Modelling Arabic data - Visualisation

Université Paris Cité

This is an R Markdown Notebook. When you execute code within the notebook, the results appear beneath the code.

Try executing this chunk by clicking the Run button within the chunk or by placing your cursor inside it and pressing Ctrl+Shift+Enter.

1 Loading libraries

library(dplyr)
library(ggplot2)
library(tidyverse)
library(car)
library(RcmdrMisc)
library(colorspace, pos=17)

library(nlme)
library(multcomp)

library(GoodmanKruskal)
library(gridExtra)
library(scales) # For the percent_format() function
library("cowplot")
#options(kableExtra.latex.load_packages = FALSE) 
library(kableExtra)
library(phonR)
library(grid)
library(RColorBrewer)
library(tictoc)

2 Read dataset and manipulate

2.1 Read datasets

Arabic <- read.csv("SpeakingRate24.csv") 
Vratio <- read.csv("Vratio.csv")

2.2 Manipulations

Arabic <- subset(Arabic, select = -Arabic_phrase) ### Supprimer la colonne des phrases en arabe pour éviter les problèmes avec PdfLaTex lors de la compilation LaTex R. Sinon, utiliser XeLaTex pour l'écriture arabe. 
Arabic$CVC <- gsub(' ', '', Arabic$CVC)#supprimer les espaces 
Arabic$V <- gsub(' ', '', Arabic$V)#supprimer les espaces
Arabic$Length <- gsub(' ', '', Arabic$Length)#supprimer les espaces 

Arabic$f0ons <- as.integer(gsub('--undefined--', NA, Arabic$f0ons))
Arabic$f0mid <- as.integer(gsub('--undefined--', NA, Arabic$f0mid))
Arabic$f0off <- as.integer(gsub('--undefined--', NA, Arabic$f0off))


Arabic <- dplyr::mutate_if(Arabic, is.character, as.factor) ## Transformer tous les variables de type "character" à des facteurs. 
#Arabic <- filter(Arabic, V!="e:" & V!="o:")
Arabic$V = factor(Arabic$V, levels = c('i','a','u','i:','a:','u:','e:','o:')) ## ordonner l'ordre de l'apparition V
Arabic$C <- factor(Arabic$C, levels=c("b","d","g","t","k")) ## ordonner l'ordre de l'apparition C
Arabic$VOTi <- as.integer(Arabic$VOTi)
#Arabic$Word_V_ratio <- as.numeric(gsub(',', '.', Arabic$Word_V_ratio)) #remplacer les virgules en points dans les nombres décimaux pour pouvoir faire des calculs. 

levels(Arabic$Rate) <- list("rapide" = "fast",        # Change factor levels
                            "moyen" = "normal",
                            "lent" = "slow")
levels(Arabic$Length) <- list("longue" = "long",        # Change factor levels
                              "courte" = "short")
Arabic <- dplyr::rename(Arabic, Debit = Rate, Longueur = Length)

Arabic$F1midnor <- with(Arabic, normLobanov(F1mid)) #normalisation de F1mid et F2mid
Arabic$F2midnor <- with(Arabic, normLobanov(F2mid)) #normalisation de F1mid et F2mid

Vratio <- dplyr::rename(Vratio, Debit = Rate)

### sous-ensemble 1
ArabicSub1 <- Arabic
ArabicSub1 <- ArabicSub1 %>% 
  filter(Timbre %in% c("i", "a", "u")) %>% droplevels()

### sous-ensemble 2
ArabicSub2 <- Arabic
ArabicSub2 <- ArabicSub2 %>% 
  filter(V %in% c("i", "a", "u", "e:", "u:", "a:")) %>% droplevels()

ArabicSub2$Timbre=gsub('i','e', ArabicSub2$Timbre)
ArabicSub2$Timbre=gsub('u','o', ArabicSub2$Timbre)

ArabicSub2$Timbre= as.factor(ArabicSub2$Timbre)

3 Duration

Arabic %>% 
  ggplot(aes(y = Duration, x = Debit, colour = Sex)) +
  geom_violin() + 
  geom_jitter(position = position_jitter(seed = 1, width = 0.2)) +
  geom_smooth(aes(x = as.numeric(Debit), y = Duration), method = "lm", color = "blue") +
  facet_grid(~ V)

`geom_smooth()` using formula = 'y ~
x'

