danika

load packages

library(tidyverse)
library(readxl)
library(here)
library(janitor)

read in sample data

test <- read_excel(here("data", "SampleParticipant.xlsx")) %>%
  clean_names()

Create separate dataframes (df) for covariates and just vid data (droppiung time first, last, clicks)

covariates <- test %>%
  select(1:80, starts_with("mfss"))

vid_data <- test %>%
  select(1, ends_with(c("_care", "_fair","_loy","_auth","_sanc"))) %>%
  select(- starts_with("time_first_"), - starts_with("time_last_"), - starts_with("time_clicks_")) 

make separate df for each video and make long

#care
care <- vid_data %>%
  select(1, ends_with("_care")) %>%
  mutate_all(as.numeric) %>%
  pivot_longer(names_to = c("question", "video"), names_sep = "_", values_to = "score", 3:26) %>%
  rename(time_submit = time_submit_care)

## Warning in mask$eval_all_mutate(dots[[i]]): NAs introduced by coercion

#fair
fair<- vid_data %>%
  select(1, ends_with("_fair")) %>%
  mutate_all(as.numeric) %>%
  pivot_longer(names_to = c("question", "video"), names_sep = "_", values_to = "score", 3:26) %>%
  rename(time_submit = time_submit_fair)

#loy
loy <- vid_data %>%
  select(1, ends_with("_loy")) %>%
  mutate_all(as.numeric) %>%
  pivot_longer(names_to = c("question", "video"), names_sep = "_", values_to = "score", 3:26) %>%
  rename(time_submit = time_submit_loy)

#auth
auth <- vid_data %>%
  select(1, ends_with("_auth")) %>%
  mutate_all(as.numeric) %>%
  pivot_longer(names_to = c("question", "video"), names_sep = "_", values_to = "score", 3:26) %>%
  rename(time_submit = time_submit_auth)

#sanc
sanc <- vid_data %>%
  select(1, ends_with("_sanc")) %>%
  mutate_all(as.numeric) %>%
  pivot_longer(names_to = c("question", "video"), names_sep = "_", values_to = "score", 3:26) %>%
  rename(time_submit = time_submit_sanc)

Bind data back together with rbind

long_vid_data <- rbind(care, fair, loy, auth, sanc)

Use Filter to only keep time values < 300

lessthan300 <- long_vid_data %>%
  filter(time_submit < 300)