Difference between revisions of "OpasnetUtils/Tidy"
From Testiwiki
m (Some thoughts added, implementation to follow) |
(→Code: Discussed changes implemented. Conversion to proper class for resulting data.frame constituents added.) |
||
| Line 21: | Line 21: | ||
# TIDY ########### tidy: a function that cleans the tables from Opasnet Base | # TIDY ########### tidy: a function that cleans the tables from Opasnet Base | ||
# data is a table from op_baseGetData function | # data is a table from op_baseGetData function | ||
| − | tidy <- function (data, idvar = "obs", direction = "wide") { | + | tidy <- function (data, objname = "", idvar = "obs", direction = "wide") { |
| − | + | data$Result <- ifelse(data$Result.Text == "", data$Result, as.character(data$Result.Text)) | |
| − | data$Result <- ifelse | + | #data <- data[ |
| − | + | # ifelse("Observation" %in% colnames(data), | |
| − | data <- data[ | + | # data$Observation != "Description", |
| − | if("obs.1" %in% colnames(data)) {data[, "obs"] <- data[, "obs.1"] | + | # TRUE |
| − | + | # ), | |
| + | # !colnames(data) %in% c("id", "Result.Text") | ||
| + | #] | ||
| + | data <- data[, !colnames(data) %in% c("id", "Result.Text")] | ||
| + | if("obs.1" %in% colnames(data)) { # this line is temporarily needed until the obs.1 bug is fixed. | ||
| + | data[, "obs"] <- data[, "obs.1"] | ||
| + | data <- data[, colnames(data) != "obs.1"] | ||
| + | } | ||
if("Row" %in% colnames(data)) { # If user has given Row, it is used instead of automatic obs. | if("Row" %in% colnames(data)) { # If user has given Row, it is used instead of automatic obs. | ||
data <- data[, colnames(data) != "obs"] | data <- data[, colnames(data) != "obs"] | ||
colnames(data)[colnames(data) == "Row"] <- "obs" | colnames(data)[colnames(data) == "Row"] <- "obs" | ||
} | } | ||
| − | if(direction == "wide" | + | if (objname != "") objname <- paste(objname, ":", sep = "") |
| − | + | if (direction == "wide") { | |
| − | + | if("Observation" %in% colnames(data)) { | |
| − | + | cols <- levels(data$Observation) | |
| − | + | data <- reshape(data, idvar = idvar, timevar = "Observation", v.names = "Result", direction = "wide") | |
| − | + | data <- data[colnames(data) != "obs"] | |
| − | colnames(data)[colnames(data) | + | colnames(data) <- gsub("^Result.", objname, colnames(data)) |
| − | + | for (i in paste(objname, cols, sep = "")) { | |
| − | + | a <- as.numeric(data[, i]) | |
| − | + | if (sum(is.na(a)) == 0) data[, i] <- a else data[, i] <- factor(data[, i]) | |
| − | + | } | |
| + | colnames(data)[grepl(paste("^", objname, "result", sep = ""), colnames(data))] <- paste(objname, "Result", sep = "") | ||
| + | colnames(data)[grepl(paste("^", objname, "Amount", sep = ""), colnames(data))] <- paste(objname, "Result", sep = "") | ||
| + | return(data) | ||
| + | } | ||
| + | if("Parameter" %in% colnames(data)) { | ||
| + | cols <- levels(data$Parameter) | ||
| + | data <- reshape(data, idvar = idvar, timevar = "Parameter", v.names = "Result", direction = "wide") | ||
| + | data <- data[colnames(data) != "obs"] | ||
| + | colnames(data) <- gsub("^Result.", objname, colnames(data)) | ||
| + | for (i in paste(objname, cols, sep = "")) { | ||
| + | a <- as.numeric(data[, i]) | ||
| + | if (sum(is.na(a)) == 0) data[, i] <- a else data[, i] <- factor(data[, i]) | ||
| + | } | ||
| + | colnames(data)[grepl(paste("^", objname, "result", sep = ""), colnames(data))] <- paste(objname, "Result", sep = "") | ||
| + | colnames(data)[grepl(paste("^", objname, "Amount", sep = ""), colnames(data))] <- paste(objname, "Result", sep = "") | ||
| + | return(data) | ||
| + | } | ||
} | } | ||
| + | data <- data[,colnames(data) != "obs"] | ||
| + | colnames(data)[colnames(data)=="Result"] <- paste(objname, "Result", sep = "") | ||
return(data) | return(data) | ||
} | } | ||
Revision as of 07:06, 19 June 2012
This page is a method.
