cute_little_R_functions.R 895 KB
Newer Older
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
# none
# REQUIRED FUNCTIONS FROM CUTE_LITTLE_R_FUNCTION
# fun_check()
# EXAMPLES
# obs1 = matrix(1:30, ncol = 5, dimnames = list(letters[1:6], LETTERS[1:5])) ; obs1 ; fun_head(obs1, 3)
# obs1 = matrix(1:30, ncol = 5, dimnames = list(letters[1:6], LETTERS[1:5])) ; obs1 ; fun_head(obs1, 3, "right")
# DEBUGGING
# data1 = matrix(1:30, ncol = 5) # for function debugging
# data1 = matrix(1:30, ncol = 5, dimnames = list(letters[1:2], LETTERS[1:5])) # for function debugging
# function name
function.name <- paste0(as.list(match.call(expand.dots = FALSE))[[1]], "()")
# end function name
# required function checking
if(length(utils::find("fun_check", mode = "function")) == 0){
tempo.cat <- paste0("ERROR IN ", function.name, ": REQUIRED fun_check() FUNCTION IS MISSING IN THE R ENVIRONMENT")
stop(paste0("\n\n================\n\n", tempo.cat, "\n\n================\n\n"), call. = FALSE) # == in stop() to be able to add several messages between ==
}
# end required function checking
# argument checking
arg.check <- NULL #
text.check <- NULL #
checked.arg.names <- NULL # for function debbuging: used by r_debugging_tools
ee <- expression(arg.check <- c(arg.check, tempo$problem) , text.check <- c(text.check, tempo$text) , checked.arg.names <- c(checked.arg.names, tempo$object.name))
tempo <- fun_check(data = n, class = "vector", typeof = "integer", double.as.integer.allowed = TRUE, length = 1, fun.name = function.name) ; eval(ee)
tempo <- fun_check(data = side, options = c("l", "r"), length = 1, fun.name = function.name) ; eval(ee)
if(any(arg.check) == TRUE){
stop(paste0("\n\n================\n\n", paste(text.check[arg.check], collapse = "\n"), "\n\n================\n\n"), call. = FALSE) #
}
Gael's avatar
tempo    
Gael committed
1029
# source("C:/Users/Gael/Documents/Git_versions_to_use/debugging_tools_for_r_dev-v1.7/r_debugging_tools-v1.7.R") ; eval(parse(text = str_basic_arg_check_dev)) ; eval(parse(text = str_arg_check_with_fun_check_dev)) # activate this line and use the function (with no arguments left as NULL) to check arguments status and if they have been checked using fun_check()
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
# end argument checking
# main code
if( ! (any(class(data1) %in% c("data.frame", "table")) | all(class(data1) %in% c("matrix", "array")))){ # before R4.0.0, it was  ! any(class(data1) %in% c("matrix", "data.frame", "table"))
return(head(data1, n))
}else{
obs.dim <- dim(data1)
row <- 1:ifelse(obs.dim[1] < n, obs.dim[1], n)
if(side == "l"){
col <- 1:ifelse(obs.dim[2] < n, obs.dim[2], n)
}
if(side == "r"){
col <- ifelse(obs.dim[2] < n, 1, obs.dim[2] - n + 1):obs.dim[2]
}
return(data1[row, col])
}
Gael's avatar
tempo    
Gael committed
1045
}
1046
1047


1048
######## fun_tail() #### tail of the left or right of big 2D objects
1049
1050


1051
1052
1053
1054
fun_tail <- function(
data1, 
n = 10, 
side = "l"
1055
){
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
# AIM
# as tail() but display the left or right head of big 2D objects
# ARGUMENTS
# data1: any object but more dedicated for matrix, data frame or table
# n: as in tail() but for for matrix, data frame or table, number of dimension to print (10 means 10 rows and columns)
# side: either "l" or "r" for the left or right side of the 2D object (only for matrix, data frame or table)
# BEWARE: other arguments of tail() not used
# RETURN
# the tail
# REQUIRED PACKAGES
# none
# REQUIRED FUNCTIONS FROM CUTE_LITTLE_R_FUNCTION
# fun_check()
# EXAMPLES
# obs1 = matrix(1:30, ncol = 5, dimnames = list(letters[1:6], LETTERS[1:5])) ; obs1 ; fun_tail(obs1, 3)
# obs1 = matrix(1:30, ncol = 5, dimnames = list(letters[1:6], LETTERS[1:5])) ; obs1 ; fun_tail(obs1, 3, "r")
# DEBUGGING
# data1 = matrix(1:10, ncol = 5) # for function debugging
# data1 = matrix(1:10, ncol = 5, dimnames = list(letters[1:2], LETTERS[1:5])) # for function debugging
# function name
function.name <- paste0(as.list(match.call(expand.dots = FALSE))[[1]], "()")
# end function name
# required function checking
if(length(utils::find("fun_check", mode = "function")) == 0){
tempo.cat <- paste0("ERROR IN ", function.name, ": REQUIRED fun_check() FUNCTION IS MISSING IN THE R ENVIRONMENT")
stop(paste0("\n\n================\n\n", tempo.cat, "\n\n================\n\n"), call. = FALSE) # == in stop() to be able to add several messages between ==
}
# end required function checking
# argument checking
arg.check <- NULL #
text.check <- NULL #
checked.arg.names <- NULL # for function debbuging: used by r_debugging_tools
ee <- expression(arg.check <- c(arg.check, tempo$problem) , text.check <- c(text.check, tempo$text) , checked.arg.names <- c(checked.arg.names, tempo$object.name))
tempo <- fun_check(data = n, class = "vector", typeof = "integer", double.as.integer.allowed = TRUE, length = 1, fun.name = function.name) ; eval(ee)
tempo <- fun_check(data = side, options = c("l", "r"), length = 1, fun.name = function.name) ; eval(ee)
if(any(arg.check) == TRUE){
stop(paste0("\n\n================\n\n", paste(text.check[arg.check], collapse = "\n"), "\n\n================\n\n"), call. = FALSE) #
}
Gael's avatar
tempo    
Gael committed
1094
# source("C:/Users/Gael/Documents/Git_versions_to_use/debugging_tools_for_r_dev-v1.7/r_debugging_tools-v1.7.R") ; eval(parse(text = str_basic_arg_check_dev)) ; eval(parse(text = str_arg_check_with_fun_check_dev)) # activate this line and use the function (with no arguments left as NULL) to check arguments status and if they have been checked using fun_check()
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
# end argument checking
# main code
if( ! (any(class(data1) %in% c("data.frame", "table")) | all(class(data1) %in% c("matrix", "array")))){ # before R4.0.0, it was  ! any(class(data1) %in% c("matrix", "data.frame", "table"))
return(tail(data1, n))
}else{
obs.dim <- dim(data1)
row <- ifelse(obs.dim[1] < n, 1, obs.dim[1] - n + 1):obs.dim[1]
if(side == "l"){
col <- 1:ifelse(obs.dim[2] < n, obs.dim[2], n)
}
if(side == "r"){
col <- ifelse(obs.dim[2] < n, 1, obs.dim[2] - n + 1):obs.dim[2]
}
return(data1[row, col])
}
Gael  MILLOT's avatar
Gael MILLOT committed
1110
1111
1112
}


1113
######## fun_comp_1d() #### comparison of two 1D datasets (vectors, factors, 1D tables)
1114
1115


