vignettes/example-gallery-10-other-charts.Rmd
example-gallery-10-other-charts.RmdThis document is adapted from the Other Charts section of the Altair Example Gallery.
Our first step is to set up our environment:
library("altair")
library("tibble")
library("dplyr")
library("jsonlite")
vega_data <- import_vega_data()
glimpse(vega_data$wheat())
#> Rows: 52
#> Columns: 3
#> $ year <dbl> 1565, 1570, 1575, 1580, 1585, 1590, 1595, 1600, 1605, 1610, 1615…
#> $ wheat <dbl> 41.0, 45.0, 42.0, 49.0, 41.5, 47.0, 64.0, 27.0, 33.0, 32.0, 33.0…
#> $ wages <dbl> 5.00, 5.05, 5.08, 5.12, 5.15, 5.25, 5.54, 5.61, 5.69, 5.78, 5.94…
source <- vega_data$wheat()
threshold <- tibble(threshold = 90)
bars <-
alt$Chart(source)$
mark_bar()$
encode(
x = "year:O",
y = "wheat:Q"
)
highlight <-
alt$Chart(source)$
mark_bar(color = "#e45755")$
encode(
x = "year:O",
y = "baseline:Q",
y2 = "wheat:Q"
)$
transform_filter("datum.wheat > 90")$
transform_calculate("baseline", "90")
rule <-
alt$Chart(threshold)$
mark_rule()$
encode(
y = "threshold:Q"
)
(bars + highlight + rule)$properties(width = 600)
glimpse(vega_data$barley())
#> Rows: 120
#> Columns: 4
#> $ yield <dbl> 27.00000, 48.86667, 27.43334, 39.93333, 32.96667, 28.96667, 43…
#> $ variety <chr> "Manchuria", "Manchuria", "Manchuria", "Manchuria", "Manchuria…
#> $ year <dbl> 1931, 1931, 1931, 1931, 1931, 1931, 1931, 1931, 1931, 1931, 19…
#> $ site <chr> "University Farm", "Waseca", "Morris", "Crookston", "Grand Rap…
glimpse(fromJSON(vega_data$movies$url))
#> Rows: 3,201
#> Columns: 16
#> $ Title <chr> "The Land Girls", "First Love, Last Rites", "I …
#> $ US_Gross <int> 146083, 10876, 203134, 373615, 1009819, 24551, …
#> $ Worldwide_Gross <dbl> 146083, 10876, 203134, 373615, 1087521, 2624551…
#> $ US_DVD_Sales <int> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,…
#> $ Production_Budget <int> 8000000, 300000, 250000, 300000, 1000000, 16000…
#> $ Release_Date <chr> "Jun 12 1998", "Aug 07 1998", "Aug 28 1998", "S…
#> $ MPAA_Rating <chr> "R", "R", NA, NA, "R", NA, "R", "R", "R", NA, N…
#> $ Running_Time_min <int> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,…
#> $ Distributor <chr> "Gramercy", "Strand", "Lionsgate", "Fine Line",…
#> $ Source <chr> NA, NA, NA, NA, "Original Screenplay", NA, NA, …
#> $ Major_Genre <chr> NA, "Drama", "Comedy", "Comedy", "Drama", NA, N…
#> $ Creative_Type <chr> NA, NA, NA, NA, "Contemporary Fiction", NA, NA,…
#> $ Director <chr> NA, NA, NA, NA, NA, NA, "Christopher Nolan", NA…
#> $ Rotten_Tomatoes_Rating <int> NA, NA, NA, 13, 62, NA, NA, NA, 25, 86, 81, 84,…
#> $ IMDB_Rating <dbl> 6.1, 6.9, 6.8, NA, 3.4, NA, 7.7, 3.8, 5.8, 7.0,…
#> $ IMDB_Votes <int> 1071, 207, 865, NA, 165, NA, 15133, 353, 3275, …This example shows how to make a basic box plot using US Population data from 2000.
