cute_little_R_functions.R 186 KB
Newer Older
Gael  MILLOT's avatar
Gael MILLOT committed
1
2
################################################################
##                                                            ##
Gael  MILLOT's avatar
Gael MILLOT committed
3
##     CUTE LITTLE R FUNCTIONS v4.8.0                         ##
Gael  MILLOT's avatar
Gael MILLOT committed
4
5
6
##                                                            ##
##     Gael A. Millot                                         ##
##                                                            ##
Gael  MILLOT's avatar
Gael MILLOT committed
7
##     Compatible with R v3.5.2                               ##
Gael  MILLOT's avatar
Gael MILLOT committed
8
9
10
11
12
13
14
15
16
17
##                                                            ##
################################################################





################################ OUTLINE ################################


Gael  MILLOT's avatar
Gael MILLOT committed
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
################ Object analysis    1
######## fun_param_check() #### Checking class, type, length, etc. of objects   1
######## fun_object_info() #### Recovering object information   7
######## fun_1D_comp() #### comparison of two 1D datasets (vectors, factors, 1D tables) 8
######## fun_2D_comp() #### comparison of two 2D datasets (row & col names, dimensions, etc.)   12
######## fun_list_comp() #### comparison of two lists   18
################ Object modification    21
######## fun_dataframe_remodeling() #### remodeling a data frame to have column name as a qualitative column and vice-versa 21
######## fun_refactorization() #### remove classes that are not anymore present in factors or factor columns in data frames 23
######## fun_rounding() #### Rounding number if decimal present 25
######## fun_90clock_matrix_rot() #### 90 clockwise matrix rotation    27
######## fun_hexa_hsv_color_matrix() #### Conversion of a numeric matrix into hexadecimal color matrix  28
######## fun_by_case_matrix_op() #### assembling of several matrices with operation 30
################ Graphics   32
######## fun_window_width_resizing() #### window width depending on classes to plot 33
######## fun_open_window() #### Open a GUI or pdf graphic window    34
######## fun_graph_param_prior_plot() #### Graph param before plotting  37
######## fun_feature_post_plot() #### Graph param after plotting    41
######## fun_close_specif_window() #### Closing specific graphic windows    52
######## fun_var_trim_display() #### Display values from a quantitative variable and trim according to defined cut-offs 54
################ Exporting results (text & tables)  62
######## fun_export_data() #### Print string or data object into output file    62
Gael  MILLOT's avatar
Gael MILLOT committed
40
41
42
43
44
45
46
47
48
49
50
51
52


################################ FUNCTIONS ################################


################ Object analysis


######## fun_param_check() #### Checking class, type, length, etc. of objects


# Check OK: clear to go Apollo
fun_param_check <- function(data, data.name = NULL, class = NULL, typeof = NULL, mode = NULL, length = NULL, prop = NULL, double.as.integer.allowed = FALSE, options = NULL, all.options.in.data = FALSE, na.contain = FALSE, neg.values = TRUE, print = TRUE){
Gael  MILLOT's avatar
Gael MILLOT committed
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
    # AIM:
    # check the class, type, mode and length of the data argument
    # mainly used to check the arguments of other functions
    # check also other kind of data parameters, is it a proportion? Is it type double even if it is an integer?
    # if options = NULL, then at least class, type, mode or length must be non null
    # if options is non null, then class, type and mode must be NULL, and length can be NULL or specified
    # REQUIRED FUNCTIONS
    # none
    # ARGUMENTS
    # data: object to test
    # data.name: name of the object to test. If NULL, use the name of the object assigned to the data argument
    # class: one of the class() result
    # typeof: one of the typeof() result
    # mode: one of the mode() result (for non vector object)
    # length: length of the object
    # prop: logical, are the numeric values between 0 and 1 (proportion)?
    # double.as.integer.allowed: logical. If TRUE, no error is reported if argument is set to typeof = "integer" or class = "integer", while the reality is typeof = "double" or class = "numeric" but the numbers have a zero as modulo (remainder of a division). This means that i<-1 , which is typeof(i) -> "double" is considered as integer with double.as.integer.allowed = TRUE
    # options: a vector of possible values for data
    # all.options.in.data: If TRUE, all of the options must be present at least once in data, and nothing else. If FALSE, some of the options must be present in data, and nothing else
    # na.contain: can data contains NA?
    # neg.values: are negative numeric values authorized? BEWARE: only considered if set to FALSE, to check for non negative values when class is set to "numeric", "matrix", "array", "data.frame", "table", or typeof is set to "double", "integer", or mode is set to "numeric"
    # print: print the error message if $problem is TRUE?
    # RETURN
    # a list containing:
    # $problem: logical. Is there any problem detected ?
    # $text: the problem detected
    # $param.name: name of the checked parameter
    # EXAMPLES
    # test <- 1:3 ; fun_param_check(data = test, data.name = NULL, print = TRUE, options = NULL, all.options.in.data = FALSE, class = NULL, typeof = NULL, mode = NULL, prop = TRUE, double.as.integer.allowed = FALSE, length = NULL)
    # test <- 1:3 ; fun_param_check(data = test, print = TRUE, class = "numeric", typeof = NULL, double.as.integer.allowed = FALSE)
    # DEBUGGING
    # data = 1:3 ; data.name = NULL ; print = TRUE; options = NULL ; all.options.in.data = FALSE ; class = "numeric" ; typeof = NULL ; mode = NULL ; prop = NULL ; double.as.integer.allowed = TRUE ; length = NULL # for function debugging
    # argument checking
    # source("C:/Users/Gael/Documents/Git_versions_to_use/debugging_tools_for_r_dev-v1.2/r_debugging_tools-v1.2.R") ; eval(parse(text = str_basic_arg_check_dev))
    if( ! is.null(data.name)){
        if( ! (length(data.name) == 1 & class(data.name) == "character")){
            tempo.cat <- paste0("\n\n================\n\nERROR IN fun_param_check(): data.name ARGUMENT MUST BE A SINGLE CHARACTER ELEMENT AND NOT ", paste(data.name, collapse = " "), "\n\n================\n\n")
            stop(tempo.cat)
        }
    }
    if(is.null(options) & is.null(class) & is.null(typeof) & is.null(mode) & is.null(prop) & is.null(length)){
        tempo.cat <- paste0("\n\n================\n\nERROR IN fun_param_check(): AT LEAST ONE OF THE options, class, typeof, mode, prop, OR length ARGUMENT MUST BE SPECIFIED\n\n================\n\n")
        stop(tempo.cat)
    }
    if( ! is.null(options) & ( ! is.null(class) | ! is.null(typeof) | ! is.null(mode) | ! is.null(prop))){
        tempo.cat <- paste0("\n\n================\n\nERROR IN fun_param_check(): THE class, typeof, mode AND prop ARGUMENTS MUST BE NULL IF THE option ARGUMENT IS SPECIFIED\nTHE option ARGUMENT MUST BE NULL IF THE class AND/OR typeof AND/OR mode  AND/OR prop ARGUMENT IS SPECIFIED\n\n================\n\n")
        stop(tempo.cat)
    }
    if( ! (all(class(neg.values) == "logical") & length(neg.values) == 1 & any(is.na(neg.values)) != TRUE)){
        tempo.cat <- paste0("\n\n================\n\nERROR IN fun_param_check(): THE neg.values ARGUMENT MUST BE TRUE OR FALSE ONLY\n\n================\n\n")
        stop(tempo.cat)
    }
    if(neg.values == FALSE & is.null(class) & is.null(typeof) & is.null(mode)){
        tempo.cat <- paste0("\n\n================\n\nERROR IN fun_param_check(): THE neg.values ARGUMENT CANNOT BE SWITCHED TO FALSE IF class, typeof AND mode ARGUMENTS ARE NULL\n\n================\n\n")
        stop(tempo.cat)
    }
    if( ! is.null(class)){
        if( ! all(class %in% c("logical", "integer", "numeric", "complex", "character", "matrix", "array", "data.frame", "list", "factor", "table", "expression", "name", "symbol", "function") & any(is.na(class)) != TRUE)){ # not length == 1 here because ordered factors are class "factor" "ordered" (length == 2)
            tempo.cat <- paste0("\n\n================\n\nERROR IN fun_param_check(): class ARGUMENT MUST BE ONE OF THESE VALUE:\n\"logical\", \"integer\", \"numeric\", \"complex\", \"character\", \"matrix\", \"array\", \"data.frame\", \"list\", \"factor\", \"table\", \"expression\", \"name\", \"symbol\", \"function\" \n\n================\n\n")
            stop(tempo.cat)
        }
        if(neg.values == FALSE & ! any(class %in% c("numeric", "integer", "table"))){
            tempo.cat <- paste0("\n\n================\n\nERROR IN fun_param_check(): class ARGUMENT CANNOT BE OTHER THAN \"numeric\", \"integer\", \"table\" IF neg.values ARGUMENT IS SWITCHED TO FALSE\n\n================\n\n")
            stop(tempo.cat)
        }
    }
    if( ! is.null(typeof)){
        if( ! (all(typeof %in% c("logical", "integer", "double", "complex", "character", "list", "expression", "name", "symbol", "closure", "special", "builtin")) & length(typeof) == 1 & any(is.na(typeof)) != TRUE)){
            tempo.cat <- paste0("\n\n================\n\nERROR IN fun_param_check(): typeof ARGUMENT MUST BE ONE OF THESE VALUE:\n\"logical\", \"integer\", \"double\", \"complex\", \"character\", \"list\", \"expression\", \"name\", \"symbol\", \"closure\", \"special\", \"builtin\" \n\n================\n\n")
            stop(tempo.cat)
        }
        if(neg.values == FALSE & ! typeof %in% c("double", "integer")){
            tempo.cat <- paste0("\n\n================\n\nERROR IN fun_param_check(): typeof ARGUMENT CANNOT BE OTHER THAN \"double\" OR \"integer\" IF neg.values ARGUMENT IS SWITCHED TO FALSE\n\n================\n\n")
            stop(tempo.cat)
        }
    }
    if( ! is.null(mode)){
        if( ! (all(mode %in% c("logical", "numeric", "complex", "character", "list", "expression", "name", "symbol", "function")) & length(mode) == 1 & any(is.na(mode)) != TRUE)){
            tempo.cat <- paste0("\n\n================\n\nERROR IN fun_param_check(): mode ARGUMENT MUST BE ONE OF THESE VALUE:\n\"logical\", \"numeric\", \"complex\", \"character\", \"list\", \"expression\", \"name\", \"symbol\", \"function\"\n\n================\n\n")
            stop(tempo.cat)
        }
        if(neg.values == FALSE & mode != "numeric"){
            tempo.cat <- paste0("\n\n================\n\nERROR IN fun_param_check(): mode ARGUMENT CANNOT BE OTHER THAN \"numeric\" IF neg.values ARGUMENT IS SWITCHED TO FALSE\n\n================\n\n")
            stop(tempo.cat)
        }
    }
    if( ! is.null(length)){
        if( ! (is.numeric(length) & length(length) == 1 & ! grepl(length, pattern = "\\.") & any(is.na(length)) != TRUE)){
            tempo.cat <- paste0("\n\n================\n\nERROR IN fun_param_check(): length ARGUMENT MUST BE A SINGLE INTEGER VALUE\n\n================\n\n")
            stop(tempo.cat)
        }
    }
    if( ! is.null(prop)){
        if( ! (is.logical(prop) | length(prop) == 1 & any(is.na(prop)) != TRUE)){
            tempo.cat <- paste0("\n\n================\n\nERROR IN fun_param_check(): prop ARGUMENT MUST BE TRUE OR FALSE ONLY\n\n================\n\n")
            stop(tempo.cat)
        }else if(prop == TRUE){
            if( ! is.null(class)){
                if( ! any(class %in% c("numeric", "matrix", "array", "data.frame", "table"))){
                    tempo.cat <- paste0("\n\n================\n\nERROR IN fun_param_check(): class ARGUMENT CANNOT BE OTHER THAN \"numeric\", \"matrix\", \"array\", \"data.frame\", \"table\" IF prop ARGUMENT IS TRUE\n\n================\n\n")
                    stop(tempo.cat)
                }
            }
            if( ! is.null(mode)){
                if(mode != "numeric"){
                    tempo.cat <- paste0("\n\n================\n\nERROR IN fun_param_check(): mode ARGUMENT CANNOT BE OTHER THAN \"numeric\" IF prop ARGUMENT IS TRUE\n\n================\n\n")
                    stop(tempo.cat)
                }
            }
            if( ! is.null(typeof)){
                if(typeof != "double"){
                    tempo.cat <- paste0("\n\n================\n\nERROR IN fun_param_check(): typeof ARGUMENT CANNOT BE OTHER THAN \"double\" IF prop ARGUMENT IS TRUE\n\n================\n\n")
                    stop(tempo.cat)
                }
            }
        }
    }
    if( ! (all(class(double.as.integer.allowed) == "logical") & length(double.as.integer.allowed) == 1 & any(is.na(double.as.integer.allowed)) != TRUE)){
        tempo.cat <- paste0("\n\n================\n\nERROR IN fun_param_check(): THE double.as.integer.allowed ARGUMENT MUST BE TRUE OR FALSE ONLY\n\n================\n\n")
        stop(tempo.cat)
    }
    if( ! (is.logical(all.options.in.data) & length(all.options.in.data) == 1 & any(is.na(all.options.in.data)) != TRUE)){
        tempo.cat <- paste0("\n\n================\n\nERROR IN fun_param_check(): all.options.in.data ARGUMENT MUST BE A SINGLE LOGICAL VALUE (TRUE OR FALSE ONLY)\n\n================\n\n")
        stop(tempo.cat)
    }
    if( ! (all(class(na.contain) == "logical") & length(na.contain) == 1 & any(is.na(na.contain)) != TRUE)){
        tempo.cat <- paste0("\n\n================\n\nERROR IN fun_param_check(): THE na.contain ARGUMENT MUST BE TRUE OR FALSE ONLY\n\n================\n\n")
        stop(tempo.cat)
    }
    if( ! (all(class(print) == "logical") & length(print) == 1 & any(is.na(print)) != TRUE)){
        tempo.cat <- paste0("\n\n================\n\nERROR IN fun_param_check(): THE print ARGUMENT MUST BE TRUE OR FALSE ONLY\n\n================\n\n")
        stop(tempo.cat)
    }
    # end argument checking
    if(is.null(data.name)){
        data.name <- deparse(substitute(data))
    }
    problem <- FALSE
    text <- paste0("NO PROBLEM DETECTED FOR THE ", data.name, " PARAMETER")
    if( ! is.null(options)){
        text <- ""
        if( ! all(data %in% options)){
            problem <- TRUE
            text <- paste0("PROBLEM: THE ", data.name, " PARAMETER MUST BE SOME OF THESE OPTIONS: ", paste(options, collapse = " "), "\nTHE PROBLEMATIC ELEMENTS OF ", data.name, " ARE: ", paste(unique(data[ ! (data %in% options)]), collapse = " "))
        }
        if(all.options.in.data == TRUE){
            if( ! all(options %in% data)){
                problem <- TRUE
                if(text == ""){
                    text <- paste0("PROBLEM: THE ", data.name, " PARAMETER MUST BE SOME OF THESE OPTIONS: ", paste(options, collapse = " "), "\nTHE PROBLEMATIC ELEMENTS OF ", data.name, " ARE: ", unique(data[ ! (data %in% options)]))
                }else{
                    text <- paste0(text, "\nPROBLEM: THE ", data.name, " PARAMETER MUST BE SOME OF THESE OPTIONS: ", paste(options, collapse = " "), "\nTHE PROBLEMATIC ELEMENTS OF ", data.name, " ARE: ", unique(data[ ! (data %in% options)]))
                }
            }
        }
        if( ! is.null(length)){
            if(length(data) != length){
                problem <- TRUE
                if(text == ""){
                    text <- paste0("PROBLEM: THE LENGTH OF ", data.name, " MUST BE ", length, " AND NOT ", length(data))
                }else{
                    text <- paste0(text, "\nPROBLEM: THE LENGTH OF ", data.name, " MUST BE ", length, " AND NOT ", length(data))
                }
            }
        }
        if(text == ""){
            text <- paste0("NO PROBLEM DETECTED FOR THE ", data.name, " PARAMETER")
        }
    }
    arg.names <- c("class", "typeof", "mode", "length")
    if(is.null(options)){
        for(i2 in 1:length(arg.names)){
            if( ! is.null(get(arg.names[i2]))){
                # script to execute
                tempo.script <- '
                problem <- TRUE ;
                if(identical(text, paste0("NO PROBLEM DETECTED FOR THE ", data.name, " PARAMETER"))){
                text <- paste0("PROBLEM: THE ", data.name, " PARAMETER MUST BE ") ;
                }else{
                text <- paste0(text, " AND "); 
                }
                text <- paste0(text, toupper(arg.names[i2]), " ", get(arg.names[i2]))
                '
                if(typeof(data) == "double" & double.as.integer.allowed == TRUE & ((arg.names[i2] == "class" & get(arg.names[i2]) == "integer") | (arg.names[i2] == "typeof" & get(arg.names[i2]) == "integer"))){
                    if(! all(data%%1 == 0)){ # to check integers (use %%, meaning the remaining of a division): see the precedent line
                        eval(parse(text = tempo.script)) # execute tempo.script
                    }
                }else if(eval(parse(text = paste0(arg.names[i2], "(data)"))) != get(arg.names[i2])){
                    eval(parse(text = tempo.script)) # execute tempo.script
                }
            }
    }
        }
    if( ! is.null(prop)){
        if(prop == TRUE){
            if(any(data < 0 | data > 1, na.rm = TRUE)){
                problem <- TRUE
                if(identical(text, paste0("NO PROBLEM DETECTED FOR THE ", data.name, " PARAMETER"))){
                    text <- paste0("PROBLEM: ")
                }else{
                    text <- paste0(text, " AND ")
                }
                text <- paste0(text, "THE ", data.name, " PARAMETER MUST BE DECIMAL VALUES BETWEEN 0 AND 1")
            }
        }
    }
    if(na.contain == FALSE & any(is.na(data)) == TRUE){
        problem <- TRUE
        if(identical(text, paste0("NO PROBLEM DETECTED FOR THE ", data.name, " PARAMETER"))){
            text <- paste0("PROBLEM: ")
        }else{
            text <- paste0(text, " AND ")
        }
        text <- paste0(text, "THE ", data.name, " PARAMETER CONTAINS NA WHILE NOT AUTHORIZED (na.contain ARGUMENT SET TO FALSE)")
    }
    if(neg.values == FALSE){
        if(any(data < 0, na.rm = TRUE)){
            problem <- TRUE
            if(identical(text, paste0("NO PROBLEM DETECTED FOR THE ", data.name, " PARAMETER"))){
                text <- paste0("PROBLEM: ")
            }else{
                text <- paste0(text, " AND ")
            }
            text <- paste0(text, "THE ", data.name, " PARAMETER MUST NON NEGATIVE NUMERIC VALUES")
        }
    }
    if(print == TRUE & problem == TRUE){
        cat(paste0("\n\n================\n\n", text, "\n\n================\n\n"))
    }
    output <- list(problem = problem, text = text, param.name = data.name)
    return(output)
    }
Gael  MILLOT's avatar
Gael MILLOT committed
285
286
287
288
289
290
291


