pacman::p_load(ggdist, ggridges, ggthemes,
colorspace, tidyverse)hands-on exercise 4
Visualizing Distribution
exam <- read_csv("data/Exam_data.csv")ggplot(exam,
aes(x = ENGLISH,
y = CLASS)) +
geom_density_ridges(
scale = 3,
rel_min_height = 0.01,
bandwidth = 3.4,
fill = lighten("#7097BB", .3),
color = "white"
) +
scale_x_continuous(
name = "English grades",
expand = c(0, 0)
) +
scale_y_discrete(name = NULL, expand = expansion(add = c(0.2, 2.6))) +
theme_ridges()
ggplot(exam,
aes(x = ENGLISH,
y = CLASS,
fill = stat(x))) +
geom_density_ridges_gradient(
scale = 3,
rel_min_height = 0.01) +
scale_fill_viridis_c(name = "Temp. [F]",
option = "C") +
scale_x_continuous(
name = "English grades",
expand = c(0, 0)
) +
scale_y_discrete(name = NULL, expand = expansion(add = c(0.2, 2.6))) +
theme_ridges()
ggplot(exam,
aes(x = ENGLISH,
y = CLASS,
fill = 0.5 - abs(0.5-stat(ecdf)))) +
stat_density_ridges(geom = "density_ridges_gradient",
calc_ecdf = TRUE) +
scale_fill_viridis_c(name = "Tail probability",
direction = -1) +
theme_ridges()
ggplot(exam,
aes(x = ENGLISH,
y = CLASS,
fill = factor(stat(quantile))
)) +
stat_density_ridges(
geom = "density_ridges_gradient",
calc_ecdf = TRUE,
quantiles = 4,
quantile_lines = TRUE) +
scale_fill_viridis_d(name = "Quartiles") +
theme_ridges()
ggplot(exam,
aes(x = ENGLISH,
y = CLASS,
fill = factor(stat(quantile))
)) +
stat_density_ridges(
geom = "density_ridges_gradient",
calc_ecdf = TRUE,
quantiles = c(0.025, 0.975)
) +
scale_fill_manual(
name = "Probability",
values = c("#FF0000A0", "#A0A0A0A0", "#0000FFA0"),
labels = c("(0, 0.025]", "(0.025, 0.975]", "(0.975, 1]")
) +
theme_ridges()
ggplot(exam,
aes(x = ENGLISH,
y = CLASS,
fill = factor(stat(quantile))
)) +
stat_density_ridges(
geom = "density_ridges_gradient",
calc_ecdf = TRUE,
quantiles = c(0.025, 0.975)
) +
scale_fill_manual(
name = "Probability",
values = c("#FF0000A0", "#A0A0A0A0", "#0000FFA0"),
labels = c("(0, 0.025]", "(0.025, 0.975]", "(0.975, 1]")
) +
theme_ridges()
ggplot(exam,
aes(x = RACE,
y = ENGLISH)) +
stat_halfeye(adjust = 0.5,
justification = -0.2,
.width = 0,
point_colour = NA)
ggplot(exam,
aes(x = RACE,
y = ENGLISH)) +
stat_halfeye(adjust = 0.5,
justification = -0.2,
.width = 0,
point_colour = NA) +
geom_boxplot(width = .20,
outlier.shape = NA)
ggplot(exam,
aes(x = RACE,
y = ENGLISH)) +
stat_halfeye(adjust = 0.5,
justification = -0.2,
.width = 0,
point_colour = NA) +
geom_boxplot(width = .20,
outlier.shape = NA) +
stat_dots(side = "left",
justification = 1.2,
binwidth = .5,
dotsize = 2)
ggplot(exam,
aes(x = RACE,
y = ENGLISH)) +
stat_halfeye(adjust = 0.5,
justification = -0.2,
.width = 0,
point_colour = NA) +
geom_boxplot(width = .20,
outlier.shape = NA) +
stat_dots(side = "left",
justification = 1.2,
binwidth = .5,
dotsize = 2)
ggplot(exam,
aes(x = RACE,
y = ENGLISH)) +
stat_halfeye(adjust = 0.5,
justification = -0.2,
.width = 0,
point_colour = NA) +
geom_boxplot(width = .20,
outlier.shape = NA) +
stat_dots(side = "left",
justification = 1.2,
binwidth = .5,
dotsize = 1.5) +
coord_flip() +
theme_economist()
Visual Statistical Analysis
pacman::p_load(ggstatsplot, tidyverse)set.seed(1234)
gghistostats(
data = exam,
x = ENGLISH,
type = "bayes",
test.value = 60,
xlab = "English scores"