glimpse(vega_data$population())
#> Rows: 570
#> Columns: 4
#> $ year <dbl> 1850, 1850, 1850, 1850, 1850, 1850, 1850, 1850, 1850, 1850, 185…
#> $ age <dbl> 0, 0, 5, 5, 10, 10, 15, 15, 20, 20, 25, 25, 30, 30, 35, 35, 40,…
#> $ sex <dbl> 1, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1, …
#> $ people <dbl> 1483789, 1450376, 1411067, 1359668, 1260099, 1216114, 1077133, …A candlestick chart inspired from Protovis. This example shows the performance of the Chicago Board Options Exchange Volatility Index (VIX) in the summer of 2009. The thick bar represents the opening and closing prices, while the thin bar shows intraday high and low prices; if the index closed higher on a given day, the bars are colored green rather than red. #### Data
data <-
jsonlite::fromJSON('[
{
"date": "01-Jun-2009",
"open": 28.7,
"high": 30.05,
"low": 28.45,
"close": 30.04,
"signal": "short",
"ret": -4.89396411092985
},
{
"date": "02-Jun-2009",
"open": 30.04,
"high": 30.13,
"low": 28.3,
"close": 29.63,
"signal": "short",
"ret": -0.322580645161295
},
{
"date": "03-Jun-2009",
"open": 29.62,
"high": 31.79,
"low": 29.62,
"close": 31.02,
"signal": "short",
"ret": 3.68663594470045
},
{
"date": "04-Jun-2009",
"open": 31.02,
"high": 31.02,
"low": 29.92,
"close": 30.18,
"signal": "short",
"ret": 4.51010886469673
},
{
"date": "05-Jun-2009",
"open": 29.39,
"high": 30.81,
"low": 28.85,
"close": 29.62,
"signal": "short",
"ret": 6.08424336973478
},
{
"date": "08-Jun-2009",
"open": 30.84,
"high": 31.82,
"low": 26.41,
"close": 29.77,
"signal": "short",
"ret": 1.2539184952978
},
{
"date": "09-Jun-2009",
"open": 29.77,
"high": 29.77,
"low": 27.79,
"close": 28.27,
"signal": "short",
"ret": -5.02431118314424
},
{
"date": "10-Jun-2009",
"open": 26.9,
"high": 29.74,
"low": 26.9,
"close": 28.46,
"signal": "short",
"ret": -5.46623794212217
},
{
"date": "11-Jun-2009",
"open": 27.36,
"high": 28.11,
"low": 26.81,
"close": 28.11,
"signal": "short",
"ret": -8.3743842364532
},
{
"date": "12-Jun-2009",
"open": 28.08,
"high": 28.5,
"low": 27.73,
"close": 28.15,
"signal": "short",
"ret": -5.52763819095477
},
{
"date": "15-Jun-2009",
"open": 29.7,
"high": 31.09,
"low": 29.64,
"close": 30.81,
"signal": "long",
"ret": 3.4920634920635
},
{
"date": "16-Jun-2009",
"open": 30.81,
"high": 32.75,
"low": 30.07,
"close": 32.68,
"signal": "short",
"ret": 0.155038759689914
},
{
"date": "17-Jun-2009",
"open": 31.19,
"high": 32.77,
"low": 30.64,
"close": 31.54,
"signal": "short",
"ret": 5.82822085889571
},
{
"date": "18-Jun-2009",
"open": 31.54,
"high": 31.54,
"low": 29.6,
"close": 30.03,
"signal": "short",
"ret": 8.17610062893082
},
{
"date": "19-Jun-2009",
"open": 29.16,
"high": 29.32,
"low": 27.56,
"close": 27.99,
"signal": "short",
"ret": 8.59872611464968
},
{
"date": "22-Jun-2009",
"open": 30.4,
"high": 32.05,
"low": 30.3,
"close": 31.17,
"signal": "short",
"ret": 15.4907975460123
},
{
"date": "23-Jun-2009",