4 F1midnor

Arabic %>% 
  ggplot(aes(y = F1midnor, x = Debit, colour = Sex)) +
  geom_violin() + 
  geom_jitter(position = position_jitter(seed = 1, width = 0.2)) + 
  geom_smooth(aes(x = as.numeric(Debit), y = F1midnor), method = "lm", color = "blue") +
  facet_grid(~ V)

`geom_smooth()` using formula = 'y ~
x'

5 F2midnor

Arabic %>% 
  ggplot(aes(y = F2midnor, x = Debit, colour = Sex)) +
  geom_violin() + 
  geom_jitter(position = position_jitter(seed = 1, width = 0.2)) +
    geom_smooth(aes(x = as.numeric(Debit), y = F2midnor), method = "lm", color = "blue") +
  facet_grid(~ V)

`geom_smooth()` using formula = 'y ~
x'

6 Word_V_ratio

Arabic %>% 
  ggplot(aes(y = Word_V_ratio, x = Debit, colour = Sex)) +
  geom_violin() + 
  geom_jitter(position = position_jitter(seed = 1, width = 0.2)) +
  geom_smooth(aes(x = as.numeric(Debit), y = Word_V_ratio), method = "lm", color = "blue") +
  facet_grid(~ V)

`geom_smooth()` using formula = 'y ~
x'

7 Vratio

Vratio %>% 
  ggplot(aes(y = Vratio, x = Debit, colour = Sex)) +
  geom_violin() + 
  geom_jitter(position = position_jitter(seed = 1, width = 0.2)) +
  facet_grid(~ Timbre)

8 F1midnor - Timbre

Arabic %>% 
  ggplot(aes(y = F1midnor, x = Debit, colour = Sex)) +
  geom_violin() + 
  geom_jitter(position = position_jitter(seed = 1, width = 0.2)) +
  geom_smooth(aes(x = as.numeric(Debit), y = F1midnor), method = "lm", color = "blue") +
  facet_grid(~ Timbre)

`geom_smooth()` using formula = 'y ~
x'

9 F2midnor - Timbre

Arabic %>% 
  ggplot(aes(y = F2midnor, x = Debit, colour = Sex)) +
  geom_violin() + 
  geom_jitter(position = position_jitter(seed = 1, width = 0.2)) +
  geom_smooth(aes(x = as.numeric(Debit), y = F2midnor), method = "lm", color = "blue") +
  facet_grid(~ Timbre)

`geom_smooth()` using formula = 'y ~
x'

10 F1midnor - Subset 1 - Timbre

ArabicSub1 %>% 
  ggplot(aes(y = F1midnor, x = Debit, colour = Sex)) +
  geom_violin() + 
  geom_jitter(position = position_jitter(seed = 1, width = 0.2)) +
  geom_smooth(aes(x = as.numeric(Debit), y = F1midnor), method = "lm", color = "blue") +
  facet_grid(~ Timbre)

`geom_smooth()` using formula = 'y ~
x'

11 F2midnor - Subset 1 - Timbre

ArabicSub1 %>% 
  ggplot(aes(y = F2midnor, x = Debit, colour = Sex)) +
  geom_violin() + 
  geom_jitter(position = position_jitter(seed = 1, width = 0.2)) +
  geom_smooth(aes(x = as.numeric(Debit), y = F2midnor), method = "lm", color = "blue") +
  facet_grid(~ Timbre)

`geom_smooth()` using formula = 'y ~
x'

12 F1midnor - Subset 2 - Timbre

ArabicSub2 %>% 
  ggplot(aes(y = F1midnor, x = Debit, colour = Sex)) +
  geom_violin() + 
  geom_jitter(position = position_jitter(seed = 1, width = 0.2)) +
  geom_smooth(aes(x = as.numeric(Debit), y = F1midnor), method = "lm", color = "blue") +
  facet_grid(~ Timbre)

`geom_smooth()` using formula = 'y ~
x'

13 F2midnor - Subset 2 - Timbre

ArabicSub2 %>% 
  ggplot(aes(y = F2midnor, x = Debit, colour = Sex)) +
  geom_violin() + 
  geom_jitter(position = position_jitter(seed = 1, width = 0.2)) +
  geom_smooth(aes(x = as.numeric(Debit), y = F2midnor), method = "lm", color = "blue") +
  facet_grid(~ Timbre)

`geom_smooth()` using formula = 'y ~
x'

14 session info

sessionInfo()

R version 4.4.1 (2024-06-14 ucrt)
Platform: x86_64-w64-mingw32/x64
Running under: Windows 10 x64 (build 19045)