1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
fun_comp_1d <- function(data1, data2){
# AIM
# compare two 1D datasets (vector or factor or 1D table, or 1D matrix or 1D array) of the same class or not. Check and report in a list if the 2 datasets have:
# same class
# common elements
# common element names (except factors)
# common levels (factors only)
# ARGUMENTS
# data1: vector or factor or 1D table, or 1D matrix or 1D array
# data2: vector or factor or 1D table, or 1D matrix or 1D array
# RETURN
# a list containing:
# $same.class: logical. Are class identical?
# $class: class of the 2 datasets (NULL otherwise)
# $same.length: logical. Are number of elements identical?
# $length: number of elements in the 2 datasets (NULL otherwise)
# $same.levels: logical. Are levels identical? NULL if data1 and data2 are not factors
# $levels: levels of the 2 datasets if identical (NULL otherwise or NULL if data1 and data2 are not factors)
# $any.id.levels: logical. Is there any identical levels? (NULL if data1 and data2 are not factors)
# $same.levels.pos1: position, in data1, of the levels identical in data2 (NULL if data1 and data2 are not factors)
# $same.levels.pos2: position, in data2, of the levels identical in data1 (NULL if data1 and data2 are not factors)
# $common.levels: common levels between data1 and data2 (can be a subset of $levels or not). NULL if no common levels or if data1 and data2 are not factors
# $same.name: logical. Are element names identical? NULL if data1 and data2 have no names
# $name: name of elements of the 2 datasets if identical (NULL otherwise)
# $any.id.name: logical. Is there any element names identical ?
# $same.name.pos1: position, in data1, of the element names identical in data2. NULL if no identical names
# $same.name.pos2: position, in data2, of the elements names identical in data1. NULL if no identical names
# $common.names: common element names between data1 and data2 (can be a subset of $name or not). NULL if no common element names
# $any.id.element: logical. is there any identical elements ?
# $same.element.pos1: position, in data1, of the elements identical in data2. NULL if no identical elements
# $same.element.pos2: position, in data2, of the elements identical in data1. NULL if no identical elements
# $common.elements: common elements between data1 and data2. NULL if no common elements
# $same.order: logical. Are all elements in the same order? TRUE or FALSE if elements of data1 and data2 are identical but not necessary in the same order. NULL otherwise (different length for instance)
# $order1: order of all elements of data1. NULL if $same.order is FALSE
# $order2: order of all elements of data2. NULL if $same.order is FALSE
# $identical.object: logical. Are objects identical (kind of object, element names, content, including content order)?
# $identical.content: logical. Are content objects identical (identical elements, including order, excluding kind of object and element names)?
# REQUIRED PACKAGES
# none
# REQUIRED FUNCTIONS FROM CUTE_LITTLE_R_FUNCTION
# none
# EXAMPLES
# obs1 = 1:5 ; obs2 = 1:5 ; names(obs1) <- LETTERS[1:5] ; names(obs2) <- LETTERS[1:5] ; fun_comp_1d(obs1, obs2)
# obs1 = 1:5 ; obs2 = 1:5 ; names(obs1) <- LETTERS[1:5] ; fun_comp_1d(obs1, obs2)
# obs1 = 1:5 ; obs2 = 3:6 ; names(obs1) <- LETTERS[1:5] ; names(obs2) <- LETTERS[1:4] ; fun_comp_1d(obs1, obs2)
# obs1 = factor(LETTERS[1:5]) ; obs2 = factor(LETTERS[1:5]) ; fun_comp_1d(obs1, obs2)
# obs1 = factor(LETTERS[1:5]) ; obs2 = factor(LETTERS[10:11]) ; fun_comp_1d(obs1, obs2)
# obs1 = factor(LETTERS[1:5]) ; obs2 = factor(LETTERS[4:7]) ; fun_comp_1d(obs1, obs2)
# obs1 = factor(c(LETTERS[1:4], "E")) ; obs2 = factor(c(LETTERS[1:4], "F")) ; fun_comp_1d(obs1, obs2)
# obs1 = 1:5 ; obs2 = factor(LETTERS[1:5]) ; fun_comp_1d(obs1, obs2)
# obs1 = 1:5 ; obs2 = 1.1:6.1 ; fun_comp_1d(obs1, obs2)
# obs1 = as.table(1:5); obs2 = as.table(1:5) ; fun_comp_1d(obs1, obs2)
# obs1 = as.table(1:5); obs2 = 1:5 ; fun_comp_1d(obs1, obs2)
# DEBUGGING
# data1 = 1:5 ; data2 = 1:5 ; names(data1) <- LETTERS[1:5] ; names(data2) <- LETTERS[1:5] # for function debugging
# function name
function.name <- paste0(as.list(match.call(expand.dots = FALSE))[[1]], "()")
# end function name
# argument checking
if( ! any(class(data1) %in% c("logical", "integer", "numeric", "character", "factor", "table"))){
tempo.cat <- paste0("ERROR IN ", function.name, ": THE data1 ARGUMENT MUST BE A NON NULL VECTOR, FACTOR OR 1D TABLE")
stop(paste0("\n\n================\n\n", tempo.cat, "\n\n================\n\n"), call. = FALSE) # == in stop() to be able to add several messages between ==
}else if(all(class(data1) %in% "table")){
if(length(dim(data1)) > 1){
tempo.cat <- paste0("ERROR IN ", function.name, ": THE data1 ARGUMENT MUST BE A 1D TABLE")
stop(paste0("\n\n================\n\n", tempo.cat, "\n\n================\n\n"), call. = FALSE) # == in stop() to be able to add several messages between ==
}
}
if( ! any(class(data2) %in% c("logical", "integer", "numeric", "character", "factor", "table"))){
tempo.cat <- paste0("ERROR IN ", function.name, ": THE data2 ARGUMENT MUST BE A NON NULL VECTOR, FACTOR OR 1D TABLE")
stop(paste0("\n\n================\n\n", tempo.cat, "\n\n================\n\n"), call. = FALSE) # == in stop() to be able to add several messages between ==
}else if(all(class(data2) %in% "table")){
if(length(dim(data2)) > 1){
tempo.cat <- paste0("ERROR IN ", function.name, ": THE data2 ARGUMENT MUST BE A 1D TABLE")
stop(paste0("\n\n================\n\n", tempo.cat, "\n\n================\n\n"), call. = FALSE) # == in stop() to be able to add several messages between ==
}
}
Gael's avatar
tempo    
Gael committed
1193
# source("C:/Users/Gael/Documents/Git_versions_to_use/debugging_tools_for_r_dev-v1.7/r_debugging_tools-v1.7.R") ; eval(parse(text = str_basic_arg_check_dev)) # activate this line and use the function to check arguments status
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
# end argument checking
# main code
same.class <- FALSE
class <- NULL
same.length <- FALSE
length <- NULL
same.levels <- NULL # not FALSE to deal with no factors
levels <- NULL
any.id.levels <- NULL
same.levels.pos1 <- NULL
same.levels.pos2 <- NULL
common.levels <- NULL
same.name <- NULL # not FALSE to deal with absence of name
name <- NULL
any.id.name <- FALSE
same.name.pos1 <- NULL
same.name.pos2 <- NULL
common.names <- NULL
any.id.element <- FALSE
same.element.pos1 <- NULL
same.element.pos2 <- NULL
common.elements <- NULL
same.order <- NULL
order1 <- NULL
order2 <- NULL
identical.object <- FALSE
identical.content <- FALSE
if(identical(data1, data2)){
same.class <- TRUE
class <- class(data1)
same.length <- TRUE
length <- length(data1)
if(any(class(data1) %in% "factor")){
same.levels <- TRUE
levels <- levels(data1)
any.id.levels <- TRUE
same.levels.pos1 <- 1:length(levels(data1))
same.levels.pos2 <- 1:length(levels(data2))
common.levels <- levels(data1)
}
if( ! is.null(names(data1))){
same.name <- TRUE
name <- names(data1)
any.id.name <- TRUE
same.name.pos1 <- 1:length(data1)
same.name.pos2 <- 1:length(data2)
common.names <- names(data1)
}
any.id.element <- TRUE
same.element.pos1 <- 1:length(data1)
same.element.pos2 <- 1:length(data2)
common.elements <- data1
same.order <- TRUE
order1 <- order(data1)
order2 <- order(data2)
identical.object <- TRUE
identical.content <- TRUE
}else{
if(identical(class(data1), class(data2))){
same.class <- TRUE
class <- class(data1)
}
if(identical(length(data1), length(data2))){
same.length<- TRUE
length <- length(data1)
}
if(any(class(data1) %in% "factor") & any(class(data2) %in% "factor")){
if(identical(levels(data1), levels(data2))){
same.levels <- TRUE
levels <- levels(data1)
}else{
same.levels <- FALSE
}
if(any(levels(data1) %in% levels(data2))){
any.id.levels <- TRUE
same.levels.pos1 <- which(levels(data1) %in% levels(data2))
}
if(any(levels(data2) %in% levels(data1))){
any.id.levels <- TRUE
same.levels.pos2 <- which(levels(data2) %in% levels(data1))
}
if(any.id.levels == TRUE){
common.levels <- unique(c(levels(data1)[same.levels.pos1], levels(data2)[same.levels.pos2]))
}
}
if(any(class(data1) %in% "factor")){ # to compare content
data1 <- as.character(data1)
}
if(any(class(data2) %in% "factor")){ # to compare content
data2 <- as.character(data2)
}
if( ! (is.null(names(data1)) & is.null(names(data2)))){
if(identical(names(data1), names(data2))){
same.name <- TRUE
name <- names(data1)
}else{
same.name <- FALSE
}
if(any(names(data1) %in% names(data2))){
any.id.name <- TRUE
same.name.pos1 <- which(names(data1) %in% names(data2))
}
if(any(names(data2) %in% names(data1))){
any.id.name <- TRUE
same.name.pos2 <- which(names(data2) %in% names(data1))
}
if(any.id.name == TRUE){
common.names <- unique(c(names(data1)[same.name.pos1], names(data2)[same.name.pos2]))
}
}
names(data1) <- NULL # names solved -> to do not be disturbed by names
names(data2) <- NULL # names solved -> to do not be disturbed by names
if(any(data1 %in% data2)){
any.id.element <- TRUE
same.element.pos1 <- which(data1 %in% data2)
}
if(any(data2 %in% data1)){
any.id.element <- TRUE
same.element.pos2 <- which(data2 %in% data1)
}
if(any.id.element == TRUE){
common.elements <- unique(c(data1[same.element.pos1], data2[same.element.pos2]))
}
if(identical(data1, data2)){
identical.content <- TRUE
same.order <- TRUE
}else if(identical(sort(data1), sort(data2))){
same.order <- FALSE
order1 <- order(data1)
order2 <- order(data2)
}
}
output <- list(same.class = same.class, class = class, same.length = same.length, length = length, same.levels = same.levels, levels = levels, any.id.levels = any.id.levels, same.levels.pos1 = same.levels.pos1, same.levels.pos2 = same.levels.pos2, common.levels = common.levels, same.name = same.name, name = name, any.id.name = any.id.name, same.name.pos1 = same.name.pos1, same.name.pos2 = same.name.pos2, common.names = common.names, any.id.element = any.id.element, same.element.pos1 = same.element.pos1, same.element.pos2 = same.element.pos2, common.elements = common.elements, same.order = same.order, order1 = order1, order2 = order2, identical.object = identical.object, identical.content = identical.content)
return(output)
}
Gael  MILLOT's avatar
Gael MILLOT committed
1329
1330


