SankeyDiagram

Sankey.py

def genSankey(df,cat_cols=[],value_cols='',title='Sankey Diagram'):
    
    '''
    https://gist.github.com/ken333135/09f8793fff5a6df28558b17e516f91ab
    '''
    # maximum of 6 value cols -> 6 colors
    colorPalette = ['#4B8BBE','#306998','#FFE873','#FFD43B','#646464']
    labelList = []
    colorNumList = []
    for catCol in cat_cols:
        labelListTemp =  list(set(df[catCol].values))
        colorNumList.append(len(labelListTemp))
        labelList = labelList + labelListTemp
        
    # remove duplicates from labelList
    labelList = list(dict.fromkeys(labelList))
    
    # define colors based on number of levels
    colorList = []
    for idx, colorNum in enumerate(colorNumList):
        colorList = colorList + [colorPalette[idx]]*colorNum
        
    # transform df into a source-target pair
    for i in range(len(cat_cols)-1):
        if i==0:
            sourceTargetDf = df[[cat_cols[i],cat_cols[i+1],value_cols]]
            sourceTargetDf.columns = ['source','target','count']
        else:
            tempDf = df[[cat_cols[i],cat_cols[i+1],value_cols]]
            tempDf.columns = ['source','target','count']
            sourceTargetDf = pd.concat([sourceTargetDf,tempDf])
        sourceTargetDf = sourceTargetDf.groupby(['source','target']).agg({'count':'sum'}).reset_index()
        
    # add index for source-target pair
    sourceTargetDf['sourceID'] = sourceTargetDf['source'].apply(lambda x: labelList.index(x))
    sourceTargetDf['targetID'] = sourceTargetDf['target'].apply(lambda x: labelList.index(x))
    
    # creating the sankey diagram
    data = dict(
        type='sankey',
        node = dict(
          pad = 15,
          thickness = 20,
          line = dict(
            color = "black",
            width = 0.5
          ),
          label = labelList,
          color = colorList
        ),
        link = dict(
          source = sourceTargetDf['sourceID'],
          target = sourceTargetDf['targetID'],
          value = sourceTargetDf['count']
        )
      )
    
    layout =  dict(
        title = title,
        font = dict(
          size = 16
        )
    )
       
    fig = dict(data=[data], layout=layout)
    return fig
  
  sankey_title = 'Vote by Ranking'

sankey_fig = genSankey(df_sankey,cat_cols=col_rounds,value_cols='value',title=sankey_title)
#plotly.offline.plot(fig, validate=False)

fig = go.Figure(sankey_fig)
fig.update_layout(width=int(1200))

fig.add_annotation(
            x=0,
            y=1.1,
            showarrow= False,
            text="First round")

fig.add_annotation(
            x=1,
            y=1.1,
            showarrow= False,
            text="Final round")

fig.show()