Created
May 8, 2019 07:57
-
-
Save ken333135/09f8793fff5a6df28558b17e516f91ab to your computer and use it in GitHub Desktop.
Wrapper Function to create Sankey Diagram from DataFrame
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def genSankey(df,cat_cols=[],value_cols='',title='Sankey Diagram'): | |
# 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 = 10 | |
) | |
) | |
fig = dict(data=[data], layout=layout) | |
return fig |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Thanks for the code!