1331
######## fun_comp_2d() #### comparison of two 2D datasets (row & col names, dimensions, etc.)
1332

Gael  MILLOT's avatar
Gael MILLOT committed
1333

1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
fun_comp_2d <- function(data1, data2){
# AIM
# compare two 2D datasets of the same class or not. Check and report in a list if the 2 datasets have:
# same class
# common row names
# common column names
# same row number
# same column number
# potential identical rows between the 2 datasets
# potential identical columns between the 2 datasets
# ARGUMENTS
# data1: matrix, data frame or table
# data2: matrix, data frame or table
# RETURN
# a list containing:
# $same.class: logical. Are class identical ?
# $class: classes of the 2 datasets (NULL otherwise)
# $same.dim: logical. Are dimension identical ?
# $dim: dimension of the 2 datasets (NULL otherwise)
# $same.row.nb: logical. Are number of rows identical ?
# $row.nb: nb of rows of the 2 datasets if identical (NULL otherwise)
# $same.col.nb: logical. Are number of columns identical ?
# $col.nb: nb of columns of the 2 datasets if identical (NULL otherwise)
# $same.row.name: logical. Are row names identical ? NULL if no row names in the two 2D datasets
# $row.name: name of rows of the 2 datasets if identical (NULL otherwise)
# $any.id.row.name: logical. Is there any row names identical ? NULL if no row names in the two 2D datasets
# $same.row.name.pos1: position, in data1, of the row names identical in data2
# $same.row.name.pos2: position, in data2, of the row names identical in data1
# $common.row.names: common row names between data1 and data2 (can be a subset of $name or not). NULL if no common row names
# $same.col.name: logical. Are column names identical ? NULL if no col names in the two 2D datasets
# $col.name: name of columns of the 2 datasets if identical (NULL otherwise)
# $any.id.col.name: logical. Is there any column names identical ? NULL if no col names in the two 2D datasets
# $same.col.name.pos1: position, in data1, of the column names identical in data2
# $same.col.name.pos2: position, in data2, of the column names identical in data1
# $common.col.names: common column names between data1 and data2 (can be a subset of $name or not). NULL if no common column names
# $any.id.row: logical. is there identical rows (not considering row names)? NULL if nrow(data1) * nrow(data2) > 1e10
# $same.row.pos1: position, in data1, of the rows identical in data2 (not considering row names). Return "TOO BIG FOR EVALUATION" if nrow(data1) * nrow(data2) > 1e10
# $same.row.pos2: position, in data2, of the rows identical in data1 (not considering row names). Return "TOO BIG FOR EVALUATION" if nrow(data1) * nrow(data2) > 1e10
# $any.id.col: logical. is there identical columns (not considering column names)? NULL if ncol(data1) * ncol(data2) > 1e10
# $same.col.pos1: position in data1 of the cols identical in data2 (not considering column names). Return "TOO BIG FOR EVALUATION" if ncol(data1) * ncol(data2) > 1e10
# $same.col.pos2: position in data2 of the cols identical in data1 (not considering column names). Return "TOO BIG FOR EVALUATION" if ncol(data1) * ncol(data2) > 1e10
# $identical.object: logical. Are objects identical (including row & column names)?
# $identical.content: logical. Are content objects identical (identical excluding row & column names)?
# REQUIRED PACKAGES
# none
# REQUIRED FUNCTIONS FROM CUTE_LITTLE_R_FUNCTION
# none
# EXAMPLES
# obs1 = matrix(1:10, ncol = 5, dimnames = list(letters[1:2], LETTERS[1:5])) ; obs2 = as.data.frame(matrix(1:10, ncol = 5, dimnames = list(letters[1:2], LETTERS[1:5])), stringsAsFactors = TRUE) ; obs1 ; obs2 ; fun_comp_2d(obs1, obs2)
# obs1 = matrix(101:110, ncol = 5, dimnames = list(letters[1:2], LETTERS[1:5])) ; obs2 = matrix(1:10, ncol = 5, dimnames = list(letters[1:2], LETTERS[1:5])) ; obs1 ; obs2 ; fun_comp_2d(obs1, obs2)
# large matrices
# obs1 = matrix(1:1e6, ncol = 5, dimnames = list(NULL, LETTERS[1:5])) ; obs2 = matrix(as.integer((1:1e6)+1e6/5), ncol = 5, dimnames = list(NULL, LETTERS[1:5])) ; head(obs1) ; head(obs2) ; fun_comp_2d(obs1, obs2)
# WARNING: when comparing content (rows, columns, or total), double and integer data are considered as different -> double(1) != integer(1)
# obs1 = matrix(1:1e6, ncol = 5, dimnames = list(NULL, LETTERS[1:5])) ; obs2 = matrix((1:1e6)+1e6/5, ncol = 5, dimnames = list(NULL, LETTERS[1:5])) ; head(obs1) ; head(obs2) ; fun_comp_2d(obs1, obs2)
# obs1 = matrix(1:10, byrow = TRUE, ncol = 5, dimnames = list(letters[1:2], LETTERS[1:5])) ; obs2 = matrix(c(1:5, 101:105, 6:10), byrow = TRUE, ncol = 5, dimnames = list(c("a", "z", "b"), c(LETTERS[1:2], "k", LETTERS[5:4]))) ; obs1 ; obs2 ; fun_comp_2d(obs1, obs2)
# obs1 = t(matrix(1:10, byrow = TRUE, ncol = 5, dimnames = list(letters[1:2], LETTERS[1:5]))) ; obs2 = t(matrix(c(1:5, 101:105, 6:10), byrow = TRUE, ncol = 5, dimnames = list(c("a", "z", "b"), c(LETTERS[1:2], "k", LETTERS[5:4])))) ; obs1 ; obs2 ; fun_comp_2d(obs1, obs2)
# DEBUGGING
# data1 = matrix(1:10, ncol = 5) ; data2 = matrix(1:10, ncol = 5) # for function debugging
# data1 = matrix(1:10, ncol = 5, dimnames = list(letters[1:2], LETTERS[1:5])) ; data2 = matrix(1:10, ncol = 5, dimnames = list(letters[1:2], LETTERS[1:5])) # for function debugging
# data1 = matrix(1:10, ncol = 5, dimnames = list(letters[1:2], LETTERS[1:5])) ; data2 = matrix(1:10, ncol = 5) # for function debugging
# data1 = matrix(1:15, byrow = TRUE, ncol = 5, dimnames = list(letters[1:3], LETTERS[1:5])) ; data2 = matrix(1:10, byrow = TRUE, ncol = 5, dimnames = list(letters[1:2], LETTERS[1:5])) # for function debugging
# data1 = matrix(1:15, ncol = 5, dimnames = list(letters[1:3], LETTERS[1:5])) ; data2 = matrix(1:10, ncol = 5, dimnames = list(letters[1:2], LETTERS[1:5])) # for function debugging
# data1 = matrix(1:15, ncol = 5, dimnames = list(paste0("A", letters[1:3]), LETTERS[1:5])) ; data2 = matrix(1:10, ncol = 5, dimnames = list(letters[1:2], LETTERS[1:5])) # for function debugging
# data1 = matrix(1:15, ncol = 5, dimnames = list(letters[1:3], LETTERS[1:5])) ; data2 = matrix(1:12, ncol = 4, dimnames = list(letters[1:3], LETTERS[1:4])) # for function debugging
# data1 = matrix(1:10, ncol = 5, dimnames = list(letters[1:2], LETTERS[1:5])) ; data2 = matrix(101:110, ncol = 5, dimnames = list(letters[1:2], LETTERS[1:5])) # for function debugging
# data1 = data.frame(a = 1:3, b= letters[1:3], row.names = LETTERS[1:3], stringsAsFactors = TRUE) ; data2 = data.frame(A = 1:3, B= letters[1:3], stringsAsFactors = TRUE) # for function debugging
# data1 = matrix(1:10, ncol = 5, dimnames = list(letters[1:2], LETTERS[1:5])) ; data2 = as.data.frame(matrix(1:10, ncol = 5, dimnames = list(letters[1:2], LETTERS[1:5])), stringsAsFactors = TRUE) # for function debugging
# data1 = matrix(1:10, byrow = TRUE, ncol = 5, dimnames = list(letters[1:2], LETTERS[1:5])) ; data2 = matrix(c(1:5, 101:105, 6:10), byrow = TRUE, ncol = 5, dimnames = list(c("a", "z", "b"), c(LETTERS[1:2], "k", LETTERS[5:4]))) # for function debugging
# data1 = table(Exp1 = c("A", "A", "A", "B", "B", "B"), Exp2 = c("A1", "B1", "A1", "C1", "C1", "B1")) ; data2 = data.frame(A = 1:3, B= letters[1:3], stringsAsFactors = TRUE) # for function debugging
# data1 = matrix(1:1e6, ncol = 5, dimnames = list(NULL, LETTERS[1:5])) ; data2 = matrix((1:1e6)+1e6/5, ncol = 5, dimnames = list(NULL, LETTERS[1:5]))
# function name
function.name <- paste0(as.list(match.call(expand.dots = FALSE))[[1]], "()")
# end function name
# argument checking
if( ! (any(class(data1) %in% c("data.frame", "table")) | all(class(data1) %in% c("matrix", "array")))){ # before R4.0.0, it was  ! any(class(data1) %in% c("matrix", "data.frame", "table"))
tempo.cat <- paste0("ERROR IN ", function.name, ": THE data1 ARGUMENT MUST BE A MATRIX, DATA FRAME OR TABLE")
