Recurrence Networks of Daily questionnaires on work motivation

Using recurrence networks to summarise time series of MS users in APPS MS

Read in necessary libraries, functions and look up tables

library(igraph)
library(qgraph)
library(casnet)
library(plyr)
library(dplyr)
library(tidyr)
library(caret)
library(psych)
library(lme4)
library(reshape2)
library(lubridate)
library(parallel)
library(wesanderson)
library(stringr)
library(matrixStats)
library(ggthemes)
library(gridExtra)
library(cowplot)
library(DataExplorer)


# save the original plotting space parameters
og_par <- par()

Show the session information

devtools::session_info()

─ Session info ───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────

─ Packages ───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
 package      * version    date       lib source                               
 abind          1.4-5      2016-07-21 [1] CRAN (R 4.0.2)                       
 assertthat     0.2.1      2019-03-21 [1] CRAN (R 4.0.2)                       
 backports      1.2.0      2020-11-02 [1] CRAN (R 4.0.2)                       
 base64enc      0.1-3      2015-07-28 [1] CRAN (R 4.0.2)                       
 BDgraph        2.63       2020-08-26 [1] CRAN (R 4.0.2)                       
 boot           1.3-25     2020-04-26 [1] CRAN (R 4.0.3)                       
 callr          3.5.1      2020-10-13 [1] CRAN (R 4.0.2)                       
 caret        * 6.0-86     2020-03-20 [1] CRAN (R 4.0.2)                       
 casnet       * 0.1.6      2020-11-14 [1] Github (FredHasselman/casnet@e9e231e)
 checkmate      2.0.0      2020-02-06 [1] CRAN (R 4.0.2)                       
 class          7.3-17     2020-04-26 [1] CRAN (R 4.0.3)                       
 cli            2.1.0      2020-10-12 [1] CRAN (R 4.0.2)                       
 cluster        2.1.0      2019-06-19 [1] CRAN (R 4.0.3)                       
 codetools      0.2-16     2018-12-24 [1] CRAN (R 4.0.3)                       
 colorspace     2.0-0      2020-11-11 [1] CRAN (R 4.0.2)                       
 corpcor        1.6.9      2017-04-01 [1] CRAN (R 4.0.2)                       
 cowplot      * 1.1.0      2020-09-08 [1] CRAN (R 4.0.2)                       
 crayon         1.3.4      2017-09-16 [1] CRAN (R 4.0.2)                       
 d3Network      0.5.2.1    2015-01-31 [1] CRAN (R 4.0.2)                       
 data.table     1.14.0     2021-02-21 [1] CRAN (R 4.0.2)                       
 DataExplorer * 0.8.2      2020-12-15 [1] CRAN (R 4.0.2)                       
 desc           1.2.0      2018-05-01 [1] CRAN (R 4.0.2)                       
 devtools       2.3.2      2020-09-18 [1] CRAN (R 4.0.2)                       
 digest         0.6.27     2020-10-24 [1] CRAN (R 4.0.2)                       
 dplyr        * 1.0.2      2020-08-18 [1] CRAN (R 4.0.2)                       
 ellipsis       0.3.1      2020-05-15 [1] CRAN (R 4.0.2)                       
 evaluate       0.14       2019-05-28 [1] CRAN (R 4.0.1)                       
 fansi          0.4.1      2020-01-08 [1] CRAN (R 4.0.2)                       
 fdrtool        1.2.15     2015-07-08 [1] CRAN (R 4.0.2)                       
 foreach        1.5.1      2020-10-15 [1] CRAN (R 4.0.2)                       
 foreign        0.8-80     2020-05-24 [1] CRAN (R 4.0.3)                       
 Formula        1.2-4      2020-10-16 [1] CRAN (R 4.0.2)                       
 fs             1.5.0      2020-07-31 [1] CRAN (R 4.0.2)                       
 generics       0.1.0      2020-10-31 [1] CRAN (R 4.0.2)                       
 ggplot2      * 3.3.2      2020-06-19 [1] CRAN (R 4.0.2)                       
 ggthemes     * 4.2.0      2019-05-13 [1] CRAN (R 4.0.2)                       
 glasso         1.11       2019-10-01 [1] CRAN (R 4.0.2)                       
 glue           1.4.2      2020-08-27 [1] CRAN (R 4.0.2)                       
 gower          0.2.2      2020-06-23 [1] CRAN (R 4.0.2)                       
 gridExtra    * 2.3        2017-09-09 [1] CRAN (R 4.0.2)                       
 gtable         0.3.0      2019-03-25 [1] CRAN (R 4.0.2)                       
 gtools         3.8.2      2020-03-31 [1] CRAN (R 4.0.2)                       
 Hmisc          4.4-1      2020-08-10 [1] CRAN (R 4.0.2)                       
 htmlTable      2.1.0      2020-09-16 [1] CRAN (R 4.0.2)                       
 htmltools      0.5.0      2020-06-16 [1] CRAN (R 4.0.2)                       
 htmlwidgets    1.5.2      2020-10-03 [1] CRAN (R 4.0.2)                       
 huge           1.3.4.1    2020-04-01 [1] CRAN (R 4.0.2)                       
 igraph       * 1.2.6      2020-10-06 [1] CRAN (R 4.0.2)                       
 invctr         0.1.0      2019-03-07 [1] CRAN (R 4.0.2)                       
 ipred          0.9-9      2019-04-28 [1] CRAN (R 4.0.2)                       
 iterators      1.0.13     2020-10-15 [1] CRAN (R 4.0.2)                       
 jpeg           0.1-8.1    2019-10-24 [1] CRAN (R 4.0.2)                       
 knitr          1.30       2020-09-22 [1] CRAN (R 4.0.2)                       
 lattice      * 0.20-41    2020-04-02 [1] CRAN (R 4.0.3)                       
