Load libraries

library(ggplot2)
library(dplyr)
library(langcog)
library(readr)
library(cowplot)
library(data.table)
library(magrittr)
library(lubridate)
library(tidyr)

na.mean <- function(x){mean(x,na.rm=T)}
pilot.data <- read_csv('data/pilot.data.4.csv') %>%
  select(EndDate,Finished,ID,game_neg:game_pos,
         self_movie:self_game,other_movie:other_game,
         sim1:like2,diff_cond:sim_cond)

#Exclusions
pilot.data %<>%
  mutate(EndDate = mdy_hm(EndDate)) %>%
  arrange(ID,EndDate) %>%
  distinct(ID) #only the first response from each participant

Get data into tidy form

munged.data <- pilot.data %>%
  mutate(cond = ifelse(is.na(sim_cond),"Different", "Similar")) %>%
  rowwise() %>%
  mutate(sim = mean(c(sim1, sim2),na.rm=TRUE),
         like = mean(c(sim1, sim2),na.rm=TRUE),
         movie_prime = if(nchar(movie_neg) > 0 & nchar(movie_pos) == 0) "Negative"
         else if(nchar(movie_pos) > 0 & nchar(movie_neg) == 0) "Positive"
         else "None",
         family_prime = if(nchar(family_neg) > 0 & nchar(family_pos) == 0) "Negative"
         else if(nchar(family_pos) > 0 & nchar(family_neg) == 0) "Positive"
         else "None",
         pjs_prime = if(nchar(pjs_neg) > 0 & nchar(pjs_pos) == 0) "Negative"
         else if(nchar(pjs_pos) > 0 & nchar(pjs_neg) == 0) "Positive"
         else "None",
         hair_prime = if(nchar(hair_neg) > 0 & nchar(hair_pos) == 0) "Negative"
         else if(nchar(hair_pos) > 0 & nchar(hair_neg) == 0) "Positive"
         else "None",
         train_prime = if(nchar(train_neg) > 0 & nchar(train_pos) == 0) "Negative"
         else if(nchar(train_pos) > 0 & nchar(train_neg) == 0) "Positive"
         else "None",
         game_prime = if(nchar(game_neg) > 0 & nchar(game_pos) == 0) "Negative"
         else if(nchar(game_pos) > 0 & nchar(game_neg) == 0) "Positive"
         else "None") %>%
  select(EndDate,ID,movie_prime:game_prime,self_movie:other_game,sim,like,cond)

# Gather primes into long format
tidy.primes <- munged.data %>%
  gather(activity,prime,movie_prime:game_prime) %>%
  separate(activity, c("activity", "measure")) %>%
  select(ID,activity,prime,sim:cond)

# Gather self-ratings into long format
tidy.self <- munged.data %>%
  gather(person_activity,score,self_movie:self_game) %>%
  separate(person_activity, c("person", "activity")) %>%
  select(ID,person,activity,score,sim:cond)

# Gather other-ratings into long format
tidy.other <- munged.data %>%
  gather(person_activity,score,other_movie:other_game) %>%
  separate(person_activity, c("person", "activity")) %>%
  select(ID,person,activity,score,sim:cond)

tidy.self.data <- left_join(tidy.primes,tidy.self)

# Split other into similar and non-similar
tidy.other.data <- left_join(tidy.primes,tidy.other) %>%
  rowwise() %>%
  mutate(similarity = if(sim >= 4) "similar"
         else if(sim <= 2) "different"
         else "neither")

Similarity scores across participants

ggplot(aes(x = sim),data=tidy.other.data) +
  geom_histogram(breaks = seq(.5,6.5,by=1),
                 color="white",fill="steelblue") +
  scale_x_continuous(name = "Similarity Rating (1-5)",
                     breaks = seq(1,5),
                     limits = c(0,6)) +
  scale_y_continuous(name = "Frequency")

Finish munging

tidy.other.data %<>%
  filter(similarity %in% c("similar", "different")) %>%
  unite(person.similar,person,similarity) %>%
  rename(person = person.similar)

tidy.data <- bind_rows(tidy.self.data,tidy.other.data) %>%
  mutate(person = factor(person, levels = c("self", "other_similar", "other_different"),
                         labels = c("self", "other-similar", "other-different")),
         prime = factor(prime, levels = c("Negative", "None", "Positive"))) %>% 
  group_by(person,prime,activity)

Aggregate scores by activity and prime

person.activity.data <- tidy.data %>%
  summarise(mean = na.mean(score)) %>%
  left_join(multi_boot(tidy.data,column="score", summary_function = "na.mean",
                     statistics_functions = c("ci_lower","ci_upper")), 
            copy = TRUE)
ggplot(aes(x = activity, y = mean, color = prime), data = person.activity.data) +
  facet_grid(person ~ .) +
  geom_pointrange(aes(ymin = ci_lower, ymax = ci_upper),
                  position=position_dodge(.3),size=.75) +
  scale_color_manual(values = c("steelblue", "gray", "darkred")) +
  scale_y_continuous(name = "Mean Rating (1-7)")

Aggregate scores by prime

person.data <- person.activity.data %>%
  summarise(mean = mean(mean)) %>%
  left_join(multi_boot(person.activity.data,column="mean",
                     statistics_functions = c("ci_lower","ci_upper")), 
            copy = TRUE)  
ggplot(aes(x = person, y = mean, color = prime), data = person.data) +
  geom_pointrange(aes(ymin = ci_lower, ymax = ci_upper),
                  position=position_dodge(.3),size=.75) +
  scale_color_manual(values = c("steelblue", "gray", "darkred")) +
  scale_y_continuous(name = "Mean Rating (1-7)")