library(sugrrants)
library(tidyverse)
library(ggmap)
sensor_loc <- rwalkr::pull_sensor()
qmplot(x = Longitude, y = Latitude, data = sensor_loc,
  colour = I("#d95f02"), size = I(4))

sensors <- c("State Library", "Flagstaff Station",
  "Flinders Street Station Underpass")
sensor_loc %>% 
  mutate(Selected = ifelse(Sensor %in% sensors, TRUE, FALSE)) %>% 
  qmplot(
    x = Longitude, y = Latitude, data = .,
    colour = Selected, shape = Selected, size = I(4)
  ) +
  scale_colour_brewer(palette = "Dark2")

pedestrian <- as_tibble(rwalkr::run_melb(year = 2016))
pedestrian

#> # A tibble: 377,712 x 5
#>                               Sensor  Date_Time       Date
#>                                <chr>     <dttm>     <date>
#>  1    Chinatown-Lt Bourke St (South) 2016-01-01 2016-01-01
#>  2                   Waterfront City 2016-01-01 2016-01-01
#>  3                   Lygon St (East) 2016-01-01 2016-01-01
#>  4                  Town Hall (West) 2016-01-01 2016-01-01
#>  5      Monash Rd-Swanston St (West) 2016-01-01 2016-01-01
#>  6             Collins Place (South) 2016-01-01 2016-01-01
#>  7     Spencer St-Collins St (North) 2016-01-01 2016-01-01
#>  8 Flinders Street Station Underpass 2016-01-01 2016-01-01
#>  9                    Birrarung Marr 2016-01-01 2016-01-01
#> 10     QV Market-Elizabeth St (West) 2016-01-01 2016-01-01
#> # ... with 377,702 more rows, and 2 more variables:
#> #   Time <int>, Count <int>

subdat <- pedestrian %>% 
  filter(Sensor %in% sensors) %>% 
  mutate(Day = wday2(Date, label = TRUE))

The frame_calendar() function

flinders <- subdat %>% 
  filter(Sensor == "Flinders Street Station Underpass") %>% 
  mutate(
    Holiday = ifelse(Date %in% au_holiday(2016)$date, 
    TRUE, FALSE)
  )
flinders_cal <- flinders %>%
  frame_calendar(x = Time, y = Count, date = Date)
flinders_cal

#> # A tibble: 8,784 x 9
#>                               Sensor           Date_Time
#>  *                             <chr>              <dttm>
#>  1 Flinders Street Station Underpass 2016-01-01 00:00:00
#>  2 Flinders Street Station Underpass 2016-01-01 01:00:00
#>  3 Flinders Street Station Underpass 2016-01-01 02:00:00
#>  4 Flinders Street Station Underpass 2016-01-01 03:00:00
#>  5 Flinders Street Station Underpass 2016-01-01 04:00:00
#>  6 Flinders Street Station Underpass 2016-01-01 05:00:00
#>  7 Flinders Street Station Underpass 2016-01-01 06:00:00
#>  8 Flinders Street Station Underpass 2016-01-01 07:00:00
#>  9 Flinders Street Station Underpass 2016-01-01 08:00:00
#> 10 Flinders Street Station Underpass 2016-01-01 09:00:00
#> # ... with 8,774 more rows, and 7 more variables:
#> #   Time <int>, Count <int>, Day <ord>, Holiday <lgl>,
#> #   Date <date>, .Time <dbl>, .Count <dbl>

p_flinders <- flinders_cal %>% 
  ggplot(aes(
    x = .Time, y = .Count, group = Date, colour = Holiday
  )) +
  geom_line() +
  scale_colour_brewer(palette = "Dark2")
p_flinders

prettify(p_flinders)

The args of frame_calendar()

frame_calendar(
  data, x, y, date, calendar = "monthly", dir = "h",
  sunday = FALSE, nrow = NULL, ncol = NULL, polar = FALSE,
  scale = "fixed", width = 0.95, height = 0.95
)

• x, y: a unquoted (or bare) variable mapping to x and y axis.
• date: a Date variable mapping to dates in the calendar.
• calendar: type of calendar. "monthly", "weekly", "daily".
• sunday: FALSE indicating to starting with Monday in a week, or TRUE for Sunday.
• nrow, ncol: number of rows and columns defined for "monthly" calendar layout.
• scale: "fixed", "free", "free_wday", and "free_mday".