stop(paste0("\n\n================\n\n", tempo.cat, "\n\n================\n\n"), call. = FALSE) # == in stop() to be able to add several messages between ==
Gael's avatar
tempo    
Gael committed
1411
}
1412
1413
1414
1415
if( ! (any(class(data2) %in% c("data.frame", "table")) | all(class(data2) %in% c("matrix", "array")))){ # before R4.0.0, it was  ! any(class(data2) %in% c("matrix", "data.frame", "table"))
tempo.cat <- paste0("ERROR IN ", function.name, ": THE data2 ARGUMENT MUST BE A MATRIX, DATA FRAME OR TABLE")
stop(paste0("\n\n================\n\n", tempo.cat, "\n\n================\n\n"), call. = FALSE) # == in stop() to be able to add several messages between ==
}
Gael's avatar
tempo    
Gael committed
1416
# source("C:/Users/Gael/Documents/Git_versions_to_use/debugging_tools_for_r_dev-v1.7/r_debugging_tools-v1.7.R") ; eval(parse(text = str_basic_arg_check_dev)) # activate this line and use the function to check arguments status
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
# end argument checking
# main code
same.class <- NULL
class <- NULL
same.dim <- NULL
dim <- NULL
same.row.nb <- NULL
row.nb <- NULL
same.col.nb <- NULL
col.nb <- NULL
same.row.name <- NULL
row.name <- NULL
any.id.row.name <- NULL
same.row.name.pos1 <- NULL
same.row.name.pos2 <- NULL
common.row.names <- NULL
same.col.name <- NULL
any.id.col.name <- NULL
same.col.name.pos1 <- NULL
same.col.name.pos2 <- NULL
common.col.names <- NULL
col.name <- NULL
any.id.row <- NULL
same.row.pos1 <- NULL
same.row.pos2 <- NULL
any.id.col <- NULL
same.col.pos1 <- NULL
same.col.pos2 <- NULL
identical.object <- NULL
identical.content <- NULL
if(identical(data1, data2) & (any(class(data1) %in% c("data.frame", "table")) | all(class(data1) %in% c("matrix", "array")))){ # before R4.0.0, it was  ! any(class(data1) %in% c("matrix", "data.frame", "table"))
same.class <- TRUE
class <- class(data1)
same.dim <- TRUE
dim <- dim(data1)
same.row.nb <- TRUE
row.nb <- nrow(data1)
same.col.nb <- TRUE
col.nb <- ncol(data1)
same.row.name <- TRUE
row.name <- dimnames(data1)[[1]]
any.id.row.name <- TRUE
same.row.name.pos1 <- 1:row.nb
same.row.name.pos2 <- 1:row.nb
common.row.names <- dimnames(data1)[[1]]
same.col.name <- TRUE
col.name <- dimnames(data1)[[2]]
any.id.col.name <- TRUE
same.col.name.pos1 <- 1:col.nb
same.col.name.pos2 <- 1:col.nb
common.col.names <- dimnames(data1)[[2]]
any.id.row <- TRUE
same.row.pos1 <- 1:row.nb
same.row.pos2 <- 1:row.nb
any.id.col <- TRUE
same.col.pos1 <- 1:col.nb
same.col.pos2 <- 1:col.nb
identical.object <- TRUE
identical.content <- TRUE
}else{
identical.object <- FALSE
if(all(class(data1) == "table") & length(dim(data1)) == 1){
tempo.cat <- paste0("ERROR IN ", function.name, ": THE data1 ARGUMENT IS A 1D TABLE. USE THE fun_comp_1d FUNCTION")
stop(paste0("\n\n================\n\n", tempo.cat, "\n\n================\n\n"), call. = FALSE) # == in stop() to be able to add several messages between ==
}
if(all(class(data2) == "table") & length(dim(data2)) == 1){
tempo.cat <- paste0("ERROR IN ", function.name, ": THE data2 ARGUMENT IS A 1D TABLE. USE THE fun_comp_1d FUNCTION")
stop(paste0("\n\n================\n\n", tempo.cat, "\n\n================\n\n"), call. = FALSE) # == in stop() to be able to add several messages between ==
}
if( ! identical(class(data1), class(data2))){
same.class <- FALSE
}else if( ! (any(class(data1) %in% c("data.frame", "table")) | all(class(data1) %in% c("matrix", "array")))){ # before R4.0.0, it was  ! any(class(data1) %in% c("matrix", "data.frame", "table"))
tempo.cat <- paste0("ERROR IN ", function.name, ": THE data1 AND data2 ARGUMENTS MUST BE EITHER MATRIX, DATA FRAME OR TABLE")
stop(paste0("\n\n================\n\n", tempo.cat, "\n\n================\n\n"), call. = FALSE) # == in stop() to be able to add several messages between ==
}else{
same.class <- TRUE
class <- class(data1)
}
if( ! identical(dim(data1), dim(data2))){
same.dim <- FALSE
}else{
same.dim <- TRUE
dim <- dim(data1)
}
if( ! identical(nrow(data1), nrow(data2))){
same.row.nb <- FALSE
}else{
same.row.nb <- TRUE
row.nb <- nrow(data1)
}
if( ! identical(ncol(data1), ncol(data2))){
same.col.nb <- FALSE
}else{
same.col.nb <- TRUE
col.nb <- ncol(data1)
}
# row and col names
if(is.null(dimnames(data1)) & is.null(dimnames(data2))){
same.row.name <- NULL
same.col.name <- NULL
# row and col names remain NULL
}else if((is.null(dimnames(data1)) & ! is.null(dimnames(data2))) | ( ! is.null(dimnames(data1)) & is.null(dimnames(data2)))){
same.row.name <- FALSE
same.col.name <- FALSE
# row and col names remain NULL
}else{
if( ! identical(dimnames(data1)[[1]], dimnames(data2)[[1]])){
same.row.name <- FALSE
# row names remain NULL
}else{
same.row.name <- TRUE
row.name <- dimnames(data1)[[1]]
}
# row names
any.id.row.name <- FALSE
if(any(dimnames(data1)[[1]] %in% dimnames(data2)[[1]])){
any.id.row.name <- TRUE
same.row.name.pos1 <- which(dimnames(data1)[[1]] %in% dimnames(data2)[[1]])
}
if(any(dimnames(data2)[[1]] %in% dimnames(data1)[[1]])){
any.id.row.name <- TRUE
same.row.name.pos2 <- which(dimnames(data2)[[1]] %in% dimnames(data1)[[1]])
}
if(any.id.row.name == TRUE){
common.row.names <- unique(c(dimnames(data1)[[1]][same.row.name.pos1], dimnames(data2)[[1]][same.row.name.pos2]))
}
# col names
any.id.col.name <- FALSE
if(any(dimnames(data1)[[2]] %in% dimnames(data2)[[2]])){
any.id.col.name <- TRUE
same.col.name.pos1 <- which(dimnames(data1)[[2]] %in% dimnames(data2)[[2]])
}
if(any(dimnames(data2)[[2]] %in% dimnames(data1)[[2]])){
any.id.col.name <- TRUE
same.col.name.pos2 <- which(dimnames(data2)[[2]] %in% dimnames(data1)[[2]])
}
if(any.id.col.name == TRUE){
common.col.names <- unique(c(dimnames(data1)[[2]][same.col.name.pos1], dimnames(data2)[[2]][same.col.name.pos2]))
}
if( ! identical(dimnames(data1)[[2]], dimnames(data2)[[2]])){
same.col.name <- FALSE
# col names remain NULL
}else{
same.col.name <- TRUE
col.name <- dimnames(data1)[[2]]
}
}
# identical row and col content
if(all(class(data1) == "table")){
as.data.frame(matrix(data1, ncol = ncol(data1)), stringsAsFactors = FALSE)
}else if(all(class(data1) %in% c("matrix", "array"))){
data1 <- as.data.frame(data1, stringsAsFactors = FALSE)
}else if(all(class(data1) == "data.frame")){
data1 <- data.frame(lapply(data1, as.character), stringsAsFactors = FALSE)
}
if(all(class(data2) == "table")){
as.data.frame(matrix(data2, ncol = ncol(data2)), stringsAsFactors = FALSE)
}else if(all(class(data2) %in% c("matrix", "array"))){
data2 <- as.data.frame(data2, stringsAsFactors = FALSE)
}else if(all(class(data2) == "data.frame")){
data2 <- data.frame(lapply(data2, as.character), stringsAsFactors = FALSE)
}
row.names(data1) <- paste0("A", 1:nrow(data1))
row.names(data2) <- paste0("A", 1:nrow(data2))
if(same.col.nb == TRUE){ # because if not the same col nb, the row cannot be identical
if(all(sapply(data1, FUN = typeof) == "integer") & all(sapply(data2, FUN = typeof) == "integer") & as.double(nrow(data1)) * nrow(data2) <= 1e10){ # as.double(nrow(data1)) to prevent integer overflow because R is 32 bits for integers
same.row.pos1 <- which(c(as.data.frame(t(data1), stringsAsFactors = FALSE)) %in% c(as.data.frame(t(data2), stringsAsFactors = FALSE))) # this work fast with only integers (because 32 bits)
same.row.pos2 <- which(c(as.data.frame(t(data2), stringsAsFactors = FALSE)) %in% c(as.data.frame(t(data1), stringsAsFactors = FALSE)))
}else if(as.double(nrow(data1)) * nrow(data2) <= 1e6){ # as.double(nrow(data1)) to prevent integer overflow because R is 32 bits for integers
same.row.pos1 <- logical(length = nrow(data1)) # FALSE by default
same.row.pos1[] <- FALSE # security
for(i3 in 1:nrow(data1)){
for(i4 in 1:nrow(data2)){
same.row.pos1[i3] <- identical(data1[i3, ], data2[i4, ])
}
}
same.row.pos1 <- which(same.row.pos1)
1594