 latticeExtra   0.6-29     2019-12-19 [1] CRAN (R 4.0.2)                       
 lava           1.6.8.1    2020-11-04 [1] CRAN (R 4.0.2)                       
 lavaan         0.6-7      2020-07-31 [1] CRAN (R 4.0.2)                       
 lifecycle      0.2.0      2020-03-06 [1] CRAN (R 4.0.2)                       
 lme4         * 1.1-25     2020-10-23 [1] CRAN (R 4.0.2)                       
 lubridate    * 1.7.9.2    2020-11-13 [1] CRAN (R 4.0.3)                       
 magrittr       1.5        2014-11-22 [1] CRAN (R 4.0.2)                       
 MASS           7.3-53     2020-09-09 [1] CRAN (R 4.0.3)                       
 Matrix       * 1.2-18     2019-11-27 [1] CRAN (R 4.0.3)                       
 matrixStats  * 0.57.0     2020-09-25 [1] CRAN (R 4.0.2)                       
 memoise        1.1.0      2017-04-21 [1] CRAN (R 4.0.2)                       
 minqa          1.2.4      2014-10-09 [1] CRAN (R 4.0.2)                       
 mnormt         2.0.2      2020-09-01 [1] CRAN (R 4.0.2)                       
 ModelMetrics   1.2.2.2    2020-03-17 [1] CRAN (R 4.0.2)                       
 munsell        0.5.0      2018-06-12 [1] CRAN (R 4.0.2)                       
 networkD3      0.4        2017-03-18 [1] CRAN (R 4.0.2)                       
 nlme           3.1-149    2020-08-23 [1] CRAN (R 4.0.3)                       
 nloptr         1.2.2.2    2020-07-02 [1] CRAN (R 4.0.2)                       
 nnet           7.3-14     2020-04-26 [1] CRAN (R 4.0.3)                       
 pbapply        1.4-3      2020-08-18 [1] CRAN (R 4.0.2)                       
 pbivnorm       0.6.0      2015-01-23 [1] CRAN (R 4.0.2)                       
 pillar         1.4.6      2020-07-10 [1] CRAN (R 4.0.2)                       
 pkgbuild       1.1.0      2020-07-13 [1] CRAN (R 4.0.2)                       
 pkgconfig      2.0.3      2019-09-22 [1] CRAN (R 4.0.2)                       
 pkgload        1.1.0      2020-05-29 [1] CRAN (R 4.0.2)                       
 plyr         * 1.8.6      2020-03-03 [1] CRAN (R 4.0.2)                       
 png            0.1-7      2013-12-03 [1] CRAN (R 4.0.2)                       
 prettyunits    1.1.1      2020-01-24 [1] CRAN (R 4.0.2)                       
 pROC           1.16.2     2020-03-19 [1] CRAN (R 4.0.2)                       
 processx       3.4.4      2020-09-03 [1] CRAN (R 4.0.2)                       
 prodlim        2019.11.13 2019-11-17 [1] CRAN (R 4.0.2)                       
 ps             1.4.0      2020-10-07 [1] CRAN (R 4.0.2)                       
 psych        * 2.0.9      2020-10-05 [1] CRAN (R 4.0.2)                       
 purrr          0.3.4      2020-04-17 [1] CRAN (R 4.0.2)                       
 qgraph       * 1.6.5      2020-02-21 [1] CRAN (R 4.0.2)                       
 R6             2.5.0      2020-10-28 [1] CRAN (R 4.0.2)                       
 RColorBrewer   1.1-2      2014-12-07 [1] CRAN (R 4.0.2)                       
 Rcpp           1.0.5      2020-07-06 [1] CRAN (R 4.0.2)                       
 recipes        0.1.15     2020-11-11 [1] CRAN (R 4.0.2)                       
 remotes        2.4.0      2021-06-02 [1] CRAN (R 4.0.2)                       
 reshape2     * 1.4.4      2020-04-09 [1] CRAN (R 4.0.2)                       
 rjson          0.2.20     2018-06-08 [1] CRAN (R 4.0.2)                       
 rlang          0.4.8      2020-10-08 [1] CRAN (R 4.0.2)                       
 rmarkdown      2.5        2020-10-21 [1] CRAN (R 4.0.3)                       
 rpart          4.1-15     2019-04-12 [1] CRAN (R 4.0.3)                       
 rprojroot      1.3-2      2018-01-03 [1] CRAN (R 4.0.2)                       
 rstudioapi     0.13       2020-11-12 [1] CRAN (R 4.0.3)                       
 scales         1.1.1      2020-05-11 [1] CRAN (R 4.0.2)                       
 sessioninfo    1.1.1      2018-11-05 [1] CRAN (R 4.0.2)                       
 statmod        1.4.35     2020-10-19 [1] CRAN (R 4.0.2)                       
 stringi        1.5.3      2020-09-09 [1] CRAN (R 4.0.2)                       
 stringr      * 1.4.0      2019-02-10 [1] CRAN (R 4.0.2)                       
 survival       3.2-7      2020-09-28 [1] CRAN (R 4.0.3)                       
 testthat       3.0.0      2020-10-31 [1] CRAN (R 4.0.2)                       
 tibble         3.0.4      2020-10-12 [1] CRAN (R 4.0.2)                       
 tidyr        * 1.1.2      2020-08-27 [1] CRAN (R 4.0.2)                       
 tidyselect     1.1.0      2020-05-11 [1] CRAN (R 4.0.2)                       
 timeDate       3043.102   2018-02-21 [1] CRAN (R 4.0.2)                       
 tmvnsim        1.0-2      2016-12-15 [1] CRAN (R 4.0.2)                       
 usethis        1.6.3      2020-09-17 [1] CRAN (R 4.0.2)                       
 vctrs          0.3.4      2020-08-29 [1] CRAN (R 4.0.2)                       
 wesanderson  * 0.3.6      2018-04-20 [1] CRAN (R 4.0.2)                       
 whisker        0.4        2019-08-28 [1] CRAN (R 4.0.2)                       
 withr          2.3.0      2020-09-22 [1] CRAN (R 4.0.2)                       
 xfun           0.19       2020-10-30 [1] CRAN (R 4.0.2)                       

