import altair as alt
from vega_datasets import data
source = data.cars()
input_dropdown = alt.binding_select(options=['Europe', 'Japan', 'USA'])
selection = alt.selection_single(fields=['Origin'],
bind=input_dropdown,
name='Country of ')
color = alt.condition(selection, alt.Color('Origin:N', legend=None),
alt.value('lightgray'))
# alt.Chart(source).mark_point().encode(
# x='Horsepower:Q',
# y='Miles_per_Gallon:Q',
# color=color,
# tooltip='Name:N'
# ).add_selection(
# selection
# )
vega = alt.Chart(source).mark_circle(size=60).encode(
x='Horsepower',
y='Miles_per_Gallon',
color=color,
).add_selection(selection)
vega.save('a.html')
import altair as alt
import pandas as pd
from altair import Color, Scale
df = pd.read_csv('/Users/saranking/weight-height.csv')
alt.data_transformers.enable('default', max_rows=None)
chart = alt.Chart(df).mark_point().encode(
Color('Gender:N',
scale=Scale(domain=['Male', 'Female'], range=['#1f77b4',
'#e377c2'])),
x=alt.X('Height_in:Q', scale=alt.Scale(zero=False)),
y=alt.Y('Weight_lbs:Q', scale=alt.Scale(zero=False)),
tooltip=['Height_in', 'Weight_lbs', 'Gender'],
opacity=alt.value(0.45)).properties(background='white')
chart
chart.save('scatterPlot.png', scale_factor=2.0)
def plot_iroas_over_time(iroas_df: pd.DataFrame,
experiment_dates: pd.DataFrame,
cooldown_date: pd.DataFrame):
"""Returns a chart of the iROAS estimate over time with confidence bands.
This function provides a visualization of the evolution of the iROAS estimate
over the duration of the experiment and cooldown, together with confidence
bands.
Args:
iroas_df: a dataframe with columns: date, lower, mean, upper
experiment_dates: dataframe with columns (date, color) which contains two
dates for each period (start, end), and the column color is the label
used in the chart to refer to the corresponding period, e.g. "Experiment
period" or "Pretes period".
cooldown_date: dataframe with column (date, color) with only one entry,
where date indicates the last day in the cooldown period, and color is the
label used in the plot legend, e.g. "End of cooldown period".
Returns:
iroas_chart: Chart containing the plot.
"""
iroas_base = alt.Chart(iroas_df).mark_line().encode(
x=alt.X('date:T', axis=alt.Axis(title='', format=('%b %e'))))
iroas_selection = alt.selection_single(fields=['date'],
nearest=True,
on='mouseover',
empty='none',
clear='mouseout')
iroas_lines = iroas_base.mark_line().encode(
y=alt.Y('mean:Q', axis=alt.Axis(title=' ', format='.1')))
iroas_points = iroas_lines.mark_point().transform_filter(iroas_selection)
iroas_rule1 = iroas_base.mark_rule().encode(
tooltip=['date:T', 'mean:Q', 'lower:Q', 'upper:Q'])
iroas_rule = iroas_rule1.encode(
opacity=alt.condition(iroas_selection, alt.value(0.3), alt.value(
0))).add_selection(iroas_selection)
iroas_ci_bands_rule = alt.Chart(iroas_df).mark_area(color='gray').encode(
alt.X('date:T'), y='lower:Q', y2='upper:Q', opacity=alt.value(0.5))
date_rule = alt.Chart(experiment_dates[
experiment_dates['color'] == 'Experiment period']).mark_rule(
strokeWidth=2).encode(x='date:T',
color=alt.Color('color',
scale=alt.Scale(domain=[
'Experiment period',
'End of cooldown period',
'iROAS estimate'
],
range=[
'black',
'black',
'#1f77b4'
])))
cooldown_date_rule = alt.Chart(cooldown_date).mark_rule(
strokeWidth=2, strokeDash=[5,
2], color='black').encode(x='date:T',
color='color:N')
# Compile chart
iroas_chart = alt.layer(iroas_lines, iroas_rule, iroas_points, date_rule,
cooldown_date_rule, iroas_ci_bands_rule)
return iroas_chart
import altair as alt
from vega_datasets import data
source = data.cars()
# Configure common options
base = alt.Chart(source)
scale = alt.Scale(paddingInner=0)
# Configure heatmap
heatmap = base.mark_rect().encode(
alt.X('Cylinders:O', scale=scale),
alt.Y('Origin:O', scale=scale),
color='count()'
)
# Configure text
text = base.mark_text(baseline='middle').encode(
x='Cylinders:O',
y='Origin:O',
text='count()',
color=alt.condition(
alt.datum['count_*'] > 100,
alt.value('black'),
alt.value('white')
)
)
# Draw the chart
heatmap + text
# Create a selection that chooses the nearest point & selects based on x-value
nearest = alt.selection(type='single', nearest=True, on='mouseover',
fields=['x'], empty='none')
# The basic line
line = alt.Chart().mark_line(interpolate='basis').encode(
x='x:Q',
y='y:Q',
color='category:N'
)
# Transparent selectors across the chart. This is what tells us
# the x-value of the cursor
selectors = alt.Chart().mark_point().encode(
x='x:Q',
opacity=alt.value(0),
).add_selection(
nearest
)
# Draw points on the line, and highlight based on selection
points = line.mark_point().encode(
opacity=alt.condition(nearest, alt.value(1), alt.value(0))
)
# Draw text labels near the points, and highlight based on selection
text = line.mark_text(align='left', dx=5, dy=-5).encode(
text=alt.condition(nearest, 'y:Q', alt.value(' '))
)
# Draw a rule at the location of the selection
# the base chart
base = alt.Chart(source)
# generate the points
points = base.mark_point(filled=True, size=50).encode(
x=alt.X(
"x",
scale=alt.Scale(domain=(0,6)),
axis=alt.Axis(title='x')
),
y=alt.Y(
'y',
scale=alt.Scale(zero=False, domain=(10, 11)),
axis=alt.Axis(title="y")
),
color=alt.value('black')
)
# generate the error bars
errorbars = base.mark_rule().encode(
x="x",
y="ymin:Q",
y2="ymax:Q"
).transform_calculate(
ymin="datum.y-datum.yerr",
ymax="datum.y+datum.yerr"
)
points + errorbars
"""
Bar Chart with Negative Values
==============================
This example shows a bar chart with both positive and negative values.
"""
# category: bar charts
import altair as alt
from vega_datasets import data
source = data.us_employment()
alt.Chart(source).mark_bar().encode(
x="month:T",
y="nonfarm_change:Q",
color=alt.condition(
alt.datum.nonfarm_change > 0,
alt.value("steelblue"), # The positive color
alt.value("orange") # The negative color
)
).properties(width=600)
def summary(self):
"View selection coefficient distributions and mutation type counts"
#calculate number of neutral mutations
neutral = 0
for mut in self.tscoal.mutations():
if mut.derived_state == '1':
neutral += 1
#record fitness coefficients
coeffs = []
for mut in self.tscoal.mutations():
mut_list = mut.metadata["mutation_list"]
for i in mut_list:
coeffs.append(i["selection_coeff"])
#altair plot of mutation distrbutions
mean = sum(coeffs) / len(coeffs)
dist = np.histogram(coeffs, 50)
source = pd.DataFrame(
{
'counts': dist[0],
'values': dist[1][:-1],
'mean': mean
},
columns=['values', 'counts', 'mean'])
base = alt.Chart(source)
histo = base.mark_bar(
opacity=0.5, color=alt.ColorName("cornflowerblue")).encode(
alt.X('values:Q', axis=alt.Axis(title='Fitness Effect')),
alt.Y('counts:Q'),
color=alt.condition(
alt.datum.values > 0,
alt.value("lightseagreen"), # The positive color
alt.value("indianred") # The negative color
),
tooltip=[
alt.Tooltip('values', title='Fitness Effect'),
])
mean = base.mark_rule(color=alt.ColorName("goldenrod"),
opacity=0.4).encode(
x='mean:Q',
size=alt.value(3),
tooltip=[
alt.Tooltip('mean(values)',
title='Mean Fitness Effect'),
])
print("Note: this plot does not contain neutral mutations overlaid "
"with `msprime`.")
