ggpmisc

library(ggpmisc)
library(data.table)
library(dplyr)
library(DT)
library(corrplot)
library(Hmisc)
library(rpart)
library(nlme)
library(ggpmisc)
library(ggrepel)
library(xts)
library(lubridate)
library(tibble)
library(dplyr)

library(ggpmisc)
library(data.table)
library(dplyr)
library(DT)
library(corrplot)
library(Hmisc)
library(rpart)
library(nlme)
library(ggpmisc)
library(ggrepel)
library(xts)
library(lubridate)
library(tibble)
library(dplyr)
old_theme <- theme_set(theme_bw())

tb <- mpg %>%
  group_by(cyl) %>%
  summarise(hwy = median(hwy), cty = median(cty))
data.tb <- tibble(x = 7, y = 44, tb = list(tb))
ggplot(mpg, aes(displ, hwy, colour = factor(cyl))) +
  geom_table(data = data.tb, aes(x, y, label = tb)) +
  geom_point() 

tb.pm <- tibble(Parameter = c("frac(beta[1], a^2)", "frac(beta[2], a^3)"),
                Value = c("10^2.4", "10^3.532"))
data.tb <- tibble(x = 7, y = 44, tb = list(tb.pm))
ggplot(mpg, aes(displ, cty)) +
  geom_point() +
  geom_table(data = data.tb, aes(x, y, label = tb), parse = TRUE) +
  theme_bw()

set.seed(4321)
# generate artificial data
x <- -99:100
y <- x + rnorm(length(x), mean = 0, sd = abs(x))
my.data <- data.frame(x, 
                      y, 
                      group = c("A", "B"))

datatable(my.data)

ggplot(my.data, aes(x, y, colour = group)) +
  geom_quadrant_lines() +
  stat_quadrant_counts(geom = "label_npc") +
  geom_point() +
  expand_limits(y = c(-260, 260)) +
  facet_wrap(~group) 

datatable(mpg)

p <- ggplot(mpg, aes(factor(cyl), hwy, fill = factor(cyl))) +
  stat_summary(geom = "col", fun.y = mean, width = 2/3) +
  labs(x = "Number of cylinders", y = NULL, title = "Means") +
  scale_fill_discrete(guide = FALSE)

data.tb <- tibble(x = 7, y = 44, 
                  plot = list(p +
                                theme_bw(8)))

ggplot(mpg, aes(displ, hwy, colour = factor(cyl))) +
  geom_plot(data = data.tb, aes(x, y, label = plot)) +
  geom_point() +
  labs(x = "Engine displacement (l)", y = "Fuel use efficiency (MPG)",
       colour = "Engine cylinders\n(number)") +
  theme_bw()

set.seed(4321)
# generate artificial data
x <- 1:100
y <- (x + x^2 + x^3) + rnorm(length(x), mean = 0, sd = mean(x^3) / 4)
my.data <- data.frame(x, 
                      y, 
                      group = c("A", "B"), 
                      y2 = y * c(0.5,2),
                      block = c("a", "a", "b", "b"),
                      wt = sqrt(x))
datatable(my.data)

formula <- y ~ poly(x, 3, raw = TRUE)
ggplot(my.data, aes(x, y2, fill = block)) +
  geom_point(shape = 21, size = 3) +
  geom_smooth(method = "lm", formula = formula) +
  stat_poly_eq(aes(label = ..rr.label..), size = 3,
               geom = "label_npc", alpha = 0.33,
               formula = formula, parse = TRUE) +
  facet_wrap(~group, scales = "free_y")

formula <- y ~ x + I(x^2) + I(x^3)
ggplot(my.data, aes(x, y)) +
  geom_point() +
  geom_smooth(method = "lm", formula = formula) +
  stat_fit_tb(method = "lm",
              method.args = list(formula = formula),
              tb.vars = c(Parameter = "term", 
                          Estimate = "estimate", 
                          "s.e." = "std.error", 
                          "italic(t)" = "statistic", 
                          "italic(P)" = "p.value"),
              label.y = "top", label.x = "left",
              parse = TRUE)

datatable(chickwts)

ggplot(chickwts, aes(factor(feed), weight)) +
  stat_summary(fun.data = "mean_se") +
  stat_fit_tb(tb.type = "fit.anova",
              label.x = "center",
              label.y = "bottom") +
  expand_limits(y = 0)

random_string <- function(len = 6) {
paste(sample(letters, len, replace = TRUE), collapse = "")
}

