cute_little_R_functions.R 678 KB
Newer Older
Gael  MILLOT's avatar
Gael MILLOT committed
1
2
################################################################
##                                                            ##
Gael  MILLOT's avatar
Gael MILLOT committed
3
##     CUTE LITTLE R FUNCTIONS v6.0.0                         ##
Gael  MILLOT's avatar
Gael MILLOT committed
4
5
6
##                                                            ##
##     Gael A. Millot                                         ##
##                                                            ##
Gael  MILLOT's avatar
Gael MILLOT committed
7
##     Compatible with R v3.5.3                               ##
Gael  MILLOT's avatar
Gael MILLOT committed
8
9
10
11
12
##                                                            ##
################################################################



Gael  MILLOT's avatar
Gael MILLOT committed
13
14
# BEWARE: do not forget to save the modifications in the .R file (through RSTUDIO for indentation)

Gael  MILLOT's avatar
Gael MILLOT committed
15
# update graphic examples with good comment, as in barplot
Gael  MILLOT's avatar
Gael MILLOT committed
16
17
# Templates: https://prettydoc.statr.me/themes.html
# https://pkgdown.r-lib.org/
Gael  MILLOT's avatar
Gael MILLOT committed
18
# https://rdrr.io/github/gastonstat/cointoss/
Gael  MILLOT's avatar
Gael MILLOT committed
19
20
21
22

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


Gael  MILLOT's avatar
Gael MILLOT committed
23
################ Object analysis    2
Gael  MILLOT's avatar
Gael MILLOT committed
24
25
######## fun_param_check() #### check class, type, length, etc., of objects 2
######## fun_object_info() #### recover object information  8
Gael  MILLOT's avatar
Gael MILLOT committed
26
27
######## fun_1D_comp() #### comparison of two 1D datasets (vectors, factors, 1D tables) 9
######## fun_2D_comp() #### comparison of two 2D datasets (row & col names, dimensions, etc.)   13
Gael  MILLOT's avatar
Gael MILLOT committed
28
######## fun_2D_head() #### head of the left or right of big 2D objects 20
Gael  MILLOT's avatar
Gael MILLOT committed
29
30
31
32
33
######## fun_2D_tail() #### tail of the left or right of big 2D objects 21
######## fun_list_comp() #### comparison of two lists   22
################ Object modification    24
######## fun_name_change() #### check a vector of character strings and modify any string if present in another vector  24
######## fun_dataframe_remodeling() #### remodeling a data frame to have column name as a qualitative values and vice-versa 26
Gael  MILLOT's avatar
Gael MILLOT committed
34
######## fun_refactorization() #### remove classes that are not anymore present in factors or factor columns in data frames 29
Gael  MILLOT's avatar
Gael MILLOT committed
35
######## fun_round() #### rounding number if decimal present    31
Gael  MILLOT's avatar
Gael MILLOT committed
36
######## fun_90clock_matrix_rot() #### 90° clockwise matrix rotation    33
Gael  MILLOT's avatar
Gael MILLOT committed
37
38
######## fun_num2color_mat() #### convert a numeric matrix into hexadecimal color matrix    33
######## fun_by_case_matrix_op() #### assemble several matrices with operation  36
Gael  MILLOT's avatar
Gael MILLOT committed
39
######## fun_mat_inv() #### return the inverse of a square matrix   39
Gael  MILLOT's avatar
Gael MILLOT committed
40
41
######## fun_mat_fill() #### fill the empty half part of a symmetric square matrix  40
######## fun_consec_pos_perm() #### progressively breaks a vector order 43
Gael  MILLOT's avatar
Gael MILLOT committed
42
################ Graphics management    48
Gael  MILLOT's avatar
Gael MILLOT committed
43
######## fun_window_width_resizing() #### window width depending on classes to plot 48
Gael  MILLOT's avatar
Gael MILLOT committed
44
45
46
######## fun_open_window() #### open a GUI or pdf graphic window    49
######## fun_prior_plot() #### set graph param before plotting  53
######## fun_scale() #### select nice numbers when setting breaks on an axis    57
Gael  MILLOT's avatar
Gael MILLOT committed
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
######## fun_post_plot() #### set graph param after plotting    61
######## fun_close_specif_window() #### close specific graphic windows  72
################ Standard graphics  73
######## fun_empty_graph() #### text to display for empty graphs    74
################ gg graphics    75
######## fun_gg_palette() #### ggplot2 default color palette    75
######## fun_gg_just() #### ggplot2 justification of the axis labeling, depending on angle  76
######## fun_gg_point_rast() #### ggplot2 raster scatterplot layer  78
######## fun_gg_scatter() #### ggplot2 scatterplot + lines (up to 6 overlays totally)   82
######## fun_gg_bar_mean() #### ggplot2 mean barplot + overlaid dots if required    104
######## fun_gg_boxplot() #### ggplot2 boxplot + background dots if required    134
######## fun_gg_bar_prop() #### ggplot2 proportion barplot  139
######## fun_gg_strip() #### ggplot2 stripchart + mean/median   139
######## fun_gg_violin() #### ggplot2 violins   139
######## fun_gg_line() #### ggplot2 lines + background dots and error bars  140
######## fun_gg_heatmap() #### ggplot2 heatmap + overlaid mask if required  169
######## fun_gg_empty_graph() #### text to display for empty graphs 175
################ Graphic extraction 176
######## fun_var_trim_display() #### display values from a quantitative variable and trim according to defined cut-offs 176
######## fun_segmentation() #### segment a dot cloud on a scatterplot and define the dots from another cloud outside the segmentation   184
################ Import 216
######## fun_pack_import() #### check if R packages are present and import into the working environment 216
######## fun_python_pack_import() #### check if python packages are present 217
################ Exporting results (text & tables)  219
######## fun_report() #### print string or data object into output file 219
Gael  MILLOT's avatar
Gael MILLOT committed
72
73
74
75
76
77
78
79