1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
same.row.pos2 <- logical(length = nrow(data2)) # FALSE by default
same.row.pos2[] <- FALSE # security
for(i3 in 1:nrow(data2)){
for(i4 in 1:nrow(data1)){
same.row.pos2[i3] <- identical(data2[i3, ], data1[i4, ])
}
}
same.row.pos2 <- which(same.row.pos2)
}else{
same.row.pos1 <- "TOO BIG FOR EVALUATION"
same.row.pos2 <- "TOO BIG FOR EVALUATION"
}
1607

1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
names(same.row.pos1) <- NULL
names(same.row.pos2) <- NULL
if(all(is.na(same.row.pos1))){
same.row.pos1 <- NULL
}else{
same.row.pos1 <- same.row.pos1[ ! is.na(same.row.pos1)]
any.id.row <- TRUE
}
if(all(is.na(same.row.pos2))){
same.row.pos2 <- NULL
}else{
same.row.pos2 <- same.row.pos2[ ! is.na(same.row.pos2)]
any.id.row <- TRUE
}
if(is.null(same.row.pos1) & is.null(same.row.pos2)){
any.id.row <- FALSE
}else if(length(same.row.pos1) == 0 & length(same.row.pos2) == 0){
any.id.row <- FALSE
}else if(all(same.row.pos1 == "TOO BIG FOR EVALUATION") & all(same.row.pos2 == "TOO BIG FOR EVALUATION")){
any.id.row <- NULL
}
}else{
any.id.row <- FALSE
# same.row.pos1 and 2 remain NULL
}
if(same.row.nb == TRUE){ # because if not the same row nb, the col cannot be identical
if(all(sapply(data1, FUN = typeof) == "integer") & all(sapply(data2, FUN = typeof) == "integer") & as.double(ncol(data1)) * ncol(data2) <= 1e10){ # as.double(ncol(data1)) to prevent integer overflow because R is 32 bits for integers
same.col.pos1 <- which(c(data1) %in% c(data2))
same.col.pos2 <- which(c(data2) %in% c(data1))
}else if(as.double(ncol(data1)) * ncol(data2) <= 1e6){ # as.double(ncol(data1)) to prevent integer overflow because R is 32 bits for integers
same.col.pos1 <- logical(length = ncol(data1)) # FALSE by default
same.col.pos1[] <- FALSE # security
for(i3 in 1:ncol(data1)){
for(i4 in 1:ncol(data2)){
same.col.pos1[i3] <- identical(data1[ , i3], data2[ ,i4])
}
}
same.col.pos1 <- which(same.col.pos1)
1646

