import pandas as pd
import altair as alt
# we use sample data from this package
from vega_datasets import data
df = data.gapminder_health_income()
df.head()
countryobject
incomeint64
0
Afghanistan
1925
1
Albania
10620
2
Algeria
13434
3
Andorra
46577
4
Angola
7615
alt.Chart(df).mark_point().encode(
x='income',
y='health'
)
df2 = data.iowa_electricity()
# while head displays the first rows, sample gives as a random selection:
df2.sample(5)
yeardatetime64[ns]
sourceobject
11
2012-01-01 00:00:00
Fossil Fuels
36
2003-01-01 00:00:00
Renewables
39
2006-01-01 00:00:00
Renewables
34
2001-01-01 00:00:00
Renewables
3
2004-01-01 00:00:00
Fossil Fuels
renewables = df2[df2["source"] == "Renewables"]
alt.Chart(renewables).mark_line().encode(
x="year",
y="net_generation",
)
alt.Chart(df2[df2["year"]=="2017"]).mark_arc().encode(
theta="net_generation",
color="source"
)
alt.Chart(df2).mark_area().encode(
x="year",
y="net_generation",
color="source"
)
alt.Chart(df).mark_point().encode(
alt.X('income').scale(type='log'),
alt.Y('health').scale(zero=False),
)
alt.Chart(df2).mark_area().encode(
alt.Color("source").scale(
domain=["Renewables", "Nuclear Energy", "Fossil Fuels"],
range=['green', 'red', 'purple']
),
x="year",
y="net_generation",
)
alt.Chart(df2).mark_line().encode(
color="source",
x="year",
y="net_generation"
)
alt.Chart(df).mark_point().encode(
alt.X('income').scale(type='log'),
alt.Y('health').scale(zero=False),
alt.Opacity('population')
)
alt.Chart(df).mark_point(shape="square").encode(
alt.X('income').scale(type='log'),
alt.Y('health').scale(zero=False),
alt.Opacity('population').scale(zero=False),
)