--- title: "Home Literacy" author: "B. Brossette" toc: true number-sections: true highlight-style: pygments format: html: code-fold: true code-tools: true editor: visual --- ```{r} #| label: package #| code-summary: "Librairies Loading" #| message: false #clean the environment rm (list = ls ())#Libraries library (readr)library (stringr)library (plyr)library (dplyr)library (tidyverse)library (lme4)library (car)library (emmeans)library (ggthemes)library (data.table)library (corrplot)library (Hmisc)library (lavaan)library (lavaanPlot)library (semPlot)library (effectsize)library (chron)library (knitr)``` ## Préparation des données ```{r} #| message: false #Formatting activity rows data. <- read_delim ("../src/home_literacy/activity_student_record.csv" , delim = ";" , escape_double = FALSE , trim_ws = TRUE )<- activity %>% mutate (uid = str_sub (user.__ref__,str_locate (user.__ref__, "/" )[1 ]+ 1 ))<- activity %>% mutate (day = as.Date ( str_sub (date,1 , str_locate (date, " " )[1 ]- 1 ), format= "%Y-%m-%d" ),hour = times (str_sub (date, str_locate (date, " " )[1 ]+ 1 )))<- activity %>% mutate (length = (duration/ 1000 )/ 60 ) %>% mutate (length = format (length, scientific = FALSE ))<- activity %>% select (uid, day, hour, length, activity_type, concentration, difficulty, interaction, perceived_time, pleasure)#Formatting users rows data. <- read_delim ("../src/home_literacy/users_list.csv" , delim = ";" , escape_double = FALSE , trim_ws = TRUE )<- users %>% select (uid,user_category, email, grade, school, teacher_name)#Jointure <- activity %>% left_join (users, by = "uid" )#Delete teacher records AND test records <- df %>% filter (school!= "TEST_SCHOOL" )<- df %>% filter (user_category!= "T" )``` # Statistiques générales - Nombre d'activités enregistrées : `r length(df$uid)` - Durée d'une activité (en min) : M = `r mean(as.numeric(df$length))` ; MED = `r median(as.numeric(df$length))` ; SD = `r sd(as.numeric(df$length))` - Nombre d'utilisateurs actifs : `r length(unique(df$uid))` ```{r} #| message: false <- df %>% group_by (grade,uid) %>% summarise (nb_act = n (), first_activity = min (day), last_activity = max (day),period_activity = last_activity - first_activity, mean_duration = mean (as.numeric (length)),shortest = min (as.numeric (length)), longest = max (as.numeric (length)))kable (describe[order (describe$ period_activity, decreasing= TRUE ),])```