"open": 31.3,
"high": 31.54,
"low": 27.83,
"close": 30.58,
"signal": "short",
"ret": 11.7370892018779
},
{
"date": "24-Jun-2009",
"open": 30.58,
"high": 30.58,
"low": 28.79,
"close": 29.05,
"signal": "long",
"ret": -10.4234527687296
},
{
"date": "25-Jun-2009",
"open": 29.45,
"high": 29.56,
"low": 26.3,
"close": 26.36,
"signal": "long",
"ret": 0
},
{
"date": "26-Jun-2009",
"open": 27.09,
"high": 27.22,
"low": 25.76,
"close": 25.93,
"signal": "long",
"ret": 0
},
{
"date": "29-Jun-2009",
"open": 25.93,
"high": 27.18,
"low": 25.29,
"close": 25.35,
"signal": "long",
"ret": 5.26315789473684
},
{
"date": "30-Jun-2009",
"open": 25.36,
"high": 27.38,
"low": 25.02,
"close": 26.35,
"signal": "long",
"ret": 6.73758865248228
}
]')
glimpse(data)
#> Rows: 22
#> Columns: 7
#> $ date <chr> "01-Jun-2009", "02-Jun-2009", "03-Jun-2009", "04-Jun-2009", "05…
#> $ open <dbl> 28.70, 30.04, 29.62, 31.02, 29.39, 30.84, 29.77, 26.90, 27.36, …
#> $ high <dbl> 30.05, 30.13, 31.79, 31.02, 30.81, 31.82, 29.77, 29.74, 28.11, …
#> $ low <dbl> 28.45, 28.30, 29.62, 29.92, 28.85, 26.41, 27.79, 26.90, 26.81, …
#> $ close <dbl> 30.04, 29.63, 31.02, 30.18, 29.62, 29.77, 28.27, 28.46, 28.11, …
#> $ signal <chr> "short", "short", "short", "short", "short", "short", "short", …
#> $ ret <dbl> -4.8939641, -0.3225806, 3.6866359, 4.5101089, 6.0842434, 1.2539…
open_close_color <-
alt$condition(
"datum.open < datum.close",
alt$value("#06982d"),
alt$value("#ae1325")
)
rule <-
alt$Chart(data)$
mark_rule()$
encode(
alt$X(
"date:T",
timeUnit = "yearmonthdate",
scale = alt$Scale(
domain = list(
list(month= 5, date= 31, year= 2009),
list(month= 7, date= 1, year= 2009)
)
),
axis = alt$Axis(format = "%m/%d", title = "Date in 2009")
),
alt$Y(
"low",
scale = alt$Scale(zero = FALSE),
axis = alt$Axis(title = "Price")
),
alt$Y2("high"),
color = open_close_color
)
bar <-
alt$Chart(data)$
mark_bar()$
encode(
alt$X("date:T", timeUnit = "yearmonthdate"),
y = "open",
y2 = "close",
color = open_close_color
)
chart <- (rule + bar)
chart
glimpse(vega_data$barley())
#> Rows: 120
#> Columns: 4
#> $ yield <dbl> 27.00000, 48.86667, 27.43334, 39.93333, 32.96667, 28.96667, 43…
#> $ variety <chr> "Manchuria", "Manchuria", "Manchuria", "Manchuria", "Manchuria…
#> $ year <dbl> 1931, 1931, 1931, 1931, 1931, 1931, 1931, 1931, 1931, 1931, 19…
#> $ site <chr> "University Farm", "Waseca", "Morris", "Crookston", "Grand Rap…
source <- vega_data$barley()
error_bars <-
alt$Chart(source)$
mark_errorbar(extent = "stdev")$
encode(
x = alt$X("yield:Q", scale = alt$Scale(zero = FALSE)),
y = alt$Y("variety:N")
)
points <-
alt$Chart(source)$
mark_point(filled = TRUE, color = "black")$
encode(
x = alt$X("yield:Q", aggregate = "mean"),
y = alt$Y("variety:N")
)
error_bars + pointsThis example shows how to show error bars using confidence intervals. The confidence intervals are computed internally in vega by a non-parametric bootstrap of the mean.
