R > Basic Charts > Sankey Diagram
Suggest an edit to this page

Sankey Diagram in R

How to create sankey diagrams in R with Plotly.


Plotly Studio: Transform any dataset into an interactive data application in minutes with AI. Sign up for early access now.

Basic Sankey Diagram

library(plotly)

fig <- plot_ly(
    type = "sankey",
    orientation = "h",

    node = list(
      label = c("A1", "A2", "B1", "B2", "C1", "C2"),
      color = c("blue", "blue", "blue", "blue", "blue", "blue"),
      pad = 15,
      thickness = 20,
      line = list(
        color = "black",
        width = 0.5
      )
    ),

    link = list(
      source = c(0,1,0,2,3,3),
      target = c(2,3,3,4,4,5),
      value =  c(8,4,2,8,4,2)
    )
  )
fig <- fig %>% layout(
    title = "Basic Sankey Diagram",
    font = list(
      size = 10
    )
)

fig

Create Canvas

library(plotly)

fig <- plot_ly(
    type = "sankey",
    domain = list(
      x =  c(0,1),
      y =  c(0,1)
    ),
    orientation = "h",
    valueformat = ".0f",
    valuesuffix = "TWh"
)
fig <- fig %>% layout(
    title = "Energy forecast for 2050, UK - Department of Energy & Climate Change",
    font = list(
      size = 10
    ),
    xaxis = list(showgrid = F, zeroline = F),
    yaxis = list(showgrid = F, zeroline = F)
  )

Add Nodes

library(plotly)
library(rjson)

json_file <- "https://raw.githubusercontent.com/plotly/plotly.js/master/test/image/mocks/sankey_energy.json"
json_data <- fromJSON(paste(readLines(json_file), collapse=""))

fig <- plot_ly(
    type = "sankey",
    domain = list(
      x =  c(0,1),
      y =  c(0,1)
    ),
    orientation = "h",
    valueformat = ".0f",
    valuesuffix = "TWh",

    node = list(
      label = json_data$data[[1]]$node$label,
      color = json_data$data[[1]]$node$color,
      pad = 15,
      thickness = 15,
      line = list(
        color = "black",
        width = 0.5
      )
    )
  ) 
fig <- fig %>% layout(
    title = "Energy forecast for 2050, UK - Department of Energy & Climate Change",
    font = list(
      size = 10
    ),
    xaxis = list(showgrid = F, zeroline = F),
    yaxis = list(showgrid = F, zeroline = F)
)

library(plotly)
library(rjson)

json_file <- "https://raw.githubusercontent.com/plotly/plotly.js/master/test/image/mocks/sankey_energy.json"
json_data <- fromJSON(paste(readLines(json_file), collapse=""))

fig <- plot_ly(
    type = "sankey",
    domain = list(
      x =  c(0,1),
      y =  c(0,1)
    ),
    orientation = "h",
    valueformat = ".0f",
    valuesuffix = "TWh",

    node = list(
      label = json_data$data[[1]]$node$label,
      color = json_data$data[[1]]$node$color,
      pad = 15,
      thickness = 15,
      line = list(
        color = "black",
        width = 0.5
      )
    ),

    link = list(
      source = json_data$data[[1]]$link$source,
      target = json_data$data[[1]]$link$target,
      value =  json_data$data[[1]]$link$value,
      label =  json_data$data[[1]]$link$label
    )
  ) 
fig <- fig %>% layout(
    title = "Energy forecast for 2050<br>Source: Department of Energy & Climate Change, Tom Counsell via <a href='https://bost.ocks.org/mike/sankey/'>Mike Bostock</a>",
    font = list(
      size = 10
    ),
    xaxis = list(showgrid = F, zeroline = F),
    yaxis = list(showgrid = F, zeroline = F)
)

fig
Agricultural 'waste'Bio-conversionLiquidLossesSolidGasBiofuel importsBiomass importsCoal importsCoalCoal reservesDistrict heatingIndustryHeating and cooling - commercialHeating and cooling - homesElectricity gridOver generation / exportsH2 conversionRoad transportAgricultureRail transportLighting & appliances - commercialLighting & appliances - homesGas importsNgasGas reservesThermal generationGeothermalH2HydroInternational shippingDomestic aviationInternational aviationNational navigationMarine algaeNuclearOil importsOilOil reservesOther wastePumped heatSolar PVSolar ThermalSolarTidalUK land based bioenergyWaveWind
Energy forecast for 2050Source: Department of Energy & Climate Change, Tom Counsell via Mike Bostock

