Confirmed cases of Coronavirus as on 4 April 2020 | plot using Python and Plotly

Sankey Diagram : power consumption by states in India

In [18]:

import pandas as pd
import numpy as np
import plotly.graph_objs as go

In [19]:

#read excel files in to pandas dataframe
file_nodes = r'D:\Python Scripts\Sankey_Power_Generation\nodes.xlsx'

In [20]:

df_nodes = pd.read_excel(file_nodes)

All values are in MW. Source of data is Wikipedia. Data is as of 31st March 2019.

In [21]:

df_nodes

Out[21]:

	ID	Label	Colour
0	0	Thermal (MW) Coal	#4994CE
1	1	Thermal (MW) Gas	#4994CE
2	2	Thermal (MW) Diesel	#4994CE
3	3	Thermal (MW) Sub-Total Thermal	#8A5988
4	4	Nuclear (MW)	#449E9E
5	5	Renewable (MW) Hydro	#7FC241
6	6	Renewable (MW) Other Renewable	#7FC241
7	7	Renewable (MW) Sub-Total Renewable	#7FC241
8	8	Total (356,100 MW)	#D3D3D3

In [22]:

#read excel files in to pandas dataframe
file_links = r'D:\Python Scripts\Sankey_Power_Generation\link.xlsx'

In [23]:

df_links = pd.read_excel(file_links)

In [24]:

df_links

Out[24]:

	Source	Value	Target	LinkColour
0	0	200704	3	rgba(127, 194, 65, 0.2)
1	1	24937	3	rgba(127, 194, 65, 0.2)
2	2	637	3	rgba(127, 194, 65, 0.2)
3	3	226279	8	rgba(211, 211, 211, 0.5)
4	4	6780	8	rgba(211, 211, 211, 0.5)
5	5	45399	7	rgba(253, 227, 212, 1)
6	6	77641	7	rgba(253, 227, 212, 1)
7	7	123040	8	rgba(211, 211, 211, 0.5)

In [ ]:

fig = go.Figure(data=[go.Sankey(node=dict(
pad=15,
thickness=20,
line=dict(color="black",width=0.5),
label=df_nodes['Label'].dropna(axis=0, how='any'),
color=df_nodes['Colour']),link=dict(
source=df_links['Source'].dropna(axis=0, how='any'),
target=df_links['Target'].dropna(axis=0, how='any'),
value=df_links['Value'].dropna(axis=0, how='any'),
color=df_links['LinkColour'].dropna(axis=0, how='any'),
))])
# print(fig)
fig.update_layout(title_text="Basic Sankey Diagram", font_size=10)
fig.show()