glimpse(vega_data$barley())
#> Rows: 120
#> Columns: 4
#> $ yield <dbl> 27.00000, 48.86667, 27.43334, 39.93333, 32.96667, 28.96667, 43…
#> $ variety <chr> "Manchuria", "Manchuria", "Manchuria", "Manchuria", "Manchuria…
#> $ year <dbl> 1931, 1931, 1931, 1931, 1931, 1931, 1931, 1931, 1931, 1931, 19…
#> $ site <chr> "University Farm", "Waseca", "Morris", "Crookston", "Grand Rap…
source <- vega_data$barley()
error_bars <-
alt$Chart(source)$
mark_errorbar(extent = "ci")$
encode(
x = alt$X("yield:Q", scale = alt$Scale(zero = FALSE)),
y = alt$Y("variety:N")
)
points <-
alt$Chart(source)$
mark_point(filled = TRUE, color = "black")$
encode(
x = alt$X("yield:Q", aggregate = "mean"),
y = alt$Y("variety:N")
)
error_bars + pointsRemoving this example in anticipation of a new example using a suitable dataset.
data <- tibble(id = 1:100)
person = c("M1.7 -1.7h-0.8c0.3 -0.2 0.6 -0.5 0.6 -0.9c0 -0.6 -0.4 -1 -1 -1c-0.6 0 -1 0.4 -1 1c0 0.4 0.2 0.7 0.6 0.9h-0.8c-0.4 0 -0.7 0.3 -0.7 0.6v1.9c0 0.3 0.3 0.6 0.6 0.6h0.2c0 0 0 0.1 0 0.1v1.9c0 0.3 0.2 0.6 0.3 0.6h1.3c0.2 0 0.3 -0.3 0.3 -0.6v-1.8c0 0 0 -0.1 0 -0.1h0.2c0.3 0 0.6 -0.3 0.6 -0.6v-2c0.2 -0.3 -0.1 -0.6 -0.4 -0.6z")
glimpse(data)
#> Rows: 100
#> Columns: 1
#> $ id <int> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, …
chart <-
alt$Chart(data)$
transform_calculate(row = "ceil(datum.id/10)")$
transform_calculate(col = "datum.id - datum.row*10")$
mark_point(filled = TRUE, size = 50)$
encode(
x = alt$X("col:O", axis = NULL),
y = alt$Y("row:O", axis = NULL),
shape = alt$ShapeValue(person)
)$
properties(width = 400, height = 400)$
configure_view(strokeWidth = 0)
chart
glimpse(vega_data$stocks())
#> Rows: 560
#> Columns: 3
#> $ symbol <chr> "MSFT", "MSFT", "MSFT", "MSFT", "MSFT", "MSFT", "MSFT", "MSFT",…
#> $ date <dttm> 2000-01-01, 2000-02-01, 2000-03-01, 2000-04-01, 2000-05-01, 20…
#> $ price <dbl> 39.81, 36.35, 43.22, 28.37, 25.45, 32.54, 28.40, 28.40, 24.53, …A 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 by first transforming the data into a suitable representation.
This example shows a modified parallel coordinates chart …, where the y-axis shows the value after min-max rather than the raw value. It’s a simplified Altair version of the VegaLite version.