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


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


Gael  MILLOT's avatar
Gael MILLOT committed
80
######## fun_param_check() #### check class, type, length, etc., of objects
Gael  MILLOT's avatar
Gael MILLOT committed
81
82
83


# Check OK: clear to go Apollo
Gael  MILLOT's avatar
Gael MILLOT committed
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
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, fun.name = NULL){
# 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 but numbers without decimal part?
# 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 FROM CUTE_LITTLE_R_FUNCTION
# 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 or "vector"
# 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?
# fun.name: name of the function when fun_param_check() is used to check its argument. If non NULL, name will be added into the error message returned by fun_param_check()
# 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)
# test <- 1:3 ; fun_param_check(data = test, print = TRUE, class = "vector", mode = "numeric")
# test <- matrix(1:3) ; fun_param_check(data = test, print = TRUE, class = "vector", mode = "numeric")
# DEBUGGING
119
# data = expression(TEST) ; data.name = NULL ; class = "vector" ; typeof = NULL ; mode = NULL ; length = 1 ; prop = NULL ; double.as.integer.allowed = FALSE ; options = NULL ; all.options.in.data = FALSE ; na.contain = FALSE ; neg.values = TRUE ; print = TRUE ; fun.name = NULL
Gael  MILLOT's avatar
Gael MILLOT committed
120
# function name: no used in this function for the error message, to avoid env colliding
Gael  MILLOT's avatar
Gael MILLOT committed
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
# argument checking
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)){
Gael  MILLOT's avatar
Gael MILLOT committed
145
if( ! all(class %in% c("vector", "logical", "integer", "numeric", "complex", "character", "matrix", "array", "data.frame", "list", "factor", "table", "expression", "name", "symbol", "function", "uneval") & any(is.na(class)) != TRUE)){ # not length == 1 here because ordered factors are class "factor" "ordered" (length == 2)
Gael  MILLOT's avatar
Gael MILLOT committed
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
tempo.cat <- paste0("\n\n================\n\nERROR IN fun_param_check(): class ARGUMENT MUST BE ONE OF THESE VALUE:\n\"vector\", \"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("vector", "numeric", "integer", "matrix", "array", "data.frame", "table"))){
tempo.cat <- paste0("\n\n================\n\nERROR IN fun_param_check(): class ARGUMENT CANNOT BE OTHER THAN \"vector\", \"numeric\", \"integer\", \"matrix\", \"array\", \"data.frame\", \"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("vector", "numeric", "integer", "matrix", "array", "data.frame", "table"))){
tempo.cat <- paste0("\n\n================\n\nERROR IN fun_param_check(): class ARGUMENT CANNOT BE OTHER THAN \"vector\", \"numeric\", \"integer\", \"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)){
Gael  MILLOT's avatar
Gael MILLOT committed
206
tempo.cat <- paste0("\n\n================\n\nERROR IN fun_param_check(): THE double.as.integer.allowed ARGUMENT MUST BE TRUE OR FALSE ONLY: ", paste(double.as.integer.allowed, collapse = " "), "\n\n================\n\n")