[1] /Library/Frameworks/R.framework/Versions/4.0/Resources/library

Read in data

plot_intro(dai_df)

plot_bar(dai_df)

3 columns ignored with more than 50 categories.
User: 102 categories
date: 125 categories
strategies: 1035 categories

plot_correlation(dai_df)

4 features with more than 20 categories ignored!
User: 102 categories
date: 125 categories
howami_participation_started: 37 categories
strategies: 1035 categories

 [1] "absorption"        "amotivation"       "autonomy"          "competence"        "dedication"        "emotional_drain"   "enjoyment"         "external.pressure"
 [9] "importance"        "interest"          "internal.pressure" "productivity_work" "relatedness"       "satisfaction_work" "time_pressure"     "vigor"            

Split the keystroke df into a list of dfs based on User

# head(dai_df)
# dai_df %>% group_by(User) %>% summarize(count = n())

df_list <- split(dai_df[c("User", vars)], dai_df["User"])

Define the functions which will be applied to each user individually

Select users with long enough time series

user_row_lengths_list <- lapply(df_list, function(x) length(rownames(x)))
user_row_lengths_df <- t(data.frame(user_row_lengths_list))
user_row_lengths_df <- data.frame(cbind(user_row_lengths_df, unique(dai_df$User)))

user_row_lengths_df$X1 <- as.numeric(user_row_lengths_df$X1)