######## fun_object_info() #### Recovering object information


# Check OK: clear to go Apollo
fun_object_info <- function(data){
Gael  MILLOT's avatar
Gael MILLOT committed
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
    # AIM:
    # provide a full description of the object
    # REQUIRED FUNCTIONS
    # none
    # ARGUMENTS
    # data: object to test
    # RETURN
    # a list containing the info
    # use names(fun_object_info()) and remove what can be to big for easy analysis
    # EXAMPLES
    # fun_object_info(data = 1:3)
    # fun_object_info(data.frame(a = 1:2, b = ordered(factor(c("A", "B")))))
    # fun_object_info(list(a = 1:3, b = ordered(factor(c("A", "B")))))
    # DEBUGGING
    # data = NULL # for function debugging
    # data = 1:3 # for function debugging
    # data = matrix(1:3) # for function debugging
    # data = data.frame(a = 1:2, b = c("A", "B")) # for function debugging
    # data = factor(c("b", "a")) # for function debugging
    # data = ordered(factor(c("b", "a"))) # for function debugging
    # data = list(a = 1:3, b = factor(c("A", "B"))) # for function debugging
    # data = list(a = 1:3, b = ordered(factor(c("A", "B")))) # for function debugging
    # argument checking
    # source("C:/Users/Gael/Documents/Git_versions_to_use/debugging_tools_for_r_dev-v1.2/r_debugging_tools-v1.2.R") ; eval(parse(text = str_basic_arg_check_dev)) # activate this line and use the function to check arguments status and if they have been checked using fun_param_check()
    # end argument checking
    data.name <- deparse(substitute(data))
    output <- list("FILE_NAME" = data.name)
    tempo <- list("CLASS" = class(data))
    output <- c(output, tempo)
    tempo <- list("FILE_HEAD" = head(data))
    output <- c(output, tempo)
    if( ! is.null(data)){
        tempo <- list("FILE_TAIL" = tail(data))
        output <- c(output, tempo)
        if( ! is.null(dim(data))){
            tempo <- list("FILE_DIMENSION" = dim(data))
            names(tempo[[1]]) <- c("NROW", "NCOL")
            output <- c(output, tempo)
        }
        tempo <- list("SUMMARY" = summary(data))
        output <- c(output, tempo)
    }
    if(all(class(data) == "data.frame" | class(data) == "matrix")){
        tempo <- list("ROW_NAMES" = dimnames(data)[[1]])
        output <- c(output, tempo)
        tempo <- list("COLUM_NAMES" = dimnames(data)[[2]])
        output <- c(output, tempo)
    }
    if(all(class(data) == "data.frame")){
        tempo <- list("STRUCTURE" = ls.str(data))
        output <- c(output, tempo)
        tempo <- list("COLUMN_TYPE" = sapply(data, FUN = "typeof"))
        if(any(sapply(data, FUN = "class") %in% "factor")){ # if an ordered factor is present, then sapply(data, FUN = "class") return a list but works with any(sapply(data, FUN = "class") %in% "factor") 
            tempo.class <- sapply(data, FUN = "class")
            if(any(unlist(tempo.class) %in% "ordered")){
                tempo2 <- sapply(tempo.class, paste, collapse = " ") # paste the "ordered" factor" in "ordered factor"
            }else{
                tempo2 <- unlist(tempo.class)
            }
            tempo[["COLUMN_TYPE"]][grepl(x = tempo2, pattern = "factor")] <- tempo2[grepl(x = tempo2, pattern = "factor")]
        }
        output <- c(output, tempo)
    }
    if(all(class(data) == "list")){
        tempo <- list("COMPARTMENT_NAMES" = names(data))
        output <- c(output, tempo)
        tempo <- list("COMPARTMENT_TYPE" = sapply(data, FUN = "typeof"))
        if(any(unlist(sapply(data, FUN = "class")) %in% "factor")){ # if an ordered factor is present, then sapply(data, FUN = "class") return a list but works with any(sapply(data, FUN = "class") %in% "factor") 
            tempo.class <- sapply(data, FUN = "class")
            if(any(unlist(tempo.class) %in% "ordered")){
                tempo2 <- sapply(tempo.class, paste, collapse = " ") # paste the "ordered" factor" in "ordered factor"
            }else{
                tempo2 <- unlist(tempo.class)
            }
            tempo[["COMPARTMENT_TYPE"]][grepl(x = tempo2, pattern = "factor")] <- tempo2[grepl(x = tempo2, pattern = "factor")]
        }
        output <- c(output, tempo)
    }
    return(output)
Gael  MILLOT's avatar
Gael MILLOT committed
371
372
373
374
375
376
377
378
}


######## fun_1D_comp() #### comparison of two 1D datasets (vectors, factors, 1D tables)


# Check OK: clear to go Apollo
fun_1D_comp <- function(data1, data2){
Gael  MILLOT's avatar
Gael MILLOT committed
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
    # AIM:
    # compare two 1D datasets (vector of factor or 1D table) 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)
    # REQUIRED FUNCTIONS
    # none
    # ARGUMENTS
    # data1: vector or factor or 1D table
    # data2: vector or factor or 1D table
    # 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 ?
    # $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 elements names identical in data1
    # $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
    # $same.element.pos2: position, in data2, of the elements identical in data1
    # $common.elements: common elements between data1 and data2. NULL if no common elements
    # $identical.object: logical. Are objects identical (kind of object, element names and content)?
    # $identical.content: logical. Are content objects identical (identical elements excluding kind of object and element names)?
    # EXAMPLES
    # obs1 = 1:5 ; obs2 = 1:5 ; names(obs1) <- LETTERS[1:5] ; names(obs2) <- LETTERS[1:5] ; fun_1D_comp(obs1, obs2)
    # obs1 = 1:5 ; obs2 = 1:5 ; names(obs1) <- LETTERS[1:5] ; fun_1D_comp(obs1, obs2)
    # obs1 = 1:5 ; obs2 = 3:6 ; names(obs1) <- LETTERS[1:5] ; names(obs2) <- LETTERS[1:4] ; fun_1D_comp(obs1, obs2)
    # obs1 = factor(LETTERS[1:5]) ; obs2 = factor(LETTERS[1:5]) ; fun_1D_comp(obs1, obs2)
    # obs1 = factor(LETTERS[1:5]) ; obs2 = factor(LETTERS[10:11]) ; fun_1D_comp(obs1, obs2)
    # obs1 = factor(LETTERS[1:5]) ; obs2 = factor(LETTERS[4:7]) ; fun_1D_comp(obs1, obs2)
    # obs1 = 1:5 ; obs2 = factor(LETTERS[1:5]) ; fun_1D_comp(obs1, obs2)
    # obs1 = 1:5 ; obs2 = 1.1:6.1 ; fun_1D_comp(obs1, obs2)
    # obs1 = as.table(1:5); obs2 = as.table(1:5) ; fun_1D_comp(obs1, obs2)
    # obs1 = as.table(1:5); obs2 = 1:5 ; fun_1D_comp(obs1, obs2)
    # DEBUGGING
    # data1 = 1:5 ; data2 = 1:5 ; names(data1) <- LETTERS[1:5] ; names(data2) <- LETTERS[1:5] # for function debugging
    # argument checking
    # source("C:/Users/Gael/Documents/Git_versions_to_use/debugging_tools_for_r_dev-v1.2/r_debugging_tools-v1.2.R") ; eval(parse(text = str_basic_arg_check_dev)) # activate this line and use the function to check arguments status and if they have been checked using fun_param_check()
    if( ! any(class(data1) %in% c("logical", "integer", "numeric", "character", "factor", "table"))){
        tempo.cat <- paste0("\n\n================\n\nERROR IN fun_1D_comp(): THE data1 ARGUMENT MUST BE A NON NULL VECTOR, FACTOR OR 1D TABLE\n\n================\n\n")
        stop(tempo.cat)
    }else if(all(class(data1) %in% "table")){
        if(length(dim(data1)) > 1){
            tempo.cat <- paste0("\n\n================\n\nERROR IN fun_1D_comp(): THE data1 ARGUMENT MUST BE A 1D TABLE\n\n================\n\n")
            stop(tempo.cat)
        }
    }
    if( ! any(class(data2) %in% c("logical", "integer", "numeric", "character", "factor", "table"))){
        tempo.cat <- paste0("\n\n================\n\nERROR IN fun_1D_comp(): THE data2 ARGUMENT MUST BE A NON NULL VECTOR, FACTOR OR 1D TABLE\n\n================\n\n")
        stop(tempo.cat)
    }else if(all(class(data2) %in% "table")){
        if(length(dim(data2)) > 1){
            tempo.cat <- paste0("\n\n================\n\nERROR IN fun_1D_comp(): THE data2 ARGUMENT MUST BE A 1D TABLE\n\n================\n\n")
            stop(tempo.cat)
        }
    }
    # end argument checking
    same.class <- NULL
    class <- NULL
    same.length <- NULL
    length <- NULL
    same.levels <- NULL
    levels <- NULL
    any.id.levels <- NULL
    same.levels.pos1 <- NULL
    same.levels.pos2 <- NULL
    common.levels <- NULL
    same.name <- NULL
    name <- NULL
    any.id.name <- NULL
    same.name.pos1 <- NULL
    same.name.pos2 <- NULL
    common.names <- NULL
    any.id.element <- NULL
    same.element.pos1 <- NULL
    same.element.pos2 <- NULL
    common.elements <- NULL
    identical.object <- NULL
    identical.content <- NULL
    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
        identical.object <- TRUE
        identical.content <- TRUE
    }else{
        identical.object <- FALSE
        if( ! identical(class(data1), class(data2))){
            same.class <- FALSE
        }else{
            same.class <- TRUE
            class <- class(data1)
        }
        if( ! identical(length(data1), length(data2))){
            same.length<- FALSE
        }else{
            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 <- FALSE
            }else{
                same.levels <- TRUE
                levels <- levels(data1)
            }
            any.id.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 <- 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))
            }
            if(any.id.name == TRUE){
                common.names <- unique(c(names(data1)[same.name.pos1], names(data2)[same.name.pos2]))
            }
        }
        any.id.element <- FALSE
        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(same.length == TRUE & ! all(is.null(same.element.pos1), is.null(same.element.pos2))){
            names(same.element.pos1) <- NULL
            names(same.element.pos2) <- NULL
            if(identical(same.element.pos1, same.element.pos2)){
                identical.content <- TRUE
            }else{
                identical.content <- FALSE
            }
        }else{
            identical.content <- FALSE
        }
    }
    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, identical.object = identical.object, identical.content = identical.content)
    return(output)
Gael  MILLOT's avatar
Gael MILLOT committed
583
584
585
586
587
588
589
590
}