Matrix products: default


locale:
[1] LC_COLLATE=English_United Kingdom.utf8 
[2] LC_CTYPE=English_United Kingdom.utf8   
[3] LC_MONETARY=English_United Kingdom.utf8
[4] LC_NUMERIC=C                           
[5] LC_TIME=English_United Kingdom.utf8    

time zone: Europe/Paris
tzcode source: internal

attached base packages:
[1] grid      stats     graphics 
[4] grDevices utils     datasets 
[7] methods   base     

other attached packages:
 [1] tictoc_1.2.1        
 [2] RColorBrewer_1.1-3  
 [3] phonR_1.0-7         
 [4] kableExtra_1.4.0    
 [5] cowplot_1.1.3       
 [6] scales_1.3.0        
 [7] gridExtra_2.3       
 [8] GoodmanKruskal_0.0.3
 [9] multcomp_1.4-26     
[10] TH.data_1.1-2       
[11] MASS_7.3-61         
[12] survival_3.7-0      
[13] mvtnorm_1.2-6       
[14] nlme_3.1-166        
[15] RcmdrMisc_2.9-1     
[16] sandwich_3.1-0      
[17] car_3.1-2           
[18] carData_3.0-5       
[19] lubridate_1.9.3     
[20] forcats_1.0.0       
[21] stringr_1.5.1       
[22] purrr_1.0.2         
[23] readr_2.1.5         
[24] tidyr_1.3.1         
[25] tibble_3.2.1        
[26] tidyverse_2.0.0     
[27] ggplot2_3.5.1       
[28] dplyr_1.1.4         
[29] lmerTest_3.1-3      
[30] colorspace_2.1-1    
[31] lme4_1.1-35.5       
[32] Matrix_1.7-0        

loaded via a namespace (and not attached):
 [1] tidyselect_1.2.1   
 [2] viridisLite_0.4.2  
 [3] farver_2.1.2       
 [4] fastmap_1.2.0      
 [5] digest_0.6.37      
 [6] rpart_4.1.23       
 [7] timechange_0.3.0   
 [8] lifecycle_1.0.4    
 [9] cluster_2.1.6      
[10] magrittr_2.0.3     
[11] compiler_4.4.1     
[12] sass_0.4.9         
[13] rlang_1.1.4        
[14] Hmisc_5.1-3        
[15] tools_4.4.1        
[16] utf8_1.2.4         
[17] yaml_2.3.10        
[18] data.table_1.16.0  
[19] knitr_1.48         
[20] labeling_0.4.3     
[21] htmlwidgets_1.6.4  
[22] xml2_1.3.6         
[23] abind_1.4-5        
[24] withr_3.0.1        
[25] foreign_0.8-86     
[26] numDeriv_2016.8-1.1
[27] nnet_7.3-19        
[28] fansi_1.0.6        
[29] e1071_1.7-14       
[30] cli_3.6.3          
[31] rmarkdown_2.28     
[32] generics_0.1.3     
[33] rstudioapi_0.16.0  
[34] tzdb_0.4.0         
[35] readxl_1.4.3       
[36] cachem_1.1.0       
[37] minqa_1.2.8        
[38] proxy_0.4-27       
[39] splines_4.4.1      
[40] cellranger_1.1.0   
[41] base64enc_0.1-3    
[42] vctrs_0.6.5        
[43] boot_1.3-30        
[44] jsonlite_1.8.8     
[45] hms_1.1.3          
[46] Formula_1.2-5      
[47] htmlTable_2.4.3    
[48] systemfonts_1.1.0  
[49] nortest_1.0-4      
[50] jquerylib_0.1.4    
[51] glue_1.7.0         
[52] nloptr_2.1.1       
[53] codetools_0.2-20   
[54] stringi_1.8.4      
[55] gtable_0.3.5       
[56] munsell_0.5.1      
[57] pillar_1.9.0       
[58] htmltools_0.5.8.1  
[59] R6_2.5.1           
[60] evaluate_0.24.0    
[61] lattice_0.22-6     
[62] haven_2.5.4        
[63] backports_1.5.0    
[64] bslib_0.8.0        
[65] class_7.3-22       
[66] Rcpp_1.0.13        
[67] svglite_2.1.3      
[68] checkmate_2.3.2    
[69] mgcv_1.9-1         
[70] xfun_0.47          
[71] zoo_1.8-12         
[72] pkgconfig_2.0.3