glimpse(vega_data$cars())
#> Rows: 406
#> Columns: 9
#> $ Name <chr> "chevrolet chevelle malibu", "buick skylark 320", "pl…
#> $ Miles_per_Gallon <dbl> 18, 15, 18, 16, 17, 15, 14, 14, 14, 15, NaN, NaN, NaN…
#> $ Cylinders <dbl> 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 4, 8, 8, 8, 8, 8, 8, 8,…
#> $ Displacement <dbl> 307, 350, 318, 304, 302, 429, 454, 440, 455, 390, 133…
#> $ Horsepower <dbl> 130, 165, 150, 150, 140, 198, 220, 215, 225, 190, 115…
#> $ Weight_in_lbs <dbl> 3504, 3693, 3436, 3433, 3449, 4341, 4354, 4312, 4425,…
#> $ Acceleration <dbl> 12.0, 11.5, 11.0, 12.0, 10.5, 10.0, 9.0, 8.5, 10.0, 8…
#> $ Year <dttm> 1970-01-01, 1970-01-01, 1970-01-01, 1970-01-01, 1970…
#> $ Origin <chr> "USA", "USA", "USA", "USA", "USA", "USA", "USA", "USA…
source <- vega_data$cars()
source <- source[complete.cases(source), ]
chart <-
alt$Chart(source)$
transform_window(index="count()")$
transform_fold(
list("Acceleration", "Displacement", "Horsepower", "Weight_in_lbs")
)$
transform_joinaggregate(
groupby = list("key"),
min = "min(value)",
max = "max(value)"
)$
transform_calculate(
minmax_value = "(datum.value - datum.min) / (datum.max - datum.min)",
mid = "(datum.min + datum.max) / 2"
)$
mark_line()$
encode(
x = "key:N",
y = "minmax_value:Q",
color = "Cylinders:N",
detail = "index:N",
opacity = alt$value(0.3)
)$
properties(width = 500)
chartA 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 by first transforming the data into a suitable representation.
Removing this example in anticipation of a new example using a suitable dataset.
This example shows a ranged dot plot that uses layer to convey changing life expectancy for the five most populous countries (between 1955 and 2000).
Cannot get the Vega-Lite data-layer to work.
glimpse(data)
#> Rows: 10
#> Columns: 8
#> $ year <int> 1955, 2000, 1955, 2000, 1955, 2000, 1955, 2000, 1955, 20…
#> $ fertility <dbl> 6.1501, 2.3450, 5.5900, 1.7000, 5.8961, 3.1132, 5.6720, …
#> $ life_expect <dbl> 53.28500, 71.00600, 50.54896, 72.02800, 40.24900, 62.879…
#> $ n_fertility <dbl> 6.1501, NA, 5.7200, NA, 5.8216, NA, 5.6200, NA, 3.3140, …
#> $ n_life_expect <dbl> 55.66500, NA, 44.50136, NA, 43.60500, NA, 42.51800, NA, …
#> $ country <chr> "Brazil", "Brazil", "China", "China", "India", "India", …
#> $ p_fertility <dbl> NA, 2.4500, NA, 1.7810, NA, 3.4551, NA, 2.5500, NA, 1.99…
#> $ p_life_expect <dbl> NA, 69.388, NA, 70.426, NA, 61.765, NA, 66.041, NA, 76.8…
# Line between life expectancy in 1955 & 2000
chart_line <-
alt$Chart(data)$
mark_line(color = "#db646f")$
encode(
x = "life_expect:Q",
y = "country:N",
detail = "country:N"
)
# Points for life expectancy in 1955 & 2000
chart_point <-
alt$Chart(data)$
mark_point(size = 100, opacity = 1, filled = TRUE)$
encode(
x = "life_expect:Q",
y = "country:N",
color = alt$Color(
"year:O",
scale = alt$Scale(
domain = list("1955", "2000"),
range = list("#e6959c", "#911a24")
)
)
)$interactive()
# Compose charts, add data and transformations
chart <-
(chart_line + chart_point)$
transform_filter(
filter = list(
field = "country",
oneOf = list("China", "India", "United States", "Indonesia", "Brazil")
)
)$
transform_filter(
filter = list(field = "year", oneOf = list(1955, 2000))
)
chartA Ridgeline plot chart is a chart that lets you visualize distribution of a numeric value for several groups.
Such a chart can be created in Altair by first transforming the data into a suitable representation.