Gael  MILLOT's avatar
Gael MILLOT committed
207
208
209
stop(tempo.cat)
}
if( ! (is.logical(all.options.in.data) & length(all.options.in.data) == 1 & any(is.na(all.options.in.data)) != TRUE)){
Gael  MILLOT's avatar
Gael MILLOT committed
210
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): ", paste(all.options.in.data, collapse = " "), "\n\n================\n\n")
Gael  MILLOT's avatar
Gael MILLOT committed
211
212
213
stop(tempo.cat)
}
if( ! (all(class(na.contain) == "logical") & length(na.contain) == 1 & any(is.na(na.contain)) != TRUE)){
Gael  MILLOT's avatar
Gael MILLOT committed
214
tempo.cat <- paste0("\n\n================\n\nERROR IN fun_param_check(): THE na.contain ARGUMENT MUST BE TRUE OR FALSE ONLY: ", paste(na.contain, collapse = " "), "\n\n================\n\n")
Gael  MILLOT's avatar
Gael MILLOT committed
215
216
217
stop(tempo.cat)
}
if( ! (all(class(print) == "logical") & length(print) == 1 & any(is.na(print)) != TRUE)){
Gael  MILLOT's avatar
Gael MILLOT committed
218
tempo.cat <- paste0("\n\n================\n\nERROR IN fun_param_check(): THE print ARGUMENT MUST BE TRUE OR FALSE ONLY: ", paste(print, collapse = " "), "\n\n================\n\n")
Gael  MILLOT's avatar
Gael MILLOT committed
219
220
221
222
stop(tempo.cat)
}
if( ! is.null(fun.name)){
if( ! (class(fun.name) == "character" & length(fun.name) == 1)){
Gael  MILLOT's avatar
Gael MILLOT committed
223
tempo.cat <- paste0("\n\n================\n\nERROR IN fun_param_check(): THE fun.name ARGUMENT MUST BE A CHARACTER VECTOR OF LENGTH 1: ", paste(fun.name, collapse = " "), "\n\n================\n\n")
Gael  MILLOT's avatar
Gael MILLOT committed
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
stop(tempo.cat)
}
}
# 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
# end argument checking
# main code
if(is.null(data.name)){
data.name <- deparse(substitute(data))
}
problem <- FALSE
text <- paste0(ifelse(is.null(fun.name), "", paste0("IN ", fun.name, ": ")), "NO PROBLEM DETECTED FOR THE ", data.name, " PARAMETER")
if( ! is.null(options)){
text <- ""
if( ! all(data %in% options)){
problem <- TRUE
text <- paste0(ifelse(is.null(fun.name), "ERROR", paste0("ERROR IN ", fun.name)), ": 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(ifelse(is.null(fun.name), "ERROR", paste0("ERROR IN ", fun.name)), ": 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, "\n", ifelse(is.null(fun.name), "ERROR", paste0("ERROR IN ", fun.name)), ": 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(ifelse(is.null(fun.name), "ERROR", paste0("ERROR IN ", fun.name)), ": THE LENGTH OF ", data.name, " MUST BE ", length, " AND NOT ", length(data))
}else{
text <- paste0(text, "\n", ifelse(is.null(fun.name), "ERROR", paste0("ERROR IN ", fun.name)), ": THE LENGTH OF ", data.name, " MUST BE ", length, " AND NOT ", length(data))
}
}
}
if(text == ""){
text <- paste0(ifelse(is.null(fun.name), "", paste0("IN ", fun.name, ": ")), "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 <- '
Gael  MILLOT's avatar
Gael MILLOT committed
271
problem <- TRUE ;
Gael  MILLOT's avatar
Gael MILLOT committed
272
273
if(identical(text, paste0(ifelse(is.null(fun.name), "", paste0("IN ", fun.name, ": ")), "NO PROBLEM DETECTED FOR THE ", data.name, " PARAMETER"))){
