easyalluvial (version 0.2.2)

alluvial_long: alluvial plot of data in long format

Description

Plots two variables of a dataframe on an alluvial plot. A third variable can be added either to the left or the right of the alluvial plot to provide coloring of the flows. All numerical variables are scaled, centered and YeoJohnson transformed before binning.

Usage

alluvial_long(
  data,
  key,
  value,
  id,
  fill = NULL,
  fill_right = T,
  bins = 5,
  bin_labels = c("LL", "ML", "M", "MH", "HH"),
  NA_label = "NA",
  order_levels_value = NULL,
  order_levels_key = NULL,
  order_levels_fill = NULL,
  complete = TRUE,
  fill_by = "first_variable",
  col_vector_flow = palette_qualitative() %>% palette_filter(greys = F),
  col_vector_value = RColorBrewer::brewer.pal(9, "Greys")[c(3, 6, 4, 7, 5)],
  verbose = F,
  stratum_labels = T,
  stratum_label_size = 4.5,
  stratum_width = 1/4,
  auto_rotate_xlabs = T,
  ...
)

Arguments

data

a dataframe

key

unquoted column name or string of x axis variable

value

unquoted column name or string of y axis variable

id

unquoted column name or string of id column

fill

unquoted column name or string of fill variable which will be used to color flows, Default: NULL

fill_right

logical, TRUE fill variable is added to the right FALSE to the left, Default: T

bins

number of bins for automatic binning of numerical variables, Default: 5

bin_labels

labels for bins, Default: c("LL", "ML", "M", "MH", "HH")

NA_label

character vector define label for missing data

order_levels_value

character vector denoting order of y levels from low to high, does not have to be complete can also just be used to bring levels to the front, Default: NULL

order_levels_key

character vector denoting order of x levels from low to high, does not have to be complete can also just be used to bring levels to the front, Default: NULL

order_levels_fill

character vector denoting order of color fill variable levels from low to high, does not have to be complete can also just be used to bring levels to the front, Default: NULL

complete

logical, insert implicitly missing observations, Default: TRUE

fill_by

one_of(c('first_variable', 'last_variable', 'all_flows', 'values')), Default: 'first_variable'

col_vector_flow

HEX color values for flows, Default: palette_filter( greys = F)

col_vector_value

HEX color values for y levels/values, Default:RColorBrewer::brewer.pal(9, 'Greys')[c(3,6,4,7,5)]

verbose

logical, print plot summary, Default: F

stratum_labels

logical, Default: TRUE

stratum_label_size

numeric, Default: 4.5

stratum_width

double, Default: 1/4

auto_rotate_xlabs

logical, Default: TRUE

...

additional parameter passed to manip_bin_numerics

Value

ggplot2 object

See Also

alluvial_wide ,geom_flow, geom_stratum ,manip_bin_numerics

Examples

# NOT RUN {

 data = quarterly_flights

 alluvial_long( data, key = qu, value = mean_arr_delay, id = tailnum, fill_by = 'last_variable' )

# }
# NOT RUN {
 # more flow coloring variants ------------------------------------

 alluvial_long( data, key = qu, value = mean_arr_delay, id = tailnum, fill_by = 'first_variable' )
 alluvial_long( data, key = qu, value = mean_arr_delay, id = tailnum, fill_by = 'all_flows' )
 alluvial_long( data, key = qu, value = mean_arr_delay, id = tailnum, fill_by = 'value' )

 # color by additional variable carrier ---------------------------

 alluvial_long( data, key = qu, value = mean_arr_delay, fill = carrier, id = tailnum )

 # use same color coding for flows and y levels -------------------

 palette = c('green3', 'tomato')

 alluvial_long( data, qu, mean_arr_delay, tailnum, fill_by = 'value'
                , col_vector_flow = palette
                , col_vector_value = palette )


 # reorder levels ------------------------------------------------

 alluvial_long( data, qu, mean_arr_delay, tailnum, fill_by = 'first_variable'
               , order_levels_value = c('on_time', 'late') )

 alluvial_long( data, qu, mean_arr_delay, tailnum, fill_by = 'first_variable'
               , order_levels_key = c('Q4', 'Q3', 'Q2', 'Q1') )

require(dplyr)
require(magrittr)

 order_by_carrier_size = data <!-- %>% -->
   group_by(carrier) <!-- %>% -->
   count() <!-- %>% -->
   arrange( desc(n) ) <!-- %>% -->
   .[['carrier']]

 alluvial_long( data, qu, mean_arr_delay, tailnum, carrier
                , order_levels_fill = order_by_carrier_size )

# }