# Exercise 06 from "dplyr, or a dance with data"
#
# Author: Danielle Navarro (d.navarro@unsw.edu.au)
# Date: 11 March 2020
# preliminaries -----------------------------------------------------------
# load packages
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.5.1 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.1
## ✔ purrr 1.0.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
# import data
swow <- "data_swow.csv.zip" %>%
read_tsv() %>% # read the data from file
mutate(id = 1:n()) %>% # add the "id" column
rename(
n_response = R1, # nicer name for the response count
n_total = N, # nicer name for the total cue presentations
strength = R1.Strength # nicer name for the estimated response strength
)
## Multiple files in zip: reading 'swow.csv'
## Rows: 483636 Columns: 5
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: "\t"
## chr (2): cue, response
## dbl (3): R1, N, R1.Strength
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
# words associated with "man" and "woman" ---------------------------------
woman_fwd <- swow %>%
filter(cue == "woman", n_response > 1) %>%
select(cue, response, strength, id) %>%
mutate(
rank = rank(-strength), # rank the data by strength
type = "forward", # this is forward associate (i.e., it's woman_FWD)
word = "woman", # the word is "woman" (i.e., it's WOMAN_fwd)
associate = response # for forward associations, the RESPONSE is the asociate
)
woman_bck <- swow %>%
filter(response == "woman", n_response > 1) %>%
arrange(desc(strength)) %>%
select(cue, response, strength, id) %>%
mutate(
rank = rank(-strength), # rank the data by strength
type = "backward", # this is backward associate (i.e., it's woman_BCK)
word = "woman", # the word is "woman" (i.e., it's WOMAN_bck)
associate = cue # for backward associations, the CUE is the associate
)
man_fwd <- swow %>%
filter(cue == "man", n_response > 1) %>%
select(-n_response, -n_total) %>%
mutate(
rank = rank(-strength), # rank of the association
type = "forward", # direction of the association
word = "man", # word being "associated to"
associate = response # word that is the "associate of"
)
man_bck <- swow %>%
filter(response == "man", n_response > 1) %>%
arrange(desc(strength)) %>%
select(-starts_with("n_")) %>% # ... remove variables starting with "n_"
mutate(
rank = rank(-strength), # rank of the association
type = "backward", # direction of the association
word = "man", # word being "associated to"
associate = cue # word that is the "associate of"
)
# combine the data sets ---------------------------------------------------
gender <- bind_rows(woman_fwd, woman_bck,
man_fwd, man_bck) %>% # binding rows of data columns matched by name
select(id:associate) %>% # selecting from id to associate
filter(associate != "man", associate != "woman") # get rid of associates with man or woman in them
# create and plot gender_fwd ----------------------------------------------
gender_fwd <- gender %>%
filter(
type == "forward"
) %>% # selecting for only forward
pivot_wider(
id_cols = associate, # first column = associate
names_from = word, # names of word column used to organise columns
values_from = rank # values taken from rank column
) %>%
mutate(
woman = replace_na(1/woman, 0), # make new woman value 1/ old woman value
man = replace_na(1/man, 0), # replace values of NA with 0
diff = woman - man # caluculate the difference between new woman and man scores
) %>%
arrange(diff) # arrange values by smallest to largest difference
picture_fwd <- ggplot(
data = gender_fwd, # taking data from gender_fwd
mapping = aes(
x = associate %>% reorder(diff), # associate is reordered by difference
y = diff
)) +
geom_col() + # create bar chart with height of data representing data
coord_flip() # flip the coordinates
#plot(picture_fwd)
# create and plot gender_bck ----------------------------------------------
# YOUR TURN...
#
# 1. The previous section contains all the code that I used in the slides
# to draw the plot of gender_fwd. Source this script to check that it
# works.
#
# 2. The code in the previous section has one very bad flaw... there are
# no comments. Try to add comments to this code so that when YOU have
# to read it again in a few weeks (months) times, you can work out
# what it is doing
#
# 3. In THIS section, try to modify the code from the previous section
# so that it creates and plots of the "gender_bck" variable. Your result
# should look the same as the figure shown in the slide
gender_bck <- gender %>%
filter(type == "backward") %>% # use only backward values
pivot_wider(
id_cols = associate, # identified by associate
names_from = word, # names from woman or man
values_from = rank # values from rank
) %>%
mutate(
woman = (1/woman) %>% replace_na(0), # new woman or man value and replace NA with 0
man = (1/man) %>% replace_na(0),
diff = woman - man # difference between new woman and man values
) %>%
arrange(diff) # organised by difference from smallest to largest
picture_bck <- ggplot(
data = gender_bck, # taking data from gender_bck
mapping = aes(
x = associate %>% reorder(diff), # associate is reordered by difference
y = diff
)) +
geom_col() + # create bar chart with height of data representing data
coord_flip() # flip the coordinates
plot(picture_bck)