######## fun_2D_comp() #### comparison of two 2D datasets (row & col names, dimensions, etc.)


# Check OK: clear to go Apollo
fun_2D_comp <- function(data1, data2){
Gael  MILLOT's avatar
Gael MILLOT committed
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
    # 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
    # REQUIRED FUNCTIONS
    # none
    # 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) ?
    # $same.row.pos1: position, in data1, of the rows identical in data2 (not considering row names)
    # $same.row.pos2: position, in data2, of the rows identical in data1 (not considering row names)
    # $any.id.col: logical. is there identical columns (not considering column names)?
    # $same.col.pos1: position in data1 of the cols identical in data2 (not considering column names)
    # $same.col.pos2: position in data2 of the cols identical in data1 (not considering column names)
    # $identical.object: logical. Are objects identical (including row & column names)?
    # $identical.content: logical. Are content objects identical (identical excluding row & column names)?
    # 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]))) ; obs1 ; obs2 ; fun_2D_comp(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_2D_comp(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_2D_comp(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_2D_comp(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]) ; data2 = data.frame(A = 1:3, B= letters[1:3]) # 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]))) # 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]) # for function debugging
    # argument checking
    # source("C:/Users/Gael/Documents/Git_versions_to_use/debugging_tools_for_r_dev-v1.2/r_debugging_tools-v1.2.R") ; eval(parse(text = str_basic_arg_check_dev)) # activate this line and use the function to check arguments status and if they have been checked using fun_param_check()
    if( ! any(class(data1) %in% c("matrix", "data.frame", "table"))){
        tempo.cat <- paste0("\n\n================\n\nERROR IN fun_2D_comp(): THE data1 ARGUMENT MUST BE A MATRIX, DATA FRAME OR TABLE\n\n================\n\n")
        stop(tempo.cat)
    }
    if( ! any(class(data2) %in% c("matrix", "data.frame", "table"))){
        tempo.cat <- paste0("\n\n================\n\nERROR IN fun_2D_comp(): THE data2 ARGUMENT MUST BE A MATRIX, DATA FRAME OR TABLE\n\n================\n\n")
        stop(tempo.cat)
    }
    # end argument checking
    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("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("\n\n================\n\nERROR IN fun_2D_comp(): THE data1 ARGUMENT IS A 1D TABLE. USE THE info_1D_dataset_fun FUNCTION\n\n================\n\n")
            stop(tempo.cat)
        }
        if(all(class(data2) == "table") & length(dim(data2)) == 1){
            tempo.cat <- paste0("\n\n================\n\nERROR IN fun_2D_comp(): THE data2 ARGUMENT IS A 1D TABLE. USE THE info_1D_dataset_fun FUNCTION\n\n================\n\n")
            stop(tempo.cat)
        }
        if( ! identical(class(data1), class(data2))){
            same.class <- FALSE
        }else if( ! any(class(data1) %in% c("matrix", "data.frame", "table"))){
            tempo.cat <- paste0("\n\n================\n\nERROR IN fun_2D_comp(): THE data1 AND data2 ARGUMENTS MUST BE EITHER MATRIX, DATA FRAME OR TABLE\n\n================\n\n")
            stop(tempo.cat)
        }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) == "matrix")){
            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) == "matrix")){
            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
            same.row.pos1 <- which(c(as.data.frame(t(data1), stringsAsFactors = FALSE)) %in% c(as.data.frame(t(data2), stringsAsFactors = FALSE)))
            same.row.pos2 <-  which(c(as.data.frame(t(data2), stringsAsFactors = FALSE)) %in% c(as.data.frame(t(data1), stringsAsFactors = FALSE)))
            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{
            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
            same.col.pos1 <- which(c(data1) %in% c(data2))
            same.col.pos2 <- which(c(data2) %in% c(data1))
            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{
            any.id.col <- FALSE
            # same.col.pos1 and 2 remain NULL
        }
        if(same.dim == TRUE & ! all(is.null(same.row.pos1), is.null(same.row.pos2), is.null(same.col.pos1), is.null(same.col.pos2))){ # same.dim == TRUE means that same.row.nb == TRUE and same.col.nb == TRUE, meaning that row.nb != NULL and col.nb != NULL. Thus, no need to include these checkings
            if(identical(same.row.pos1, 1:row.nb) & identical(same.row.pos2, 1:row.nb) & identical(same.col.pos1, 1:col.nb) & identical(same.col.pos2, 1:col.nb)){
                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  MILLOT's avatar
Gael MILLOT committed
886
887
888
889
890
891
892
893
}


######## fun_list_comp() #### comparison of two lists


# Check OK: clear to go Apollo
fun_list_comp <- function(data1, data2){
Gael  MILLOT's avatar
Gael MILLOT committed
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
    # AIM:
    # compare two lists. Check and report in a list if the 2 datasets have:
    # same length
    # common names
    # common compartments
    # REQUIRED FUNCTIONS
    # none
    # 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)?
    # 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_list_comp(obs1, obs2)
    # obs1 = list(1:5, LETTERS[1:2]) ; obs2 = list(a = 1:5, b = LETTERS[1:2]) ; fun_list_comp(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_list_comp(obs1, obs2)
    # obs1 = list(b = 1:5, c = LETTERS[1:2]) ; obs2 = list(LETTERS[5:9], matrix(1:6), 1:5) ; fun_list_comp(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
    # argument checking
    # source("C:/Users/Gael/Documents/Git_versions_to_use/debugging_tools_for_r_dev-v1.2/r_debugging_tools-v1.2.R") ; eval(parse(text = str_basic_arg_check_dev)) # activate this line and use the function to check arguments status and if they have been checked using fun_param_check()
    if( ! any(class(data1) %in% "list")){
        tempo.cat <- paste0("\n\n================\n\nERROR IN fun_list_comp(): THE data1 ARGUMENT MUST BE A LIST\n\n================\n\n")
        stop(tempo.cat)
    }
    if( ! any(class(data2) %in% "list")){
        tempo.cat <- paste0("\n\n================\n\nERROR IN fun_list_comp(): THE data2 ARGUMENT MUST BE A LIST\n\n================\n\n")
        stop(tempo.cat)
    }
    # end argument checking
    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)
Gael  MILLOT's avatar
Gael MILLOT committed
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
}


################ Object modification


######## fun_dataframe_remodeling() #### remodeling a data frame to have column name as a qualitative column and vice-versa


# Check OK: clear to go Apollo
fun_dataframe_remodeling <- function(data, quanti.col.name = "quanti", quali.col.name = "quali"){
Gael  MILLOT's avatar
Gael MILLOT committed
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
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
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
    # AIM:
    # if the data frame is made of numeric columns, a new data frame is created, with the 1st column gathering all the numeric values, and the 2nd column being the name of the columns of the initial data frame. If row names were present in the initial data frame, then a new ini_rowname column is added with the names of the rows
    
    
    # If the data frame is made of one numeric column and one character or factor column, a new data frame is created, with the new columns corresponding to the split numeric values (according to the character column). NA are added a the end of each column to have the same number of rows. BEWARE: in such data frame, rows are not individuals. This means that in the example below, values 10 and 20 are associated on the same row but that means nothing in term of association
    
    
    
    # REQUIRED FUNCTIONS
    # fun_param_check()
    # ARGUMENTS
    # data: data frame to convert
    # quanti.col.name: optional name for the quanti column of the new data frame
    # quali.col.name: optional name for the quali column of the new data frame
    # RETURN
    # the modified data frame
    # EXAMPLES
    # obs <- data.frame(col1 = (1:4)*10, col2 = c("A", "B", "A", "A")) ; obs ; fun_dataframe_remodeling(obs)
    # obs <- data.frame(col1 = (1:4)*10, col2 = 5:8) ; obs ; fun_dataframe_remodeling(obs, quanti.col.name = "quanti", quali.col.name = "quali")
    # obs <- data.frame(col1 = (1:4)*10, col2 = 5:8) ; rownames(obs) <- paste0("row", 1:4) ; obs ; fun_dataframe_remodeling(obs, quanti.col.name = "quanti", quali.col.name = "quali")
    # DEBUGGING
    # data = data.frame(a = 1:3, b = 4:6) ; quanti.col.name = "quanti" ; quali.col.name = "quali" # for function debugging
    # data = data.frame(a = 1:3, b = 4:6, c = 11:13) ; quanti.col.name = "quanti" ; quali.col.name = "quali" # for function debugging
    # data = data.frame(a = 1:3, b = letters[1:3]) ; quanti.col.name = "quanti" ; quali.col.name = "quali" # for function debugging
    # data = data.frame(a = 1:3, b = letters[1:3]) ; quanti.col.name = "TEST" ; quali.col.name = "quali" # for function debugging
    # data = data.frame(b = letters[1:3], a = 1:3) ; quanti.col.name = "quanti" ; quali.col.name = "quali" # for function debugging
    # data = data.frame(b = c("e", "e", "h"), a = 1:3) ; quanti.col.name = "quanti" ; quali.col.name = "quali" # for function debugging
    # required function checking
    if(length(find("fun_param_check", mode = "function")) == 0){
        tempo.cat <- paste0("\n\n================\n\nERROR IN fun_dataframe_remodeling(): REQUIRED fun_param_check() FUNCTION IS MISSING IN THE R ENVIRONMENT\n\n================\n\n")
        stop(tempo.cat)
    }
    # end required function checking
    arg.check <- NULL # for function debbuging
    checked.arg.names <- NULL # for function debbuging
    ee <- expression(arg.check <- c(arg.check, tempo$problem) , checked.arg.names <- c(checked.arg.names, tempo$param.name))
    tempo <- fun_param_check(data = quanti.col.name, class = "character", length = 1) ; eval(ee)
    tempo <- fun_param_check(data = quali.col.name, class = "character", length = 1) ; eval(ee)
    if(any(arg.check) == TRUE){
        stop() # nothing else because print = TRUE by default in fun_param_check()
    }
    # source("C:/Users/Gael/Documents/Git_versions_to_use/debugging_tools_for_r_dev-v1.2/r_debugging_tools-v1.2.R") ; eval(parse(text = str_basic_arg_check_dev)) ; eval(parse(text = str_arg_check_with_fun_param_check_dev)) # activate this line and use the function to check arguments status and if they have been checked using fun_param_check()
    if( ! any(class(data) %in% "data.frame")){
        tempo.cat <- paste0("\n\n================\n\nERROR IN fun_dataframe_remodeling(): THE data ARGUMENT MUST BE A DATA FRAME\n\n================\n\n")
        stop(tempo.cat)
    }
    # end argument checking
    tempo.factor <- unlist(lapply(data, class))
    for(i in 1:length(tempo.factor)){ # convert factor columns as character
        if(all(tempo.factor[i] == "factor")){
            data[, i] <- as.character(data[, i])
        }
    }
    tempo.factor <- unlist(lapply(data, mode))
    if(length(data) == 2){
        if( ! ((mode(data[, 1]) == "character" & mode(data[, 2]) == "numeric") | mode(data[, 2]) == "character" & mode(data[, 1]) == "numeric" | mode(data[, 2]) == "numeric" & mode(data[, 1]) == "numeric") ){
            tempo.cat <- paste0("\n\n================\n\nERROR IN fun_dataframe_remodeling(): IF data ARGUMENT IS A DATA FRAME MADE OF 2 COLUMNS, EITHER A COLUMN MUST BE NUMERIC AND THE OTHER CHARACTER, OR THE TWO COLUMNS MUST BE NUMERIC\n\n================\n\n")
            stop(tempo.cat)
        }
        if((mode(data[, 1]) == "character" | mode(data[, 2]) == "character") & (quanti.col.name != "quanti" | quali.col.name != "quali")){
            tempo.cat <- paste0("\n\n================\n\nERROR IN fun_dataframe_remodeling(): IMPROPER quanti.col.name OR quali.col.name RESETTINGS. THESE ARGUMENTS ARE RESERVED FOR DATA FRAMES MADE OF n NUMERIC COLUMNS ONLY\n\n================\n\n")
            stop(tempo.cat)
        }
    }else{
        if( ! all(tempo.factor %in% "numeric")){
            tempo.cat <- paste0("\n\n================\n\nERROR IN fun_dataframe_remodeling(): IF data ARGUMENT IS A DATA FRAME MADE OF ONE COLUMN, OR MORE THAN 2 COLUMNS, THESE COLUMNS MUST BE NUMERIC\n\n================\n\n")
            stop(tempo.cat)
        }
    }
    if(( ! any(tempo.factor %in% "character")) & is.null(names(data))){
        tempo.cat <- paste0("\n\n================\n\nERROR IN fun_dataframe_remodeling(): NUMERIC DATA FRAME in the data ARGUMENT MUST HAVE COLUMN NAMES\n\n================\n\n")
        stop()
    }
    if(all(tempo.factor %in% "numeric")){ # transfo 1
        quanti <- NULL
        for(i in 1:length(data)){
            quanti <-c(quanti, data[, i])
        }
        quali <- rep(names(data), each = nrow(data))
        output.data <- data.frame(quanti, quali)
        names(output.data) <- c(quanti.col.name, quali.col.name)
        # add the ini_rowname column
        ini.rownames <- rownames(data)
        tempo.data <- data
        rownames(tempo.data) <- NULL
        null.rownames <- (tempo.data)
        if( ! identical(ini.rownames, null.rownames)){
            ini_rowname <- rep(ini.rownames, times = ncol(data))
            output.data <- cbind(output.data, ini_rowname)
        }
    }else{ # transfo 2
        if(class(data[, 1]) == "character"){
            data <- cbind(data[2], data[1])
        }
        nc.max <- max(table(data[, 2])) # effectif maximum des classes
        nb.na <- nc.max - table(data[,2]) # nombre de NA  ajouter pour raliser la data frame
        tempo<-split(data[, 1], data[, 2])
        for(i in 1:length(tempo)){tempo[[i]] <- append(tempo[[i]], rep(NA, nb.na[i]))} # des NA doivent tre ajouts lorsque les effectifs sont diffrents entre les classes. C'est uniquement pour que chaque colonne ait le mme nombre de lignes
        output.data<-data.frame(tempo)
    }
    return(output.data)
Gael  MILLOT's avatar
Gael MILLOT committed
1124
1125
1126
1127
1128
1129
1130
1131
}


