| BumpyDataFrameMatrix {BumpyMatrix} | R Documentation |
The BumpyDataFrameMatrix provides a two-dimensional object where each entry is a DataFrame. This is useful for storing data that has a variable number of observations per sample/feature combination, e.g., for inclusion as another assay in a SummarizedExperiment object.
In the following code snippets, x is a BumpyDataFrameMatrix.
commonColnames(x) will return a character vector with the names of the available commonColnames.
This can be modified with commonColnames(x) <- value.
x[i, j, k, ..., .dropk=drop, drop=TRUE] will subset the BumpyDataFrameMatrix:
If k is not specified, this will either produce another BumpyDataFrameMatrix corresponding to the specified submatrix,
or a CompressedSplitDataFrameList containing the entries of interest if drop=TRUE.
If k is specified, it should contain the names or indices of the columns of the underlying DataFrame to retain.
For multiple fields or with .dropk=FALSE, a new BumpyDataFrameMatrix is returned with the specified columns in the DataFrame.
If k only specifies a single column and .dropk=TRUE,
a BumpyMatrix (or CompressedList, if drop=TRUE) corresponding to the type of the field is returned.
x[i, j, k, ...] <- value will modify x by replacing the specified values with those in the BumpyMatrix value of the same dimensions.
If k is not specified, value should be a BumpyDataFrameMatrix with the same fields as x.
If k is specified, value should be a BumpyDataFrameMatrix with the specified fields.
If k contains a single field, value can also be a BumpyAtomicMatrix containing the values to use in that field.
All methods described for the BumpyMatrix parent class are available.
Aaron Lun
library(S4Vectors) df <- DataFrame(x=runif(100), y=runif(100)) f <- factor(sample(letters[1:20], nrow(df), replace=TRUE), letters[1:20]) out <- split(df, f) # Making our BumpyDataFrameMatrix. mat <- BumpyMatrix(out, c(5, 4)) mat[,1] mat[1,] # Subsetting capabilities. xmat <- mat[,,"x"] ymat <- mat[,,"y"] filtered <- mat[xmat > 0.5 & ymat > 0.5] filtered[,1] # Subset replacement works as expected. mat2 <- mat mat2[,,"x"] <- mat2[,,"x"] * 2 mat2[,1]