-
Notifications
You must be signed in to change notification settings - Fork 8
/
ListTransforms.R
383 lines (289 loc) · 13.6 KB
/
ListTransforms.R
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
#------------------------------------------------------#
# THESE ARE THE FUNCTIONS PRESENT IN THIS FILE #
#------------------------------------------------------#
#------------------------------------------------------#
# depth ( x, counter=0 )
# listStr ( obj, showValues=TRUE )
# longestLength ( obj, currentMax=0 )
# listFlatten ( obj, filler=NA )
# tableFlatten ( tableWithLists, filler="" )
# insertListAsCols ( input, target, targetCols, replaceOriginalTargetCol=FALSE, preserveNames=TRUE )
# insertListAsCols.list ( input, target, targetCols, replaceOriginalTargetCol=FALSE, preserveNames=TRUE )
# findGroupRanges ( booleanVec )
# nestedIndx ( obj, pre=NULL, expandLast=FALSE, asDF=FALSE )
###############################################################
########### LIST UTILITIES ###########
###############################################################
depth <- function(x, counter=0) {
# Returns the depth of a list-like object.
# Vectors are considered to have depth 0
# an un-nested list has depth 1
ifelse (!is.list(x), counter, max(sapply(x, depth, counter+1)))
}
#--------------------------------------------
listStr <- function(obj, showValues=TRUE) {
# A cleaner way to view the structure of a list.
# (ie, by index, instead of by indentation)
# returns a data frame indicating the structure of a nested list
# Optionally returns values at end of list
#
# Args:
# obj: a list-like object whose structure is to be determined
# showValues: FALSE: values of `obj` are not returned (only indices)
# -1: values are returned in column 1
# TRUE: values are returned in final column
inds <- nestedIndx(obj, expandLast=showValues)
# flag of -1 indicates to put values first in the df.
if (showValues==-1) {
print("TRUE")
inds <- data.frame(cbind(value=apply(inds, 1, function(ind) obj[[ind[!is.na(ind)]]]), inds))
# flag of 1/T indicates to put values last in the df
} else if (showValues) {
inds <- data.frame(cbind(inds, value=apply(inds, 1, function(ind) obj[[ind[!is.na(ind)]]])))
}
# flag of F indicates no values in the df
return(data.frame(inds))
}
#--------------------------------------------
longestLength <- function(obj, currentMax=0) {
## returns the length of the longest row or longest list in obj
# obj should be list-like or matrix-like
# If we're at a vector, return the max between its length and running ma
if (is.vector(obj)) # (!is.list(obj) && is.null(dim(obj)))
return(max(currentMax, length(obj)))
# If obj is array or matrix, find the max of each row
if (!is.null(dim(obj)))
return(max(currentMax, apply(obj, 1, longestLength, currentMax=currentMax)))
# If obj is list, find max within each element
if (is.list(obj))
return(max(currentMax, sapply(obj, longestLength, currentMax=currentMax)))
stop("Uknown Object Type")
}
#--------------------------------------------
listFlatten <- function(obj, filler=NA) {
## Flattens obj like rbind, but if elements are of different length, plugs in value filler
## DEPENDS ON: insertListAsCols (and insertListAsCols.list )
# if obj is a list of all single elements, pop them up one level
if (is.list(obj) && all(sapply(obj, length) == 1)) {
obj <- sapply(obj, function(x) x) ## TODO: Double check that this does not need to be transposed. Or perhaps use SimplfyTo..
}
# If obj contains a mix of lists/non-lists elements, then
# all list elements need to be handled first via a recursive call to listFlatten
listIndex <- sapply(obj, is.list)
if (any(listIndex)) {
input <- sapply(obj[listIndex], listFlatten, filler=filler, simplify=FALSE)
# if object is a list without columns (ie, not dataframe, etc), then we can just insert the input back in.
# Otherwise, we need to call isertListAsCols
if (is.list(obj) && is.null(dim(obj))) {
obj[listIndex] <- input
} else {
obj <- insertListAsCols(input, target=obj, targetCols=which(listIndex), replaceOriginalTargetCol=TRUE, preserveNames=TRUE)
}
} # end if (any(listIndex))
# Next, Any elements of obj that are factors need to be converted to character
factorIndex <- sapply(obj, is.factor)
obj[factorIndex] <- sapply(obj[factorIndex], as.character)
# Initialize Vars
bind <- FALSE
# IF ALL ELEMENTS ARE MATRIX-LIKE OR VECTORS, MAKE SURE SAME NUMBER OF COLUMNS
matLike <- sapply(obj, function(x) !is.null(dim(x)))
vecLike <- sapply(obj, is.vector)
# If all matrix-like.
if (all(matLike)) {
maxLng <- max(sapply(obj[matLike], ncol))
obj[matLike] <- lapply(obj[matLike], function(x) t(apply(x, 1, c, rep(filler, maxLng - ncol(x)))))
bind <- TRUE
# If all vector-like
} else if (all(vecLike)) {
maxLng <- max(sapply(obj[vecLike], length))
obj[vecLike] <- lapply(obj[vecLike], function(x) c(x, rep(filler, maxLng - length(x))))
bind <- TRUE
# If all are either matrix- or vector-like
} else if (all(matLike | vecLike)) { # TODO: Double check this. I had this with '&' before. I think that was incorrect.