IPython.display.display_html(histo + mean)
print(
f"Total mutations: {self.tscoal.num_mutations}\n"
f"Neutral mutations: {neutral}\n"
f"Non-neutral mutations: {self.tscoal.num_mutations - neutral}\n")
#static toyplot
print("Mutation positions along chromosome:")
chrom = Chromosome(genome=self.genome)
chrom.toyplot()
self.rectangles = chrom.rectangles
canvas = toyplot.Canvas(width=2500, height=200)
axes = canvas.cartesian()
axes.show = False
#draw the rectangles
for index, row in self.rectangles.iterrows():
axes.rectangle(
row['x1'],
row['x2'],
row['y1'],
row['y2'],
color=row['color'],
style={"opacity": 0.6},
)
#draw the positions
lines = axes.vlines(self.positions,
style={
"stroke": "blue",
"stroke-width": 2
})
borough boundaries. It is based on the vega-lite example at
https://vega.github.io/vega-lite/examples/geo_layer_line_london.html.
"""
# category: case studies
import altair as alt
from vega_datasets import data
boroughs = alt.topo_feature(data.londonBoroughs.url, 'boroughs')
tubelines = alt.topo_feature(data.londonTubeLines.url, 'line')
centroids = data.londonCentroids.url
background = alt.Chart(boroughs).mark_geoshape(
stroke='white',
strokeWidth=2
).encode(
color=alt.value('#eee'),
).properties(
width=700,
height=500
)
labels = alt.Chart(centroids).mark_text().encode(
longitude='cx:Q',
latitude='cy:Q',
text='bLabel:N',
size=alt.value(8),
opacity=alt.value(0.6)
).transform_calculate(
"bLabel", "indexof (datum.name,' ') > 0 ? substring(datum.name,0,indexof(datum.name, ' ')) : datum.name"
)
def generate_countries_map(data: pd.DataFrame,
date,
interactive: bool = False,
width: int = 600,
height: int = 600,
log_scale: bool = True) -> alt.Chart:
fechas = data['fecha'].apply(lambda x: x.date())
data = data[(fechas == date)]
scale = alt.Scale(type='log', scheme='teals') if log_scale else alt.Scale(
type='linear', scheme='teals')
url_country_name = 'https://raw.githubusercontent.com/alisle/world-110m-country-codes/master/world-110m-country-codes.json'
country_names = pd.read_json(url_country_name).drop('name', axis=1)
country_data = get_country_data()
country_data = country_names.join((country_data.set_index('code')),
on='code')
data = pd.merge(left=country_data,
right=data,
left_on='name',
right_on='pais').dropna()
data = data.astype({'id': int, 'casos': int})
sphere = alt.sphere()
graticule = alt.graticule()
source = alt.topo_feature(vd.data.world_110m.url, 'countries')
sphere_chart = alt.Chart(
sphere,
title='Ubicación de los casos confirmados por país').mark_geoshape(
fill='lightblue')
graticule_chart = alt.Chart(graticule).mark_geoshape(stroke='white',
strokeWidth=0.5)
countries_chart = (alt.Chart(source).mark_geoshape().encode(
color=alt.Color('casos:Q', title='Casos', scale=scale, legend=None),
tooltip=[
alt.Tooltip('name:N', title='País'),
alt.Tooltip('code:N', title='Código'),
alt.Tooltip('casos:Q', title='Casos')
]).transform_lookup('id',
from_=alt.LookupData(
data=data,
key='id',
fields=['code', 'name', 'casos'])))
single = alt.selection_single(
on='mouseover', nearest=True, fields=['pais'],
empty='all') if interactive else alt.selection_single()
circle_chart = (alt.Chart(source).mark_circle(
opacity=0.4, color='red').encode(
longitude='lon:Q',
latitude='lat:Q',
size=(alt.condition(
single,
alt.Size('casos:Q',
scale=alt.Scale(range=[50, 4000]),
legend=None), alt.value(0))),
tooltip=[
alt.Tooltip('pais:N', title='País'),
alt.Tooltip('code:N', title='Código'),
alt.Tooltip('casos:Q', title='Casos')
]).transform_lookup('id',
from_=alt.LookupData(data=data,
key='id',
fields=[
'code', 'pais',
'casos', 'lat', 'lon'
])).add_selection(single))
final_chart = ((sphere_chart + graticule_chart + countries_chart +
circle_chart).project('naturalEarth1').properties(
width=800, height=500).configure_view(stroke=None))
return final_chart
height=500
).interactive()
st.write(fig)
# Altair の表示
st.markdown('## Altair を使ったインタラクティブなグラフ表示')
cars = data.cars()
brush = alt.selection_interval()
points = alt.Chart(cars).mark_point().encode(
x='Horsepower:Q',
y='Miles_per_Gallon:Q',
color=alt.condition(brush, 'Origin:N', alt.value('lightgray'))
).add_selection(
brush
)
bars = alt.Chart(cars).mark_bar().encode(
y='Origin:N',
color='Origin:N',
x='count(Origin):Q'
).transform_filter(
brush
)
points & bars
def generate_regions_map(data: pd.DataFrame,
date,
feature: str,
title: str,
width: int = 600,
height: int = 600,
log_scale: bool = True) -> alt.Chart:
fechas = data['fecha'].apply(lambda x: x.date())
data = data[(fechas == date)]
url_geojson = 'https://raw.githubusercontent.com/rubens36/covid19/master/maps/regiones.geojson'
regions_shape = alt.Data(url=url_geojson,
format=alt.DataFormat(property='features',
type='json'))
chart_data = data[(data[feature] > 0)][[feature, 'id']]
base_chart = (alt.Chart(
regions_shape,
title='Ubicación de los casos confirmados por región').mark_geoshape(
stroke='black', strokeWidth=0.5, color='white').encode(
tooltip=[alt.Tooltip('properties.Region:N', title='Región')]))
scale = alt.Scale(type='log', scheme='teals') if log_scale else alt.Scale(
type='linear', scheme='teals')
color_chart = (alt.Chart(regions_shape).mark_geoshape(
stroke='black', strokeWidth=0.5).encode(
color=alt.Color(f"{feature}:Q",
title=(get_title(feature)),
scale=scale),
tooltip=[
alt.Tooltip('properties.Region:N', title='Región'),
alt.Tooltip(f"{feature}:Q", title=(get_title(feature)))
]).transform_lookup('properties.id',
from_=alt.LookupData(data=chart_data,
key='id',
fields=[feature])))
single = alt.selection_single(on='mouseover')
circle_chart = (alt.Chart(regions_shape).mark_circle(
opacity=0.4, color='red').encode(
longitude='properties.centroid_lon:Q',
latitude='properties.centroid_lat:Q',
size=(alt.condition(
single,
alt.Size('infectados:Q',
scale=alt.Scale(range=[50, 4000]),
legend=None), alt.value(0))),
tooltip=[
alt.Tooltip('properties.Region:N', title='Región'),
alt.Tooltip(f"{feature}:Q", title=(get_title(feature)))
]).transform_lookup('properties.id',
from_=alt.LookupData(
data=chart_data,
key='id',
fields=['infectados'
])).properties(selection=single))
final_chart = ((base_chart + color_chart + circle_chart).configure_view(
strokeWidth=0).properties(width=width, height=height))
return final_chart
https://bl.ocks.org/amitkaps/fe4238e716db53930b2f1a70d3401701
"""
# category: interactive charts
import altair as alt
from vega_datasets import data
source = data.stocks()
highlight = alt.selection(type='single', on='mouseover',
fields=['symbol'], nearest=True)
base = alt.Chart(source).encode(
x='date:T',
y='price:Q',
color='symbol:N'
)
points = base.mark_circle().encode(
opacity=alt.value(0)
).add_selection(
highlight
).properties(
width=600
)
lines = base.mark_line().encode(
size=alt.condition(~highlight, alt.value(1), alt.value(3))
)
points + lines
"""
Histogram with a Global Mean Overlay
------------------------------------
This example shows a histogram with a global mean overlay.