######## fun_refactorization() #### remove classes that are not anymore present in factors or factor columns in data frames


# Check OK: clear to go Apollo
fun_refactorization <- function(data, also.ordered = TRUE){
Gael  MILLOT's avatar
Gael MILLOT committed
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
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
    # AIM:
    # refactorize a factor or the factor columns of a data frame, such as only the class present are in the levels (no empty levels). The class order in levels is kept
    # useful to remove the empty classes after row removing for instance
    # REQUIRED FUNCTIONS
    # fun_param_check()
    # ARGUMENTS
    # data: factor (ordered or not) or data frame
    # also.ordered: refactorize also ordered factors? This to deal with ordered factors that have class "ordered" "factor"
    # RETURN
    # a list containing:
    # $data: the modified object
    # $removed: the removed classes for a factor and a list of the removed classes for each factor class of the data frame
    # EXAMPLES
    # obs <- data.frame(a = LETTERS[1:6], b = paste0(letters[1.6], c(1,1,2,2,3,3)), c = ordered(LETTERS[7:12]), d = 1:6, e = "A")[-c(1:2),] ; sapply(obs, levels) ; fun_refactorization(obs, FALSE)
    # obs <- data.frame(a = LETTERS[1:6], b = paste0(letters[1.6], c(1,1,2,2,3,3)), c = ordered(LETTERS[7:12]), d = 1:6, e = "A")[-c(1:2),] ; sapply(obs, levels) ; fun_refactorization(obs, TRUE)
    # obs <- factor(LETTERS[1:6])[-c(1:2)] ; obs ; fun_refactorization(obs, TRUE)
    # obs <- ordered(LETTERS[1:6])[-c(1:2)] ; obs ; fun_refactorization(obs, TRUE)
    # obs <- factor(LETTERS[1:6], levels = rev(LETTERS[1:6]))[-c(1:2)] ; obs ; fun_refactorization(obs, FALSE)
    # DEBUGGING
    # data <- data.frame(a = LETTERS[1:6], b = paste0(letters[1.6], c(1,1,2,2,3,3)), c = ordered(LETTERS[7:12]), d = 1:6, e = "A") ; data <- data[-c(1:2),] ; also.ordered <- TRUE # for function debugging
    # data <- factor(LETTERS[1:6])[-c(1:2)] ; also.ordered <- TRUE # for function debugging
    # data <- ordered(LETTERS[1:6])[-c(1:2)] ; also.ordered <- TRUE # for function debugging
    # required function checking
    if(length(find("fun_param_check", mode = "function")) == 0){
        tempo.cat <- paste0("\n\n================\n\nERROR IN fun_refactorization(): REQUIRED fun_param_check() FUNCTION IS MISSING IN THE R ENVIRONMENT\n\n================\n\n")
        stop(tempo.cat)
    }
    # end required function checking
    # argument checking
    arg.check <- NULL # for function debbuging
    checked.arg.names <- NULL # for function debbuging
    ee <- expression(arg.check <- c(arg.check, tempo$problem) , checked.arg.names <- c(checked.arg.names, tempo$param.name))
    tempo <- fun_param_check(data = also.ordered, class = "logical", length = 1) ; eval(ee)
    if(any(arg.check) == TRUE){
        stop() # nothing else because print = TRUE by default in fun_param_check()
    }
    # source("C:/Users/Gael/Documents/Git_versions_to_use/debugging_tools_for_r_dev-v1.2/r_debugging_tools-v1.2.R") ; eval(parse(text = str_basic_arg_check_dev)) ; eval(parse(text = str_arg_check_with_fun_param_check_dev)) # activate this line and use the function to check arguments status and if they have been checked using fun_param_check()
    if(also.ordered == FALSE){
        if( ! (all(class(data) == "data.frame") | all(class(data) == "factor"))){
            tempo.cat <- paste0("\n\n================\n\nERROR IN fun_refactorization(): data ARGUMENT MUST BE A FACTOR (NON ORDERED BECAUSE THE also.ordered ARGUMENT IS SET TO FALSE) OR A DATA FRAME\n\n================\n\n")
            stop(tempo.cat)
        }
    }
    if(also.ordered == TRUE){
        if( ! (all(class(data) == "data.frame") | all(class(data) == "factor") | all(class(data) %in% c("ordered", "factor")))){
            tempo.cat <- paste0("\n\n================\n\nERROR IN fun_refactorization(): data ARGUMENT MUST BE A FACTOR OR A DATA FRAME\n\n================\n\n")
            stop(tempo.cat)
        }
    }
    # end argument checking
    text <- NULL
    if(all(class(data) == "factor")){
        tempo.keep.log <- levels(data) %in% unique(data)
        text <- levels(data)[ ! tempo.keep.log]
        data <- factor(data, levels = levels(data)[tempo.keep.log])
    }else if(all(class(data) %in% c("ordered", "factor"))){
        tempo.keep.log <- levels(data) %in% unique(data)
        text <- levels(data)[ ! tempo.keep.log]
        data <- ordered(data, levels = levels(data)[tempo.keep.log])
    }else if(all(class(data) == "data.frame")){
        text <- vector("list", length(data))
        names(text) <- names(data)
        tempo.factor.col <- sapply(sapply(lapply(data, class), FUN = "%in%", "factor"), FUN = "all") # get the factor column (logical)
        for(i in 1:length(tempo.factor.col)){
            if(tempo.factor.col[i] == TRUE){
                tempo.keep.log <- levels(data[[i]]) %in% unique(data[[i]])
                text[[i]] <- levels(data[[i]])[ ! tempo.keep.log]
                data[[i]] <- factor(data[[i]], levels = levels(data[[i]])[tempo.keep.log])
            }
        }
        tempo.ordered.col <- sapply(sapply(lapply(data, class), FUN = "%in%", "ordered"), FUN = "any") # get the ordered factor column (logical) if they exist
        if(also.ordered == TRUE){
            for(i in 1:length(tempo.ordered.col)){
                if(tempo.ordered.col[i] == TRUE){
                    tempo.keep.log <- levels(data[[i]]) %in% unique(data[[i]])
                    text[[i]] <- levels(data[[i]])[ ! tempo.keep.log]
                    data[[i]] <- ordered(data[[i]], levels = levels(data[[i]])[tempo.keep.log])
                }
            }
        }
        text <- text[(tempo.factor.col | tempo.ordered.col) & ! (sapply(text, FUN = length) == 0)] # remove the compartments of text that are not modified factors columns of data frame
    }
    output <- list(data = data, removed = text)
    return(output)
Gael  MILLOT's avatar
Gael MILLOT committed
1216
1217
1218
1219
1220
1221
1222
1223
}


######## fun_rounding() #### Rounding number if decimal present


# Check OK: clear to go Apollo
fun_rounding <- function(data, dec.nb = 2, after.lead.zero = TRUE){
Gael  MILLOT's avatar
Gael MILLOT committed
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
    # AIM:
    # round a vector of values, if decimal, with the desired number of decimal digits after the decimal leading zeros
    # BEWARE
    # Work well with numbers as character strings, but not always with numerical numbers because of the floating point
    # Numeric values are really truncated from a part of their decimal digits, whatever options(digits) settings
    # ARGUMENTS
    # data: a vector of numbers (numeric or character mode)
    # dec.nb: number of required decimal digits
    # after.lead.zero: logical. If FALSE, rounding is performed for all the decimal numbers, whatever the leading zeros (e.g., 0.123 -> 0.12 and 0.00128 -> 0.00). If TRUE, dec.nb are taken after the leading zeros (e.g., 0.123 -> 0.12 and 0.00128 -> 0.0013)
    # REQUIRED FUNCTIONS
    # fun_param_check()
    # RETURN
    # the modified vector
    # EXAMPLES
    # cat(fun_rounding(data = c(10, 100.001, 333.0001254, 12312.1235), dec.nb = 2, after.lead.zero = FALSE))
    # cat(fun_rounding(data = c("10", "100.001", "333.0001254", "12312.1235"), dec.nb = 2, after.lead.zero = FALSE))
    # DEBUGGING
    # data = data = c(10, 100.001, 333.0001254, 12312.1235) ; dec.nb = 2 ; after.lead.zero = FALSE # # for function debugging
    # data = data = c("10", "100.001", "333.0001254", "12312.1235") ; dec.nb = 2 ; after.lead.zero = TRUE # # for function debugging
    # argument checking
    if( ! (all(typeof(data) == "character") | all(typeof(data) == "double") | all(typeof(data) == "integer"))){
        tempo.cat <- paste0("\n\n================\n\nERROR IN fun_rounding(): data ARGUMENT MUST BE A VECTOR OF NUMBERS (IN NUMERIC OR CHARACTER MODE)\n\n================\n\n")
        stop(tempo.cat)
    }
    arg.check <- NULL # for function debbuging
    checked.arg.names <- NULL # for function debbuging
    ee <- expression(arg.check <- c(arg.check, tempo$problem) , checked.arg.names <- c(checked.arg.names, tempo$param.name))
    tempo <- fun_param_check(data = dec.nb, typeof = "integer", length = 1, double.as.integer.allowed = TRUE, neg.values = FALSE) ; eval(ee)
    tempo <- fun_param_check(data = after.lead.zero, class = "logical", length = 1) ; eval(ee)
    if(any(arg.check) == TRUE){
        stop() # nothing else because print = TRUE by default in fun_param_check()
    }
    # source("C:/Users/Gael/Documents/Git_versions_to_use/debugging_tools_for_r_dev-v1.2/r_debugging_tools-v1.2.R") ; eval(parse(text = str_basic_arg_check_dev)) ; eval(parse(text = str_arg_check_with_fun_param_check_dev)) # activate this line and use the function to check arguments status and if they have been checked using fun_param_check()
    # end argument checking
    tempo <- grepl(x = data, pattern = "\\.") # detection of decimal numbers
    ini.mode <- mode(data)
    data <- as.character(data) # to really truncate decimal digits
    for(i in 1:length(data)){ # scan all the numbers of the vector
        if(tempo[i] == TRUE){ # means decimal number
            if(after.lead.zero == TRUE){
                zero.pos <- unlist(gregexpr(text=data[i], pattern = 0)) # recover all the position of the zeros in the number. -1 if no zeros (do not record the leading and trailing zeros)
            }else{
                zero.pos <- -1 # -1 as if no zero
            }
            dot.pos <- unlist(gregexpr(text=data[i], pattern = "\\.")) # recover all the position of the zeros in the number
            digit.pos <- unlist(gregexpr(text=data[i], pattern = "[[:digit:]]")) # recover all the position of the digits in the number
            dec.pos <- digit.pos[digit.pos > dot.pos]
            count <- 0
            while((dot.pos + count + 1) %in% zero.pos & (dot.pos + count + 1) <= max(dec.pos) & (count + dec.nb) < length(dec.pos)){ # count the number of leading zeros in the decimal part
                count <- count + 1
            }
            data[i] <- formatC(as.numeric(data[i]), digits = (count + dec.nb), format = "f")
        }
    }
    if(ini.mode != "character"){
        data <- as.numeric(data)
    }
    return(data)
}


######## fun_90clock_matrix_rot() #### 90 clockwise matrix rotation
Gael  MILLOT's avatar
Gael MILLOT committed
1286
1287
1288
1289