Style Sankey Diagram

library(plotly)
library(rjson)

json_file <- "https://raw.githubusercontent.com/plotly/plotly.js/master/test/image/mocks/sankey_energy_dark.json"
json_data <- fromJSON(paste(readLines(json_file), collapse=""))

fig <- plot_ly(
    type = "sankey",
    domain = list(
      x =  c(0,1),
      y =  c(0,1)
    ),
    orientation = "h",
    valueformat = ".0f",
    valuesuffix = "TWh",

    node = list(
      label = json_data$data[[1]]$node$label,
      color = json_data$data[[1]]$node$color,
      pad = 15,
      thickness = 15,
      line = list(
        color = "black",
        width = 0.5
      )
    ),

    link = list(
      source = json_data$data[[1]]$link$source,
      target = json_data$data[[1]]$link$target,
      value =  json_data$data[[1]]$link$value,
      label =  json_data$data[[1]]$link$label
    )
  )
fig <- fig %>% layout(
    title = "Energy forecast for 2050<br>Source: Department of Energy & Climate Change, Tom Counsell via <a href='https://bost.ocks.org/mike/sankey/'>Mike Bostock</a>",
    font = list(
      size = 10,
      color = 'white'
    ),
    xaxis = list(showgrid = F, zeroline = F, showticklabels = F),
    yaxis = list(showgrid = F, zeroline = F, showticklabels = F),
    plot_bgcolor = 'black',
    paper_bgcolor = 'black'
)

fig
Agricultural 'waste'Bio-conversionLiquidLossesSolidGasBiofuel importsBiomass importsCoal importsCoalCoal reservesDistrict heatingIndustryHeating and cooling - commercialHeating and cooling - homesElectricity gridOver generation / exportsH2 conversionRoad transportAgricultureRail transportLighting & appliances - commercialLighting & appliances - homesGas importsNgasGas reservesThermal generationGeothermalH2HydroInternational shippingDomestic aviationInternational aviationNational navigationMarine algaeNuclearOil importsOilOil reservesOther wastePumped heatSolar PVSolar ThermalSolarTidalUK land based bioenergyWaveWind
Energy forecast for 2050Source: Department of Energy & Climate Change, Tom Counsell via Mike Bostock

Define Node Position

The following example sets node.x and node.y to place nodes in the specified locations, except in the snap arrangement (default behaviour when node.x and node.y are not defined) to avoid overlapping of the nodes, therefore, an automatic snapping of elements will be set to define the padding between nodes via nodepad. The other possible arrangements are: 1) perpendicular 2) freeform 3) fixed

library(plotly)
fig <- plot_ly(
  type = "sankey",
  arrangement = "snap",
  node = list(
    label = c("A", "B", "C", "D", "E", "F"),
    x = c(0.2, 0.1, 0.5, 0.7, 0.3, 0.5),
    y = c(0.7, 0.5, 0.2, 0.4, 0.2, 0.3),
    pad = 10), # 10 Pixel
  link = list(
    source = c(0, 0, 1, 2, 5, 4, 3, 5),
    target = c(5, 3, 4, 3, 0, 2, 2, 3),
    value = c(1, 2, 1, 1, 1, 1, 1, 2)))
fig <- fig %>% layout(title = "Sankey with manually positioned node")

fig

Reference

See https://plotly.com/r/reference/#sankey for more information and options!

What About Dash?

Dash for R is an open-source framework for building analytical applications, with no Javascript required, and it is tightly integrated with the Plotly graphing library.

Learn about how to install Dash for R at https://dashr.plot.ly/installation.

Everywhere in this page that you see fig, you can display the same figure in a Dash for R application by passing it to the figure argument of the Graph component from the built-in dashCoreComponents package like this:

library(plotly)

fig <- plot_ly() 
# fig <- fig %>% add_trace( ... )
# fig <- fig %>% layout( ... ) 

library(dash)
library(dashCoreComponents)
library(dashHtmlComponents)

app <- Dash$new()
app$layout(
    htmlDiv(
        list(
            dccGraph(figure=fig) 
        )
     )
)

app$run_server(debug=TRUE, dev_tools_hot_reload=FALSE)