1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
same.col.pos2 <- logical(length = ncol(data2)) # FALSE by default
same.col.pos2[] <- FALSE # security
for(i3 in 1:ncol(data2)){
for(i4 in 1:ncol(data1)){
same.col.pos2[i3] <- identical(data2[ , i3], data1[ , i4])
}
}
same.col.pos2 <- which(same.col.pos2)
}else{
same.col.pos1 <- "TOO BIG FOR EVALUATION"
same.col.pos2 <- "TOO BIG FOR EVALUATION"
}
names(same.col.pos1) <- NULL
names(same.col.pos2) <- NULL
if(all(is.na(same.col.pos1))){
same.col.pos1 <- NULL
}else{
same.col.pos1 <- same.col.pos1[ ! is.na(same.col.pos1)]
any.id.col <- TRUE
}
if(all(is.na(same.col.pos2))){
same.col.pos2 <- NULL
}else{
same.col.pos2 <- same.col.pos2[ ! is.na(same.col.pos2)]
any.id.col <- TRUE
}
if(is.null(same.col.pos1) & is.null(same.col.pos2)){
any.id.col <- FALSE
}else if(length(same.col.pos1) == 0 & length(same.col.pos2) == 0){
any.id.col <- FALSE
}else if(all(same.col.pos1 == "TOO BIG FOR EVALUATION") & all(same.col.pos2 == "TOO BIG FOR EVALUATION")){
any.id.col <- NULL
}
}else{
any.id.col <- FALSE
# same.col.pos1 and 2 remain NULL
}
if(same.dim == TRUE){
names(data1) <- NULL
row.names(data1) <- NULL
names(data2) <- NULL
row.names(data2) <- NULL
if(identical(data1, data2)){
identical.content <- TRUE
}else{
identical.content <- FALSE
}
}else{
identical.content <- FALSE
}
}
output <- list(same.class = same.class, class = class, same.dim = same.dim, dim = dim, same.row.nb = same.row.nb, row.nb = row.nb, same.col.nb = same.col.nb , col.nb = col.nb, same.row.name = same.row.name, row.name = row.name, any.id.row.name = any.id.row.name, same.row.name.pos1 = same.row.name.pos1, same.row.name.pos2 = same.row.name.pos2, common.row.names = common.row.names, same.col.name = same.col.name, col.name = col.name,any.id.col.name = any.id.col.name, same.col.name.pos1 = same.col.name.pos1, same.col.name.pos2 = same.col.name.pos2, common.col.names = common.col.names, any.id.row = any.id.row, same.row.pos1 = same.row.pos1, same.row.pos2 = same.row.pos2, any.id.col = any.id.col, same.col.pos1 = same.col.pos1, same.col.pos2 = same.col.pos2, identical.object = identical.object, identical.content = identical.content)
return(output)
Gael's avatar
tempo    
Gael committed
1700
}
1701
1702


1703
######## fun_comp_list() #### comparison of two lists
1704
1705


1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
fun_comp_list <- function(data1, data2){
# AIM
# compare two lists. Check and report in a list if the 2 datasets have:
# same length
# common names
# common compartments
# ARGUMENTS
# data1: list
# data2: list
# RETURN
# a list containing:
# $same.length: logical. Are number of elements identical?
# $length: number of elements in the 2 datasets (NULL otherwise)
# $same.name: logical. Are element names identical ?
# $name: name of elements of the 2 datasets if identical (NULL otherwise)
# $any.id.name: logical. Is there any element names identical ?
# $same.name.pos1: position, in data1, of the element names identical in data2
# $same.name.pos2: position, in data2, of the compartment names identical in data1
# $any.id.compartment: logical. is there any identical compartments ?
# $same.compartment.pos1: position, in data1, of the compartments identical in data2
# $same.compartment.pos2: position, in data2, of the compartments identical in data1
# $identical.object: logical. Are objects identical (kind of object, compartment names and content)?
# $identical.content: logical. Are content objects identical (identical compartments excluding compartment names)?
# REQUIRED PACKAGES
# none
# REQUIRED FUNCTIONS FROM CUTE_LITTLE_R_FUNCTION
# none
# EXAMPLES
# obs1 = list(a = 1:5, b = LETTERS[1:2], d = matrix(1:6)) ; obs2 = list(a = 1:5, b = LETTERS[1:2], d = matrix(1:6)) ; fun_comp_list(obs1, obs2)
# obs1 = list(1:5, LETTERS[1:2]) ; obs2 = list(a = 1:5, b = LETTERS[1:2]) ; fun_comp_list(obs1, obs2)
# obs1 = list(b = 1:5, c = LETTERS[1:2]) ; obs2 = list(a = 1:5, b = LETTERS[1:2], d = matrix(1:6)) ; fun_comp_list(obs1, obs2)
# obs1 = list(b = 1:5, c = LETTERS[1:2]) ; obs2 = list(LETTERS[5:9], matrix(1:6), 1:5) ; fun_comp_list(obs1, obs2)
# DEBUGGING
# data1 = list(a = 1:5, b = LETTERS[1:2], d = matrix(1:6)) ; data2 = list(a = 1:5, b = LETTERS[1:2], d = matrix(1:6)) # for function debugging
# data1 = list(a = 1:5, b = LETTERS[1:2]) ; data2 = list(a = 1:5, b = LETTERS[1:2], d = matrix(1:6)) # for function debugging
# function name
function.name <- paste0(as.list(match.call(expand.dots = FALSE))[[1]], "()")
# end function name
# argument checking
if( ! any(class(data1) %in% "list")){
tempo.cat <- paste0("ERROR IN ", function.name, ": THE data1 ARGUMENT MUST BE A LIST")
stop(paste0("\n\n================\n\n", tempo.cat, "\n\n================\n\n"), call. = FALSE) # == in stop() to be able to add several messages between ==
}
if( ! any(class(data2) %in% "list")){
tempo.cat <- paste0("ERROR IN ", function.name, ": THE data2 ARGUMENT MUST BE A LIST")
stop(paste0("\n\n================\n\n", tempo.cat, "\n\n================\n\n"), call. = FALSE) # == in stop() to be able to add several messages between ==
}
Gael's avatar
tempo    
Gael committed
1753
# source("C:/Users/Gael/Documents/Git_versions_to_use/debugging_tools_for_r_dev-v1.7/r_debugging_tools-v1.7.R") ; eval(parse(text = str_basic_arg_check_dev)) # activate this line and use the function to check arguments status
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
# end argument checking
# main code
same.length <- NULL
length <- NULL
same.name <- NULL
name <- NULL
any.id.name <- NULL
same.name.pos1 <- NULL
same.name.pos2 <- NULL
any.id.compartment <- NULL
same.compartment.pos1 <- NULL
same.compartment.pos2 <- NULL
identical.object <- NULL
identical.content <- NULL
if(identical(data1, data2)){
same.length <- TRUE
length <- length(data1)
if( ! is.null(names(data1))){
same.name <- TRUE
name <- names(data1)
any.id.name <- TRUE
same.name.pos1 <- 1:length(data1)
same.name.pos2 <- 1:length(data2)
}
any.id.compartment <- TRUE
same.compartment.pos1 <- 1:length(data1)
same.compartment.pos2 <- 1:length(data2)
identical.object <- TRUE
identical.content <- TRUE
}else{
identical.object <- FALSE
if( ! identical(length(data1), length(data2))){
same.length<- FALSE
}else{
same.length<- TRUE
length <- length(data1)
}
if( ! (is.null(names(data1)) & is.null(names(data2)))){
if( ! identical(names(data1), names(data2))){
same.name <- FALSE
}else{
same.name <- TRUE
name <- names(data1)
}
any.id.name <- FALSE
if(any(names(data1) %in% names(data2))){
any.id.name <- TRUE
same.name.pos1 <- which(names(data1) %in% names(data2))
}
if(any(names(data2) %in% names(data1))){
any.id.name <- TRUE
same.name.pos2 <- which(names(data2) %in% names(data1))
}
}
names(data1) <- NULL
names(data2) <- NULL
any.id.compartment <- FALSE
if(any(data1 %in% data2)){
any.id.compartment <- TRUE
same.compartment.pos1 <- which(data1 %in% data2)
}
if(any(data2 %in% data1)){
any.id.compartment <- TRUE
same.compartment.pos2 <- which(data2 %in% data1)
}
if(same.length == TRUE & ! all(is.null(same.compartment.pos1), is.null(same.compartment.pos2))){
if(identical(same.compartment.pos1, same.compartment.pos2)){
identical.content <- TRUE
}else{
identical.content <- FALSE
}
}else{
identical.content <- FALSE
}
}
output <- list(same.length = same.length, length = length, same.name = same.name, name = name, any.id.name = any.id.name, same.name.pos1 = same.name.pos1, same.name.pos2 = same.name.pos2, any.id.compartment = any.id.compartment, same.compartment.pos1 = same.compartment.pos1, same.compartment.pos2 = same.compartment.pos2, identical.object = identical.object, identical.content = identical.content)
return(output)
}


