.Rhistory

ps_data <- import("data/ps_data.sav")
ps_data <- import("https://raw.githubusercontent.com/Coryc3133/uoregon_r_bootcamp/master/pragmatic_scales_data.csv")
export(ps_data,
"data/ps_data.xlsx")
head(ps_data)
head(ps_data, n = 20)
tail(ps_data)
str(ps_data)
summary(ps_data)
ps_data[1, 5]
ps_data[1, "condition"]
ps_data[, "condition"]
ps_data$condition
which(ps_data$condition == "Label")
ps_data[which(ps_data$condition == "Label"),]
ps_data[which(ps_data$age >= 2.5),]
ps_data[,grep("^c", colnames(ps_data))]
ps_data[which(ps_data$condition == "Label" & ps_data$age < 3),]
ps_data[which(ps_data$item == "faces" | ps_data$item == "houses"),]
select(ps_data, age)
select(ps_data, age, condition)
select(ps_data, 1)
select(ps_data, -age)
select(ps_data, -5)
# select first three:
select(ps_data, 1:3)
# de-select last three:
select(ps_data, -(1:3)) # - requires parenthetical sequence
# select first three
select(ps_data, subid:correct)
# deselect first three
select(ps_data, -(subid:correct))
select(ps_data, starts_with("c"))
ps_data[, grep("^c", colnames(ps_data))]
select(ps_data, ends_with("e"))
select(ps_data, contains("i"))
filter(ps_data, condition == "No Label")
filter(ps_data, condition == "No Label" & age <= 3)
filter(ps_data, condition == "Label" | age <= 3)
filter(ps_data, between(age, 2.1, 2.5))
ps_data$age %>% # LHS is age vector from ps_data
sum() # pass that to the sum function
ps_data %>% # take the data, then...
select(age) %>%  # select age, then...
sum() # take the sum
ps_data %>% select(age) %>% sum()
ps_data %>%
select(age) %>%
sum()
ps_data %>% # take the data, then...
select(age) %>%  # select age, then...
sum()
sum(select(ps_data, age), na.rm = TRUE)
ps_data %>% # take the data, then...
filter(age > 2.5 | age > 3.2) %>% # filter for kids between 2.5 and 3.2, then...
select(subid, age) %>% # select subject id and centered age, then...
unique() # get unique rows
unique_filtered_data <- ps_data %>% # take the data, then...
filter(age > 2.5 | age > 3.2) %>% # filter for kids between 2.5 and 3.2, then...
select(subid, age) %>% # select subject id and centered age, then...
unique() # get unique rows
starwars %>%
select(name, homeworld)
starwars %>%
select(name:homeworld)
starwars %>%
select(contains("color"))
starwars %>%
select(homeworld, name, everything())
starwars %>%
filter(height < 100)
starwars %>%
filter(height > mean(height, na.rm = TRUE) + sd(height, na.rm = TRUE)) # don't forget na.rm!