)
ggbetweenstats(
data = exam,
x = GENDER,
y = MATHS,
type = "np",
messages = FALSE
)
ggbetweenstats(
data = exam,
x = RACE,
y = ENGLISH,
type = "p",
mean.ci = TRUE,
pairwise.comparisons = TRUE,
pairwise.display = "s",
p.adjust.method = "fdr",
messages = FALSE
)
ggscatterstats(
data = exam,
x = MATHS,
y = ENGLISH,
marginal = FALSE,
)
exam1 <- exam %>%
mutate(MATHS_bins =
cut(MATHS,
breaks = c(0,60,75,85,100))
)ggbarstats(exam1,
x = MATHS_bins,
y = GENDER)
pacman::p_load(readxl, performance, parameters, see)car_resale <- read_xls("data/ToyotaCorolla.xls",
"data")
car_resale# A tibble: 1,436 × 38
Id Model Price Age_08_04 Mfg_Month Mfg_Year KM Quarterly_Tax Weight
<dbl> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 81 TOYOTA … 18950 25 8 2002 20019 100 1180
2 1 TOYOTA … 13500 23 10 2002 46986 210 1165
3 2 TOYOTA … 13750 23 10 2002 72937 210 1165
4 3 TOYOTA… 13950 24 9 2002 41711 210 1165
5 4 TOYOTA … 14950 26 7 2002 48000 210 1165
6 5 TOYOTA … 13750 30 3 2002 38500 210 1170
7 6 TOYOTA … 12950 32 1 2002 61000 210 1170
8 7 TOYOTA… 16900 27 6 2002 94612 210 1245
9 8 TOYOTA … 18600 30 3 2002 75889 210 1245
10 44 TOYOTA … 16950 27 6 2002 110404 234 1255
# ℹ 1,426 more rows
# ℹ 29 more variables: Guarantee_Period <dbl>, HP_Bin <chr>, CC_bin <chr>,
# Doors <dbl>, Gears <dbl>, Cylinders <dbl>, Fuel_Type <chr>, Color <chr>,
# Met_Color <dbl>, Automatic <dbl>, Mfr_Guarantee <dbl>,
# BOVAG_Guarantee <dbl>, ABS <dbl>, Airbag_1 <dbl>, Airbag_2 <dbl>,
# Airco <dbl>, Automatic_airco <dbl>, Boardcomputer <dbl>, CD_Player <dbl>,
# Central_Lock <dbl>, Powered_Windows <dbl>, Power_Steering <dbl>, …model <- lm(Price ~ Age_08_04 + Mfg_Year + KM +
Weight + Guarantee_Period, data = car_resale)
model
Call:
lm(formula = Price ~ Age_08_04 + Mfg_Year + KM + Weight + Guarantee_Period,
data = car_resale)
Coefficients:
(Intercept) Age_08_04 Mfg_Year KM
-2.637e+06 -1.409e+01 1.315e+03 -2.323e-02
Weight Guarantee_Period
1.903e+01 2.770e+01 check_collinearity(model)# Check for Multicollinearity
Low Correlation
Term VIF VIF 95% CI Increased SE Tolerance Tolerance 95% CI
KM 1.46 [ 1.37, 1.57] 1.21 0.68 [0.64, 0.73]
Weight 1.41 [ 1.32, 1.51] 1.19 0.71 [0.66, 0.76]
Guarantee_Period 1.04 [ 1.01, 1.17] 1.02 0.97 [0.86, 0.99]
High Correlation
Term VIF VIF 95% CI Increased SE Tolerance Tolerance 95% CI
Age_08_04 31.07 [28.08, 34.38] 5.57 0.03 [0.03, 0.04]
Mfg_Year 31.16 [28.16, 34.48] 5.58 0.03 [0.03, 0.04]check_c <- check_collinearity(model)
plot(check_c)
model1 <- lm(Price ~ Age_08_04 + KM +
Weight + Guarantee_Period, data = car_resale)check_n <- check_normality(model1)plot(check_n)
check_h <- check_heteroscedasticity(model1)plot(check_h)
check_model(model1)
plot(parameters(model1))
ggcoefstats(model1,
output = "plot")
Visualising Uncertainty
devtools::install_github("wilkelab/ungeviz")pacman::p_load(ungeviz, plotly, crosstalk,
DT, ggdist, ggridges,
colorspace, gganimate, tidyverse)exam <- read_csv("data/Exam_data.csv")my_sum <- exam %>%
group_by(RACE) %>%
summarise(
n=n(),
mean=mean(MATHS),
sd=sd(MATHS)
) %>%
mutate(se=sd/sqrt(n-1))knitr::kable(head(my_sum), format = 'html')| RACE | n | mean | sd | se |
|---|---|---|---|---|
| Chinese | 193 | 76.50777 | 15.69040 | 1.132357 |