"""
# category: histograms
import altair as alt
from vega_datasets import data
source = data.movies.url
base = alt.Chart(source)
bar = base.mark_bar().encode(
x=alt.X('IMDB_Rating:Q', bin=True, axis=None),
y='count()'
)
rule = base.mark_rule(color='red').encode(
x='mean(IMDB_Rating):Q',
size=alt.value(5)
)
bar + rule
"level_1": "second"
})
correlation_data["correlation_label"] = correlation_data["correlation"].map(
"{:.2f}".format)
base_correlation_plot = altair.Chart(correlation_data).encode(x="second:O",
y="first:O")
# Text layer with correlation labels
# Colors are for easier readability
correlation_plot_text = base_correlation_plot.mark_text(
tooltip=altair.TooltipContent("encoding")).encode(
text="correlation_label",
color=altair.condition(altair.datum.correlation > 0.5,
altair.value("white"), altair.value("black")))
correlation_plot = base_correlation_plot.mark_rect(
tooltip=altair.TooltipContent("encoding")).encode(color=altair.Color(
"correlation:Q",
scale=altair.Scale(domain=[-1, 0, 1],
range=["DarkBlue", "White", "DarkRed"],
type="linear")))
CORRELATION_MATRIX = correlation_plot + correlation_plot_text
(CORRELATION_MATRIX_COLUMN,
CORRELATION_OBSERVATION_COLUMN) = streamlit.columns([2, 1])
CORRELATION_MATRIX_COLUMN.altair_chart(
CORRELATION_MATRIX.properties(width=600, height=600).configure_axis(
import altair as alt
from vega_datasets import data
cars = data.cars()
highlight = alt.selection_single()
select = alt.selection_single(encodings=['x', 'y'])
chart = alt.Chart(cars).mark_rect().encode(
x=alt.X('Miles_per_Gallon', bin=True),
y=alt.X('Horsepower', bin=True),
color=alt.condition(highlight, 'count()',
alt.value('lightgray'))).add_selection(
highlight, select)
hist = alt.Chart(cars).mark_bar().encode(y='count()',
x='Origin').transform_filter(select)
chart | hist
color = alt.Color('weather:N', scale=scale)
# We create two selections:
# - a brush that is active on the top panel
# - a multi-click that is active on the bottom panel
brush = alt.selection_interval(encodings=['x'])
click = alt.selection_multi(encodings=['color'])
# Top panel is scatter plot of temperature vs time
points = alt.Chart().mark_point().encode(
alt.X('monthdate(date):T', axis=alt.Axis(title='Date')),
alt.Y('temp_max:Q',
axis=alt.Axis(title='Maximum Daily Temperature (C)'),
scale=alt.Scale(domain=[-5, 40])
),
color=alt.condition(brush, color, alt.value('lightgray')),
size=alt.Size('precipitation:Q', scale=alt.Scale(range=[5, 200]))
).properties(
width=600,
height=300
).add_selection(
brush
).transform_filter(
click
)
# Bottom panel is a bar chart of weather type
bars = alt.Chart().mark_bar().encode(
x='count()',
y='weather:N',
color=alt.condition(click, color, alt.value('lightgray')),
def viz_paired(df, input_city):
# Data Transform
cities = df.groupby(['city', 'category_name'])[[
'city', 'category_name', 'total_business_count', 'sample_rating',
'sample_review_count'
]].mean()
cities = cities.join(df.groupby(['city'])[['city',
'total_business_count']].sum(),
on='city',
rsuffix='_by_city')
cities['%_of_total'] = cities['total_business_count'] / cities[
'total_business_count_by_city']
## Input city
selected_cities = ['New York, New York', input_city]
cities_pair = cities.reset_index()
cities_pair = cities_pair[cities_pair['city'].isin(selected_cities)]
# Create layered visualization
viz_cities_slope_circles = alt.Chart(cities_pair).mark_point(
size=40, filled=True, opacity=1).encode(
x=alt.X('city:N',
sort=alt.Sort(selected_cities),
axis=alt.Axis(labelAngle=0)),
y=alt.Y('%_of_total:Q',
axis=alt.Axis(format='.2p',
title='Percent of Total Businesses')),
color=alt.Color('category_name:N', legend=None),
tooltip=[
alt.Tooltip('category_name:N', title='Ethnic Category'),
alt.Tooltip('%_of_total:Q',
format='.2%',
title='Percentage of Total'),
alt.Tooltip('total_business_count:Q', title='Count')
]).interactive(bind_x=False)
selection_opacity = alt.selection_single(encodings=['y'],
on='mouseover',
clear="click",
empty='none')
condition_opacity = alt.condition(selection_opacity, alt.value(1),
alt.value(0.2))
condition_size = alt.condition(selection_opacity, alt.value(3),
alt.value(2))
viz_cities_slope_line = alt.Chart(cities_pair).mark_line().add_selection(
selection_opacity).encode(
x=alt.X('city:N',
sort=alt.Sort(selected_cities),
axis=alt.Axis(labelAngle=0)),
y=alt.Y('%_of_total:Q',
axis=alt.Axis(format='.2p',
title='Percent of Total Businesses')),
color=alt.Color('category_name:N', legend=None),
opacity=condition_opacity,
size=condition_size,
tooltip=[
alt.Tooltip('category_name:N', title='Ethnic Category'),
alt.Tooltip('%_of_total:Q',
format='.2%',
title='Percentage of Total'),
alt.Tooltip('total_business_count:Q', title='Count')
]).interactive(bind_x=False)
viz_cities_slope = (viz_cities_slope_line +
viz_cities_slope_circles).properties(height=600)
return viz_cities_slope
# US states background
background = alt.Chart(states).mark_geoshape(
fill='lightgray',
stroke='white'
).properties(
title='US State Capitols',
width=700,
height=400
).project('albersUsa')
# Points and text
hover = alt.selection(type='single', on='mouseover', nearest=True,
fields=['lat', 'lon'])
base = alt.Chart(capitals).encode(
longitude='lon:Q',
latitude='lat:Q'
)
text = base.mark_text(dy=-5, align='right').encode(
alt.Text('city', type='nominal'),
opacity=alt.condition(~hover, alt.value(0), alt.value(1))
)
points = base.mark_point().encode(
color=alt.value('black'),
size=alt.condition(~hover, alt.value(30), alt.value(100))
).add_selection(hover)
background + points + text
# generate time series vizs
for municipality in municipalities:
t = f"<option value=\"{municipality}\">{municipality}</option>"
options.append(t)
fname = join("charts", municipality + ".html")
data = df[["date", municipality]]
nearest = alt.selection(type="single",
nearest=True,
on="mouseover",
fields=[municipality],
empty="none")
line = (alt.Chart(data).mark_line(interpolate="basis").encode(
x="date:Q", y=f"{municipality}:Q"))
selectors = (alt.Chart(data).mark_point().encode(
x="date:Q",
opacity=alt.value(0),
).add_selection(nearest))
points = line.mark_point().encode(
opacity=alt.condition(nearest, alt.value(1), alt.value(0)))
text = line.mark_text(align="left", dx=5, dy=-5).encode(
text=alt.condition(nearest, f"{municipality}:Q", alt.value(" ")))
# Draw a rule at the location of the selection
rules = (alt.Chart(data).mark_rule(color="gray").encode(
x="date:Q", ).transform_filter(nearest))
# Put the five layers into a chart and bind the data
chart = alt.layer(line, selectors, points, rules,
text).properties(width=600, height=300)
"""
Line Chart with Layered Aggregates
----------------------------------
This example shows how to make a multi-series line chart of the daily closing
stock prices for AAPL, AMZN, GOOG, IBM, and MSFT between 2000 and 2010, along
with a layered rule showing the average values.