starwars %>%
filter(is.na(mass)) # note you wrap the variable in is.na()
starwars %>%
filter(!is.na(mass))
!TRUE
!FALSE
! 5 == 5
! 5 == 4
starwars %>%
filter(height > mean(height, na.rm = TRUE) + sd(height, na.rm = TRUE) &
mass < mean(mass, na.rm = TRUE))
starwars %>%
filter(height > mean(height, na.rm = TRUE) + sd(height, na.rm = TRUE) |
height < mean(height, na.rm = TRUE) + sd(height, na.rm = TRUE))
starwars %>%
filter(hair_color == "grey")
starwars %>%
filter(hair_color == "grey" |
hair_color == "brown")
starwars %>%
filter(hair_color != "brown")
starwars %>%
filter(str_detect(hair_color, "grey")) # first argument is string var,
# followed by pattern it looks for
starwars %>%
filter(!str_detect(hair_color, "grey"))
starwars$height_in_m = starwars$height/100
starwars
# cleaning it back up
starwars <- starwars %>%
select(-height_in_m)
search()
starwars %>%
mutate(height_in_mm = height*10, # height in millimeters
height_in_m = height/100) # height in meters
starwars %>%
mutate(height_in_mm = height*10, # height in millimeters
height_in_m = height/100) # height in meters
starwars %>%
mutate(height_z = scale(height),
mass_z = scale(mass),
height_mass_z = rowMeans(data.frame(height_z, mass_z), na.rm = TRUE))
starwars %>%
mutate(height_z = scale(height),
mass_z = scale(mass),
height_mass_z = mean(data.frame(height_z, mass_z), na.rm = TRUE))
starwars %>%
rowwise() %>%
mutate(height_z = scale(height),
mass_z = scale(mass),
height_mass_z = mean(c(height_z, mass_z), na.rm = TRUE))
starwars %>%
mutate(height_z = scale(height),
mass_z = scale(mass)) %>%
rowwise() %>%
mutate(height_mass_z = mean(c(height_z, mass_z), na.rm = TRUE))
starwars
starwars %>%
mutate(gender = factor(gender))
starwars %>%
transmute(gender = factor(gender))
starwars %>%
mutate(gender = factor(gender))
starwars %>%
mutate(gender = mass*50)
starwars %>%
transmute(height_z = scale(height),
mass_z = scale(mass))
temp<- starwars %>%
transmute(height_z = scale(height),
mass_z = scale(mass))
View(temp)
View(temp)
starwars %>%
mutate(height_in_m = height / 100,
bmi = mass / height_in_m^2)
starwars %>%
mutate(height_in_m = height / 100,
bmi = mass / height_in_m^2)
starwars %>%
transmute(name = name,
mass = mass,
height_in_m = height / 100,
bmi = mass / height_in_m^2)
starwars %>%
group_by(homeworld)
starwars %>%
group_by(homeworld)
x <- starwars %>%
group_by(homeworld)
starwars %>%
group_by(homeworld)
starwars %>%
group_by(homeworld)
starwars %>%
group_by(homeworld)
starwars %>%
group_by(homeworld)
starwars %>%
group_by(homeworld)
5 + 5
starwars %>%
group_by(homeworld)
starwars %>%
mutate(mean_mass = mean(mass, na.rm = TRUE)) %>%
select(homeworld, mean_mass, everything()) # re-arrange for easy viewing
starwars %>%
group_by(homeworld) %>%
mutate(mean_mass = mean(mass, na.rm = TRUE)) %>%
select(homeworld, mean_mass, everything())
starwars %>%
group_by(homeworld, species) %>%
mutate(mean_mass = mean(mass, na.rm = TRUE)) %>%
select(homeworld, mean_mass, everything())
starwars %>%
summarize(mean_mass = mean(mass, na.rm = TRUE))
?n
starwars %>%
summarize(mean_mass = mean(mass, na.rm = TRUE),
sd_mass = sd(mass, na.rm = TRUE),
n = n())
starwars %>%
summarize(mean_mass = mean(mass, na.rm = TRUE),
sd_mass = sd(mass, na.rm = TRUE),
n = n(na.rm = TRUE))
starwars %>%
summarize(mean_mass = mean(mass, na.rm = TRUE),
sd_mass = sd(mass, na.rm = TRUE),
n = n())
starwars %>%
filter(!is.na(mass)) %>%
summarize(mean_mass = mean(mass, na.rm = TRUE),
sd_mass = sd(mass, na.rm = TRUE),
n = n())
starwars %>%
summarize(mean_mass = mean(mass, na.rm = TRUE),
sd_mass = sd(mass, na.rm = TRUE),
n = n())
starwars %>%
group_by(species) %>% # just add the group_by() call
summarize(mean_mass = mean(mass, na.rm = TRUE),
