Digital Humanist. Manhattan-based.
plot.plotAPI({
duration: 100,
encoding: {
// color: {},
x : {
field : location === 'dropoff' ? 'x' : 'pickup.x',
transform: 'literal'
},
y : {
field : location === 'dropoff' ? 'y' : 'pickup.y',
transform: 'literal'
},
filter: {
field: "tod",
op: "within",
a: within,
b: time
}
}
})
time
plot = {
d3.select("#plot").selectAll("div").remove()
const plot = new Deepscatter("#plot", width, Math.floor(width * .75))
await plot.plotAPI({
"arrow_table" : plot_data_raw,
"background_color": [45, 0, 75],
"max_points": 4e6,
"alpha": 85,
point_size : 3,
background_color: "#0A1610",
zoom_balance: .5,
duration: 3000,
encoding: {
jitter_radius: {
constant: .02,
method: 'normal'
},
color: {
field: 'tod',
domain: [0, 1440],
range: 'rdbu'
},
x: {
field: 'x',
transform: 'literal'
},
y: {
field: 'y',
transform: 'literal'
}
}
})
return plot
}
client = DuckDBClient.of({coords: FileAttachment("taxi_coords.parquet")})
plot_data_raw = {
insert_data
await client.query("DROP SEQUENCE IF EXISTS serial")
await client.query("CREATE SEQUENCE serial START 1")
return client.query(`SELECT
nextval('serial')::FLOAT ix,
dropoff.x::FLOAT x,
((60 * HOUR(pickup_time) + MINUTE(pickup_time)))::FLOAT tod,
((DAY(pickup_time)))::FLOAT date,
-1 * dropoff.y::FLOAT y,
pickup.x::FLOAT "pickup.x",
-1 * pickup.y::FLOAT "pickup.y",
FROM
trips JOIN taxi_coords.parquet dropoff
ON (dropoff.location_id = trips.DOLocationID) JOIN taxi_coords.parquet pickup ON (pickup.location_id = trips.PULocationID) USING SAMPLE 2000000;`)
}
client
Type SQL, then Shift-Enter. Ctrl-space for more options.
arrow = require("apache-arrow@9.0.0")
insert_data = {
const letter = color=="green" ? "l" : "t"
const columns = ["PULocationID", "DOLocationID", `${letter}pep_pickup_datetime as pickup_time`, `${letter}pep_dropoff_datetime as dropoff_time`, `'${color}' AS color`]
await client.query(`CREATE TABLE IF NOT EXISTS "${label}" AS SELECT ${columns.join(", ")} FROM parquet_scan('${fname}')`)
const all_tables = (await client.table("SHOW TABLES")).value.map(d => d['name']).filter(d => d.startsWith('green-') || d.startsWith("yellow-"))
const q = all_tables.map(d => `SELECT * FROM "${d}"`).join("\nUNION\n")
await client.query(`CREATE OR REPLACE VIEW "trips" AS ${q}`)
}
label = `${color}-${year}-${month}`
fname = `https://bmschmidt-cors-observable.herokuapp.com/https://d37ci6vzurychx.cloudfront.net/trip-data/${color}_tripdata_${year}-${("000" + month).slice(-2)}.parquet`
Deepscatter = import('https://benschmidt.org/deepscatter/deepscatter@2.4.0.js').then(d => d.default)
import {DuckDBClient} from '@cmudig/duckdb'
One platform to build and deploy the best data apps
Experiment and prototype by building visualizations in live JavaScript notebooks. Collaborate with your team and decide which concepts to build out.
Use Observable Framework to build data apps locally. Use data loaders to build in any language or library, including Python, SQL, and R.
Seamlessly deploy to Observable. Test before you ship, use automatic deploy-on-commit, and ensure your projects are always up-to-date.