"""
# category: line charts
import altair as alt
from vega_datasets import data
source = data.stocks()
base = alt.Chart(source).properties(width=600)
line = base.mark_line().encode(
x='date',
y='price',
color='symbol'
)
rule = base.mark_rule().encode(
y='average(price)',
color='symbol',
size=alt.value(2)
)
line + rule
"""
Error Bars showing Confidence Interval
======================================
This example shows how to show error bars using covidence intervals.
The confidence intervals are computed internally in vega by
a non-parametric [bootstrap of the mean](https://github.com/vega/vega-statistics/blob/master/src/bootstrapCI.js).
"""
import altair as alt
from vega_datasets import data
barley = data.barley()
points = alt.Chart(barley).mark_point(filled=True).encode(
alt.X(
'mean(yield)',
scale=alt.Scale(zero=False),
axis=alt.Axis(title='Barley Yield')
),
y='variety',
color=alt.value('black')
)
error_bars = alt.Chart(barley).mark_rule().encode(
x='ci0(yield)',
x2='ci1(yield)',
y='variety'
)
chart = points + error_bars
===================
This chart shows an example of using an interval selection to filter the
contents of an attached histogram, allowing the user to see the proportion
of items in each category within the selection.
"""
# category: interactive charts
import altair as alt
from vega_datasets import data
source = data.cars()
brush = alt.selection(type='interval')
points = alt.Chart().mark_point().encode(
x='Horsepower:Q',
y='Miles_per_Gallon:Q',
color=alt.condition(brush, 'Origin:N', alt.value('lightgray'))
).add_selection(
brush
)
bars = alt.Chart().mark_bar().encode(
y='Origin:N',
color='Origin:N',
x='count(Origin):Q'
).transform_filter(
brush
)
alt.vconcat(points, bars, data=source)
def plot(county, state):
charts = []
for daily in (True, False):
if daily:
vals = ['cases-daily', 'deaths-daily']
daily_or_total = 'Daily'
angle = 0
else:
daily_or_total = 'Total'
vals = ['cases', 'deaths']
angle = 270
thecounty = county_data[(county_data.state == state)
& (county_data.county == county)]
thecounty['realdate'] = pd.to_datetime(thecounty['date'])
thecounty = thecounty.set_index(['realdate'])
thecounty['cases-daily'] = (thecounty['cases'].shift(-1) -
thecounty['cases']).shift(1)
thecounty['deaths-daily'] = (thecounty['deaths'].shift(-1) -
thecounty['deaths']).shift(1)
thecounty = thecounty.loc['2020-03-01':] # not much data before then
# Shorten dates
thecounty['month-day'] = thecounty.date.str.slice(6)
# Plot daily cases and deaths
base = alt.Chart(thecounty).mark_bar().transform_fold(
fold=vals, as_=['variable', 'value']).encode(
x='month-day',
y='max(value):Q',
color=alt.Color('variable:N', scale=alt.Scale(scheme='set2')),
tooltip=[
'cases-daily', 'deaths-daily', 'cases', 'deaths'
]).properties(
width=900,
title='%s County %s COVID-19 %s Cases and Deaths' %
(county, state, daily_or_total))
if daily: x, y = -5, -8
else: x, y = 8, 0
text1 = base.mark_text(align='left',
baseline='middle',
dx=x,
dy=y,
angle=angle,
fontSize=8,
binSpacing=1).encode(y=vals[1],
text=vals[1],
color=alt.value('black'))
text2 = base.mark_text(align='left',
baseline='middle',
dx=x,
dy=y,
angle=angle,
fontSize=8,
binSpacing=1).encode(y=vals[0],
text=vals[0],
color=alt.value('black'))
newchart = base.interactive() + text1 + text2
charts.append(newchart)
combined = alt.vconcat(charts[0], charts[1])
combined.save('%s.html' % county)
return charts
def tl_summary(df,
values,
time,
bars,
col,
text,
title='',
bars_w=810,
bars_h=200,
bars_stack='zero',
timeline_w=450,
timeline_h=200,
slope_avg='Average',
slope_w=300,
slope_h=200,
slope_y_pos=10,
palette='tableau10'):
'''
Plots 3 charts: bars, timeline and slopegraph
Parameters
----------
df : pandas.DataFrame
values : str
Name of the column used for values.
time : str
Name of the column used for time values.
bars : str
Name of the column used to plot as X-axis on the bars.
col : str
Name of the column used for colors.
text : str
Name of the column used to show text on slopegraph.
title : str
Title of the plot.
bars_w : int
Bars plot width.
bars_h : int
Bars plot height.
timeline_w : int
Timeline plot width.
timeline_h : int
Timeline plot height.
slope_avg : str
Title for the avg measures on slopegraph.
slope_w : int
Slopegraph plot width.
slope_h : int
Slopegraph plot height.
slope_y_pos : int
Slopegraph titles position.