# Check OK: clear to go Apollo
fun_90clock_matrix_rot <- function(data){
Gael  MILLOT's avatar
Gael MILLOT committed
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
    # AIM:
    # 90 clockwise matrix rotation
    # applied twice, the function provide the mirror matrix, according to vertical and horizontal symmetry
    # REQUIRED FUNCTIONS
    # fun_param_check()
    # ARGUMENTS
    # data: matrix (matrix class)
    # RETURN
    # the modified matrix
    # EXAMPLES
    # obs <- matrix(1:10, ncol = 1) ; obs ; fun_90clock_matrix_rot(obs)
    # obs <- matrix(LETTERS[1:10], ncol = 5) ; obs ; fun_90clock_matrix_rot(obs)
    # DEBUGGING
    # data = matrix(1:10, ncol = 1)
    # required function checking
    if(length(find("fun_param_check", mode = "function")) == 0){
        tempo.cat <- paste0("\n\n================\n\nERROR IN fun_90clock_matrix_rot(): REQUIRED fun_param_check() FUNCTION IS MISSING IN THE R ENVIRONMENT\n\n================\n\n")
        stop(tempo.cat)
    }
    # end required function checking
    # argument checking
    # source("C:/Users/Gael/Documents/Git_versions_to_use/debugging_tools_for_r_dev-v1.2/r_debugging_tools-v1.2.R") ; eval(parse(text = str_basic_arg_check_dev)) # activate this line and use the function to check arguments status and if they have been checked using fun_param_check()
    if( ! any(class(data) %in% "matrix")){
        tempo.cat <- paste0("\n\n================\n\nERROR IN fun_90clock_matrix_rot(): THE data ARGUMENT MUST BE A MATRIX\n\n================\n\n")
        stop(tempo.cat)
    }
    # end argument checking
    for (i in 1:ncol(data)){data[,i] <- rev(data[,i])}
    data <- t(data)
    return(data)
Gael  MILLOT's avatar
Gael MILLOT committed
1320
1321
1322
1323
1324
1325
1326
1327
}


######## fun_hexa_hsv_color_matrix() #### Conversion of a numeric matrix into hexadecimal color matrix


# Check OK: clear to go Apollo
fun_hexa_hsv_color_matrix <- function(mat1, mat.hsv.h = TRUE, notch = 1, s = 1, v = 1, forced.color = NULL){
Gael  MILLOT's avatar
Gael MILLOT committed
1328
1329
1330
1331
1332
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
1411
1412
1413
1414
1415
1416
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
    # AIM:
    # convert a matrix made of numbers into a hexadecimal matrix for rgb colorization
    # REQUIRED FUNCTIONS
    # fun_param_check()
    # ARGUMENTS:
    # mat1: matrix 1 of non negative numerical values that has to be colored (matrix class). NA allowed
    # mat.hsv.h: logical. Is mat1 the h of hsv colors ? (if TRUE, mat1 must be between zero and 1)
    # notch: single value between 0 and 1 to shift the successive colors on the hsv circle by + notch
    # s: s argument of hsv(). Must be between 0 and 1
    # v: v argument of hsv(). Must be between 0 and 1
    # forced.color: Must be NULL or hexadecimal color code or name given by colors(). The first minimal values of mat1 will be these colors. All the color of mat1 can be forced using this argument
    # RETURN
    # a list containing:
    # $mat1.name: name of mat1
    # $colored.mat: colors of mat1 in hexa
    # $problem: logical. Is any colors of forced.color overlap the colors designed by the function. NULL if forced.color = NULL
    # $text.problem: text when overlapping colors. NULL if forced.color = NULL or problem == FALSE
    # EXAMPLES
    # mat1 = matrix(c(1,1,1,2,1,5,9,NA), ncol = 2) ; dimnames(mat1) <- list(LETTERS[1:4], letters[1:2]) ; fun_hexa_hsv_color_matrix(mat1, mat.hsv.h = FALSE, notch = 1, s = 1, v = 1, forced.color = NULL)
    # DEBUGGING
    # mat1 = matrix(c(1,1,1,2,1,5,9,NA), ncol = 2) ; dimnames(mat1) <- list(LETTERS[1:4], letters[1:2]); mat.hsv.h = FALSE ; notch = 1 ; s = 1 ; v = 1 ; forced.color = c(hsv(1,1,1), hsv(0,0,0)) # for function debugging
    # required function checking
    if(length(find("fun_param_check", mode = "function")) == 0){
        tempo.cat <- paste0("\n\n================\n\nERROR IN fun_hexa_hsv_color_matrix(): REQUIRED fun_param_check() FUNCTION IS MISSING IN THE R ENVIRONMENT\n\n================\n\n")
        stop(tempo.cat)
    }
    # end required function checking
    # argument checking
    arg.check <- NULL # for function debbuging
    checked.arg.names <- NULL # for function debbuging
    ee <- expression(arg.check <- c(arg.check, tempo$problem) , checked.arg.names <- c(checked.arg.names, tempo$param.name))
    tempo <- fun_param_check(data = mat1, mode = "numeric", class = "matrix", na.contain = TRUE, neg.values = FALSE) ; eval(ee)
    tempo <- fun_param_check(data = mat.hsv.h, class = "logical", length = 1) ; eval(ee)
    tempo <- fun_param_check(data = notch, mode = "numeric", length = 1, prop = TRUE) ; eval(ee)
    tempo <- fun_param_check(data = s, mode = "numeric", length = 1, prop = TRUE) ; eval(ee)
    tempo <- fun_param_check(data = v, mode = "numeric", length = 1, prop = TRUE) ; eval(ee)
    if(any(arg.check) == TRUE){
        stop() # nothing else because print = TRUE by default in fun_param_check()
    }
    # source("C:/Users/Gael/Documents/Git_versions_to_use/debugging_tools_for_r_dev-v1.2/r_debugging_tools-v1.2.R") ; eval(parse(text = str_basic_arg_check_dev)) ; eval(parse(text = str_arg_check_with_fun_param_check_dev)) # activate this line and use the function to check arguments status and if they have been checked using fun_param_check()
    if(mat.hsv.h == TRUE & fun_param_check(data = mat1, mode = "numeric", prop = TRUE, print = FALSE)$problem == TRUE){
        tempo.cat <- paste0("\n\n================\n\nERROR IN fun_hexa_hsv_color_matrix(): mat1 ARGUMENT MUST BE A MATRIX OF PROPORTIONS SINCE THE mat.hsv.h ARGUMENT IS SET TO TRUE\n\n================\n\n")
        stop(tempo.cat)
    }
    if( ! is.null(forced.color)){
        tempo <- fun_param_check(data = forced.color, class = "character")
        if(tempo$problem == TRUE){
            stop()
        }
        if( ! all(forced.color %in% colors() | grepl(pattern = "^#", forced.color))){ # check that all strings of forced.color start by #
            tempo.cat <- paste0("\n\n================\n\nERROR IN fun_hexa_hsv_color_matrix(): forced.color ARGUMENT MUST BE A HEXADECIMAL COLOR VECTOR STARTING BY # AND/OR COLOR NAMES GIVEN BY colors()\n\n================\n\n")
            stop(tempo.cat)
        }
    }
    # end argument checking
    problem <- NULL
    text.problem <- NULL
    mat1.name <- deparse(substitute(mat1))
    # change the scale of the plotted matrix
    if(mat.hsv.h == TRUE){
        if(any(min(mat1, na.rm = TRUE) < 0 | max(mat1, na.rm = TRUE) > 1, na.rm = TRUE)){
            tempo.cat <- paste0("\n\n================\n\nERROR IN fun_hexa_hsv_color_matrix(): mat1 MUST BE MADE OF VALUES BETWEEN 0 AND 1 BECAUSE mat.hsv.h ARGUMENT SET TO TRUE\n\n================\n\n")
            stop(tempo.cat)
        }
    }else{
        if(any(mat1 - floor(mat1) > 0, na.rm = TRUE) | any(mat1 == 0, na.rm = TRUE)){
            tempo.cat <- paste0("\n\n================\n\nERROR IN fun_hexa_hsv_color_matrix(): mat1 MUST BE MADE OF INTEGER VALUES WITHOUT 0 BECAUSE mat.hsv.h ARGUMENT SET TO FALSE\n\n================\n\n")
            stop(tempo.cat)
        }else{
            mat1 <- mat1 / max(mat1, na.rm = TRUE)
        }
    }
    if(notch != 1){
        different.color <- unique(as.vector(mat1))
        different.color <- different.color[ ! is.na(different.color)]
        tempo.different.color <- different.color + c(0, cumsum(rep(notch, length(different.color) - 1)))
        tempo.different.color <- tempo.different.color - floor(tempo.different.color)
        if(any(duplicated(tempo.different.color) == TRUE)){
            tempo.cat <- paste0("\n\n================\n\nERROR IN fun_hexa_hsv_color_matrix(): DUPLICATED VALUES AFTER USING notch (", paste(tempo.different.color[duplicated(tempo.different.color)], collapse = " "), "). TRY ANOTHER notch VALUE\n\n================\n\n")
            stop(tempo.cat)
        }else if(length(different.color) != length(tempo.different.color)){
            tempo.cat <- paste0("\n\n================\n\nERROR IN fun_hexa_hsv_color_matrix(): LENGTH OF different.color (", paste(different.color, collapse = " "), ") DIFFERENT FROM LENGTH OF tempo.different.color (", paste(tempo.different.color, collapse = " "), ")\n\n================\n\n")
            stop(tempo.cat)
        }else{
            for(i in 1:length(different.color)){
                mat1[mat1 == different.color[i]] <- tempo.different.color[i]
            }
        }
    }
    if( ! is.null(forced.color)){
        hexa.values.to.change <- hsv(unique(sort(mat1))[1:length(forced.color)], s, v)
    }
    mat1[ ! is.na(mat1)] <- hsv(mat1[ ! is.na(mat1)], s, v)
    if( ! is.null(forced.color)){
        if(any(forced.color %in% mat1, na.rm = TRUE)){
            problem <- TRUE
            text.problem <- paste0("THE FOLLOWING COLORS WHERE INTRODUCED USING forced.color BUT WHERE ALREADY PRESENT IN THE COLORED MATRIX :", paste(forced.color[forced.color %in% mat1], collapse = " "))
        }else{
            problem <- FALSE
        }
        for(i in 1:length(hexa.values.to.change)){
            if( ! any(mat1 == hexa.values.to.change[i], na.rm = TRUE)){
                tempo.cat <- paste0("\n\n================\n\nERROR IN fun_hexa_hsv_color_matrix(): THE ", hexa.values.to.change[i], " VALUE FROM hexa.values.to.change IS NOT REPRESENTED IN mat1 : ", paste(unique(as.vector(mat1)), collapse = " "), "\n\n================\n\n")
                stop(tempo.cat)
            }else{
                mat1[which(mat1 == hexa.values.to.change[i])] <- forced.color[i]
            }
        }
    }
    output <- list(mat1.name = mat1.name, colored.mat = mat1, problem = problem, text.problem = text.problem)
    return(output)
}


######## fun_by_case_matrix_op() #### assembling of several matrices with operation


# Check OK: clear to go Apollo
fun_by_case_matrix_op <- function(mat.list, kind.of.operation = "+"){
    # AIM:
    # assemble several matrices of same dimensions by performing by case operation. For instance add the value of all the case 1 (row1 & column1) of the matrices and put it in the case 1 of a new matrix M, add the value of all the case 2 (row2 & column1) of the matrices and put it in the case 2 of a new matrix M, etc.
    