sd_mass = sd(mass, na.rm = TRUE),
n = n())
starwars %>%
group_by(species) %>% # just add the group_by() call
summarize(mean_mass = mean(mass, na.rm = TRUE),
sd_mass = sd(mass, na.rm = TRUE),
n = n()) %>%
filter(n > 1)
starwars %>% filter(species == "Zabrak")
starwars %>%
group_by(species, gender) %>% # just change the group_by() call
summarize(mean_mass = mean(mass, na.rm = TRUE),
sd_mass = sd(mass, na.rm = TRUE),
n = n()) %>%
filter(n > 1)
starwars %>% filter(is.na(species))
ps_data %>%
group_by(condition, item) %>%
summarize(num_correct = sum(correct),
num_trials = n(),
prop_correct = mean(correct))
starwars %>%
arrange(mass)
starwars %>%
arrange(desc(mass))
starwars %>%
arrange(height, mass)
starwars %>%
arrange(name)
starwars %>%
rename(char_name = name)
starwars %>%
rename(char_name = name,
height_cm = height,
mass_kg = mass)
lightsabers <- data.frame(name = c("Luke Skywalker",
"Darth Vader",
"Obi-Wan Kenobi",
"Dooku"),
lightsaber_color = c("green",
"red",
"blue",
"red"))
lightsabers
left_join(starwars,
lightsabers)
left_join(lightsabers,
starwars)
lightsabers
starwars %>%
distinct(homeworld)
starwars %>%
distinct(homeworld, species)
starwars %>%
distinct(homeworld, species, .keep_all = TRUE)
starwars %>%
distinct()
starwars %>%
count(species)
head(iris)
ggplot(data = iris)
ggplot(data = iris) + # attach data
geom_histogram(mapping = aes(x = Sepal.Length)) # add geom w/ aesthetic map
ggplot(data = iris) + # attach data
geom_histogram(mapping = aes(x = Sepal.Length), # add geom to aesthetic mapping
bins = 9) # change bins to 9
ggplot(data = iris) + # attach data
geom_histogram(mapping = aes(x = Sepal.Length),
fill = "red") # fill, bc hist bars are 2-d
ggplot(data = iris) + # attach data
geom_histogram(mapping = aes(x = Sepal.Length), # add geom to aesthetic mapping
bins = 100) # change bins to 9
ggplot(data = iris) + # attach data
geom_histogram(mapping = aes(x = Sepal.Length),
fill = "red") # fill, bc hist bars are 2-d
ggplot(data = iris) + # attach data
geom_histogram(mapping = aes(x = Sepal.Length),
color = "red") # fill, bc hist bars are 2-d
ggplot(data = iris) + # attach data
geom_histogram(mapping = aes(x = Sepal.Length),
fill = "red") # fill, bc hist bars are 2-d
ggplot(data = iris) + # attach data
geom_point(mapping = aes(x = Sepal.Length)) # add geom w/ aesthetic map
ggplot(data = iris) + # attach data
geom_point(mapping = aes(x = Sepal.Length, y = Petal.Length)) # add geom w/ aesthetic map
ggplot(data = iris) + # attach data
geom_point(mapping = aes(x = Sepal.Length, # geom w/ aesthetic mapping
y = Petal.Length,
color = Species)) # color including in aes()
ggplot(data = iris) + # attach data
geom_point(mapping = aes(x = Sepal.Length, # geom w/ aesthetic mapping
y = Petal.Length,
color = "red")) # color including in aes()
ggplot(data = iris) +
geom_point(mapping = aes(x = Sepal.Length, y = Petal.Length)) +
facet_wrap(~ Species)
ggplot(data = iris) +
geom_point(mapping = aes(x = Sepal.Length, y = Petal.Length, color = Species)) +
geom_smooth(mapping = aes(x = Sepal.Length, y = Petal.Length), color = "black")
ggplot(data = iris) +
geom_point(aes(x = Sepal.Length, y = Petal.Length, color = Species)) +
geom_smooth(aes(x = Sepal.Length, y = Petal.Length),
color = "black",
method = "lm")
ggplot(data = iris, aes(x = Sepal.Length, y = Petal.Length)) +
geom_point(aes(color = Species)) +
geom_smooth(color = "black", method = "lm")
ggplot(data = iris, aes(x = Sepal.Length, y = Petal.Length, color = Species)) +
geom_point() +
geom_smooth()
ggplot(data = iris, aes(x = Sepal.Length, y = Petal.Length, color = Species)) +
geom_point() +
geom_smooth(color = "black")
ggplot(data = iris, aes(x = Sepal.Length, y = Petal.Length, color = Species)) +