palette : str
Check https://vega.github.io/vega/docs/schemes/#reference
Returns
-------
altair.Chart
'''
df = df.copy()
df['slope_x'] = 'measures'
df_avg = df.groupby([col, time]).mean().reset_index()
df_avg[bars] = slope_avg
df_avg['slope_x'] = 'averages'
df = pd.concat([df, df_avg], ignore_index=True, sort=True)
df[values] = df[values].round(2)
df['slope_text'] = df[values].astype(str) + ' ' + df[col]
max_time = df[time].max()
orders = (df[df[time] == max_time].groupby(bars)[values].sum().sort_values(
ascending=False).index.tolist())
orders.remove(slope_avg)
filter_in = alt.selection_single(fields=[bars],
on='mouseover',
empty='none')
base = alt.Chart(df)
barsplot = base.mark_bar().encode(
alt.X(f'{bars}:N', title=None, scale=alt.Scale(domain=orders)),
alt.Y(f'{values}:Q', title=text, stack=bars_stack),
alt.Color(col,
legend=alt.Legend(orient='bottom-left', title=None),
scale=alt.Scale(scheme=palette)),
opacity=alt.condition(
filter_in, alt.value('1'), alt.value('0.6'))).transform_filter({
'and':
[f'datum.{time} == {max_time}', 'datum.slope_x == "measures"']
}).properties(title=title,
selection=filter_in,
width=bars_w,
height=bars_h)
timeline_base = base.mark_line().encode(
alt.X(f'{time}:O'),
alt.Y(f'{values}:Q',
title=text,
scale=alt.Scale(domain=[df[values].min(), df[values].max()])),
alt.Color(col, legend=None)).properties(width=timeline_w,
height=timeline_h)
timeline = timeline_base.transform_filter(filter_in)
timeline += timeline.mark_circle(size=25)
timeline_avg = timeline_base.mark_line(
strokeDash=[4, 2],
opacity=0.45).transform_filter(f'datum.{bars} == {slope_avg!r}')
slope = _build_slope(df, values, time, bars, col, text, filter_in,
slope_y_pos, slope_w, slope_h)
chart = barsplot & ((timeline_avg + timeline) | slope)
return chart
# Create a selection that chooses the nearest point & selects based on x-value
nearest = alt.selection(type='single', nearest=True, on='mouseover',
fields=['x'], empty='none')
# The basic line
line = alt.Chart().mark_line(interpolate='basis').encode(
x='x:Q',
y='y:Q',
color='category:N'
)
# Transparent selectors across the chart. This is what tells us
# the x-value of the cursor
selectors = alt.Chart().mark_point().encode(
x='x:Q',
opacity=alt.value(0),
).add_selection(
nearest
)
# Draw points on the line, and highlight based on selection
points = line.mark_point().encode(
opacity=alt.condition(nearest, alt.value(1), alt.value(0))
)
# Draw text labels near the points, and highlight based on selection
text = line.mark_text(align='left', dx=5, dy=-5).encode(
text=alt.condition(nearest, 'y:Q', alt.value(' '))
)
# Draw a rule at the location of the selection
+csv["Solar Energy (kWh)"]
csv = csv.round(0)
background = altair.Chart(states).mark_geoshape(
fill="black",
stroke="white",
).properties(width=1300, height=750).project("albersUsa")
points = altair.Chart(csv).mark_circle(
color='red',
size=50,
opacity=0.6,
).encode(
longitude='Longitude:Q',
latitude='Latitude:Q',
size=altair.Size("Total Energy (kWh):Q", title="Total Energy (kWh)"),
color="Total Energy (kWh):Q",
opacity=altair.value(0.6),
tooltip=[
'State:N', 'Capital:N', 'Wind Energy (MWh):N', 'Solar Energy (kWh):N',
'Total Energy (kWh):N'
],
)
chart = altair.layer(background, points).configure_legend(
labelFontSize=15,
titleFontSize=15,
labelFont="Times New Roman",
titleFont="Times New Roman",
).properties(background="none").configure_view(strokeOpacity=0)
chart.save('templates/energy.html', embed_options={'renderer': 'svg'})
chart
num_cars='count()', groupby=['Origin', 'Cylinders']).encode(
alt.X('Cylinders:O', scale=alt.Scale(paddingInner=0)),
alt.Y('Origin:O', scale=alt.Scale(paddingInner=0)),
)
# Configure heatmap
heatmap = base.mark_rect().encode(
color=alt.Color('num_cars:Q',
scale=alt.Scale(scheme='viridis'),
legend=alt.Legend(direction='horizontal')))
# Configure text
text = base.mark_text(baseline='middle').encode(text='num_cars:Q',
color=alt.condition(
alt.datum.num_cars > 100,
alt.value('black'),
alt.value('white')))
# Draw the chart
heatmap + text
##
import altair as alt
from vega_datasets import data
alt.Chart(data.cars()).transform_density(
'Miles_per_Gallon',
as_=['Miles_per_Gallon', 'density'],
extent=[5, 50],
groupby=['Origin']).mark_area(orient='horizontal').encode(
y='Miles_per_Gallon:Q',
def get_context_data(self, **kwargs):
"""
:param kwargs:
:return:
"""
kwargs = super(DoctorWelcome, self).get_context_data(**kwargs)
# look for oauth user, so we can use it's access_token
oauth_provider = get_object_or_404(UserSocialAuth, provider='drchrono')
# check if token is about to expire, and refresh it if so
# I couldn't get oauth_provider.access_token_expired() to work properly so wrote my own method
if self.is_access_token_expired(oauth_provider.extra_data['access_token']):
oauth_provider.refresh_token(load_strategy())
access_token = oauth_provider.extra_data['access_token']
patient_client = PatientEndpoint(access_token)
appointments_client = AppointmentEndpoint(access_token)
# information about the doctor
kwargs['doctor'] = next(DoctorEndpoint(access_token).list())
# list of patients
patients = list(patient_client.list())
# list of today's appointments
today_str = timezone.now().strftime('%m-%d-%y')
todays_appointments = list(appointments_client.list({}, start=today_str, end=today_str))
for appointment in todays_appointments:
patient = [patient for patient in patients if patient.get('id') == appointment.get('patient')][0]
appointment['first_name'] = patient.get('first_name')
appointment['last_name'] = patient.get('last_name')
kwargs['appointments'] = todays_appointments
# fetch information about patients who have checked in
visits = Visit.objects.filter(status='Arrived', arrival_time__isnull=False, start_time__isnull=True).all()
for visit in visits:
visit.wait_since_arrived = visit.get_wait_duration().seconds
patient = [patient for patient in patients if patient.get('id') == visit.patient_id][0]
visit.first_name = patient.get('first_name')
visit.last_name = patient.get('last_name')
kwargs['arrived'] = visits
# fetch information about our current appointment
current_appointment = Visit.objects.filter(status='In Session', arrival_time__isnull=False,
start_time__isnull=False).first()
if current_appointment:
kwargs['current_appointment'] = current_appointment
current_appointment.visit_duration = current_appointment.get_visit_duration().seconds
patient = [patient for patient in patients if patient.get('id') == current_appointment.patient_id][0]
current_appointment.first_name = patient.get('first_name')
current_appointment.last_name = patient.get('last_name')
current_appointment.date_of_birth = patient.get('date_of_birth')
current_appointment.date_of_last_appointment = patient.get('date_of_last_appointment')
current_appointment.race = patient.get('race')
current_appointment.gender = patient.get('gender')
current_appointment.ethnicity = patient.get('ethnicity')
# create list of past visit, and use it to generate average wait and visit duration
past_visits = Visit.objects.filter(status="Finished", arrival_time__isnull=False,
start_time__isnull=False).all()
if len(past_visits) > 0:
avg_wait_time = sum([(visit.start_time - visit.arrival_time).seconds for visit in past_visits]) / len(
past_visits)
kwargs['avg_wait_duration'] = math.ceil(avg_wait_time)
avg_visit_duration = sum([(visit.end_time - visit.start_time).seconds for visit in past_visits]) / len(
past_visits)
kwargs['avg_visit_duration'] = math.ceil(avg_visit_duration)
else:
kwargs['avg_wait_duration'] = "You have no arrivals!"
kwargs['avg_visit_duration'] = "You have no visits!"
# creating altair visualization
# create a df with list of times and durations
visit_data = [{
'start_time': visit.start_time,
'arrival_time': visit.arrival_time,
'wait_duration': visit.get_wait_duration().seconds,
'visit_duration': visit.get_visit_duration().seconds,
} for visit in past_visits]
visit_data_df = pd.DataFrame(visit_data)
# https://altair-viz.github.io/user_guide/interactions.html#selections-building-blocks-of-interactions
brush = alt.selection_interval(encodings=['x'])
chart = alt.Chart(visit_data_df).mark_bar().properties(
width=300,
height=150
).add_selection(
brush
)
# combine two charts one with wait duration and one with visit duration
kwargs['chart'] = alt.hconcat(chart.encode(
x=alt.X('start_time:T', axis=alt.Axis(title='Time the visit started')),
y=alt.Y('wait_duration:Q', axis=alt.Axis(title='Wait Duration')),
color=alt.condition(brush, alt.value('black'), alt.value('lightgray'))
), chart.encode(
x=alt.X('start_time:T', axis=alt.Axis(title='Time the visit started')),
y=alt.Y('visit_duration:Q', axis=alt.Axis(title='Visit Duration')),
color=alt.condition(brush, alt.value('black'), alt.value('lightgray'))
)).resolve_scale(
y='shared'
)
return kwargs
This is a temporary script file.