Weekly calendar

flinders_weekly <- flinders %>%
  frame_calendar(
    x = Time, y = Count, date = Date, calendar = "weekly"
  )
p_flinders_weekly <- flinders_weekly %>% 
  ggplot(aes(
    x = .Time, y = .Count, group = Date, colour = Holiday
  )) +
  geom_line() +
  scale_colour_brewer(palette = "Dark2")
prettify(p_flinders_weekly)

Weekly calendar

Daily calendar

flinders_daily <- flinders %>%
  frame_calendar(
    x = Time, y = Count, date = Date, calendar = "daily"
  )
p_flinders_daily <- flinders_daily %>% 
  ggplot(aes(
    x = .Time, y = .Count, group = Date, colour = Holiday
  )) +
  geom_line() +
  scale_colour_brewer(palette = "Dark2")
prettify(p_flinders_daily)

Daily calendar

Local scale when scale = "free"

# calendar plot for flinders street station using local scale
flinders_cal_free <- flinders %>% 
  frame_calendar(
    x = Time, y = Count, date = Date, scale = "free"
  )
p_flinders_free <- flinders_cal_free %>% 
  ggplot(aes(x = .Time, y = .Count, group = Date)) +
  geom_line()
prettify(p_flinders_free)

Local scale when scale = "free"

Lagged scatterplot

flinders_cal_day <- flinders %>% 
  mutate(Lagged_Count = lag(Count)) %>% 
  frame_calendar(
    x = Lagged_Count, y = Count, date = Date, 
    width = 0.95, height = 0.8
  )
p_flinders_day <- flinders_cal_day %>% 
  ggplot(aes(x = .Lagged_Count, y = .Count, group = Date)) +
  geom_point(size = 0.7, alpha = 0.6)
prettify(p_flinders_day)

Lagged scatterplot

Work with group_by()

facet_cal <- subdat %>% 
  group_by(Sensor) %>% 
  frame_calendar(
    x = Time, y = Count, date = Date, nrow = 2
  )
p_facet <- facet_cal %>% 
  ggplot(aes(x = .Time, y = .Count, group = Date)) +
  geom_line(aes(colour = Sensor)) +
  facet_grid(
    Sensor ~ ., 
    labeller = labeller(Sensor = label_wrap_gen(20))
  ) +
  scale_colour_brewer(
    palette = "Dark2", 
    guide = guide_legend(title = "Sensor")
  )
prettify(p_facet, label = NULL)

Work with group_by()

Boxplots

# boxplots for hourly counts across all the sensors in 2016 December
pedestrian_dec <- pedestrian %>% 
  filter(Date >= as.Date("2016-12-01")) %>% 
  frame_calendar(
    x = Time, y = Count, date = Date, 
    width = 0.97, height = 0.97
  )
p_boxplot <- pedestrian_dec %>% 
  ggplot() +
  geom_boxplot(
    aes(x = .Time, y = .Count, group = Date_Time),
    outlier.size = 0.8, width = 0.005, 
    position = "identity", colour = "grey30"
  ) +
  geom_smooth(
    aes(.Time, .Count, group = Date), 
    se = FALSE, method = "loess"
  )
prettify(p_boxplot, label = c("label", "text", "text2"))

Boxplots

• Other languages support: ?frame_calendar

• More examples: vignette("frame-calendar")

• Algorithm description: http://pub.earo.me/calendar-vis.pdf

The tsibble package provides a data class of tbl_ts to manage temporal data frames in a tidy and modern way. A tsibble consists of a time index, keys and other measured variables in a data-centric format, which is built on top of the tibble.

Installation

# install.packages("devtools")
devtools::install_github("earowang/tsibble")

Start with a tibble/data.frame

pedestrian

#> # A tibble: 377,712 x 5
#>                               Sensor  Date_Time       Date
#>                                <chr>     <dttm>     <date>
#>  1    Chinatown-Lt Bourke St (South) 2016-01-01 2016-01-01
#>  2                   Waterfront City 2016-01-01 2016-01-01
#>  3                   Lygon St (East) 2016-01-01 2016-01-01
#>  4                  Town Hall (West) 2016-01-01 2016-01-01
#>  5      Monash Rd-Swanston St (West) 2016-01-01 2016-01-01
#>  6             Collins Place (South) 2016-01-01 2016-01-01
#>  7     Spencer St-Collins St (North) 2016-01-01 2016-01-01
#>  8 Flinders Street Station Underpass 2016-01-01 2016-01-01
#>  9                    Birrarung Marr 2016-01-01 2016-01-01
#> 10     QV Market-Elizabeth St (West) 2016-01-01 2016-01-01
#> # ... with 377,702 more rows, and 2 more variables:
#> #   Time <int>, Count <int>

What makes a valid tsibble?