| Indian | 12 | 60.66667 | 23.35237 | 7.041005 |
| Malay | 108 | 57.44444 | 21.13478 | 2.043177 |
| Others | 9 | 69.66667 | 10.72381 | 3.791438 |
ggplot(my_sum) +
geom_errorbar(
aes(x=RACE,
ymin=mean-se,
ymax=mean+se),
width=0.2,
colour="black",
alpha=0.9,
size=0.5) +
geom_point(aes
(x=RACE,
y=mean),
stat="identity",
color="red",
size = 1.5,
alpha=1) +
ggtitle("Standard error of mean maths score by rac")
ggplot(my_sum) +
geom_errorbar(
aes(x=reorder(RACE, -mean),
ymin=mean-1.96*se,
ymax=mean+1.96*se),
width=0.2,
colour="black",
alpha=0.9,
size=0.5) +
geom_point(aes
(x=RACE,
y=mean),
stat="identity",
color="red",
size = 1.5,
alpha=1) +
labs(x = "Maths score",
title = "95% confidence interval of mean maths score by race")
shared_df = SharedData$new(my_sum)
bscols(widths = c(4,8),
ggplotly((ggplot(shared_df) +
geom_errorbar(aes(
x=reorder(RACE, -mean),
ymin=mean-2.58*se,
ymax=mean+2.58*se),
width=0.2,
colour="black",
alpha=0.9,
size=0.5) +
geom_point(aes(
x=RACE,
y=mean,
text = paste("Race:", `RACE`,
"<br>N:", `n`,
"<br>Avg. Scores:", round(mean, digits = 2),
"<br>95% CI:[",
round((mean-2.58*se), digits = 2), ",",
round((mean+2.58*se), digits = 2),"]")),
stat="identity",
color="red",
size = 1.5,
alpha=1) +
xlab("Race") +
ylab("Average Scores") +
theme_minimal() +
theme(axis.text.x = element_text(
angle = 45, vjust = 0.5, hjust=1)) +
ggtitle("99% Confidence interval of average /<br>maths scores by race")),
tooltip = "text"),
DT::datatable(shared_df,
rownames = FALSE,
class="compact",
width="100%",
options = list(pageLength = 10,
scrollX=T),
colnames = c("No. of pupils",
"Avg Scores",
"Std Dev",
"Std Error")) %>%
formatRound(columns=c('mean', 'sd', 'se'),
digits=2))exam %>%
ggplot(aes(x = RACE,
y = MATHS)) +
stat_pointinterval() +
labs(
title = "Visualising confidence intervals of mean math score",
subtitle = "Mean Point + Multiple-interval plot")
exam %>%
ggplot(aes(x = RACE, y = MATHS)) +
stat_pointinterval(.width = 0.95,
.point = median,
.interval = qi) +
labs(
title = "Visualising confidence intervals of median math score",
subtitle = "Median Point + Multiple-interval plot")
exam %>%
ggplot(aes(x = RACE,
y = MATHS)) +
stat_pointinterval(
show.legend = FALSE) +
labs(
title = "Visualising confidence intervals of mean math score",
subtitle = "Mean Point + Multiple-interval plot")
exam %>%
ggplot(aes(x = RACE,
y = MATHS)) +
stat_gradientinterval(
fill = "skyblue",
show.legend = TRUE
) +
labs(
title = "Visualising confidence intervals of mean math score",
subtitle = "Gradient + interval plot")
devtools::install_github("wilkelab/ungeviz")ggplot(data = exam,
(aes(x = factor(RACE), y = MATHS))) +
geom_point(position = position_jitter(
height = 0.3, width = 0.05),
size = 0.4, color = "#0072B2", alpha = 1/2) +
geom_hpline(data = sampler(25, group = RACE), height = 0.6, color = "#D55E00") +
theme_bw() +
# `.draw` is a generated column indicating the sample draw
transition_states(.draw, 1, 3)
ggplot(data = exam,
(aes(x = factor(RACE),
y = MATHS))) +
geom_point(position = position_jitter(
height = 0.3,
width = 0.05),
size = 0.4,
color = "#0072B2",
alpha = 1/2) +
geom_hpline(data = sampler(25,
group = RACE),
height = 0.6,
color = "#D55E00") +
theme_bw() +
transition_states(.draw, 1, 3)