text <- paste0(ifelse(is.null(fun.name), "ERROR", paste0("ERROR IN ", fun.name)), ": THE ", data.name, " PARAMETER MUST BE ") ;
Gael  MILLOT's avatar
Gael MILLOT committed
274
275
276
277
278
}else{
text <- paste0(text, " AND "); 
}
text <- paste0(text, toupper(arg.names[i2]), " ", get(arg.names[i2]))
'
Gael  MILLOT's avatar
Gael MILLOT committed
279
280
281
282
283
284
285
286
287
288
289
290
291
# end script to execute
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(get(arg.names[i2]) != "vector" & eval(parse(text = paste0(arg.names[i2], "(data)"))) != get(arg.names[i2])){
eval(parse(text = tempo.script)) # execute tempo.script
}else if(arg.names[i2] == "class" & get(arg.names[i2]) == "vector" & ! (class(data) == "numeric" | class(data) == "integer" | class(data) == "character" | class(data) == "logical")){
eval(parse(text = tempo.script)) # execute tempo.script
}
}
}
}
Gael  MILLOT's avatar
Gael MILLOT committed
292
if( ! is.null(prop)){
Gael  MILLOT's avatar
Gael MILLOT committed
293
294
295
296
297
298
299
300
301
302
303
if(prop == TRUE){
if(any(data < 0 | data > 1, na.rm = TRUE)){
problem <- TRUE
if(identical(text, paste0(ifelse(is.null(fun.name), "", paste0("IN ", fun.name, ": ")), "NO PROBLEM DETECTED FOR THE ", data.name, " PARAMETER"))){
text <- paste0(ifelse(is.null(fun.name), "ERROR", paste0("ERROR IN ", fun.name)), ": ")
}else{
text <- paste0(text, " AND ")
}
text <- paste0(text, "THE ", data.name, " PARAMETER MUST BE DECIMAL VALUES BETWEEN 0 AND 1")
}
}
Gael  MILLOT's avatar
Gael MILLOT committed
304
}
305
306
307
if(all(class(data) %in% "expression")){
data <- as.character(data) # to evaluate the presence of NA
}
Gael  MILLOT's avatar
Gael MILLOT committed
308
if(na.contain == FALSE & any(is.na(data)) == TRUE){
Gael  MILLOT's avatar
Gael MILLOT committed
309
310
311
312
313
314
315
problem <- TRUE
if(identical(text, paste0(ifelse(is.null(fun.name), "", paste0("IN ", fun.name, ": ")), "NO PROBLEM DETECTED FOR THE ", data.name, " PARAMETER"))){
text <- paste0(ifelse(is.null(fun.name), "ERROR", paste0("ERROR IN ", fun.name)), ": ")
}else{
text <- paste0(text, " AND ")
}
text <- paste0(text, "THE ", data.name, " PARAMETER CONTAINS NA WHILE NOT AUTHORIZED (na.contain ARGUMENT SET TO FALSE)")
Gael  MILLOT's avatar
Gael MILLOT committed
316
317
}
if(neg.values == FALSE){
Gael  MILLOT's avatar
Gael MILLOT committed
318
319
320
321
322
323
324
325
326
if(any(data < 0, na.rm = TRUE)){
problem <- TRUE
if(identical(text, paste0(ifelse(is.null(fun.name), "", paste0("IN ", fun.name, ": ")), "NO PROBLEM DETECTED FOR THE ", data.name, " PARAMETER"))){
text <- paste0(ifelse(is.null(fun.name), "ERROR", paste0("ERROR IN ", fun.name)), ": ")
}else{
text <- paste0(text, " AND ")
}
text <- paste0(text, "THE ", data.name, " PARAMETER MUST BE NON NEGATIVE NUMERIC VALUES")
}
Gael  MILLOT's avatar
Gael MILLOT committed
327
328
}
if(print == TRUE & problem == TRUE){
Gael  MILLOT's avatar
Gael MILLOT committed
329
cat(paste0("\n\n================\n\n", text, "\n\n================\n\n"))
Gael  MILLOT's avatar
Gael MILLOT committed
330
331
332
333
}
output <- list(problem = problem, text = text, param.name = data.name)
return(output)
}
Gael  MILLOT's avatar
Gael MILLOT committed
334
335