    # c: case
    # i: row number
    # j: column number
    # k: matrix number
    # z: number of matrices
    # REQUIRED FUNCTIONS
    # fun_param_check()
    # fun_2D_comp()
    # ARGUMENTS:
    # mat.list: list of matrices
    # kind.of.operation: either "+" (by case addition), "-" (by case subtraction) or "*" (by case multiplication)
    # RETURN
    # the assembled matrix, with row and/or column names only if all the matrices have identical row/column names
    # EXAMPLES
    # mat1 = matrix(c(1,1,1,2,1,5,9,8), ncol = 2) ; mat2 = matrix(c(1,1,1,2,1,5,9,NA), ncol = 2) ; fun_by_case_matrix_op(mat.list = list(mat1, mat2), kind.of.operation = "+")
    # mat1 = matrix(c(1,1,1,2,1,5,9,8), ncol = 2, dimnames = list(LETTERS[1:4], letters[1:2])) ; mat2 = matrix(c(1,1,1,2,1,5,9,NA), ncol = 2, dimnames = list(LETTERS[1:4], letters[1:2])) ; fun_by_case_matrix_op(mat.list = list(mat1, mat2), kind.of.operation = "*")
    # mat1 = matrix(c(1,1,1,2,1,5,9,8), ncol = 2, dimnames = list(LETTERS[1:4], c(NA, NA))) ; mat2 = matrix(c(1,1,1,2,1,5,9,NA), ncol = 2, dimnames = list(LETTERS[1:4], letters[1:2])) ; fun_by_case_matrix_op(mat.list = list(mat1, mat2), kind.of.operation = "-")
    # mat1 = matrix(c(1,1,1,2,1,5,9,8), ncol = 2, dimnames = list(c("A1", "A2", "A3", "A4"), letters[1:2])) ; mat2 = matrix(c(1,1,1,2,1,5,9,NA), ncol = 2, dimnames = list(LETTERS[1:4], letters[1:2])) ; mat3 = matrix(c(1,1,1,2,1,5,9,NA), ncol = 2, dimnames = list(LETTERS[1:4], letters[1:2])) ; fun_by_case_matrix_op(mat.list = list(mat1, mat2, mat3), kind.of.operation = "+")
    # DEBUGGING
    # mat1 = matrix(c(1,1,1,2,1,5,9,8), ncol = 2) ; mat2 = matrix(c(1,1,1,2,1,5,9,NA), ncol = 2) ; mat.list = list(mat1, mat2) ; kind.of.operation = "+" # for function debugging
    # mat1 = matrix(c(1,1,1,2,1,5,9,8), ncol = 2, dimnames = list(LETTERS[1:4], c(NA, NA))) ; mat2 = matrix(c(1,1,1,2,1,5,9,NA), ncol = 2, dimnames = list(LETTERS[1:4], letters[1:2])) ; mat.list = list(mat1, mat2) ; kind.of.operation = "*" # for function debugging
    # required function checking
    if(length(find("fun_param_check", mode = "function")) == 0){
        tempo.cat <- paste0("\n\n================\n\nERROR IN fun_by_case_matrix_op(): REQUIRED fun_param_check() FUNCTION IS MISSING IN THE R ENVIRONMENT\n\n================\n\n")
        stop(tempo.cat)
    }
    if(length(find("fun_param_check", mode = "function")) == 0){
        tempo.cat <- paste0("\n\n================\n\nERROR IN fun_by_case_matrix_op(): REQUIRED fun_2D_comp() FUNCTION IS MISSING IN THE R ENVIRONMENT\n\n================\n\n")
        stop(tempo.cat)
    }
    # end required function checking
    # argument checking
    arg.check <- NULL # for function debbuging
    checked.arg.names <- NULL # for function debbuging
    ee <- expression(arg.check <- c(arg.check, tempo$problem) , checked.arg.names <- c(checked.arg.names, tempo$param.name))
    tempo <- fun_param_check(data = mat.list, class = "list") ; eval(ee)
    tempo <- fun_param_check(data = kind.of.operation, options = c("+", "-", "*"), length = 1) ; eval(ee)
    if(any(arg.check) == TRUE){
        stop() # nothing else because print = TRUE by default in fun_param_check()
    }
    # source("C:/Users/Gael/Documents/Git_versions_to_use/debugging_tools_for_r_dev-v1.2/r_debugging_tools-v1.2.R") ; eval(parse(text = str_basic_arg_check_dev)) ; eval(parse(text = str_arg_check_with_fun_param_check_dev)) # activate this line and use the function to check arguments status and if they have been checked using fun_param_check()
    if(length(mat.list) < 2){
        tempo.cat <- paste0("\n\n================\n\nERROR IN fun_by_case_matrix_op(): mat.list ARGUMENT MUST BE A LIST CONTAINING AT LEAST 2 MATRICES\n\n================\n\n")
        stop(tempo.cat)
    }
    for(i0 in 1:length(mat.list)){
        tempo <- fun_param_check(data = mat.list[[i0]], class = "matrix", mode = "numeric", na.contain = TRUE)
        if(tempo$problem == TRUE){
            tempo.cat <- paste0("\n\n================\n\nERROR IN fun_by_case_matrix_op(): ELEMENT ", i0, " OF mat.list ARGUMENT MUST BE A NUMERIC MATRIX\n\n================\n\n")
            stop(tempo.cat)
        }
    }
    ident.row.names <- TRUE
    ident.col.names <- TRUE
    for(i0 in 2:length(mat.list)){
        tempo <- fun_2D_comp(data1 =  mat.list[[1]], data2 =  mat.list[[i0]])
        if(tempo$same.dim == FALSE){
            tempo.cat <- paste0("\n\n================\n\nERROR IN fun_by_case_matrix_op(): MATRIX ", i0, " OF mat.list ARGUMENT MUST HAVE THE SAME DIMENSION (", paste(dim(mat.list[[i0]]), collapse = " "), ") THAN THE MATRIX 1 IN mat.list (", paste(dim(mat.list[[1]]), collapse = " "), ")\n\n================\n\n")
            stop(tempo.cat)
        }
        if( ! is.null(tempo$same.row.name)){
            if(tempo$same.row.name != TRUE){ # != TRUE to deal with NA
                ident.row.names <- FALSE
            }
        }
        if( ! is.null(tempo$same.col.name)){
            if(tempo$same.col.name != TRUE){ # != TRUE to deal with NA
                ident.col.names <- FALSE
            }
        }
    }
    # end argument checking
    output <- mat.list[[1]]
    for(i0 in 2:length(mat.list)){
        output <- get(kind.of.operation)(output, mat.list[[i0]])
    }
    dimnames(output) <- NULL
    if(ident.row.names == TRUE){
        rownames(output) <- rownames(mat.list[[1]])
    }
    if(ident.col.names == TRUE){
        colnames(output) <- colnames(mat.list[[1]])
    }
    return(output)
Gael  MILLOT's avatar
Gael MILLOT committed
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
}


################ Graphics


# this order can be used:
# fun_window_width_resizing()
# fun_open_window()
# fun_graph_param_prior_plot() # not for ggplot2
# plot() or any other plotting
# fun_feature_post_plot() if fun_graph_param_prior_plot() has been used # not for ggplot2
# fun_close_specif_window()


######## fun_window_width_resizing() #### window width depending on classes to plot


# Check OK: clear to go Apollo
fun_window_width_resizing <- function(class.nb, inches.per.class.nb = 1, ini.window.width = 7, inch.left.space, inch.right.space, boundarie.space = 0.5){
Gael  MILLOT's avatar
Gael MILLOT committed
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
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
    # AIM:
    # rescale the width of a window to open depending on the number of classes to plot
    # can be used for height, considering that it is as if it was a width
    # this order can be used:
    # fun_window_width_resizing()
    # fun_open_window()
    # fun_graph_param_prior_plot() # not for ggplot2
    # plot() or any other plotting
    # fun_feature_post_plot() if fun_graph_param_prior_plot() has been used # not for ggplot2
    # fun_close_specif_window()
    # REQUIRED FUNCTIONS
    # fun_param_check()
    # ARGUMENTS
    # class.nb: number of class to plot
    # inches.per.class.nb: number of inches per unit of class.nb. 2 means 2 inches for each boxplot for instance
    # ini.window.width:initial window width in inches
    # inch.left.space: left horizontal margin of the figure region (in inches)
    # inch.right.space: right horizontal margin of the figure region (in inches)
    # boundarie.space: space between the right and left limits of the plotting region and the plot (0.5 means half a class width)
    # RETURN
    # the new window width in inches
    # EXAMPLES
    # fun_window_width_resizing(class.nb = 10, inches.per.class.nb = 0.2, ini.window.width = 7, inch.left.space = 1, inch.right.space = 1, boundarie.space = 0.5)
    # DEBUGGING
    # class.nb = 10 ; inches.per.class.nb = 0.2 ; ini.window.width = 7 ; inch.left.space = 1 ; inch.right.space = 1 ; boundarie.space = 0.5 # for function debugging
    # required function checking
    if(length(find("fun_param_check", mode = "function")) == 0){
        tempo.cat <- paste0("\n\n================\n\nERROR IN fun_window_width_resizing(): REQUIRED fun_param_check() FUNCTION IS MISSING IN THE R ENVIRONMENT\n\n================\n\n")
        stop(tempo.cat)
    }
    # end required function checking
    # argument checking
    arg.check <- NULL # for function debbuging
    checked.arg.names <- NULL # for function debbuging
    ee <- expression(arg.check <- c(arg.check, tempo$problem) , checked.arg.names <- c(checked.arg.names, tempo$param.name))
    tempo <- fun_param_check(data = class.nb, typeof = "integer", length = 1, double.as.integer.allowed = TRUE, neg.values = FALSE) ; eval(ee)
    tempo <- fun_param_check(data = inches.per.class.nb, mode = "numeric", length = 1, neg.values = FALSE) ; eval(ee)
    tempo <- fun_param_check(data = ini.window.width, mode = "numeric", length = 1, neg.values = FALSE) ; eval(ee)
    tempo <- fun_param_check(data = inch.left.space, mode = "numeric", length = 1, neg.values = FALSE) ; eval(ee)
    tempo <- fun_param_check(data = inch.right.space, mode = "numeric", length = 1, neg.values = FALSE) ; eval(ee)
    tempo <- fun_param_check(data = boundarie.space, mode = "numeric", length = 1, neg.values = FALSE) ; eval(ee)
    if(any(arg.check) == TRUE){
        stop() # nothing else because print = TRUE by default in fun_param_check()
    }
    # source("C:/Users/Gael/Documents/Git_versions_to_use/debugging_tools_for_r_dev-v1.2/r_debugging_tools-v1.2.R") ; eval(parse(text = str_basic_arg_check_dev)) ; eval(parse(text = str_arg_check_with_fun_param_check_dev)) # activate this line and use the function to check arguments status and if they have been checked using fun_param_check()
    # end argument checking
    range.max <- class.nb + boundarie.space # the max range of the future plot
    range.min <- boundarie.space # the min range of the future plot
    window.width <- inch.left.space + inch.right.space + inches.per.class.nb * (range.max - range.min)
    return(window.width)
Gael  MILLOT's avatar
Gael MILLOT committed
1604
1605
1606
1607
1608
1609
1610
1611
}


