In this article, I will show you, the most advanced interactive visualizations techniques for Data Science, using python, plotly and bar chart race.
I will use the Electricity power consumption Data set for this tutorial. I will analyse the power consumption of according to the states in India using Interactive Visualizations.
An Interactive EDA of Electricity Consumption
Power is one of the most critical components of infrastructure crucial for the economic growth and welfare of nations. The existence and development of adequate infrastructure is essential for sustained growth of the Indian economy.
India is the world’s third largest producer and third largest consumer of electricity. Sustained economic growth continues to drive electricity demand in India.
Consumption of electricity is known to follow economic activity closely. The industries that produce essential goods are operating at very low utilization levels. Hence, in such a scenario one expects electricity demands to go down.
Download the data sets
Lets start with Importing the libraries
import numpy as np import pandas as pd import matplotlib.pyplot as plt %matplotlib notebook import plotly.express as px import plotly.graph_objects as go import plotly.figure_factory as ff from IPython.display import HTML import calendar from plotly.subplots import make_subplots import bar_chart_race as bcr
Read the data sets
df = pd.read_csv('power data.csv')
df_long = pd.read_csv('long_data_.csv')Let’s see some insights of the data
df.info()
<class 'pandas.core.frame.DataFrame'> RangeIndex: 210 entries, 0 to 209 Data columns (total 35 columns): # Column Non-Null Count Dtype --- ------ -------------- ----- 0 Date 210 non-null object 1 Punjab 210 non-null float64 2 Haryana 210 non-null float64 3 Rajasthan 210 non-null float64 4 Delhi 210 non-null float64 5 UP 210 non-null float64 6 Uttarakhand 210 non-null float64 7 HP 210 non-null float64 8 J&K 210 non-null float64 9 Chandigarh 210 non-null float64 10 Chhattisgarh 210 non-null float64 11 Gujarat 210 non-null float64 12 MP 210 non-null float64 13 Maharashtra 210 non-null float64 14 Goa 210 non-null float64 15 DNH 210 non-null float64 16 Andhra Pradesh 210 non-null float64 17 Telangana 210 non-null float64 18 Karnataka 210 non-null float64 19 Kerala 210 non-null float64 20 Tamil Nadu 210 non-null float64 21 Pondy 210 non-null float64 22 Bihar 210 non-null float64 23 Jharkhand 210 non-null float64 24 Odisha 210 non-null float64 25 West Bengal 210 non-null float64 26 Sikkim 210 non-null float64 27 Arunachal Pradesh 210 non-null float64 28 Assam 210 non-null float64 29 Manipur 210 non-null float64 30 Meghalaya 210 non-null float64 31 Mizoram 210 non-null float64 32 Nagaland 210 non-null float64 33 Tripura 210 non-null float64 34 ALL INDIA TOTAL 210 non-null float64 dtypes: float64(34), object(1) memory usage: 57.5+ KB
df['Date'] = pd.to_datetime(df.Date, dayfirst=True) df_long['Dates'] = pd.to_datetime(df_long.Dates, dayfirst=True)
Region Wise Daily Power Consumption
df['NR'] = df['Punjab']+ df['Haryana']+ df['Rajasthan']+ df['Delhi']+df['UP']+df['Uttarakhand']+df['HP']+df['J&K']+df['Chandigarh'] df['WR'] = df['Chhattisgarh']+df['Gujarat']+df['MP']+df['Maharashtra']+df['Goa']+df['DNH'] df['SR'] = df['Andhra Pradesh']+df['Telangana']+df['Karnataka']+df['Kerala']+df['Tamil Nadu']+df['Pondy'] df['ER'] = df['Bihar']+df['Jharkhand']+ df['Odisha']+df['West Bengal']+df['Sikkim'] df['NER'] =df['Arunachal Pradesh']+df['Assam']+df['Manipur']+df['Meghalaya']+df['Mizoram']+df['Nagaland']+df['Tripura']
fig = go.Figure()
fig.add_trace(go.Scatter(
x=df.Date, y=df.NR,
mode='lines+markers',
name='Northern region',
marker=dict(
color='rgba(300, 50, 50, 0.8)',
size=5,
line=dict(
color='DarkSlateGrey',
width = 1
)
)
))
