f_plot_alluvial_1v1: plot alluvial of gathered data

In erblast/oetteR: Collection of personal R functions

Description

Plots two variables of a dataframe on an alluvial plot. A third variable can be added either two 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

f_plot_alluvial_1v1(data, col_x, col_y, col_id, col_fill = NULL,
  fill_right = T, bins = 5, bin_labels = c("LL", "ML", "M", "MH",
  "HH"), NA_label = "NA", order_levels_y = NULL,
  order_levels_x = NULL, order_levels_fill = NULL, complete = TRUE,
  fill_by = "first_variable",
  col_vector_flow = f_plot_col_vector74(faint = F, greys = F),
  col_vector_value = RColorBrewer::brewer.pal(9, "Greys")[c(3, 6, 4, 7,
  5)])

Arguments

data	a dataframe
col_x	character vector denoting column for the x axis variable
col_y	character vector denoting column for the y axis variable
col_id	character vector denoting id column
col_fill	character vector denoting color fill variable for 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	labesl for bins, Default: c("LL", "ML", "M", "MH", "HH")
NA_label	character vector define label for missing data
order_levels_y	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_x	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	boolean, 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 colors for flows, Default: f_plot_col_vector74(faint = F, greys = F)
col_vector_value	Hex colors for y levels/values, Default: RColorBrewer::brewer.pal(9, "Greys")[c(3, 6, 4, 7, 5)]

Value

plot

See Also

brewer.pal fct_relevel,fct_rev UQ geom_flow,geom_stratum

Examples

## Not run: 
if(interactive()){
# sample data
 monthly_flights = nycflights13::flights %>%
 group_by(month, tailnum, origin, dest, carrier) %>%
 summarise() %>%
 group_by( tailnum, origin, dest, carrier) %>%
 count() %>%
 filter( n == 12 ) %>%
 select( - n ) %>%
 left_join( nycflights13::flights ) %>%
 .[complete.cases(.), ] %>%
 ungroup() %>%
 mutate( tailnum = pmap_chr(list(tailnum, origin, dest, carrier), paste )
         , qu = cut(month, 4)) %>%
 group_by(tailnum, carrier, origin, dest, qu ) %>%
 summarise( mean_arr_delay = mean(arr_delay) ) %>%
 ungroup() %>%
 mutate( mean_arr_delay = ifelse( mean_arr_delay < 10, 'on_time', 'late' ) )

levels(monthly_flights$qu) = c('Q1', 'Q2', 'Q3', 'Q4')

data = monthly_flights

col_x = 'qu'
col_y = 'mean_arr_delay'
col_fill = 'carrier'
col_id = 'tailnum'

# flow coloring variants
f_plot_alluvial_1v1( data, col_x, col_y, col_id, col_fill )
f_plot_alluvial_1v1( data, col_x, col_y, col_id, fill_by = 'last_variable' )
f_plot_alluvial_1v1( data, col_x, col_y, col_id, fill_by = 'first_variable' )
f_plot_alluvial_1v1( data, col_x, col_y, col_id, fill_by = 'all_flows' )
f_plot_alluvial_1v1( data, col_x, col_y, col_id, fill_by = 'value' )

# use same color coding for flows and y levels
f_plot_alluvial_1v1( data, col_x, col_y, col_id, fill_by = 'last_variable'
                    , col_vector_flow = f_plot_col_vector74()
                    , col_vector_value = f_plot_col_vector74() )

# move fill variable to the left
f_plot_alluvial_1v1( data, col_x, col_y, col_id, col_fill, fill_right = F )

# reorder levels
f_plot_alluvial_1v1( data, col_x, col_y, col_id, fill_by = 'first_variable'
                    , order_levels_y = c('on_time', 'late') )

f_plot_alluvial_1v1( data, col_x, col_y, col_id, fill_by = 'first_variable'
                    , order_levels_x = c('Q4', 'Q3', 'Q2', 'Q1') )

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

f_plot_alluvial_1v1( data, col_x, col_y, col_id, col_fill
                    , order_levels_fill = order_by_carrier_size )

}

## End(Not run)

erblast/oetteR documentation built on May 27, 2019, 12:11 p.m.