# Make random data.
set.seed(1001)
d <- tibble::tibble(
  x = rnorm(100),
  y = rnorm(100),
  group = rep(c("A", "B"), c(50, 50)),
  lab = replicate(100, { random_string() })
)

datatable(d)

ggplot(data = d, aes(x, y, label = lab, color = group)) +
  geom_point() +
  stat_dens2d_labels(geom = "label_repel", 
                     keep.fraction = 0.35, 
                     alpha = 0.8,
                     label.fill = NA)

ggplot(data = d, aes(x, y, label = lab, color = group)) +
  geom_point() +
  stat_dens2d_labels(geom = "label_repel", 
                     keep.fraction = 0.6, 
                     alpha = 0.9,
                     label.fill = NA)

lindia

library(lindia)
library(MASS)
data(Cars93)
datatable(Cars93)

# create linear model
cars_lm <- lm(Price ~ Passengers + Length + RPM, data = Cars93)
plots <- gg_diagnose(cars_lm, plot.all = FALSE)
names(plots)

## [1] "residual_hist" "Passengers"    "Length"        "RPM"          
## [5] "res_fitted"    "qqplot"        "scalelocation" "resleverage"  
## [9] "cooksd"

#  [1] "residual_hist" "Passengers"    "Length"        "RPM"          
#  [5] "res_fitted"    "qqplot"        "scalelocation" "resleverage"  
#  [9] "cooksd"
exclude_plots <- plots[-c(1, 3)]    # exclude certain diagnostics plots
include_plots <- plots[c(1, 3)]      # include certain diagnostics plots
plot_all(exclude_plots)

cars_lm_2 <- lm(Price ~ Passengers + Length + RPM + Origin, data = Cars93)

gg_diagnose(cars_lm_2)

gg_diagnose(cars_lm_2, theme = theme_bw())

sugrrants

library(tidyr)
library(dplyr)
library(viridis)
library(sugrrants)
##library(tsibble)
library(ggplot2)

library(sugrrants)
datatable(pedestrian)

names(pedestrian)

##  [1] "Date_Time"     "Date"          "Year"          "Month"        
##  [5] "Mdate"         "Day"           "Time"          "Sensor_ID"    
##  [9] "Sensor_Name"   "Hourly_Counts"

pedestrian17 <- pedestrian
pedestrian17

## # A tibble: 78,755 x 10
##    Date_Time           Date        Year Month Mdate Day    Time Sensor_ID
##    <dttm>              <date>     <int> <ord> <int> <ord> <int>     <int>
##  1 2016-01-01 00:00:00 2016-01-01  2016 Janu~     1 Frid~     0        18
##  2 2016-01-01 00:00:00 2016-01-01  2016 Janu~     1 Frid~     0        13
##  3 2016-01-01 00:00:00 2016-01-01  2016 Janu~     1 Frid~     0         3
##  4 2016-01-01 00:00:00 2016-01-01  2016 Janu~     1 Frid~     0         9
##  5 2016-01-01 00:00:00 2016-01-01  2016 Janu~     1 Frid~     0         6
##  6 2016-01-01 00:00:00 2016-01-01  2016 Janu~     1 Frid~     0        25
##  7 2016-01-01 00:00:00 2016-01-01  2016 Janu~     1 Frid~     0        30
##  8 2016-01-01 01:00:00 2016-01-01  2016 Janu~     1 Frid~     1        18
##  9 2016-01-01 01:00:00 2016-01-01  2016 Janu~     1 Frid~     1        13
## 10 2016-01-01 01:00:00 2016-01-01  2016 Janu~     1 Frid~     1         3
## # ... with 78,745 more rows, and 2 more variables: Sensor_Name <chr>,
## #   Hourly_Counts <int>