The page identifier is Op_en5742 |
|---|
| Moderator:Nobody (see all) Click here to sign up. |
| This page is a stub. You may improve it into a full page, and then a rating bar will appear here. |
| Upload data
|
Contents
Description
a function that cleans the tables from Opasnet Base
Parameters
- data is a table from op_baseGetData function
Code
--# : Tidy should widen the "Parameter" index as well as "Observation". Also it should enable marginal recognition of the widened variables. --Teemu R 15:57, 18 June 2012 (EEST)
- --# : Recognition could be achieved by adding a "variable name" -prefix to every location under the involved indices. --Teemu R 15:57, 18 June 2012 (EEST)
# TIDY ########### tidy: a function that cleans the tables from Opasnet Base
# data is a table from op_baseGetData function
tidy <- function (data, objname = "", idvar = "obs", direction = "wide") {
data$Result <- ifelse(data$Result.Text == "", data$Result, as.character(data$Result.Text))
#data <- data[
# ifelse("Observation" %in% colnames(data),
# data$Observation != "Description",
# TRUE
# ),
# !colnames(data) %in% c("id", "Result.Text")
#]
data <- data[, !colnames(data) %in% c("id", "Result.Text")]
if("obs.1" %in% colnames(data)) { # this line is temporarily needed until the obs.1 bug is fixed.
data[, "obs"] <- data[, "obs.1"]
data <- data[, colnames(data) != "obs.1"]
}
if("Row" %in% colnames(data)) { # If user has given Row, it is used instead of automatic obs.
data <- data[, colnames(data) != "obs"]
colnames(data)[colnames(data) == "Row"] <- "obs"
}
if (objname != "") objname <- paste(objname, ":", sep = "")
if (direction == "wide") {
if("Observation" %in% colnames(data)) {
cols <- levels(data$Observation)
data <- reshape(data, idvar = idvar, timevar = "Observation", v.names = "Result", direction = "wide")
data <- data[colnames(data) != "obs"]
colnames(data) <- gsub("^Result.", objname, colnames(data))
for (i in paste(objname, cols, sep = "")) {
a <- as.numeric(data[, i])
if (sum(is.na(a)) == 0) data[, i] <- a else data[, i] <- factor(data[, i])
}
colnames(data)[grepl(paste("^", objname, "result", sep = ""), colnames(data))] <- paste(objname, "Result", sep = "")
colnames(data)[grepl(paste("^", objname, "Amount", sep = ""), colnames(data))] <- paste(objname, "Result", sep = "")
return(data)
}
if("Parameter" %in% colnames(data)) {
cols <- levels(data$Parameter)
data <- reshape(data, idvar = idvar, timevar = "Parameter", v.names = "Result", direction = "wide")
data <- data[colnames(data) != "obs"]
colnames(data) <- gsub("^Result.", objname, colnames(data))
for (i in paste(objname, cols, sep = "")) {
a <- as.numeric(data[, i])
if (sum(is.na(a)) == 0) data[, i] <- a else data[, i] <- factor(data[, i])
}
colnames(data)[grepl(paste("^", objname, "result", sep = ""), colnames(data))] <- paste(objname, "Result", sep = "")
colnames(data)[grepl(paste("^", objname, "Amount", sep = ""), colnames(data))] <- paste(objname, "Result", sep = "")
return(data)
}
}
data <- data[,colnames(data) != "obs"]
colnames(data)[colnames(data)=="Result"] <- paste(objname, "Result", sep = "")
return(data)
}
|