glimpse(vega_data$seattle_weather())
#> Rows: 1,461
#> Columns: 6
#> $ date <dttm> 2012-01-01, 2012-01-02, 2012-01-03, 2012-01-04, 2012-01…
#> $ precipitation <dbl> 0.0, 10.9, 0.8, 20.3, 1.3, 2.5, 0.0, 0.0, 4.3, 1.0, 0.0,…
#> $ temp_max <dbl> 12.8, 10.6, 11.7, 12.2, 8.9, 4.4, 7.2, 10.0, 9.4, 6.1, 6…
#> $ temp_min <dbl> 5.0, 2.8, 7.2, 5.6, 2.8, 2.2, 2.8, 2.8, 5.0, 0.6, -1.1, …
#> $ wind <dbl> 4.7, 4.5, 2.3, 4.7, 6.1, 2.2, 2.3, 2.0, 3.4, 3.4, 5.1, 1…
#> $ weather <chr> "drizzle", "rain", "rain", "rain", "rain", "rain", "rain…
source <- vega_data$seattle_weather()
step <- 20
overlap <- 1
chart <-alt$Chart(source)$
transform_timeunit(Month = "month(date)")$
transform_joinaggregate(
mean_temp = "mean(temp_max)",
groupby = list("Month")
)$
transform_bin(list("bin_max", "bin_min"), "temp_max")$
transform_aggregate(
value = "count()",
groupby = list("Month", "mean_temp", "bin_min", "bin_max")
)$
transform_impute(
impute = "value",
groupby = list("Month", "mean_temp"),
key = "bin_min",
value = 0
)$
mark_area(
interpolate = "monotone",
fillOpacity = 0.8,
stroke = "lightgray",
strokeWidth = 0.5
)$encode(
alt$X("bin_min:Q", bin = "binned", title = "Maximum Daily Temperature (C)"),
alt$Y(
"value:Q",
scale = alt$Scale(range = list(step, -step * overlap)),
axis = NULL
),
alt$Fill(
"mean_temp:Q",
legend = NULL,
scale = alt$Scale(domain = list(30, 5), scheme = "redyellowblue")
),
alt$Row(
"Month:T",
title = NULL,
header = alt$Header(labelAngle = 0, labelAlign = "right", format = "%B")
)
)$
properties(bounds ="flush", title = "Seattle Weather", height = step)$
configure_facet(spacing = 0)$
configure_view(stroke = NULL)$
configure_title(anchor = "end")
chartThis example shows how to show error bars using confidence intervals, while also sorting the y-axis based on x-axis values.
glimpse(vega_data$barley())
#> Rows: 120
#> Columns: 4
#> $ yield <dbl> 27.00000, 48.86667, 27.43334, 39.93333, 32.96667, 28.96667, 43…
#> $ variety <chr> "Manchuria", "Manchuria", "Manchuria", "Manchuria", "Manchuria…
#> $ year <dbl> 1931, 1931, 1931, 1931, 1931, 1931, 1931, 1931, 1931, 1931, 19…
#> $ site <chr> "University Farm", "Waseca", "Morris", "Crookston", "Grand Rap…
source <- vega_data$barley()
points <-
alt$Chart(source)$
mark_point(filled = TRUE, color = "black")$
encode(
x=alt$X("mean(yield):Q", title="Barley Yield"),
y=alt$Y(
"variety",
sort = alt$EncodingSortField(
field = "yield",
op = "mean",
order = "descending"
)
)
)$properties(width = 400, height = 250)
error_bars <-
points$
mark_rule()$
encode(
x = "ci0(yield)",
x2 = "ci1(yield)"
)
points + error_bars
glimpse(data)
#> Rows: 100
#> Columns: 4
#> $ sample <int> 19, 21, 24, 27, 28, 30, 30, 31, 32, 32, 33, 33, 33, 33, 34, 3…
#> $ stem <int> 1, 2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3…
#> $ leaf <int> 9, 1, 4, 7, 8, 0, 0, 1, 2, 2, 3, 3, 3, 3, 4, 4, 5, 5, 5, 5, 6…
#> $ position <int> 1, 1, 2, 3, 4, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14,…
chart <-
alt$Chart(data)$
mark_text(align = "left", baseline = "middle", dx = -5)$
encode(
x = alt$X(
"position:Q",
axis = alt$Axis(title="", ticks = FALSE, labels = FALSE, grid = FALSE)
),
y = alt$Y("stem:N", axis = alt$Axis(title = "", tickSize = 0)),
text = "leaf:N"
)$
configure_axis(labelFontSize = 20)$
configure_text(fontSize = 20)
chartAn example of a layered chart of text over a heatmap using the cars dataset.