pedestrian17$Sensor_ID= as.factor(pedestrian17$Sensor_ID)
centre <- subset(pedestrian17, Sensor_Name == "Melbourne Central")
centre_calendar <- centre %>%
  frame_calendar(x = Time, y = Hourly_Counts, date = Date, calendar = "monthly")
centre_calendar

## # A tibble: 8,880 x 12
##    Date_Time           Date        Year Month Mdate Day    Time Sensor_ID
##    <dttm>              <date>     <int> <ord> <int> <ord> <int> <fct>    
##  1 2016-01-01 00:00:00 2016-01-01  2016 Janu~     1 Frid~     0 3        
##  2 2016-01-01 01:00:00 2016-01-01  2016 Janu~     1 Frid~     1 3        
##  3 2016-01-01 02:00:00 2016-01-01  2016 Janu~     1 Frid~     2 3        
##  4 2016-01-01 03:00:00 2016-01-01  2016 Janu~     1 Frid~     3 3        
##  5 2016-01-01 04:00:00 2016-01-01  2016 Janu~     1 Frid~     4 3        
##  6 2016-01-01 05:00:00 2016-01-01  2016 Janu~     1 Frid~     5 3        
##  7 2016-01-01 06:00:00 2016-01-01  2016 Janu~     1 Frid~     6 3        
##  8 2016-01-01 07:00:00 2016-01-01  2016 Janu~     1 Frid~     7 3        
##  9 2016-01-01 08:00:00 2016-01-01  2016 Janu~     1 Frid~     8 3        
## 10 2016-01-01 09:00:00 2016-01-01  2016 Janu~     1 Frid~     9 3        
## # ... with 8,870 more rows, and 4 more variables: Sensor_Name <chr>,
## #   Hourly_Counts <int>, .Time <dbl>, .Hourly_Counts <dbl>

p1 <- centre_calendar %>% 
  ggplot(aes(x = .Time, y = .Hourly_Counts, group = Date)) +
  geom_line()
p1

prettify(p1)+theme_bw()

two_sensors <- c("Lonsdale St (South)", "Melbourne Convention Exhibition Centre")
two_sensors_df <- subset(pedestrian17, Sensor_Name == "Lonsdale St (South)" |
                           Sensor_Name =="Melbourne Convention Exhibition Centre")

two_sensors_calendar <- two_sensors_df %>%
  frame_calendar(x = Time, y = Hourly_Counts, date = Date, ncol = 4)
p4 <- ggplot(two_sensors_calendar) +
  geom_line(
    data = subset(two_sensors_calendar, Sensor_Name == "Lonsdale St (South)" ),
    aes(.Time, .Hourly_Counts, group = Date), colour = "#1b9e77"
  ) +
  geom_line(
    data = subset(two_sensors_calendar, Sensor_Name =="Melbourne Convention Exhibition Centre" ),
    aes(.Time, .Hourly_Counts, group = Date), colour = "#d95f02"
  )
prettify(p4)

library(dplyr, warn.conflicts = FALSE)
# compute the calendar layout for the data frame
calendar_df <- pedestrian %>%
  filter(Sensor_ID == 13, Year == 2016) %>%
  frame_calendar(x = Time, y = Hourly_Counts, date = Date, nrow = 4)

# ggplot
p1 <- calendar_df %>%
  ggplot(aes(x = .Time, y = .Hourly_Counts, group = Date)) +
  geom_line()+theme_bw()
prettify(p1, size = 3, label.padding = unit(0.15, "lines"))