maxLng <- max(sapply(obj[matLike], ncol), sapply(obj[vecLike], length))
# Add in filler's as needed
obj[matLike] <-
lapply(obj[matLike], function(x) t(apply(x, 1, c, rep(filler, maxLng - ncol(x)))))
obj[vecLike] <-
lapply(obj[vecLike], function(x) c(x, rep(filler, maxLng - length(x))))
bind <- TRUE
}
# If processed and ready to be returned, then just clean it up
if(bind) {
# If obj is a data.frame, then it might be all ready to go
if (is.data.frame(obj) && length(obj) == ncol(obj))
return(obj)
# Otherwise, flatten 'obj' with rbind.
ret <- (do.call(rbind, obj))
colnames(ret) <- paste0("L", fw0(1:ncol(ret), digs=2))
return(ret)
}
# Otherwise, if obj is sitll a list, continue recursively
if (is.list(obj)) {
return(lapply(obj, listFlatten))
}
# If none of the above, return an error.
stop("Unknown object type")
}
#--------------------------------------------
tableFlatten <- function(tableWithLists, filler="") {
# takes as input a table-like object with lists and returns a flat table
# empty spots in lists are filled with value of 'filler'
#
# depends on: listFlatten(.), findGroupRanges(.), fw0(.)
# index which columns are lists
listCols <- sapply(tableWithLists, is.list)
tableWithLists[listCols]
tableWithLists[!listCols]
# flatten lists into table
flattened <- sapply(tableWithLists[listCols], listFlatten, filler=filler, simplify=FALSE)
# fix names
for (i in 1:length(flattened)) colnames(flattened[[i]]) <- fw0(ncol(flattened[[i]]), 2)
# REASSEMBLE, IN ORDER
# find pivot point counts
pivots <- sapply(findGroupRanges(listCols), length)
#index markers
indNonList <- indList <- 1
# nonListGrp <- (0:(length(pivots)/2)) * 2 + 1
# ListGrp <- (1:(length(pivots)/2)) * 2
final <- data.frame(row.names=row.names(tableWithLists))
for (i in 1:length(pivots)) {
if(i %% 2 == 1) {
final <- cbind(final,
tableWithLists[!listCols][indNonList:((indNonList<-indNonList+pivots[[i]])-1)]
)
} else {
final <- cbind(final,
flattened[indList:((indList<-indList+pivots[[i]])-1)]
)
}
}
return(final)
}
#---------------------------------------------
#%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
#___________________________________________%
# Generic form of insertListAsCols
insertListAsCols <- function(input, target, targetCols, replaceOriginalTargetCol=FALSE, preserveNames=TRUE)
UseMethod("insertListAsCols")
#___________________________________________%
#%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
insertListAsCols.list <- function(input, target, targetCols, replaceOriginalTargetCol=FALSE, preserveNames=TRUE) {
# input should be table-like or a list of table-like elements.
# if input is list or multidimensional, but targetCols has length 1, is an error.
# note: If uncareful, preserveNames=TRUE can cause infinite loop # TODO: insert safetybreak
## ERROR CHECK
if (length(input) != length(targetCols))
stop("length(input) and length(targetCols) do not match")
## If there are no names to preserve, then adjust the flag accordingly
## If there are target names, but not list names, then
if (is.null(names(input))) {
if (is.null(names(target))) {
preserveNames <- FALSE
} else {
names(input) <- paste("L", fw0(seq(length(input)), 2), sep="_")
}
}
# If prserve names, then call function just on names. They get reapplied at end.
if (preserveNames) {
# OLD nms: mapply(function(name, thelist) {t(rep(name, ncol(thelist)))}, names(input), input, SIMPLIFY=FALSE)
nms <- mapply(function(name, thelist) {t(paste(name, 1:ncol(thelist), sep="."))}, names(input), input, SIMPLIFY=FALSE)
targetNames <- insertListAsCols(input=nms, target=rbind(names(target)),
targetCols=targetCols, replaceOriginalTargetCol=replaceOriginalTargetCol, preserveNames=FALSE)
}
# If we are preserving the original, then we add 1 to the index values.
# ie, rOT is 0 if replaceOriginalTargetCol is TRUE
rOT <- as.numeric(!replaceOriginalTargetCol)
## length of targetcols used many times
numbOfSplices <- length(targetCols) # this variable might need a better name. Does 'A B' have one splice (the space) or two (the A and the B)?
