table(dataNew)
114	114		setkeyv(dataNew, c(idvar, betweenvars)) # sort
115	115
116	116		measureNormedVar <- paste0(measurevar, "Normed")

232	231		nWithinGroups <- prod(vapply(ndatac[,withinvars, drop = FALSE], FUN = function(x) length(levels(x)), FUN.VALUE = numeric(1)))
233	232		correctionFactor <- sqrt( nWithinGroups / (nWithinGroups-1) )
234	233
235		-	ndatacTbl <- tbl_dt(ndatac)
	234	+	ndatacTbl <- data.table::data.table(ndatac)
236	235
237	236		# Apply the correction factor
238	237		# setnames(ndatacTbl, c("sd", "se"), c("stdev", "stderror"))

245	244		merged <- left_join(datac, ndatacTbl)
246	245		merged <- mutate_if(merged, is.factor, as.character) #if factor, convert to character
247	246		merged[order( unlist((merged[, 1])), decreasing = F), ] #arrange by first column
248		-	merged <- tbl_dt(merged)
	247	+	merged <- data.table::data.table(merged)
249	248		message("Factors have been converted to characters.")
250	249
251	250		# convert columns to numeric class if possible, else, leave as character

1	comment: false
2
3	coverage:
4	status:
5	project:
6	default:
7	target: auto
8	threshold: 1%
9	patch:
10	default:
11	target: auto
12	threshold: 1%

Navigation	Overlay
`t` Navigate files	`h` Toggle hits
`y` Change url to tip of branch	`m` Toggle misses
`b / v` Jump to prev/next hit line	`p` Toggle partial
`z / x` Jump to prev/next missed or partial line	`1..9` Toggle flags
`shift + o` Open current page in GitHub	`a` Toggle all on
`/ or ?` Show keyboard shortcuts dialog	`c` Toggle context lines or commits