geom_point() + # inhereit global
geom_smooth() + # inherit global
geom_smooth(color = "black") # change color to constant
ggplot(data = iris, aes(x = Species, y = Petal.Length)) +
geom_bar() # inhereit global
?geom_bar
ggplot(data = iris, aes(x = Species, y = Petal.Length)) +
geom_bar(stat = "identity") # inhereit global
iris$Petal.Length
ggplot(data = iris, aes(x = Species, y = Petal.Length, fill = Species)) +
geom_bar(stat = "identity") # inhereit global
# get summary data
starwars_means <- starwars %>%
filter(species == "Human" | species == "Droid") %>%
group_by(species) %>%
summarize(mean_mass = mean(mass, na.rm = TRUE))
ggplot(starwars_means, aes(x = species, y = mean_mass, fill = species)) +
geom_bar(stat = "identity")
# uisng the summary data as the global data
ggplot(starwars_means, aes(x = species, y = mean_mass, fill = species)) +
geom_bar(stat = "identity") +
geom_point(data = filter(starwars, species == "Human" |
species == "Droid"), # using individual
# data as geom specific data
aes(x = species, y = mass))
# uisng the summary data as the global data
ggplot(starwars_means, aes(x = species, y = mean_mass, fill = species)) +
geom_bar(stat = "identity") +
geom_point(data = filter(starwars, species == "Human" |
species == "Droid"), # using individual
# data as geom specific data
aes(x = species, y = mass),
position = position_jitter())
# uisng the summary data as the global data
ggplot(starwars_means, aes(x = species, y = mean_mass, fill = species)) +
geom_bar(stat = "identity") +
geom_point(data = filter(starwars, species == "Human" |
species == "Droid"), # using individual
# data as geom specific data
aes(x = species, y = mass),
position = position_jitter(height = 0, width = .1))
# uisng the summary data as the global data
ggplot(starwars_means, aes(x = species, y = mean_mass, fill = species)) +
geom_bar(stat = "identity") +
geom_point(data = filter(starwars, species == "Human" |
species == "Droid"), # using individual
# data as geom specific data
aes(x = species, y = mass),
alpha = .3)
# Import ps_data (uneccesary if you completed exercise 1.2a)
ps_data <- import("pragmatic_scales_data.csv")
# Mean Data:
ps_mean_age <- ps_data %>%
group_by(condition) %>%
summarize(mean_age = mean(age, na.rm = TRUE))
# distinct kids data
ps_distinct_age <- ps_data %>%
distinct(subid, condition, age)
ggplot(ps_mean_age, aes(x = condition, y = mean_age, fill = condition)) +
geom_bar(stat = "identity") +
geom_point(data = ps_distinct_age, aes(x = condition, y = age),
position = position_jitter(height = 0, width = .2))
ggplot(ps_mean_age, aes(x = condition, y = mean_age, fill = condition)) +
geom_bar(stat = "identity") +
geom_point(data = ps_distinct_age, aes(x = condition, y = age),
position = position_jitter(height = 0, width = .2)) +
# change labels with labs:
labs(title = "Age by Condition:", # add a title with title
subtitle = "Group- and Kid-level age", # you can even add a subtitle
x = "Condition",
y = "Mean Age")
ggplot(ps_mean_age, aes(x = condition, y = mean_age, fill = condition)) +
geom_bar(stat = "identity") +
geom_point(data = ps_distinct_age, aes(x = condition, y = age),
position = position_jitter(height = 0, width = .2)) +
# change labels with labs:
labs(title = "Age by Condition:", # add a title with title
subtitle = "Group- and Kid-level age", # you can even add a subtitle
x = "Condition",
fill = "Condition",
y = "Mean Age")
ggplot(ps_mean_age, aes(x = condition, y = mean_age, fill = condition)) +
geom_bar(stat = "identity") +
geom_point(data = ps_distinct_age, aes(x = condition, y = age),
position = position_jitter(height = 0, width = .2)) +
# change labels with labs:
labs(title = "Age by Condition:", # add a title with title