## we take the amount of each padding to be the number of columns of each input
padAmounts <- unlist(sapply(input, ncol))
padAmounts[is.null(padAmounts)] <- 1 # TODO: confirm that this in fact is acceptable (and not that we are masking errors)
padAmounts <- padAmounts - (1-rOT)
## Pad target with filler-columns
# a filler column of just NA's will be used for padding
fillerCol <- rep(NA, nrow(target))
for (i in seq_along(targetCols)) {
t <- targetCols[[i]]
ln <- padAmounts[[i]]
#------------------
# This pads 'target' once. Then we have to re-adjust our indicies
#------------------
target.tmp <- target[,1:t, drop=FALSE] # was 's:t+rOT' but I dont think thats needed
for (j in seq(ln))
target.tmp <- cbind(target.tmp, fillerCol)
# if we just padded the last columns of target, then just replace target, else append appropriately
if (t < ncol(target)) {
target <- cbind(target.tmp, target[,(t+1):ncol(target), drop=FALSE])
} else {
target <- target.tmp
}
# increment all targetCols beyond the i'th one by the number of reps, so long as there are any left
if (i < numbOfSplices)
targetCols[(i+1):numbOfSplices] <- targetCols[(i+1):numbOfSplices] + ln
#------------------
} # end for-loop
# Shift target Cols according to whether we are preserving column in current spot or not
targetCols <- targetCols + rOT # shift over 1 if we are preserving the original
# # make a matrix of indexes, we will iterate over each row.
# indxs <- t(mapply(seq, from=targetCols, to=targetCols+padAmounts-rOT)) # Note that padAmounts has already been adjusted by rOT
# OLD
# # Insert the input columns in their appropriate spots in the target
# for (i in seq_along(padAmounts)) {
# target[ indxs[i, ] ] <- input[[i]] # or... <- apply(input[[i]], 2, function(x) x)
# }
# make a matrix of indexes, we will iterate over each row.
indxs <- mapply(seq, from=targetCols, to=targetCols+padAmounts-rOT, SIMPLIFY=FALSE) # Note that padAmounts has already been adjusted by rOT
# Insert the input columns in their appropriate spots in the target
for (i in seq_along(padAmounts)) {
target[ indxs[[i]] ] <- input[[i]] # or... <- apply(input[[i]], 2, function(x) x)
}
# cleanup names of 'target' and remove last NA of 'targetCol'
if (preserveNames) {
names(target) <- targetNames
} else {
names(target) <- 1:ncol(target)
}
# return modified target
return(target)
}
#--------------------------------------------
findGroupRanges <- function(booleanVec) {
# returns list of indexes indicating a series of identical values
pivots <- which(sapply(2:length(booleanVec), function(i) booleanVec[[i]] != booleanVec[[i-1]]))
pivots <- c(0, pivots, length(booleanVec))
lapply(seq(2, length(pivots)), function(i)
seq(pivots[i-1]+1, pivots[i])
)
}
#--------------------------------------------
nestedIndx <- function(obj, pre=NULL, expandLast=FALSE, asDF=FALSE) {
## returns a matrix (or data.frame) whose rows are
## the extended indecies of a nested list
## DEPENDENT ON: listFlatten(), fw0()
# final depth level (ie, end recursion)
if (!is.list(obj)) {
# not flagged otherwise, return the last column just as a length value
if (!expandLast)
return(c(pre, length(obj)))
# otherwise, expand it.
# If there is no pre, then we're just seq on obj
if (is.null(pre))
return(cbind(seq(obj)))
# otherwise, combine seq with pre, transposing for correct orientation
return(t(sapply(seq(obj), function(x) c(pre, x))))
}
s <- seq(length(obj))
soFar <- lapply (s, function(i) c(pre, i) )
ret <- listFlatten (lapply(s, function(i) nestedIndx(obj=obj[[i]], pre=soFar[[i]], expandLast=expandLast)))
if (is.null(pre)) {
colnames(ret) <- gsub("L", "Lev_", colnames(ret))
}
# clean up name of last column, if not flagged to expand last depth
if(!expandLast)
colnames(ret)[ncol(ret)] <- "Length"
if (asDF)
return(data.frame(ret))
ret
}
#--------------------------------------------