######## fun_test() #### test combinations of argument values of a function and return errors (and graphs)


# add traceback https://stackoverflow.com/questions/47414119/how-to-read-a-traceback-in-r

fun_test <- function(
fun, 
arg, 
val, 
expect.error = NULL, 
thread.nb = NULL, 
print.count = 10, 
plot.fun = FALSE, 
export = FALSE, 
res.path = NULL, 
lib.path = NULL, 
cute.path = "C:\\Users\\Gael\\Documents\\Git_projects\\cute_little_R_functions\\cute_little_R_functions.R"
){
# AIM
# test combinations of argument values of a function
# WARNINGS
# Limited to 43 arguments with at least 2 values each. The total number of arguments tested can be more if the additional arguments have a single value. The limit is due to nested "for" loops (https://stat.ethz.ch/pipermail/r-help/2008-March/157341.html), but it should not be a problem since the number of tests would be 2^43 > 8e12
# ARGUMENTS
# fun: character string indicating the name of the function tested (without brackets)
# arg: vector of character strings of arguments of fun. At least arguments that do not have default values must be present in this vector
# val: list with number of compartments equal to length of arg, each compartment containing values of the corresponding argument in arg. Each different value must be in a list or in a vector. For instance, argument 3 in arg is a logical argument (values accepted TRUE, FALSE, NA). Thus, compartment 3 of val can be either list(TRUE, FALSE, NA), or c(TRUE, FALSE, NA)
# expect.error: list of exactly the same structure as val argument, but containing FALSE or TRUE, depending on whether error is expected (TRUE) or not (FALSE) for each corresponding value of val. A message is returned depending on discrepancies between the expected and observed errors. BEWARE: not always possible to write the expected errors for all the combination of argument values. Ignored if NULL
# thread.nb: numeric value indicating the number of available threads. Write NULL if no parallelization wanted
# print.count: interger value. Print a working progress message every print.count during loops. BEWARE: can increase substentially the time to complete the process using a small value, like 10 for instance. Use Inf is no loop message desired
# plot.fun: logical. Plot the plotting function tested for each test?
# export: logical. Export the results into a .RData file and into a .txt file? If FALSE, return a list into the console (see below). BEWARE: will be automatically set to TRUE if thread.nb is not NULL. This means that when using parallelization, the results are systematically exported, not returned into the console
# res.path: character string indicating the absolute pathway of folder where the txt results and pdfs, containing all the plots, will be saved. Several txt and pdf, one per thread, if parallelization. Ignored if export is FALSE. Must be specified if thread.nb is not NULL or if export is TRUE
# lib.path: character vector specifying the absolute pathways of the directories containing the required packages if not in the default directories. Ignored if NULL
# cute.path: character string indicating the absolute path of the cute.R file. Will be remove when cute will be a package. Not considered if thread.nb is NULL
# REQUIRED PACKAGES
# lubridate
# parallel if thread.nb argument is not NULL (included in the R installation packages but not automatically loaded)
# if the tested function is in a package, this package must be imported first (no parallelization) or must be in the classical R package folder indicated by the lib.path argument (parallelization)
# RETURN
# if export is FALSE a list containing:
# $fun: the tested function
# $data: a data frame of all the combination tested, containing the following columns:
# the different values tested, named by arguments
# $kind: a vector of character strings indicating the kind of test result: either "ERROR", or "WARNING", or "OK"
# $problem: a logical vector indicating if error or not
# $expected.error: optional logical vector indicating the expected error specified in the expect.error argument
# $message: either NULL if $kind is always "OK", or the messages
# $instruction: the initial instruction
# $sys.info: system and packages info
# if export is TRUE 1) the same list object into a .RData file, 2) also the $data data frame into a .txt file, and 3) if expect.error is non NULL and if any discrepancy, the $data data frame into a .txt file but containing only the rows with discrepancies between expected and observed errors
# one or several pdf if a plotting function is tested and if the plot.fun argument is TRUE
# REQUIRED PACKAGES
# none
# REQUIRED FUNCTIONS FROM CUTE_LITTLE_R_FUNCTION
# fun_check()
# fun_get_message()
# fun_pack()
# EXAMPLES
# fun_test(fun = "unique", arg = c("x", "incomparables"), val = list(x = list(1:10, c(1,1,2,8), NA), incomparable = c(TRUE, FALSE, NA)))
# fun_test(fun = "fun_round", arg = c("data", "dec.nb", "after.lead.zero"), val = list(L1 = list(c(1, 1.0002256, 1.23568), "a", NA), L2 = list(2, c(1,3), NA), L3 = c(TRUE, FALSE, NA)))
# fun_test(fun = "plot", arg = c("x", "y"), val = list(x = list(1:10, 12:13, NA, (1:10)^2), y = list(1:10, NA, NA)),  expect.error = list(x = list(FALSE, TRUE, TRUE, FALSE), y = list(FALSE, TRUE, TRUE)), thread.nb = NULL, plot.fun = TRUE, res.path = "C:\\Users\\Gael\\Desktop\\", lib.path = NULL)
# fun_test(fun = "plot", arg = c("x", "y"), val = list(x = list(1:10, 12:13, NA, (1:10)^2), y = list(1:10, NA, NA)), thread.nb = 4, plot.fun = TRUE, res.path = "C:\\Users\\Gael\\Desktop\\", lib.path = "C:\\Program Files\\R\\R-4.0.2\\library\\")
# set.seed(1) ; obs1 <- data.frame(Time = c(rnorm(10), rnorm(10) + 2), Group1 = rep(c("G", "H"), each = 10), stringsAsFactors = TRUE) ; fun_test(fun = "fun_gg_boxplot", arg = c("data1", "y", "categ"), val = list(L1 = list(L1 = obs1), L2 = list(L1 = "Time"), L3 = list(L1 = "Group1")))
# set.seed(1) ; obs1 <- data.frame(Time = c(rnorm(10), rnorm(10) + 2), Group1 = rep(c("G", "H"), each = 10), stringsAsFactors = TRUE) ; fun_test(fun = "fun_gg_boxplot", arg = c("data1", "y", "categ"), val = list(L1 = list(obs1), L2 = "Time", L3 = "Group1"), thread.nb = NULL, plot.fun = TRUE, res.path = "C:\\Users\\Gael\\Desktop\\", lib.path = "C:\\Program Files\\R\\R-4.0.2\\library\\")
# library(ggplot2) ; fun_test(fun = "geom_histogram", arg = c("data", "mapping"), val = list(x = list(data.frame(X = "a", stringsAsFactors = TRUE)), y = list(ggplot2::aes(x = X))), thread.nb = NULL, plot.fun = TRUE, res.path = "C:\\Users\\Gael\\Desktop\\", lib.path = "C:\\Program Files\\R\\R-4.0.2\\library\\") # BEWARE: ggplot2::geom_histogram does not work
# DEBUGGING
# fun = "unique" ; arg = "x" ; val = list(x = list(1:10, c(1,1,2,8), NA)) ; expect.error = list(x = list(FALSE, FALSE, TRUE)) ; thread.nb = NULL ; plot.fun = FALSE ; export = FALSE ; res.path = "C:\\Users\\Gael\\Desktop\\" ; lib.path = NULL ; print.count = 1 ; cute.path = "C:\\Users\\Gael\\Documents\\Git_projects\\cute_little_R_functions\\cute_little_R_functions.R" # for function debugging
# fun = "unique" ; arg = c("x", "incomparables") ; val = list(x = list(1:10, c(1,1,2,8), NA), incomparable = c(TRUE, FALSE, NA)) ; expect.error = NULL ; thread.nb = 2 ; plot.fun = FALSE ; export = TRUE ; res.path = "C:\\Users\\Gael\\Desktop\\" ; lib.path = NULL ; print.count = 10 ; cute.path = "C:\\Users\\Gael\\Documents\\Git_projects\\cute_little_R_functions\\cute_little_R_functions.R" # for function debugging
# fun = "plot" ; arg = c("x", "y") ; val = list(x = list(1:10, 12:13, NA), y = list(1:10, NA, NA)) ; expect.error = list(x = list(FALSE, FALSE, TRUE, FALSE), y = list(FALSE, TRUE, TRUE)) ; print.count = 10 ; thread.nb = NULL ; plot.fun = TRUE ; export = TRUE ; res.path = "C:\\Users\\Gael\\Desktop\\" ; lib.path = NULL # for function debugging
# set.seed(1) ; obs1 <- data.frame(Time = c(rnorm(10), rnorm(10) + 2), Group1 = rep(c("G", "H"), each = 10), stringsAsFactors = TRUE) ; fun = "fun_gg_boxplot" ; arg = c("data1", "y", "categ") ; val = list(L1 = list(L1 = obs1), L2 = list(L1 = "Time"), L3 = list(L1 = "Group1")) ; expect.error = NULL ; print.count = 10 ; thread.nb = NULL ; plot.fun = TRUE ; export = TRUE ; res.path = "C:\\Users\\Gael\\Desktop\\" ; lib.path = NULL # for function debugging
1904