"""
import altair as alt
import pandas as pd
from vega_datasets import data as vega_data
morse = pd.read_csv(
'https://raw.githubusercontent.com/jvelleu/649_final_project/7648fb227384b3dad2707efdf8fb960f502b52ad/morse_data.csv',
encoding='utf-8')
mouseSelection = alt.selection_single(on="mouseover",
nearest=True,
empty='none')
opacityCondition = alt.condition(mouseSelection, alt.value(1.0),
alt.value(0.6))
scatter1 = alt.Chart(
morse, width=400, height=400).mark_point(filled=True).encode(
alt.X("x", title="", axis=None), alt.Y("y", title="", axis=None),
alt.Tooltip(["char", "code"], title=None),
alt.Size("components:O")).add_selection(mouseSelection).encode(
opacity=opacityCondition)
scatter2 = alt.Chart(
morse, width=400, height=400).mark_point(filled=True).encode(
alt.X("x", title="", axis=None),
alt.Y("y", title="", axis=None),
alt.Tooltip(["char", "code"], title=None),
alt.Color("type:N"),
df = pd.read_excel(file,index_col=False)
interval = alt.selection_interval()
base = alt.Chart(df).properties(
width=350,
height=350,
).add_selection(interval)
points = base.mark_point(filled=True, size=1000).encode(
x='XX_Bottom:Q',
y='YY_Bottom:Q',
size='BOPD:Q',
#color=alt.condition(interval, 'Well_Name', alt.value('lightgray')),
color=alt.condition(interval, 'Well_Name', alt.value('lightgray')),
tooltip='Well_Name',
).properties(
title='Volve Field Map',
selection=interval
)
timeseries = base.mark_line().encode(
x='Date',
y=alt.Y('BOPD', scale=alt.Scale(domain=(0, 40000))),
color=alt.Color('Well_Name:O')
).properties(
title='Volve Production by Well in BOPD',
tot_y='sum(Total)',
mean_x='mean(Income)',
groupby=['State']
).interactive().transform_filter(brush
)
st.write("### *Pan and zoom to see data points more clearly on the scatter plot*")
#
#
#BAR
bar = alt.Chart(df_w).mark_bar(
).transform_filter(
alt.datum['Year'] == year_slider
).encode(
x=alt.X('State:N',sort='-y', scale=alt.Scale(zero=False),axis=alt.Axis(titleFontSize=20,labelFontSize=14)),
y=alt.Y('mean(Unemployment):Q',title='Unemployment Rate (%)', scale=alt.Scale(zero=False),axis=alt.Axis(titleFontSize=20,labelFontSize=14)),
color= alt.condition(brush,'State:N',alt.value('lightgray'), legend=None),
tooltip=[alt.Tooltip('State:N'),alt.Tooltip('mean(Unemployment):Q',title="Unemployment")]
).properties(
width=1000,
height=500
).add_selection(
brush
)
states_us = alt.topo_feature('https://vega.github.io/vega-datasets/data/us-10m.json', 'states')
source = 'https://raw.githubusercontent.com/sammyhajomar/test/main/altair-dataset.csv'
variables = ['State','Total','id']
US_map = alt.Chart(states_us).mark_geoshape().encode(
color=alt.condition(multi_state,'Total:Q',alt.value('lightgray'),title='Total Deaths'),
capitals = data.us_state_capitals.url
# US states background
background = alt.Chart(states).mark_geoshape(
fill='lightgray',
stroke='white').properties(title='US State Capitols',
projection={'type': 'albersUsa'},
width=700,
height=400)
# Points and text
hover = alt.selection(type='single',
on='mouseover',
nearest=True,
fields=['lat', 'lon'])
base = alt.Chart(capitals).encode(longitude='lon:Q', latitude='lat:Q')
text = base.mark_text(dy=-5, align='right').encode(alt.Text('city',
type='nominal'),
opacity=alt.condition(
~hover, alt.value(0),
alt.value(1)))
points = base.mark_point().encode(
color=alt.value('black'),
size=alt.condition(~hover, alt.value(30),
alt.value(100))).properties(selection=hover)
chart = background + points + text
def build_altair_text_error(error: str) -> str:
return alt.Chart(pd.DataFrame({'message': [f'❌ {error}']}))\
.mark_text(size=20, font='monospace').encode(
text='message',
color=alt.value('red')
).properties(width=500, height=50).configure_view(strokeWidth=0).to_json()
timeseries = timeseries.reset_index().melt('time')
# Merge the (x, y) metadata into the long-form view
timeseries['id'] = timeseries['id'].astype(int) # make merge not complain
data = pd.merge(timeseries, locations, on='id')
# Data is prepared, now make a chart
selector = alt.selection_single(empty='all', fields=['id'])
base = alt.Chart(data).properties(
width=250,
height=250
).add_selection(selector)
points = base.mark_point(filled=True, size=200).encode(
x='mean(x)',
y='mean(y)',
color=alt.condition(selector, 'id:O', alt.value('lightgray'), legend=None),
).interactive()
timeseries = base.mark_line().encode(
x='time',
y=alt.Y('value', scale=alt.Scale(domain=(-15, 15))),
color=alt.Color('id:O', legend=None)
).transform_filter(
selector
)
points | timeseries
settle_data = pd.read_csv(
"D:/OneDrive/data/seattle-weather.csv") # 导入数据集，数据见文末
settle_data.weather.unique() # 定义比例：根据天气类型的分布来绘制数据
scale = alt.Scale(
domain=['sun', 'fog', 'drizzle', 'rain', 'snow'],
range=['#e7ba52', '#a7a7a7', '#aec7e8', '#1f77b4', '#9467bd'])
color = alt.Color('weather:N', scale=scale)
brush = alt.selection_interval(encodings=['x']) #添加互动功能
click = alt.selection_multi(encodings=['color'])
#顶部散射图：温度 Vs 日期
points = alt.Chart().mark_point().encode(
alt.X('monthdate(date):T', title='Date'),
alt.Y('temp_max:Q',
title='Maximum Daily Temperature (C)',
scale=alt.Scale(domain=[-5, 40])),
color=alt.condition(brush, color, alt.value('lightgray')),
size=alt.Size('precipitation:Q',
scale=alt.Scale(range=[5, 200]))).properties(
width=1080,
height=500).add_selection(brush).transform_filter(click)
##########################
# 2. 底部栏图：天气类型
bars = alt.Chart().mark_bar().encode(
x='count()',
y='weather:N',
color=alt.condition(click, color, alt.value('lightgray')),
).transform_filter(brush).properties(width=550, ).add_selection(click)
##########################
#3. 构建复合图：垂直串联两个图表
tu = alt.vconcat(points, bars, data=settle_data, title="天气数据: 2012-2015")
tu.save('c:/in/4.html')
"""
# category: scatter plots
import altair as alt
from vega_datasets import data
source = data.cars()
# Configure the options common to all layers
brush = alt.selection(type='interval')
base = alt.Chart(source).add_selection(brush)
# Configure the points
points = base.mark_point().encode(
x=alt.X('Miles_per_Gallon', axis=alt.Axis(title='')),
y=alt.Y('Horsepower', axis=alt.Axis(title='')),
color=alt.condition(brush, 'Origin', alt.value('grey'))
)
# Configure the ticks
tick_options = dict(labels=False, domain=False, ticks=False)
tick_axis = alt.Axis(**tick_options)
tick_axis_notitle = alt.Axis(title='', **tick_options)
x_ticks = base.mark_tick().encode(
alt.X('Miles_per_Gallon', axis=tick_axis),
alt.Y('Origin', axis=tick_axis_notitle),
color=alt.condition(brush, 'Origin', alt.value('lightgrey'))
)
y_ticks = base.mark_tick().encode(
alt.X('Origin', axis=tick_axis_notitle),