fig.add_trace(go.Scatter(
x=df.Date, y=df.SR,
mode='lines+markers',
name='Southern Region',
marker=dict(
color='rgba(50, 300, 50, 0.8)',
size=5,
line=dict(
color='DarkSlateGrey',
width = 1
)
)
))
fig.add_trace(go.Scatter(
x=df.Date, y=df.ER,
mode='lines+markers',
name='Eastern Region',
marker=dict(
color='rgba(50, 50, 300, 0.8)',
size=5,
line=dict(
color='DarkSlateGrey',
width = 1
)
)
))
fig.add_trace(go.Scatter(
x=df.Date, y=df.WR,
mode='lines+markers',
name='Western Region',
marker=dict(
color='rgba(300, 100, 200, 0.8)',
size=5,
line=dict(
color='DarkSlateGrey',
width = 1
)
)
))
fig.add_trace(go.Scatter(
x=df.Date, y=df.NER,
mode='lines+markers',
name='North-Eastern',
marker=dict(
color='rgba(100, 200, 300, 0.8)',
size=5,
line=dict(
color='DarkSlateGrey',
width = 1
)
)
))
fig.update_xaxes(
rangeslider_visible=True,
rangeselector=dict(
buttons=list([
dict(count=1, label="1m", step="month", stepmode="backward"),
dict(count=3, label="3m", step="month", stepmode="backward"),
dict(count=6, label="6m", step="month", stepmode="backward"),
dict(step="all")
])
)
)
fig.update_layout(title='Power Consumption in Various Region')
fig.update_layout(width=800,height=500)
fig.show()
State-wise mean Power consumption
df1= df[['Date', 'Punjab', 'Haryana', 'Rajasthan', 'Delhi', 'UP',
'Uttarakhand', 'HP', 'J&K', 'Chandigarh', 'Chhattisgarh', 'Gujarat',
'MP', 'Maharashtra', 'Goa', 'DNH',
'Andhra Pradesh', 'Telangana', 'Karnataka', 'Kerala', 'Tamil Nadu',
'Pondy', 'Bihar', 'Jharkhand', 'Odisha', 'West Bengal', 'Sikkim',
'Arunachal Pradesh', 'Assam', 'Manipur', 'Meghalaya', 'Mizoram',
'Nagaland', 'Tripura']]
df1 = df1.set_index('Date')
bcr.bar_chart_race(df1, figsize=(4, 3.5),period_length =500,filename = None, title='power usage by states')monthly_df = df_long.groupby([df_long.Dates.dt.year, df_long.Dates.dt.month,df_long.States,df_long.Regions, df_long.latitude,df_long.longitude])['Usage'].mean() monthly_df.index = monthly_df.index.set_names(['year', 'month','State','Region','latitude','longitude']) monthly_df = monthly_df.reset_index() monthly_df['month'] = monthly_df['month'].apply(lambda x: calendar.month_abbr[x])
fig = px.sunburst(monthly_df, path=['Region', 'State','month'], values='Usage',
color='Usage',
color_continuous_scale='RdBu')
fig.update_layout(title='Click various Regions/States to view power distribution')
fig.update_layout( width=800,height=600)
fig.show()fig = px.bar(monthly_df, x="Region", y="Usage",color='State',animation_frame = 'month')
fig.update_layout(xaxis={'categoryorder':'total descending'})
fig.update_layout(title='Region-wise Bar plots')
fig.show()
Before and After lock down Scenarios
df_before = df.iloc[0:150,:]
df_after = df.iloc[151:,]
fig = go.Figure()
fig.add_trace(go.Scatter( x=df_before['Date'], y=df_before['Gujarat'], name='Gujarat before lockdown',fill='tonexty',
line=dict(width=2,dash='dot',color='firebrick')
))
fig.add_trace(go.Scatter( x=df_before['Date'], y=df_before['Maharashtra'], name='Maharashtra before lockdown',fill='tonexty',
line=dict(width=2,dash='dot',color='coral')
))
fig.add_trace(go.Scatter( x=df_before['Date'], y=df_before['MP'], name='MP before lockdown',fill='tozeroy',
line=dict(width=2,dash='dot',color='darkred')
))
fig.add_trace(go.Scatter(x=df_after['Date'], y=df_after['Gujarat'],name='Gujarat after lockdown',fill='tozeroy',
line=dict(color='firebrick', width=2)
))
fig.add_trace(go.Scatter(x=df_after['Date'], y=df_after['Maharashtra'],name='Maharashtra after lockdown',fill='tozeroy',
line=dict(color='coral', width=2)
))
fig.add_trace(go.Scatter(x=df_after['Date'], y=df_after['MP'],name='MP after lockdown',fill='tozeroy',
line=dict(color='darkred', width=2)
))
fig.update_layout(title='Power Consumption in top 3 WR states')
fig.update_layout( width=800,height=500)
fig.show()