Gael  MILLOT's avatar
Gael MILLOT committed
336
######## fun_object_info() #### recover object information
Gael  MILLOT's avatar
Gael MILLOT committed
337
338
339
340


# Check OK: clear to go Apollo
fun_object_info <- function(data){
Gael  MILLOT's avatar
Gael MILLOT committed
341
342
343
344
345
346
347
348
# AIM
# provide a full description of the object
# REQUIRED FUNCTIONS FROM CUTE_LITTLE_R_FUNCTION
# none
# ARGUMENTS
# data: object to test
# RETURN
# a list containing the info
Gael  MILLOT's avatar
Gael MILLOT committed
349
# please, use names(fun_object_info()) and remove what can be too big for easy analysis
Gael  MILLOT's avatar
Gael MILLOT committed
350
351
352
353
354
355
356
357
358
359
360
361
362
# 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
Gael  MILLOT's avatar
Gael MILLOT committed
363
# function name: no need because no check and no message
Gael  MILLOT's avatar
Gael MILLOT committed
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
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
# 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
# end argument checking
# main code
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
422
423
424
425
426
427
428
429
}


######## 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
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
583
584
585
586
587
588
589
590
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
# 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 FROM CUTE_LITTLE_R_FUNCTION
# 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
# function name
function.name <- paste0(as.list(match.call(expand.dots=FALSE))[[1]], "()")
# end function name
# argument checking
if( ! any(class(data1) %in% c("logical", "integer", "numeric", "character", "factor", "table"))){
tempo.cat <- paste0("\n\n================\n\nERROR IN ", function.name, ": 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 ", function.name, ": 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 ", function.name, ": 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 ", function.name, ": THE data2 ARGUMENT MUST BE A 1D TABLE\n\n================\n\n")
stop(tempo.cat)
}
}
# 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
# end argument checking
# main code
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
638
639
640
641
642
643
644
645
}


######## 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
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
886
887
888
889
890
891
892
893
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
# 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 FROM CUTE_LITTLE_R_FUNCTION
# 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
# function name
function.name <- paste0(as.list(match.call(expand.dots=FALSE))[[1]], "()")
# end function name
# argument checking
if( ! any(class(data1) %in% c("matrix", "data.frame", "table"))){
tempo.cat <- paste0("\n\n================\n\nERROR IN ", function.name, ": 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 ", function.name, ": THE data2 ARGUMENT MUST BE A MATRIX, DATA FRAME OR TABLE\n\n================\n\n")
stop(tempo.cat)
}
# 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
# end argument checking
# main code
same.class <- NULL
class <- NULL
same.dim <- NULL
dim <- NULL
same.row.nb <- NULL
row.nb <- NULL
same.col.nb <- NULL
col.nb <- NULL
same.row.name <- NULL
row.name <- NULL
any.id.row.name <- NULL
same.row.name.pos1 <- NULL
same.row.name.pos2 <- NULL
common.row.names <- NULL
same.col.name <- NULL
any.id.col.name <- NULL
same.col.name.pos1 <- NULL
same.col.name.pos2 <- NULL
common.col.names <- NULL
col.name <- NULL
any.id.row <- NULL
same.row.pos1 <- NULL
same.row.pos2 <- NULL
any.id.col <- NULL
same.col.pos1 <- NULL
same.col.pos2 <- NULL
identical.object <- NULL
identical.content <- NULL
if(identical(data1, data2) & any(class(data1) %in% c("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 ", function.name, ": 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 ", function.name, ": 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 ", function.name, ": 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
945
946
947
}