# fun = "unique" ; arg = "x" ; val = list(list(1:3, mean)) ; expect.error = list(TRUE, TRUE) ; thread.nb = NULL ; plot.fun = FALSE ; export = FALSE ; res.path = "C:\\Users\\Gael\\Desktop\\" ; lib.path = NULL ; print.count = 1 ; cute.path = "C:\\Users\\Gael\\Documents\\Git_projects\\cute_little_R_functions\\cute_little_R_functions.R" # for function debugging
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
# function name
function.name <- paste0(as.list(match.call(expand.dots = FALSE))[[1]], "()")
instruction <- match.call()
# end function name
# required function checking
req.function <- c(
"fun_check", 
"fun_get_message", 
"fun_pack"
)
for(i1 in req.function){
1916
if(base::length(find(i1, mode = "function")) == 0){
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
tempo.cat <- paste0("ERROR IN ", function.name, ": REQUIRED ", i1, "() FUNCTION IS MISSING IN THE R ENVIRONMENT")
stop(paste0("\n\n================\n\n", tempo.cat, "\n\n================\n\n"), call. = FALSE) # == in stop() to be able to add several messages between ==
}
}
# end required function checking
# argument primary checking
# arg with no default values
if(any(missing(fun) | missing(arg) | missing(val))){
tempo.cat <- paste0("ERROR IN ", function.name, ": ARGUMENTS fun, arg AND val HAVE NO DEFAULT VALUE AND REQUIRE ONE")
stop(paste0("\n\n================\n\n", tempo.cat, "\n\n================\n\n"), call. = FALSE) # == in stop() to be able to add several messages between ==
}
# end arg with no default values
# using fun_check()
arg.check <- NULL #
text.check <- NULL #
checked.arg.names <- NULL # for function debbuging: used by r_debugging_tools
ee <- expression(arg.check <- c(arg.check, tempo$problem) , text.check <- c(text.check, tempo$text) , checked.arg.names <- c(checked.arg.names, tempo$object.name))
tempo <- fun_check(data = fun, class = "vector", mode = "character", length = 1, fun.name = function.name) ; eval(ee)
if(tempo$problem == FALSE){
if(grepl(x = fun, pattern = "()$")){ # remove ()
fun <- sub(x = fun, pattern = "()$", replacement = "")
}
if( ! exists(fun)){
tempo.cat <- paste0("ERROR IN ", function.name, ": CHARACTER STRING IN fun ARGUMENT DOES NOT EXIST IN THE R WORKING ENVIRONMENT: ", paste(fun, collapse = "\n"))
text.check <- c(text.check, tempo.cat)
arg.check <- c(arg.check, TRUE)
1943
1944
}else if( ! all(base::class(get(fun)) == "function")){ # here no env = sys.nframe(), inherit = FALSE for get() because fun is a function in the classical scope
tempo.cat <- paste0("ERROR IN ", function.name, ": fun ARGUMENT IS NOT CLASS \"function\" BUT: ", paste(base::class(get(fun)), collapse = "\n"), "\nCHECK IF ANY CREATED OBJECT WOULD HAVE THE NAME OF THE TESTED FUNCTION")
1945
1946
1947
1948
1949
text.check <- c(text.check, tempo.cat)
arg.check <- c(arg.check, TRUE)
}
}
tempo <- fun_check(data = arg, class = "vector", mode = "character", fun.name = function.name) ; eval(ee)
1950
if(tempo$problem == FALSE & base::length(arg) == 0){
1951
1952
1953
1954
1955
1956
tempo.cat <- paste0("ERROR IN ", function.name, ": arg ARGUMENT CANNOT BE LENGTH 0")
text.check <- c(text.check, tempo.cat)
arg.check <- c(arg.check, TRUE)
}
tempo <- fun_check(data = val, class = "list", fun.name = function.name) ; eval(ee)
if(tempo$problem == FALSE){
1957
for(i2 in 1:base::length(val)){
1958
1959
1960
1961
1962
1963
1964
tempo1 <- fun_check(data = val[[i2]], class = "vector", na.contain = TRUE, fun.name = function.name)
tempo2 <- fun_check(data = val[[i2]], class = "list", na.contain = TRUE, fun.name = function.name)
if(tempo1$problem == TRUE & tempo2$problem == TRUE){
tempo.cat <- paste0("ERROR IN ", function.name, ": COMPARTMENT ", i2, " OF val ARGUMENT MUST BE A VECTOR OR A LIST")
text.check <- c(text.check, tempo.cat)
arg.check <- c(arg.check, TRUE)
}else if(tempo1$problem == FALSE){ # vector split into list compartments
1965
val[[i2]] <- split(x = val[[i2]], f = 1:base::length(val[[i2]]))
1966
1967
1968
1969
1970
1971
}
}
}
if( ! is.null(expect.error)){
tempo <- fun_check(data = expect.error, class = "list", fun.name = function.name) ; eval(ee)
if(tempo$problem == FALSE){
1972
for(i3 in 1:base::length(expect.error)){
1973
1974
1975
1976
1977
1978
1979
tempo1 <- fun_check(data = expect.error[[i3]], class = "vector",  mode = "logical", fun.name = function.name)
tempo2 <- fun_check(data =  expect.error[[i3]], class = "list", fun.name = function.name)
if(tempo1$problem == TRUE & tempo2$problem == TRUE){
tempo.cat <- paste0("ERROR IN ", function.name, ": COMPARTMENT ", i3, " OF expect.error ARGUMENT MUST BE TRUE OR FALSE")
text.check <- c(text.check, tempo.cat)
arg.check <- c(arg.check, TRUE)
}else if(tempo1$problem == FALSE){ # vector split into list compartments
1980
expect.error[[i3]] <- split(x = expect.error[[i3]], f = 1:base::length(expect.error[[i3]]))
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
}
}
}
}
if( ! is.null(thread.nb)){
tempo <- fun_check(data = thread.nb, typeof = "integer", double.as.integer.allowed = TRUE, neg.values = FALSE, length = 1, fun.name = function.name) ; eval(ee)
if(tempo$problem == FALSE & thread.nb < 1){
tempo.cat <- paste0("ERROR IN ", function.name, ": thread.nb PARAMETER MUST EQUAL OR GREATER THAN 1: ", thread.nb)
text.check <- c(text.check, tempo.cat)
arg.check <- c(arg.check, TRUE)
}
}
tempo <- fun_check(data = print.count, class = "vector", typeof = "integer", length = 1, double.as.integer.allowed = TRUE, neg.values = FALSE, fun.name = function.name) ; eval(ee)
tempo <- fun_check(data = plot.fun, class = "vector", mode = "logical", length = 1, fun.name = function.name) ; eval(ee)
tempo <- fun_check(data = export, class = "vector", mode = "logical", length = 1, fun.name = function.name) ; eval(ee)
if( ! is.null(res.path)){
tempo <- fun_check(data = res.path, class = "vector", mode = "character", fun.name = function.name) ; eval(ee)
if(tempo$problem == FALSE){
if( ! all(dir.exists(res.path))){ # separation to avoid the problem of tempo$problem == FALSE and res.path == NA
tempo.cat <- paste0("ERROR IN ", function.name, ": DIRECTORY PATH INDICATED IN THE res.path ARGUMENT DOES NOT EXISTS:\n", paste(res.path, collapse = "\n"))