def test_areaplot():
return alt.vconcat(*map(
lambda stack: ar.areaplot(
data.iowa_electricity(),
x="year",
y="net_generation",
color="source",
stack=stack,
),
ar.StackType,
))
width=600,
height=200
)
lower = upper.properties(
height=60
).add_selection(brush)
upper & lower
##
import altair as alt
from vega_datasets import data
source = data.iowa_electricity()
alt.Chart(source).mark_area(opacity=0.3).encode(
x="year:T",
y=alt.Y("net_generation:Q", stack=None),
color="source:N"
)
##
import altair as alt
from vega_datasets import data
source = data.iowa_electricity()
mu = df4.delay.mean() se = 2.58 * (df4.delay.std()/math.sqrt(df4.shape[0])) ub, lb = mu + se, mu - se plt.hlines(mu, -.5, 2.5, ls = '--') plt.hlines([lb, ub], -.5, 2.5,ls =':') plt.xticks(rotation = 0) plt.show() # In[47]: from vega_datasets import data iowa = data.iowa_electricity() iowa.head() # In[48]: iowa.shape # In[49]: iowa.year.value_counts()
"""
Trellis Area Chart
------------------
This example shows small multiples of an area chart.
"""
# category: area charts
import altair as alt
from vega_datasets import data
source = data.iowa_electricity()
alt.Chart(source).mark_area().encode(
x="year:T",
y="net_generation:Q",
color="source:N",
row="source:N"
)
def test_lineplot():
return ar.lineplot(data.iowa_electricity(),
x="year",
y="net_generation",
color="source")
seattle['rained'] = seattle.precipitation > 0
seattle.groupby(seattle.index.month).rained.sum().idxmax()
flights = data.flights_20k().set_index('date').sort_index()
flights['delay'] = flights.delay.apply(lambda x: 0 if x < 0 else x)
flights.groupby(flights.index.hour).delay.mean().idxmax()
flights.groupby(flights.index.weekday_name).delay.mean(
) # Yes, Friday > Thursday > Wednesday > Sunday > Tuesday > Saturday > Monday
flights.groupby(flights.index.month).delay.mean(
) # Kind of but not really. I'd say it doesn't because the difference in mean times is a minute or so
iowa = data.iowa_electricity().set_index('year').sort_index()
pivot = iowa.pivot(columns='source', values='net_generation')
pivot['totals'] = pivot.sum(axis=1)
pivot['fossil_pct'] = pivot['Fossil Fuels'] / pivot.totals
pivot['renew_pct'] = pivot['Renewables'] / pivot.totals
pivot['nuclear_pct'] = pivot['Nuclear Energy'] / pivot.totals
pivot.drop(columns=['totals', 'fossil_pct', 'renew_pct', 'nuclear_pct']).plot()
pivot.T
pivot[['totals']].plot() # Totals are increasing over time
sf['desc'] = pd.qcut(x=sf.temp, q=4, labels=['cold', 'cool', 'warm', 'hot'])
cats = pd.get_dummies(sf.desc)