Gael  MILLOT's avatar
Gael MILLOT committed
948
949
950
951
######## fun_2D_head() #### head of the left or right of big 2D objects


# Check OK: clear to go Apollo
Gael  MILLOT's avatar
Gael MILLOT committed
952
fun_2D_head <- function(data1, n = 10, side = "l"){
Gael  MILLOT's avatar
Gael MILLOT committed
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
# AIM
# display the head of the left or right of big 2D objects
# REQUIRED FUNCTIONS FROM CUTE_LITTLE_R_FUNCTION
# fun_param_check()
# ARGUMENTS
# data1: matrix, data frame or table
# n: number of dimension to print (10 means 10 rows and columns)
# side: either "l" or "r" for the left or right side of the 2D object
# RETURN
# the head
# EXAMPLES
# obs1 = matrix(1:30, ncol = 5, dimnames = list(letters[1:6], LETTERS[1:5])) ; obs1 ; fun_2D_head(obs1, 3)
# obs1 = matrix(1:30, ncol = 5, dimnames = list(letters[1:6], LETTERS[1:5])) ; obs1 ; fun_2D_head(obs1, 3, "right")
# DEBUGGING
# data1 = matrix(1:30, ncol = 5) # for function debugging
# data1 = matrix(1:30, ncol = 5, dimnames = list(letters[1:2], LETTERS[1:5])) # for function debugging
# function name
function.name <- paste0(as.list(match.call(expand.dots=FALSE))[[1]], "()")
# end function name
# required function checking
if(length(find("fun_param_check", mode = "function")) == 0){
tempo.cat <- paste0("\n\n================\n\nERROR IN ", function.name, ": REQUIRED fun_param_check() FUNCTION IS MISSING IN THE R ENVIRONMENT\n\n================\n\n")
stop(tempo.cat)
}
# end required function checking
# argument checking
# argument checking without fun_param_check()
if( ! any(class(data1) %in% c("matrix", "data.frame", "table"))){
tempo.cat <- paste0("\n\n================\n\nERROR IN ", function.name, ": THE data1 ARGUMENT MUST BE A MATRIX, DATA FRAME OR TABLE\n\n================\n\n")
stop(tempo.cat)
}
# end argument checking without fun_param_check()
# argument checking with fun_param_check()
arg.check <- NULL # for function debbuging
checked.arg.names <- NULL # for function debbuging: used by r_debugging_tools
ee <- expression(arg.check <- c(arg.check, tempo$problem) , checked.arg.names <- c(checked.arg.names, tempo$param.name))
tempo <- fun_param_check(data = n, class = "vector", typeof = "integer", double.as.integer.allowed = TRUE, length = 1, fun.name = function.name) ; eval(ee)
tempo <- fun_param_check(data = side, options = c("l", "r"), length = 1, fun.name = function.name) ; eval(ee)
if(any(arg.check) == TRUE){
stop() # nothing else because print = TRUE by default in fun_param_check()
}
# end argument checking with 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 (with no arguments left as NULL) to check arguments status and if they have been checked using fun_param_check()
# end argument checking
# main code
obs.dim <- dim(data1)
row <- 1:ifelse(obs.dim[1] < n, obs.dim[1], n)
if(side == "l"){