# Production values only
df["power"] = df["power"].clip(lower=0)
max_production = df["power"].max()
# Create selection brush
date_selection_brush = alt.selection_multi(encodings=["x", "y"], name="date_select")
# Create calendar
calendar = (
alt.Chart(df).mark_rect()
.encode(
x=alt.Y("date(datetime):O", title="Day of the month"),
y=alt.X("month(datetime):O", title="Month"),
color=alt.Color("sum(power):Q", title="Excess solar production (kWh)", scale=alt.Scale(scheme="dark2")),
opacity=alt.condition(date_selection_brush, alt.value(1), alt.value(0.7)))
)
# Make calendar days selectable
calendar = calendar.add_selection(date_selection_brush)
# Create a chart that shows a power profile of a single day (the selected day)
chart = (
alt.Chart(df).mark_line()
.transform_filter(date_selection_brush)
.encode(
x=alt.X(
"datetime",
title="Time of day",
),
y=alt.Y("power", title="Power (kW)", scale=alt.Scale(domain=(0, max_production))),
# left panel: scatter plot
points = alt.Chart().mark_point(filled=True, color="black").encode(
x='x',
y='y'
).transform_filter(
pts.ref()
).properties(
width=300,
height=300
)
# right panel: histogram
mag = alt.Chart().mark_bar().encode(
x='mbin:N',
y="count()",
color=alt.condition(pts, alt.value("black"), alt.value("lightgray"))
).properties(
selection=pts,
width=300,
height=300
)
# build the chart:
alt.hconcat(
points,
mag,
data=source
).transform_bin(
"mbin",
field="m",
bin=alt.Bin(maxbins=20)
def plot_interactive_histograms_sm():
data1 = pd.read_csv(
'https://raw.githubusercontent.com/jamescoller/multilayer_design_network_tool/master/results/all_data2018-01-01.csv'
)
data2 = pd.read_csv(
'https://raw.githubusercontent.com/jamescoller/multilayer_design_network_tool/master/results/all_data2018-02-01.csv'
)
data3 = pd.read_csv(
'https://raw.githubusercontent.com/jamescoller/multilayer_design_network_tool/master/results/all_data2018-03-01.csv'
)
data4 = pd.read_csv(
'https://raw.githubusercontent.com/jamescoller/multilayer_design_network_tool/master/results/all_data2018-04-01.csv'
)
data5 = pd.read_csv(
'https://raw.githubusercontent.com/jamescoller/multilayer_design_network_tool/master/results/all_data2018-05-01.csv'
)
data6 = pd.read_csv(
'https://raw.githubusercontent.com/jamescoller/multilayer_design_network_tool/master/results/all_data2018-06-01.csv'
)
data7 = pd.read_csv(
'https://raw.githubusercontent.com/jamescoller/multilayer_design_network_tool/master/results/all_data2018-07-01.csv'
)
data8 = pd.read_csv(
'https://raw.githubusercontent.com/jamescoller/multilayer_design_network_tool/master/results/all_data2018-08-01.csv'
)
data9 = pd.read_csv(
'https://raw.githubusercontent.com/jamescoller/multilayer_design_network_tool/master/results/all_data2018-09-01.csv'
)
data10 = pd.read_csv(
'https://raw.githubusercontent.com/jamescoller/multilayer_design_network_tool/master/results/all_data2018-10-01.csv'
)
data11 = pd.read_csv(
'https://raw.githubusercontent.com/jamescoller/multilayer_design_network_tool/master/results/all_data2018-11-01.csv'
)
data12 = pd.read_csv(
'https://raw.githubusercontent.com/jamescoller/multilayer_design_network_tool/master/results/all_data2018-12-01.csv'
)
node_info = pd.read_csv(
'https://raw.githubusercontent.com/jamescoller/multilayer_design_network_tool/master/Data/Node_List.csv'
)
time_summary = pd.read_csv(
'https://raw.githubusercontent.com/jamescoller/multilayer_design_network_tool/master/results/summary_data.csv'
)
data1['month'] = 'January'
data2['month'] = 'February'
data3['month'] = 'March'
data4['month'] = 'April'
data5['month'] = 'May'
data6['month'] = 'June'
data7['month'] = 'July'
data8['month'] = 'August'
data9['month'] = 'September'
data10['month'] = 'October'
data11['month'] = 'November'
data12['month'] = 'December'
data1 = pd.merge(data1,
node_info,
how='inner',
left_on='NodeID',
right_on='ID')
data2 = pd.merge(data2,
node_info,
how='inner',
left_on='NodeID',
right_on='ID')
data3 = pd.merge(data3,
node_info,
how='inner',
left_on='NodeID',
right_on='ID')
data4 = pd.merge(data4,
node_info,
how='inner',
left_on='NodeID',
right_on='ID')
data5 = pd.merge(data5,
node_info,
how='inner',
left_on='NodeID',
right_on='ID')
data6 = pd.merge(data6,
node_info,
how='inner',
left_on='NodeID',
right_on='ID')
data7 = pd.merge(data7,
node_info,
how='inner',
left_on='NodeID',
right_on='ID')
data8 = pd.merge(data8,
node_info,
how='inner',
left_on='NodeID',
right_on='ID')
data9 = pd.merge(data9,
node_info,
how='inner',
left_on='NodeID',
right_on='ID')
data10 = pd.merge(data10,
node_info,
how='inner',
left_on='NodeID',
right_on='ID')
data11 = pd.merge(data11,
node_info,
how='inner',
left_on='NodeID',
right_on='ID')
data12 = pd.merge(data12,
node_info,
how='inner',
left_on='NodeID',
right_on='ID')
all_data = pd.concat([
data1, data2, data3, data4, data5, data6, data7, data8, data9, data10,
data11, data12
])
months = [
'January', 'February', 'March', 'April', 'May', 'June', 'July',
'August', 'September', 'October', 'November', 'December'
]
layers = ['Algorithm', 'Physical', 'Task', 'Function', 'Information']
input_dropdown = alt.binding_select(options=months)
selection = alt.selection_single(fields=['month'],
bind=input_dropdown,
name='Month')
layer_dropdown = alt.binding_select(options=layers)
layer_selection = alt.selection_single(fields=['Layer'],
bind=layer_dropdown,
name='Layer')
cn = alt.Chart(all_data).mark_bar().encode(
x=alt.X('Cn:Q', bin=alt.Bin(maxbins=20), title='Connectedness Rating'),
y=alt.Y('count()', title='Number of Nodes'),
color=alt.value('#4e79a7')).add_selection(selection).transform_filter(
selection).add_selection(layer_selection).transform_filter(
layer_selection)
rn = alt.Chart(all_data).mark_bar().encode(
x=alt.X('Rn:Q', bin=alt.Bin(maxbins=20), title='Reliability Rating'),
y=alt.Y('count()', title='Number of Nodes'),
color=alt.value('#f28e2b')).add_selection(selection).transform_filter(
selection).add_selection(layer_selection).transform_filter(
layer_selection)
id = alt.Chart(all_data).mark_bar().encode(
x=alt.X('Id:Q',
bin=alt.Bin(maxbins=20),
title='Interdependency Rating'),
y=alt.Y('count()', title='Number of Nodes'),
color=alt.value('#e15759')).add_selection(selection).transform_filter(
selection).add_selection(layer_selection).transform_filter(
layer_selection)
chart = alt.hconcat(cn, rn, id)
#(cn | rn | id)
chart.serve()
return
"""
Parallel Coordinates Example
----------------------------
A `Parallel Coordinates <https://en.wikipedia.org/wiki/Parallel_coordinates>`_
chart is a chart that lets you visualize the individual data points by drawing
a single line for each of them.