######## fun_open_window() #### Open a GUI or pdf graphic window


# Check OK: clear to go Apollo
fun_open_window <- function(pdf.disp = TRUE, path.fun = "working.dir", pdf.name.file = "graph", width.fun = 7, height.fun = 7, paper = "special", no.pdf.overwrite = TRUE, return.output = FALSE){
Gael  MILLOT's avatar
Gael MILLOT committed
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
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
1700
1701
1702
1703
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
    # AIM:
    # open a pdf or screen (GUI) graphic window
    # BEWARE: on Linux, use pdf.disp = TRUE, if (GUI) graphic window is not always available, meaning that X is not installed (clusters for instance). Use X11() in R to test if available
    # this order can be used:
    # fun_window_width_resizing()
    # fun_open_window()
    # fun_graph_param_prior_plot() # not for ggplot2
    # plot() or any other plotting
    # fun_feature_post_plot() if fun_graph_param_prior_plot() has been used # not for ggplot2
    # fun_close_specif_window()
    # REQUIRED FUNCTIONS
    # fun_param_check()
    # ARGUMENTS:
    # pdf.disp: use pdf or not
    # path.fun: where the pdf is saved. Write "working.dir" if working directory is required (default)
    # pdf.name.file: name of the pdf file containing the graphs (the .pdf extension is added by the function)
    # width.fun: width of the windows (in inches)
    # height.fun: height of the windows (in inches)
    # paper: paper argument of the pdf function (paper format). Only used for pdf(). Either "a4", "letter", "legal", "us", "executive", "a4r", "USr" or "special". If "special", means that width.fun and height.fun specify the paper size
    # no.pdf.overwrite: existing pdf can be overwritten ? Only used if pdf.disp = TRUE
    # return.output: return output ? If TRUE but function not assigned, the output list is displayed
    # RETURN
    # a list containing:
    # $pdf.loc: path of the pdf created
    # $ini.par: initial par() parameters (to reset in a new graph)
    # $zone.ini: initial window spliting (to reset in a new graph)
    # EXAMPLES
    # fun_open_window(pdf.disp = FALSE, path.fun = "C:/Users/Gael/Desktop", pdf.name.file = "graph", width.fun = 7, height.fun = 7, paper = "special", no.pdf.overwrite = TRUE, return.output = TRUE)
    # DEBUGGING
    # pdf.disp = TRUE ; path.fun = "C:/Users/Gael/Desktop" ; pdf.name.file = "graphs" ; width.fun = 7 ; height.fun = 7 ; paper = "special" ; no.pdf.overwrite = TRUE ; return.output = TRUE # for function debugging
    # pdf.disp = TRUE ; path.fun = "/pasteur/homes/gmillot/" ; pdf.name.file = "graphs" ; width.fun = 7 ; height.fun = 7 ; paper = "special" ; no.pdf.overwrite = TRUE ; return.output = TRUE # for function debugging
    # required function checking
    if(length(find("fun_param_check", mode = "function")) == 0){
        tempo.cat <- paste0("\n\n================\n\nERROR IN fun_open_window(): REQUIRED fun_param_check() FUNCTION IS MISSING IN THE R ENVIRONMENT\n\n================\n\n")
        stop(tempo.cat)
    }
    # end required function checking
    # argument checking
    arg.check <- NULL # for function debbuging
    checked.arg.names <- NULL # for function debbuging
    ee <- expression(arg.check <- c(arg.check, tempo$problem) , checked.arg.names <- c(checked.arg.names, tempo$param.name))
    tempo <- fun_param_check(data = pdf.disp, class = "logical", length = 1) ; eval(ee)
    tempo <- fun_param_check(data = path.fun, class = "character", length = 1) ; eval(ee)
    tempo <- fun_param_check(data = pdf.name.file, class = "character", length = 1) ; eval(ee)
    tempo <- fun_param_check(data = width.fun, mode = "numeric", length = 1, neg.values = FALSE) ; eval(ee)
    tempo <- fun_param_check(data = height.fun, mode = "numeric", length = 1, neg.values = FALSE) ; eval(ee)
    tempo <- fun_param_check(data = path.fun, class = "character", length = 1) ; eval(ee)
    tempo <- fun_param_check(data = paper, options = c("a4", "letter", "legal", "us", "executive", "a4r", "USr", "special", "A4", "LETTER", "LEGAL", "US"), length = 1) ; eval(ee)
    tempo <- fun_param_check(data =no.pdf.overwrite, class = "logical", length = 1) ; eval(ee)
    tempo <- fun_param_check(data = return.output, class = "logical", length = 1) ; eval(ee)
    if(any(arg.check) == TRUE){
        stop() # nothing else because print = TRUE by default in fun_param_check()
    }
    # source("C:/Users/Gael/Documents/Git_versions_to_use/debugging_tools_for_r_dev-v1.2/r_debugging_tools-v1.2.R") ; eval(parse(text = str_basic_arg_check_dev)) ; eval(parse(text = str_arg_check_with_fun_param_check_dev)) # activate this line and use the function to check arguments status and if they have been checked using fun_param_check()
    # end argument checking
    if(path.fun == "working.dir"){
        path.fun <- getwd()
    }else{
        if(grepl(x = path.fun, pattern = ".+/$")){
            path.fun <- substr(path.fun, 1, nchar(path.fun) - 1) # remove the last /
        }
        if(dir.exists(path.fun) == FALSE){
            tempo.cat <- paste0("\n\n================\n\nERROR IN fun_open_window(): path.fun ARGUMENT DOES NOT CORRESPOND TO EXISTING DIRECTORY\n\n================\n\n")
            stop(tempo.cat)
        }
    }
    if(Sys.info()["sysname"] == "Windows"){ # Note that .Platform$OS.type() only says "unix" for macOS and Linux and "Windows" for Windows
        open.fail <- NULL
        windows()
        ini.par <- par(no.readonly = TRUE) # to recover the initial graphical parameters if required (reset). BEWARE: this command alone opens a pdf of GUI window if no window already opened. But here, protected with the code bacause always a tempo window opened
        invisible(dev.off()) # close the new window
    }else if(Sys.info()["sysname"] == "Linux"){
        if(pdf.disp == TRUE){
            if(file.exists(paste0(path.fun, "/recover_ini_par.pdf"))){
                tempo.cat <- paste0("\n\n================\n\nPROBLEM IN fun_open_window(): THIS FUNCTION CANNOT BE USED ON LINUX IF A recover_ini_par.pdf FILE ALREADY EXISTS HERE: ", paste(path.fun, collapse = " "), "\n\n================\n\n")
                stop(tempo.cat)
            }else{
                pdf(width = width.fun, height = height.fun, file=paste0(path.fun, "/recover_ini_par.pdf"), paper = paper)
                ini.par <- par(no.readonly = TRUE) # to recover the initial graphical parameters if required (reset). BEWARE: this command alone opens a pdf of GUI window if no window already opened. But here, protected with the code bacause always a tempo window opened
                invisible(dev.off()) # close the pdf windows
                file.remove(paste0(path.fun, "/recover_ini_par.pdf")) # remove the pdf file
            }
        }else{
            # test if X11 can be opened
            if(file.exists(paste0(getwd(), "/Rplots.pdf"))){
                tempo.cat <- paste0("\n\n================\n\nERROR IN fun_open_window(): THIS FUNCTION CANNOT BE USED ON LINUX IF A Rplots.pdf FILE ALREADY EXISTS HERE: ", getwd(), "\n\n================\n\n")
                stop(tempo.cat)
            }else{
                open.fail <- suppressWarnings(try(X11(), silent = TRUE))[] # try to open a X11 window. If open.fail == NULL, no problem, meaning that the X11 window is opened. If open.fail != NULL, a pdf can be opened here paste0(getwd(), "/Rplots.pdf")
                if(is.null(open.fail)){
                    ini.par <- par(no.readonly = TRUE) # to recover the initial graphical parameters if required (reset). BEWARE: this command alone opens a pdf of GUI window if no window already opened. But here, protected with the code bacause always a tempo window opened
                    invisible(dev.off()) # close the new window
                }else if(file.exists(paste0(getwd(), "/Rplots.pdf"))){
                    file.remove(paste0(getwd(), "/Rplots.pdf")) # remove the pdf file
                    tempo.cat <- ("\n\n================\n\nPROBLEM IN fun_open_window(): THIS FUNCTION CANNOT OPEN GUI ON LINUX OR NON MACOS UNIX SYSTEM (X GRAPHIC INTERFACE HAS TO BE SET).\nTO OVERCOME THIS, PLEASE SET pdf.disp ARGUMENT TO TRUE AND RERUN\n\n================\n\n")
                    stop(tempo.cat)
                }
            }
        }
    }else{
        open.fail <- NULL
        quartz()
        ini.par <- par(no.readonly = TRUE) # to recover the initial graphical parameters if required (reset). BEWARE: this command alone opens a pdf of GUI window if no window already opened. But here, protected with the code bacause always a tempo window opened
        invisible(dev.off()) # close the new window
    }
    zone.ini <- matrix(1, ncol=1) # to recover the initial parameters for next figure region when device region split into several figure regions
    if(pdf.disp == TRUE){
        pdf.loc <- paste0(path.fun, "/", pdf.name.file, ".pdf")
        if(file.exists(pdf.loc) == TRUE & no.pdf.overwrite == TRUE){
            tempo.cat <- paste0("\n\n================\n\nERROR IN fun_open_window(): pdf.loc FILE ALREADY EXISTS AND CANNOT BE OVERWRITTEN DUE TO no.pdf.overwrite ARGUMENT SET TO TRUE: ", pdf.loc, "\n\n================\n\n")
            stop(tempo.cat)
        }else{
            pdf(width = width.fun, height = height.fun, file=pdf.loc, paper = paper)
        }
    }else if(pdf.disp == FALSE){
        pdf.loc <- NULL
        if(Sys.info()["sysname"] == "Windows"){ # .Platform$OS.type() only says "unix" for macOS and Linux and "Windows" for Windows
            windows(width = width.fun, height = height.fun, rescale="fixed")
        }else if(Sys.info()["sysname"] == "Linux"){
            if( ! is.null(open.fail)){
                stop("\n\n================\n\nPROBLEM IN fun_open_window(): THIS FUNCTION CANNOT OPEN GUI ON LINUX OR NON MACOS UNIX SYSTEM (X GRAPHIC INTERFACE HAS TO BE SET).\nTO OVERCOME THIS, PLEASE SET pdf.disp ARGUMENT TO TRUE AND RERUN\n\n================\n\n")
            }else{
                X11(width = width.fun, height = height.fun)
            }
        }else{
            quartz(width = width.fun, height = height.fun)
        }
    }
    if(return.output == TRUE){
        output <- list(pdf.loc = pdf.loc, ini.par = ini.par, zone.ini = zone.ini)
        return(output)
    }
Gael  MILLOT's avatar
Gael MILLOT committed
1744
1745
1746
1747
1748
1749
1750
1751
}


######## fun_graph_param_prior_plot() #### Graph param before plotting


# Check OK: clear to go Apollo
fun_graph_param_prior_plot <- function(param.reinitial = FALSE, xlog.scale = FALSE, ylog.scale = FALSE, remove.label = TRUE, remove.x.axis = TRUE, remove.y.axis = TRUE, std.x.range = TRUE, std.y.range = TRUE, down.space = 1, left.space = 1, up.space = 1, right.space = 1, orient = 1, dist.legend = 3.5, tick.length = 0.5, box.type = "n", amplif.label = 1, amplif.axis = 1, display.extend = FALSE, return.par = FALSE){
Gael  MILLOT's avatar
Gael MILLOT committed
1752
1753
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
    # AIM:
    # very convenient to erase the axes for post plot axis redrawing using fun_feature_post_plot()
    # reinitialize and set the graphic parameters before plotting
    # CANNOT be used if no graphic device already opened
    # REQUIRED FUNCTIONS
    # fun_param_check()
    # ARGUMENTS
    # param.reinitial: reinitialize graphic parameters before applying the new ones, as defined by the other arguments? Either TRUE or FALSE
    # xlog.scale: Log scale for the x-axis? Either TRUE or FALSE. If TRUE, erases the x-axis, except legend, for further drawing by fun_feature_post_plot()(xlog argument of par())
    # ylog.scale: Log scale for the y-axis? Either TRUE or FALSE. If TRUE, erases the y-axis, except legend, for further drawing by fun_feature_post_plot()(ylog argument of par())
    # remove.label: remove labels (axis legend) of the two axes? Either TRUE or FALSE (ann argument of par())
    # remove.x.axis: remove x-axis except legend? Either TRUE or FALSE (control the xaxt argument of par()). Automately set to TRUE if xlog.scale == TRUE
    # remove.y.axis: remove y-axis except legend? Either TRUE or FALSE (control the yaxt argument of par()). Automately set to TRUE if ylog.scale == TRUE
    # std.x.range: standard range on the x-axis? TRUE (no range extend) or FALSE (4% range extend). Controls xaxs argument of par() (TRUE is xaxs = "i", FALSE is xaxs = "r")
    # std.y.range: standard range on the y-axis? TRUE (no range extend) or FALSE (4% range extend). Controls yaxs argument of par() (TRUE is yaxs = "i", FALSE is yaxs = "r")
    # down.space: lower vertical margin (in inches, mai argument of par())
    # left.space: left horizontal margin (in inches, mai argument of par())
    # up.space: upper vertical margin between plot region and grapical window (in inches, mai argument of par())
    # right.space: right horizontal margin (in inches, mai argument of par())
    # orient: scale number orientation (las argument of par()). 0, always parallel to the axis; 1, always horizontal; 2, always perpendicular to the axis; 3, always vertical
    # dist.legend: numeric value that moves axis legends away in inches (first number of mgp argument of par() but in inches thus / 0.2)
    # tick.length: length of the ticks (1 means complete the distance between the plot region and the axis numbers, 0.5 means half the length, etc. 0 means no tick
    # box.type: bty argument of par(). Either "o", "l", "7", "c", "u", "]", the resulting box resembles the corresponding upper case letter. A value of "n" suppresses the box
    # amplif.label: increase or decrease the size of the text in legends
    # amplif.axis: increase or decrease the size of the scale numbers in axis
    # display.extend: extend display beyond plotting region? Either TRUE or FALSE (xpd argument of par() without NA)
    # return.par: return graphic parameter modification?
    # RETURN
    # return graphic parameter modification
    # EXAMPLES
    # fun_graph_param_prior_plot(param.reinitial = FALSE, xlog.scale = FALSE, ylog.scale = FALSE, remove.label = TRUE, remove.x.axis = TRUE, remove.y.axis = TRUE, std.x.range = TRUE, std.y.range = TRUE, down.space = 1, left.space = 1, up.space = 1, right.space = 1, orient = 1, dist.legend = 4.5, tick.length = 0.5, box.type = "n", amplif.label = 1, amplif.axis = 1, display.extend = FALSE, return.par = FALSE)
    # DEBUGGING
    # param.reinitial = FALSE ; xlog.scale = FALSE ; ylog.scale = FALSE ; remove.label = TRUE ; remove.x.axis = TRUE ; remove.y.axis = TRUE ; std.x.range = TRUE ; std.y.range = TRUE ; down.space = 1 ; left.space = 1 ; up.space = 1 ; right.space = 1 ; orient = 1 ; dist.legend = 4.5 ; tick.length = 0.5 ; box.type = "n" ; amplif.label = 1 ; amplif.axis = 1 ; display.extend = FALSE ; return.par = FALSE # for function debugging
    # required function checking
    if(length(find("fun_param_check", mode = "function")) == 0){
        tempo.cat <- paste0("\n\n================\n\nERROR IN fun_graph_param_prior_plot(): REQUIRED fun_param_check() FUNCTION IS MISSING IN THE R ENVIRONMENT\n\n================\n\n")
        stop(tempo.cat)
    }
    # end required function checking
    # argument checking
    arg.check <- NULL # for function debbuging
    checked.arg.names <- NULL # for function debbuging
    ee <- expression(arg.check <- c(arg.check, tempo$problem) , checked.arg.names <- c(checked.arg.names, tempo$param.name))
    tempo <- fun_param_check(data = param.reinitial, class = "logical", length = 1) ; eval(ee)
    tempo <- fun_param_check(data = xlog.scale, class = "logical", length = 1) ; eval(ee)
    tempo <- fun_param_check(data = ylog.scale, class = "logical", length = 1) ; eval(ee)
    tempo <- fun_param_check(data = remove.label, class = "logical", length = 1) ; eval(ee)
    tempo <- fun_param_check(data = remove.x.axis, class = "logical", length = 1) ; eval(ee)
    tempo <- fun_param_check(data = remove.y.axis, class = "logical", length = 1) ; eval(ee)
    tempo <- fun_param_check(data = std.x.range, class = "logical", length = 1) ; eval(ee)
    tempo <- fun_param_check(data = std.y.range, class = "logical", length = 1) ; eval(ee)
Gael  MILLOT's avatar
Gael MILLOT committed
1803
1804
1805
1806
1807
1808
1809
    tempo <- fun_param_check(data = down.space, mode = "numeric", length = 1, neg.values = FALSE) ; eval(ee)
    tempo <- fun_param_check(data = left.space, mode = "numeric", length = 1, neg.values = FALSE) ; eval(ee)
    tempo <- fun_param_check(data = up.space, mode = "numeric", length = 1, neg.values = FALSE) ; eval(ee)
    tempo <- fun_param_check(data = right.space, mode = "numeric", length = 1, neg.values = FALSE) ; eval(ee)
    tempo <- fun_param_check(data = orient, mode = "numeric", length = 1, neg.values = FALSE) ; eval(ee)
    tempo <- fun_param_check(data = dist.legend, mode = "numeric", length = 1, neg.values = FALSE) ; eval(ee)
    tempo <- fun_param_check(data = tick.length, mode = "numeric", length = 1, prop = TRUE) ; eval(ee)
Gael  MILLOT's avatar
Gael MILLOT committed
1810
    tempo <- fun_param_check(data = box.type, options = c("o", "l", "7", "c", "u", "]", "n"), length = 1) ; eval(ee)
Gael  MILLOT's avatar
Gael MILLOT committed
1811
1812
    tempo <- fun_param_check(data = amplif.label, mode = "numeric", length = 1, neg.values = FALSE) ; eval(ee)
    tempo <- fun_param_check(data = amplif.axis, mode = "numeric", length = 1, neg.values = FALSE) ; eval(ee)
Gael  MILLOT's avatar
Gael MILLOT committed
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
    tempo <- fun_param_check(data = display.extend, class = "logical", length = 1) ; eval(ee)
    tempo <- fun_param_check(data = return.par, class = "logical", length = 1) ; eval(ee)
    if(any(arg.check) == TRUE){
        stop() # nothing else because print = TRUE by default in fun_param_check()
    }
    # source("C:/Users/Gael/Documents/Git_versions_to_use/debugging_tools_for_r_dev-v1.2/r_debugging_tools-v1.2.R") ; eval(parse(text = str_basic_arg_check_dev)) ; eval(parse(text = str_arg_check_with_fun_param_check_dev)) # activate this line and use the function to check arguments status and if they have been checked using fun_param_check()
    # end argument checking
    if(is.null(dev.list())){
        tempo.cat <- paste0("\n\n================\n\nERROR IN fun_graph_param_prior_plot(): THIS FUNCTION CANNOT BE USED IF NO GRAPHIC DEVICE ALREADY OPENED (dev.list() IS CURRENTLY NULL)\n\n================\n\n")
        stop(tempo.cat)
    }
    if(param.reinitial == TRUE){
        if( ! all(names(dev.cur()) == "null device")){
            active.wind.nb <- dev.cur()
        }else{
            active.wind.nb <- 0
        }
        if(Sys.info()["sysname"] == "Windows"){ # Note that .Platform$OS.type() only says "unix" for macOS and Linux and "Windows" for Windows
            windows()
            ini.par <- par(no.readonly = TRUE)  # to recover the initial graphical parameters if required (reset). BEWARE: this command alone opens a pdf of GUI window if no window already opened. But here, protected with the code bacause always a tempo window opened
            invisible(dev.off()) # close the new window
        }else if(Sys.info()["sysname"] == "Linux"){
            if(file.exists(paste0(getwd(), "/Rplots.pdf"))){
                tempo.cat <- paste0("\n\n================\n\nERROR IN fun_graph_param_prior_plot(): THIS FUNCTION CANNOT BE USED ON LINUX WITH param.reinitial SET TO TRUE IF A Rplots.pdf FILE ALREADY EXISTS HERE: ", getwd(), "\n\n================\n\n")
                stop(tempo.cat)
            }else{
                open.fail <- suppressWarnings(try(X11(), silent = TRUE))[] # try to open a X11 window. If open.fail == NULL, no problem, meaning that the X11 window is opened. If open.fail != NULL, a pdf can be opened here paste0(getwd(), "/Rplots.pdf")
                if(is.null(open.fail)){
                    ini.par <- par(no.readonly = TRUE) # to recover the initial graphical parameters if required (reset). BEWARE: this command alone opens a pdf of GUI window if no window already opened. But here, protected with the code bacause always a tempo window opened
                    invisible(dev.off()) # close the new window
                }else if(file.exists(paste0(getwd(), "/Rplots.pdf"))){
                    ini.par <- par(no.readonly = TRUE) # to recover the initial graphical parameters if required (reset). BEWARE: this command alone opens a pdf of GUI window if no window already opened. But here, protected with the code bacause always a tempo window opened
                    invisible(dev.off()) # close the new window
                    file.remove(paste0(getwd(), "/Rplots.pdf")) # remove the pdf file
                }else{
                    tempo.cat <- ("\n\n================\n\nPROBLEM IN fun_graph_param_prior_plot(): THIS FUNCTION CANNOT OPEN GUI ON LINUX OR NON MACOS UNIX SYSTEM (X GRAPHIC INTERFACE HAS TO BE SET).\nTO OVERCOME THIS, PLEASE USE PDF GRAPHIC INTERFACES AND RERUN\n\n================\n\n")
                    stop(tempo.cat)
                }
            }
        }else{ # macOS
            quartz()
            ini.par <- par(no.readonly = TRUE)  # to recover the initial graphical parameters if required (reset). BEWARE: this command alone opens a pdf of GUI window if no window already opened. But here, protected with the code bacause always a tempo window opened)
            invisible(dev.off()) # close the new window
        }
        if( ! all(names(dev.cur()) == "null device")){
            dev.set(active.wind.nb) # go back to the active windows if exists
            par(ini.par) # apply the initial par to current window
        }
    }
    if(remove.x.axis == TRUE){
        par(xaxt = "n") # suppress the y-axis label
    }else{
        par(xaxt = "s")
    }
    if(remove.y.axis == TRUE){
        par(yaxt = "n") # suppress the y-axis label
    }else{
        par(yaxt = "s")
    }
    if(std.x.range == TRUE){
        par(xaxs = "i")
    }else{
        par(xaxs = "r")
    }
    if(std.y.range == TRUE){
        par(yaxs = "i")
    }else{
        par(yaxs = "r")
    }
    par(mai = c(down.space, left.space, up.space, right.space), ann = ! remove.label, las = orient, mgp = c(dist.legend/0.2, 1, 0), xpd = display.extend, bty= box.type, cex.lab = amplif.label, cex.axis = amplif.axis)
    par(tcl = -par()$mgp[2] * tick.length) # tcl gives the length of the ticks as proportion of line text, knowing that mgp is in text lines. So the main ticks are a 0.5 of the distance of the axis numbers by default. The sign provides the side of the tick (negative for outside of the plot region)
    if(xlog.scale == TRUE){
        par(xaxt = "n", xlog = TRUE) # suppress the x-axis label
    }else{
        par(xlog = FALSE)
    }
    if(ylog.scale == TRUE){
        par(yaxt = "n", ylog = TRUE) # suppress the y-axis label
    }else{
        par(ylog = FALSE)
    }
    if(return.par == TRUE){
        tempo.par <- par()
        return(tempo.par)
    }
Gael  MILLOT's avatar
Gael MILLOT committed
1898
1899
1900
1901
1902
1903
1904
}