glimpse(vega_data$cars())
#> Rows: 406
#> Columns: 9
#> $ Name <chr> "chevrolet chevelle malibu", "buick skylark 320", "pl…
#> $ Miles_per_Gallon <dbl> 18, 15, 18, 16, 17, 15, 14, 14, 14, 15, NaN, NaN, NaN…
#> $ Cylinders <dbl> 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 4, 8, 8, 8, 8, 8, 8, 8,…
#> $ Displacement <dbl> 307, 350, 318, 304, 302, 429, 454, 440, 455, 390, 133…
#> $ Horsepower <dbl> 130, 165, 150, 150, 140, 198, 220, 215, 225, 190, 115…
#> $ Weight_in_lbs <dbl> 3504, 3693, 3436, 3433, 3449, 4341, 4354, 4312, 4425,…
#> $ Acceleration <dbl> 12.0, 11.5, 11.0, 12.0, 10.5, 10.0, 9.0, 8.5, 10.0, 8…
#> $ Year <dttm> 1970-01-01, 1970-01-01, 1970-01-01, 1970-01-01, 1970…
#> $ Origin <chr> "USA", "USA", "USA", "USA", "USA", "USA", "USA", "USA…
source <- vega_data$cars()
# Configure common options
base <-
alt$Chart(source)$
transform_aggregate(
num_cars = "count()",
groupby = list("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$condition(
"datum.num_cars > 100",
alt$value("black"),
alt$value("white")
)
)
# Draw the chart
heatmap + textThis example shows how to make a kind of a Violinplot.
glimpse(vega_data$cars())
#> Rows: 406
#> Columns: 9
#> $ Name <chr> "chevrolet chevelle malibu", "buick skylark 320", "pl…
#> $ Miles_per_Gallon <dbl> 18, 15, 18, 16, 17, 15, 14, 14, 14, 15, NaN, NaN, NaN…
#> $ Cylinders <dbl> 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 4, 8, 8, 8, 8, 8, 8, 8,…
#> $ Displacement <dbl> 307, 350, 318, 304, 302, 429, 454, 440, 455, 390, 133…
#> $ Horsepower <dbl> 130, 165, 150, 150, 140, 198, 220, 215, 225, 190, 115…
#> $ Weight_in_lbs <dbl> 3504, 3693, 3436, 3433, 3449, 4341, 4354, 4312, 4425,…
#> $ Acceleration <dbl> 12.0, 11.5, 11.0, 12.0, 10.5, 10.0, 9.0, 8.5, 10.0, 8…
#> $ Year <dttm> 1970-01-01, 1970-01-01, 1970-01-01, 1970-01-01, 1970…
#> $ Origin <chr> "USA", "USA", "USA", "USA", "USA", "USA", "USA", "USA…
source <- vega_data$cars()
chart <-
alt$Chart(source)$
transform_filter("datum.Miles_per_Gallon > 0")$
transform_bin(
list("bin_max", "bin_min"),
field = "Miles_per_Gallon",
bin = alt$Bin(maxbins = 20)
)$
transform_calculate(binned = "(datum.bin_max + datum.bin_min) / 2")$
transform_aggregate(
value_count = "count()",
groupby = list("Origin", "binned")
)$
transform_impute(
impute = "value_count",
groupby = list("Origin"),
key = "binned",
value = 0
)$
mark_area(interpolate = "monotone", orient = "horizontal")$
encode(
x = alt$X(
"value_count:Q",
title = NULL,
stack = "center",
axis = alt$Axis(
labels = FALSE,
values = list(0),
grid = FALSE,
ticks = TRUE
)
),
y = alt$Y("binned:Q", bin = "binned", title = "Miles per Gallon"),
color = alt$Color("Origin:N", legend = NULL),
column = alt$Column(
"Origin:N",
header = alt$Header(
titleOrient = "bottom",
labelOrient = "bottom",
labelPadding = 0
)
)
)$
properties(width = 80)$
configure_facet(spacing = 0)$
configure_view(stroke = NULL)
chart