Such a chart can be created in Altair, but requires some data preprocessing
to transform the data into a suitable representation.
This example shows a parallel coordinates chart with the Iris dataset.
"""
# category: other charts
import altair as alt
from vega_datasets import data
source = data.iris()
source_transformed = source.reset_index().melt(['species', 'index'])
alt.Chart(source_transformed).mark_line().encode(
x='variable:N',
y='value:Q',
color='species:N',
detail='index:N',
opacity=alt.value(0.5)
).properties(width=500)
import altair as alt
from vega_datasets import data
source = data.cars()
# Configure the options common to all layers
brush = alt.selection(type='interval')
base = alt.Chart(source).add_selection(brush)
# Configure the points
points = base.mark_point().encode(x=alt.X('Miles_per_Gallon',
axis=alt.Axis(title='')),
y=alt.Y('Horsepower',
axis=alt.Axis(title='')),
color=alt.condition(brush, 'Origin',
alt.value('grey')))
# Configure the ticks
tick_options = dict(labels=False, domain=False, ticks=False)
tick_axis = alt.Axis(**tick_options)
tick_axis_notitle = alt.Axis(title='', **tick_options)
x_ticks = base.mark_tick().encode(alt.X('Miles_per_Gallon', axis=tick_axis),
alt.Y('Origin', axis=tick_axis_notitle),
color=alt.condition(brush, 'Origin',
alt.value('lightgrey')))
y_ticks = base.mark_tick().encode(alt.X('Origin', axis=tick_axis_notitle),
alt.Y('Horsepower', axis=tick_axis),
color=alt.condition(brush, 'Origin',
alt.value('lightgrey')))
"""
Interactive Rectangular Brush
=============================
This example shows how to add a simple rectangular brush to a scatter plot.
By clicking and dragging on the plot, you can highlight points within the
range.
"""
# category: interactive charts
import altair as alt
from vega_datasets import data
source = data.cars()
brush = alt.selection(type='interval')
alt.Chart(source).mark_point().encode(
x='Horsepower:Q',
y='Miles_per_Gallon:Q',
color=alt.condition(brush, 'Cylinders:O', alt.value('grey'))
).add_selection(brush)
import altair as alt
import pandas as pd
penguins_df = pd.read_csv('data/penguins.csv')
slider = alt.____(name=.____, max=max(penguins_df.____))
select_rating = alt.____(
fields=[____],
bind=____)
slider_scatter = (alt.Chart(penguins_df).mark_circle().encode(
alt.X('culmen_length_mm', title='Culmen length (mm)', scale=alt.Scale(zero=False)),
alt.Y('culmen_depth_mm', title='Culmen depth (mm)', scale=alt.Scale(zero=False)),
color='species',
opacity=alt.condition(____ < ____, alt.value(0.7), alt.value(0.05)))
.add_selection(____))
slider_scatter
brush = alt.selection(type='interval', encodings=['x'])
# Define the base chart, with the common parts of the
# background and highlights
base = alt.Chart().mark_bar().encode(
x=alt.X(alt.repeat('column'), type='quantitative', bin=alt.Bin(maxbins=20)),
y='count()'
).properties(
width=180,
height=130
)
# blue background with selection
background = base.properties(selection=brush)
# yellow highlights on the transformed data
highlight = base.encode(
color=alt.value('goldenrod')
).transform_filter(brush)
# layer the two charts & repeat
alt.layer(
background,
highlight,
data=source
).transform_calculate(
"time",
"hours(datum.date)"
).repeat(column=["distance", "delay", "time"])
def slope_comparison(df,
values,
bars,
col,
text,
bars_w=200,
bars_h=515,
slope_avg='Average',
slope_w=350,
slope_h=240,
slope_y_pos=10,
slope_y_title=None):
'''
Plots 3 charts: v-bars and 2 slopegraph for comparison.
Parameters
----------
df : pandas.DataFrame
values : str
Name of the column used for values.
bars : str
Name of the column used to plot as X-axis on the bars.
col : str
Name of the column used for colors.
text : str
Name of the column used to show text on slopegraph.
bars_w : int
Bars plot width.
bars_h : int
Bars plot height.
slope_avg : str
Title for the avg measures on slopegraph.
slope_w : int
Slopegraph plot width.
slope_h : int
Slopegraph plot height.
slope_y_pos : int
Slopegraph titles position.
slope_y_title : str
Title to use on slope y axis.
Returns
-------
altair.Chart
Parameters
----------
df : pandas.DataFrame
vs : str list
List of variables to include in the plot.
year : int
Year to extract from data.
custom_fn : function
Function to apply to df after formatting.
Use it to format names on the df.
kwargs : arguments passed to get_data_series
'''
df = df.copy()
df['slope_x'] = 'measures'
df_avg = df.groupby(col).mean().reset_index()
df_avg[bars] = slope_avg
df_avg['slope_x'] = 'averages'
df = pd.concat([df, df_avg], ignore_index=True, sort=True)
df[values] = df[values].round(2)
df['slope_text'] = df[values].astype(str) + ' ' + df[col]
mouse = alt.selection_single(on='mouseover',
fields=[bars],
empty='none',
nearest=True)
click = alt.selection_single(fields=[bars], empty='none')
base = alt.Chart(df)
barsplot = base.mark_point(filled=True).encode(
alt.X(f'mean({values})',
scale=alt.Scale(zero=False),
axis=alt.Axis(title=None)),
alt.Y(f'{bars}:N', axis=alt.Axis(title=None)),
size=alt.condition(mouse, alt.value(400), alt.value(
200))).transform_filter('datum.slope_x == "measures"').properties(
selection=mouse, width=bars_w, height=bars_h)
barsplot += barsplot.encode(
size=alt.condition(click, alt.value(350), alt.value(200)),
color=alt.condition(click, alt.ColorValue('#800000'),
alt.value('#879cab'))).properties(selection=click)
bars_ci = base.mark_rule().encode(
x=f'ci0({values})', x2=f'ci1({values})',
y=f'{bars}:N').transform_filter(
'datum.slope_x == "measures"').properties(width=bars_w,
height=bars_h)
slope_mouse = _build_slope(df, values, None, bars, col, text, mouse,
slope_y_pos, slope_w, slope_h, slope_y_title)
slope_click = _build_slope(df, values, None, bars, col, text, click,
slope_y_pos, slope_w, slope_h)
chart = (bars_ci + barsplot) | (slope_mouse & slope_click)
return chart
"""
Bar Chart with Highlighted Bar
------------------------------
This example shows a basic bar chart with a single bar highlighted.
"""
# category: bar charts
import altair as alt
from vega_datasets import data
source = data.wheat.url
alt.Chart(source).mark_bar().encode(
x='year:O',
y="wheat:Q",
# The highlight will be set on the result of a conditional statement
color=alt.condition(
alt.datum.year == 1810, # If the year is 1810 this test returns True,
alt.value('orange'), # which sets the bar orange.
alt.value('steelblue') # And if it's not true it sets the bar steelblue.
)
).properties(width=600)
Locations of US Airports
========================
This is a layered geographic visualization that shows the positions of US
airports on a background of US states.
"""
# category: case studies
import altair as alt
from vega_datasets import data
airports = data.airports()
states = alt.topo_feature(data.us_10m.url, feature='states')
# US states background
background = alt.Chart(states).mark_geoshape(
fill='lightgray',
stroke='white'
).properties(
width=500,
height=300
).project('albersUsa')
# airport positions on background
points = alt.Chart(airports).mark_circle().encode(
longitude='longitude:Q',
latitude='latitude:Q',
size=alt.value(10),
color=alt.value('steelblue')
)
background + points