## S3 method for class 'tbl_df', 'data.frame'
as_tsibble(x, ..., index, validate = TRUE, regular = TRUE)

• x: other objects to be coerced to a tsibble (tbl_ts).
• ...: unquoted (or bare) variable(s) giving the key.
• index: an unquoted (or bare) variable to specify the time index variable.
• validate: TRUE suggests to verify that the key together with the index uniquely identifies each observation (i.e. a valid tsibble).
• regular: regular time interval (TRUE) or irregular (FALSE).

* The key is not constrained to a single variable, but expressive for nested and crossed data structures.

Coerce to a tsibble with as_tsibble()

library(tsibble)
pedestrian %>% 
  as_tsibble(Sensor, index = Date_Time)

#> # A tsibble: 377,712 x 5 [1HOUR]
#> # Keys:      Sensor
#>  *                            Sensor  Date_Time       Date
#>                                <chr>     <dttm>     <date>
#>  1    Chinatown-Lt Bourke St (South) 2016-01-01 2016-01-01
#>  2                   Waterfront City 2016-01-01 2016-01-01
#>  3                   Lygon St (East) 2016-01-01 2016-01-01
#>  4                  Town Hall (West) 2016-01-01 2016-01-01
#>  5      Monash Rd-Swanston St (West) 2016-01-01 2016-01-01
#>  6             Collins Place (South) 2016-01-01 2016-01-01
#>  7     Spencer St-Collins St (North) 2016-01-01 2016-01-01
#>  8 Flinders Street Station Underpass 2016-01-01 2016-01-01
#>  9                    Birrarung Marr 2016-01-01 2016-01-01
#> 10     QV Market-Elizabeth St (West) 2016-01-01 2016-01-01
#> # ... with 377,702 more rows, and 2 more variables:
#> #   Time <int>, Count <int>

• column-wise verbs *:
  • mutate(): add new variables
  • select(): select variables by name
  • summarise(): reduce multiple values down to a single value (ToDo)
• row-wise verbs:
  • filter(): filter observations with matching conditions
  • slice(): select observations by row
  • arrange(): arrange observations by variables
• other verbs:
  • rename(): rename variables by name
  • group_by(): group by one or more variables
• tsibble verbs:
  • tsummarise(): aggregate over calendar periods

The tsummarise() function

ped_ts <- as_tsibble(pedestrian, Sensor, index = Date_Time)
ped_ts %>% 
  group_by(Sensor) %>% 
  tsummarise(
    YrMon = yearmth(Date_Time),
    MinC = min(Count, na.rm = TRUE),
    MaxC = max(Count, na.rm = TRUE)
  )

#> # A tsibble: 516 x 4 [1MONTH]
#> # Keys:      Sensor
#> # Groups:    Sensor
#>          Sensor    YrMon  MinC  MaxC
#>  *        <chr>    <mth> <dbl> <dbl>
#>  1 Alfred Place 2016 Jan     0  1067
#>  2 Alfred Place 2016 Feb     0  1099
#>  3 Alfred Place 2016 Mar     1  1161
#>  4 Alfred Place 2016 Apr     0  1107
#>  5 Alfred Place 2016 May     0  1099
#>  6 Alfred Place 2016 Jun     0  1101
#>  7 Alfred Place 2016 Jul     0  1174
#>  8 Alfred Place 2016 Aug     0  1075
#>  9 Alfred Place 2016 Sep     0  1071
#> 10 Alfred Place 2016 Oct     0  1057
#> # ... with 506 more rows

More on the way

• as_tsibble: tsibble for forecast (tbl_forecast)
• fill_na: make implicit missing cases to be explicit
• slide: rolling window calculation

Graphical support for tsibble in sugrrants

Forecast methods for tsibble in forecast, hts and fasster