# User_list <- user_row_lengths_df[user_row_lengths_df["X1"] > 30, "X2"]
# User_list <- unique(dai_df$User)
# User_list <- c('Moti148', 'Moti143', 'Moti140', 'Moti156', 'Moti151')
User_list <- c(
  # 'Moti114',
 # 'Moti147',
 'Moti149',
 'Moti164',
 'Moti106',
 'Moti121',
 'Moti137',
 'Moti138',
 'Moti150',
 'Moti157',
 'Moti148',
 'Moti143',
 'Moti140',
 'Moti156',
 'Moti151')

df_list <- df_list[names(df_list) %in% User_list]
# df_list_imp_scal <- df_list_imp_scal[names(df_list_imp_scal) %in% User_list]

Prepare the data (impute and min max scale) and plot an example feature

df_list_imp <- lapply(df_list, apply_imputation, vars)

Number of logged events: 60replacement element 1 has 125 rows to replace 60 rowsNumber of logged events: 35replacement element 1 has 125 rows to replace 60 rowsreplacement element 1 has 125 rows to replace 60 rowsreplacement element 1 has 125 rows to replace 60 rowsreplacement element 1 has 125 rows to replace 60 rowsreplacement element 1 has 125 rows to replace 60 rowsreplacement element 1 has 125 rows to replace 60 rowsreplacement element 1 has 125 rows to replace 60 rowsreplacement element 1 has 125 rows to replace 60 rowsreplacement element 1 has 125 rows to replace 60 rowsreplacement element 1 has 125 rows to replace 60 rowsreplacement element 1 has 125 rows to replace 60 rowsreplacement element 1 has 125 rows to replace 60 rows

df_list_imp_scal <- lapply(df_list_imp, apply_scaling, vars)
df_list_imp[example_user]

$Moti143

df_list_imp_scal[example_user]

$Moti143

NA

Remove users from the imputed and scaled dfs list that had too many missing values

user_drop_list <- c()
for (User in User_list) {
  missing_amount <- sum(sapply(df_list_imp_scal[[as.character(User)]], function(x) sum(is.na(x))))
  # print(User)
  # print(missing_amount)
  if (missing_amount > 0) {
    print(User)
    print(missing_amount)
    user_drop_list <- c(user_drop_list, as.character(User))
  }
}

df_list_imp_scal <- df_list_imp_scal[!names(df_list_imp_scal) %in% user_drop_list]

# for (User in unique(dai_df$User)) {
#   print(User)
#   apply_RP_measures(df_list_imp_scal[as.character(User)], vars, emLag, emDim)
# }

Identify the feature with the most variable Determinism (variance within users) and assign this the feature of interest for the rest of the analysis.

all_RP_measures_df <- reshape::merge_all(RP_measures_list)

rqa_feature <- "ENT_dl" #TT_vl DET

all_RP_measures_df_long <- melt(all_RP_measures_df[, c("feature", rqa_feature)], id.vars = "feature")

g <- ggplot(all_RP_measures_df_long, aes(x=feature, y=value)) +
    geom_boxplot(outlier.colour="#e58038", outlier.shape=8,
                outlier.size=4) +
  theme(axis.text.x = element_text(angle = 90))
print(g)

agg_RP_measures_df <- aggregate(all_RP_measures_df[, c(rqa_feature)], list(all_RP_measures_df$feature), var, na.rm=TRUE)
colnames(agg_RP_measures_df) <- c("feature", rqa_feature)

feature_of_interest <- agg_RP_measures_df[which(agg_RP_measures_df[rqa_feature]==max(agg_RP_measures_df[rqa_feature])), "feature"][1]

print("New feature of interest:")

[1] "New feature of interest:"

feature_of_interest

[1] "satisfaction_work"

Spiral graphs of the feature of interest per user with embedding lag and embedding dimension the same across all users

plot.ts(x=df_list_imp_scal[["Moti156"]]$enjoyment)

plot.ts(x=df_list[["Moti156"]]$enjoyment)

feature_of_interest_RN_measures_df <- reshape::merge_all(RN_measures_list)

# write.csv(feature_of_interest_RN_measures_df, 
#           file=paste("data/", feature_of_interest, "_RN_measures.csv", sep = ""))