subtitle = "Group- and Kid-level age", # you can even add a subtitle
x = "Condition",
y = "Mean Age") +
theme(axis.text = # axis.title argument of theme
element_text(size = 30)) # size element of element_text
ggplot(ps_mean_age, aes(x = condition, y = mean_age, fill = condition)) +
geom_bar(stat = "identity") +
geom_point(data = ps_distinct_age, aes(x = condition, y = age),
position = position_jitter(height = 0, width = .2)) +
# change labels with labs:
labs(title = "Age by Condition:", # add a title with title
subtitle = "Group- and Kid-level age", # you can even add a subtitle
x = "Condition",
y = "Mean Age") +
theme(axis.text = # axis.title argument of theme
element_blank()) # set to element_blank
label_madness_theme <- theme(axis.text = # axis.title argument of theme
element_text(size = 30)) # size element of element_text
ggplot(ps_data, aes(x = item, y = correct, fill = item)) +
geom_bar(stat = "identity") +
facet_wrap(~condition) +
label_madness_theme # add in the custom theme
# Custom theme for the reputation manuscript
theme_rep_manuscript <-  theme(panel.background = element_blank(),
panel.grid.major.x = element_line(size=.4, color="gray90"))+
theme(axis.line.x = element_line(color="black", size = 1),
axis.line.y = element_line(color="black", size = 1))+
theme(axis.title = element_text(size = rel(1), color="black"),
axis.text = element_text(size = rel(1), color="black"))+
theme(plot.title= element_text(size=rel(1), hjust = .5))
# Custom theme for the reputation manuscript
theme_rep_ppt <-  theme(panel.background = element_blank(),
panel.grid.major.x = element_line(size=1, color="gray90"))+
theme(axis.line.x = element_line(color="black", size = 2),
axis.line.y = element_line(color="black", size = 2))+
theme(axis.title = element_text(size = rel(2), color="black"),
axis.text = element_text(size = rel(2), color="black"))+
theme(plot.title= element_text(size=rel(2), hjust = .5))
ggplot(ps_data, aes(x = item, y = correct, fill = item)) +
geom_bar(stat = "identity") +
facet_wrap(~condition) +
theme_rep_manuscript
ggplot(ps_data, aes(x = item, y = correct, fill = item)) +
geom_bar(stat = "identity") +
facet_wrap(~condition) +
theme_rep_ppt +
coord_flip() # flip the coordinates to accomodate size of text
ggplot(ps_data, aes(x = item, y = correct, fill = item)) +
geom_bar(stat = "identity") +
facet_wrap(~condition) +
theme_minimal()
ggplot(ps_data, aes(x = item, y = correct, fill = item)) +
geom_bar(stat = "identity") +
facet_wrap(~condition) +
theme_linedraw()
diamonds <- diamonds %>%
sample_n(1000)
diamonds
ggplot(diamonds, aes(x = carat)) +
geom_histogram()
ggplot(diamonds, aes(x = price)) +
geom_histogram()
ggplot(diamonds, aes(x = carat, y = price)) +
geom_point() +
theme_minimal() +
scale_x_log10() +
scale_y_log10()
ggplot(diamonds, aes(x = carat, y = price)) +
geom_point() +
theme_minimal() +
scale_x_log10() +
scale_y_log10()
ggplot(diamonds, aes(x = carat, y = price, color = cut)) +
geom_point(alpha = .5) + # changing alpha bc of overlap
theme_minimal() +
scale_x_log10() +
scale_y_log10()
?scale_color_brewer
ggplot(diamonds, aes(x = carat, y = price, color = cut)) +
geom_point(alpha = .5) + # changing alpha bc of overlap
theme_minimal() +
scale_x_log10() +
scale_y_log10() +
scale_color_brewer(palette="Set1")
ggplot(diamonds, aes(x = carat, y = price, color = cut)) +
geom_point(alpha = .5) + # changing alpha bc of overlap
theme_minimal() +
scale_x_log10() +
scale_y_log10() +
scale_color_brewer(palette="Dark2")
ggplot(diamonds, aes(x = carat, y = price, color = cut)) +
geom_point(alpha = .5) + # changing alpha bc of overlap
theme_minimal() +
scale_x_log10() +
scale_y_log10() +
scale_color_brewer(palette="Dark2") +
annotation_logticks()