######## fun_feature_post_plot() #### Graph param after plotting


# Check OK: clear to go Apollo
Gael  MILLOT's avatar
Gael MILLOT committed
1905
fun_feature_post_plot <- function(x.side = 0, x.log.scale = FALSE, x.categ = NULL, x.categ.pos = NULL, x.lab = "", x.axis.magnific = 1.5, x.label.magnific = 1.5, x.dist.legend = 0.5, x.nb.inter.tick = 1, y.side = 0, y.log.scale = FALSE, y.categ = NULL, y.categ.pos = NULL, y.lab = "", y.axis.magnific = 1.5, y.label.magnific = 1.5, y.dist.legend = 0.5, y.nb.inter.tick = 1, text.angle = 90, tick.length = 0.5, sec.tick.length = 0.3, bg.color = NULL, grid.lwd = NULL, grid.col = "white", corner.text = "", magnific.corner.text = 1, just.label.add = FALSE, par.reset = FALSE, custom.par = NULL){
Gael  MILLOT's avatar
Gael MILLOT committed
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
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
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
    # AIM:
    # redesign axis. If x.side = 0, y.side = 0, the function just adds text at topright of the graph and reset par() for next graphics and provides outputs (see below)
    # provide also positions for legend or additional text on the graph
    # use fun_graph_param_prior_plot() before this function for initial inactivation of the axis drawings
    # REQUIRED FUNCTIONS
    # fun_param_check()
    # fun_open_window() to reinitialize graph parameters if par.reset = TRUE and custom.par = NULL
    # ARGUMENTS
    # x.side: axis at the bottom (1) or top (3) of the region figure. Write 0 for no change
    # x.log.scale: Log scale for the x-axis? Either TRUE or FALSE
    # x.categ: character vector representing the classes (levels()) to specify when the x-axis is qualititative(stripchart, boxplot)
    # x.categ.pos: position of the classes names (numeric vector of identical length than x.categ). If left NULL, this will be 1:length(levels())
    # x.lab: label of the x-axis. If x.side == 0 and x.lab != "", then x.lab is printed
    # x.axis.magnific: increase or decrease the value to increase or decrease the size of the x axis numbers. Also control the size of displayed categories
    # x.label.magnific: increase or decrease the value to increase or decrease the size of the x axis legend
    # x.dist.legend: increase the number to move x-axis legends away in inches (first number of mgp argument of par() but in inches)
    # x.nb.inter.tick: number of secondary ticks between main ticks on x-axis (only if not log scale). 0 means no secondary ticks
    # y.side: axis at the left (2) or right (4) of the region figure. Write 0 for no change
    # y.log.scale: Log scale for the y-axis? Either TRUE or FALSE
    # y.categ: classes (levels()) to specify when the y-axis is qualititative(stripchart, boxplot)
    # y.categ.pos: position of the classes names (numeric vector of identical length than y.categ). If left NULL, this will be 1:length(levels())
    # y.lab: label of the y-axis. If y.side == 0 and y.lab != "", then y.lab is printed
    # y.axis.magnific: increase or decrease the value to increase or decrease the size of the y axis numbers. Also control the size of displayed categories
    # y.label.magnific: increase or decrease the value to increase or decrease the size of the y axis legend
    # y.dist.legend: increase the number to move y-axis legends away in inches (first number of mgp argument of par() but in inches)
    # y.nb.inter.tick: number of secondary ticks between main ticks on y-axis (only if not log scale). 0 means non secondary ticks
    # text.angle: angle of the text when axis is qualitative
    # tick.length: length of the main ticks (1 means complete the distance between the plot region and the axis numbers, 0.5 means half the length, etc., 0 for no ticks)
    # sec.tick.length: length of the secondary ticks (1 means complete the distance between the plot region and the axis numbers, 0.5 means half the length, etc., 0 for no ticks)
    # bg.color: background color of the plot region. NULL for no color. BEWARE: cover/hide an existing plot !
    # grid.lwd: if non NULL, activate the grid line (specify the line width)
    # grid.col: grid line color (only if grid.lwd non NULL)
    # corner.text: text to add at the top right corner of the window
    # magnific.corner.text: increase or decrease the size of the text
    # par.reset: to reset all the graphics parameters. BEWARE: TRUE can generate display problems, mainly in graphic devices with multiple figure regions
    # just.label.add: just add axis labels (legend)? Either TRUE or FALSE. If TRUE, at least (x.side == 0 & x.lab != "") or (y.side == 0 & y.lab != "") must be set to display the corresponding x.lab or y.lab
    # custom.par: list that provides the parameters that reset all the graphics parameters. BEWARE: if NULL and par.reset == TRUE, the default par() parameters are used
    # RETURN
    # a list containing: 
    # $x.mid.left.dev.region: middle of the left margin of the device region, in coordinates of the x-axis
    # $x.left.dev.region: left side of the left margin (including the potential margin of the device region), in coordinates of the x-axis
    # $x.mid.right.dev.region: middle of the right margin of the device region, in coordinates of the x-axis
    # $x.right.dev.region: right side of the right margin (including the potential margin of the device region), in coordinates of the x-axis
    # $x.mid.left.fig.region: middle of the left margin of the figure region, in coordinates of the x-axis
    # $x.left.fig.region: left side of the left margin, in coordinates of the x-axis
    # $x.mid.right.fig.region: middle of the right margin of the figure region, in coordinates of the x-axis
    # $x.right.fig.region: right side of the right margin, in coordinates of the x-axis
    # $x.left.plot.region: left side of the plot region, in coordinates of the x-axis
    # $x.right.plot.region: right side of the plot region, in coordinates of the x-axis
    # $x.mid.plot.region: middle of the plot region, in coordinates of the x-axis
    # $y.mid.bottom.dev.region: middle of the bottom margin of the device region, in coordinates of the y-axis
    # $y.bottom.dev.region: bottom side of the bottom margin (including the potential margin of the device region), in coordinates of the y-axis
    # $y.mid.top.dev.region: middle of the top margin of the device region, in coordinates of the y-axis
    # $y.top.dev.region: top side of the top margin (including the potential margin of the device region), in coordinates of the y-axis
    # $y.mid.bottom.fig.region: middle of the bottom margin of the figure region, in coordinates of the y-axis
    # $y.bottom.fig.region: bottom of the bottom margin of the figure region, in coordinates of the y-axis
    # $y.mid.top.fig.region: middle of the top margin of the figure region, in coordinates of the y-axis
    # $y.top.fig.region: top of the top margin of the figure region, in coordinates of the y-axis
    # $y.top.plot.region: top of the plot region, in coordinates of the y-axis
    # $y.bottom.plot.region: bottom of the plot region, in coordinates of the y-axis
    # $y.mid.plot.region: middle of the plot region, in coordinates of the y-axis
    # $text: warning text
    # EXAMPLES
    # Example of log axis with log y-axis and unmodified x-axis:
    # prior.par <- fun_graph_param_prior_plot(param.reinitial = TRUE, xlog.scale = FALSE, ylog.scale = TRUE, remove.label = TRUE, remove.x.axis = FALSE, remove.y.axis = TRUE, down.space = 1, left.space = 1, up.space = 1, right.space = 1, orient = 1, dist.legend = 0.5, tick.length = 0.5, box.type = "n", amplif.label = 1, amplif.axis = 1, display.extend = FALSE, return.par = TRUE) ; plot(1:100, log = "y") ; fun_feature_post_plot(y.side = 2, y.log.scale = prior.par$ylog, x.lab = "Values", y.lab = "TEST", y.axis.magnific = 1.25, y.label.magnific = 1.5, y.dist.legend = 0.7, just.label.add = ! prior.par$ann)
    # Example of log axis with redrawn x-axis and y-axis:
    # prior.par <- fun_graph_param_prior_plot(param.reinitial = TRUE) ; plot(1:100) ; fun_feature_post_plot(x.side = 1, x.lab = "Values", y.side = 2, y.lab = "TEST", y.axis.magnific = 1, y.label.magnific = 2, y.dist.legend = 0.6)
    # example with margins in the device region:
    # windows(5,5) ; par(mai=c(0.5,0.5,0.5,0.5), omi = c(0.25,0.25,1,0.25), xaxs = "i", yaxs = "i") ; plot(0:10) ; a <- fun_feature_post_plot(x.side = 0, y.side = 0) ; x <- c(a$x.mid.left.dev.region, a$x.left.dev.region, a$x.mid.right.dev.region, a$x.right.dev.region, a$x.mid.left.fig.region, a$x.left.fig.region, a$x.mid.right.fig.region, a$x.right.fig.region, a$x.right.plot.region, a$x.left.plot.region, a$x.mid.plot.region) ; y <- c(a$y.mid.bottom.dev.region, a$y.bottom.dev.region, a$y.mid.top.dev.region, a$y.top.dev.region, a$y.mid.bottom.fig.region, a$