md`# 355 parks data`
d3 = require('d3@5')
VegaLite = require('vega-embed@5')
md`We are loading the gas prices here and the only 2 important fields are the year and the current gas prices so we decided to return them`
gasPrice = d3.csv("https://www.sfu.ca/~ridgez/ParkData/gas_price.txt", d => {
return {
year: d.year,
price: d.gas_current,
}
})
md`We are loading the relative income data here here and the only 2 important fields are the year and the annual income. Since a date format is given, we have decided to split the date and only retrieve the year.`
income = d3.csv("https://www.sfu.ca/~ridgez/ParkData/MEHOINUSA672N.txt", d => {
return {
year: d.DATE.split("/")[2],
income: +d["Income (2018 Adjusted Dollars)"]
}
})
md`We are loading the park data here and returning the year, state, region, type of park, the name of the park and the number of visitors.`
park = d3.csv("https://www.sfu.ca/~ridgez/ParkData/national_parks.txt", d => {
if (d["year"].includes("Total")) return undefined;
return {
year: d.year,
state: d.state,
region:d.region,
type: d.unit_type,
name:d.parkname,
visitors: d.visitors,
count: 1,
}
})
md`We are loading the population per state here and returning the year, the state, and the population.`
population = d3.csv("https://www.sfu.ca/~ridgez/ParkData/state_pop.txt", d => {
return {
year: d.year,
state: d.state,
pop: d.pop === "NA" ? 0 : d.pop,
}
})
md`We are loading inbound tourism data from the world to the united states and we are returning the year, country, and the population.`
tourismIn = d3.csv("https://www.sfu.ca/~ridgez/ParkData/TOURISM_INBOUND_09112019011654690.txt", d => {
if (d["VARIABLE"].includes("INB_")) return undefined;
return {
year: d.YEAR,
country: d.Variable,
population: +d.Value,
}
})
md`Using the same data as the previous set, we are returning the type of accommodataions that the tourism are staying in.`
tourismAccommodation = d3.csv("https://www.sfu.ca/~ridgez/ParkData/TOURISM_INBOUND_09112019011654690.txt", d => {
if (!d["VARIABLE"].includes("INB_")) return undefined;
return {
year: d.YEAR,
accommodation: d.Variable,
population: d.Value,
}
})
md`In order to create a concat view with data from different datasets, we must combine them into one data set which is what the following array is doing.`
allDataUnion = {
let array = [];
for (let year = 1900; year < 2020; year++) {
let gasPriceThisYear = gasPrice.filter(d => d.year == year);
if (gasPriceThisYear.length > 0) gasPriceThisYear = gasPriceThisYear[0].price;
else gasPriceThisYear = 0;
let parkVisits = park.filter(d => d.year == year);
if (parkVisits.length > 0) parkVisits = d3.sum(parkVisits.map(d => d.visitors))
else parkVisits = 0;
let incomeThisYear = income.filter(d => d.year == year);
if (incomeThisYear.length > 0) incomeThisYear = incomeThisYear[0].income;
else incomeThisYear = 0;
let populationThisYear = population.filter(d => d.year == year);
if (populationThisYear.length > 0) populationThisYear = d3.sum(populationThisYear.map(d => d.pop));
else populationThisYear = 0;
let tourismThisYear = tourismIn.filter(d => d.year == year);
if (tourismThisYear.length > 0) tourismThisYear = d3.sum(tourismThisYear.map(d => d.population));
else tourismThisYear = 0;
let numberOfParksThisYear = park.filter(d => d.year == year);
if (numberOfParksThisYear.length > 0) numberOfParksThisYear = d3.sum(numberOfParksThisYear.map(d => d.count));
else numberOfParksThisYear = 0;
let d = {
year: year,
parkVisits: parkVisits,
gasPrice: gasPriceThisYear,
income: incomeThisYear,
population: populationThisYear,
tourist: tourismThisYear,
numberOfParks: numberOfParksThisYear
}
array.push(d);
}
return array;
}
md`The graphs below are for us to see if the datasets are working and provide us with an idea of what is happening.`
VegaLite({
data: { values: tourismIn },
width: 800,
height: 300,
mark: { type: "bar"},
encoding: {
x: {
field: "country",
type: "nominal",
sort: "y"
},
y: {
field: "population", type: "quantitative",
},
}
})
VegaLite({
data: { values: tourismAccommodation },
width: 500,
height: 300,
mark: { type: "bar"},
encoding: {
x: {
field: "accommodation",
type: "nominal",
sort: {encoding: "y", order: "descending"}
},
y: {
field: "population", type: "quantitative",
},
}
})
VegaLite({
data: {values: gasPrice},
mark: "line",
encoding: {
x: {field: "year", type: "temporal", sort: {encoding: "x", order: "assending"}},
y: {field: "price", type: "quantitative"},
}
})
md`We have tried a horizon graph to visualize the population change for the states in the United States.`
{
let numOfLayers = 20;
// let maxPop = d3.max(population.map(d => d.pop));
let maxPop = 40000000;
let perLayerRange = maxPop / numOfLayers;
let layers = [];
let templateLayer = {
width: 300,
height: 50,
mark: { type: "area", line: true, clip: true, orient: "vertical" },
transform: [
{
calculate: "datum.pop - 50",
as: "popShifted"
}
],
encoding: {
x: {
field: "year",
type: "temporal",
scale: {
zero: false,
nice: false
},
axis: {
ticks: false,
title: null,
}
},
y: {
field: "popShifted", type: "quantitative",
scale: { domain: [0, 1000000] }
},
opacity: { value: .1 }
}
};
for (let i = 0; i < numOfLayers; i++) {
let newLayer = JSON.parse(JSON.stringify(templateLayer));
newLayer.encoding.y.scale.domain[0] = 0;
newLayer.encoding.y.scale.domain[1] = perLayerRange;
newLayer.transform[0].calculate = "datum.pop - " + perLayerRange * i;
layers.push(newLayer);
}
return VegaLite({
data: { values: population },
facet: {
row: {
field: "state",
type: "nominal",
}
},
spec: {
layer: layers
}
})
}
VegaLite({
data: { values: population },
width: 300,
height: 300,
mark: { type: "line"},
encoding: {
x: {
field: "year",
type: "temporal",
},
y: {
aggregate: "sum", field: "pop", type: "quantitative",
},
}
})
VegaLite({
data: { values: income },
width: 300,
height: 300,
mark: { type: "line"},
encoding: {
x: {
field: "year",
type: "temporal",
},
y: {
field: "income", type: "quantitative",
},
}
})
md`Type of Parks`
md`We have also decided to look into the number different types of parks as well.`
md`The slider below controls the follow 2 visualizations making them interactive and linked.`
viewof range = rangeSlider({
min: d3.min(allDataUnion, d => d.year),
max: d3.max(allDataUnion, d => d.year),
title: 'Year',
step: 1,
description: 'filtering by year'
})
{
let rangedPark = park.filter(d => d.year < range[1] && d.year > range[0])
let data = d3.nest().key(d => d.name).rollup(v => v[0].type).entries(rangedPark)
return VegaLite({
data: { values: data },
mark: { type: "bar" },
encoding: {
x: {
field: "value",
type: "nominal",
axis: {title: "Types of Parks"}
},
y: {
aggregate: "count",
field: "*",
axis: {title: "Number of Parks"}
},
}
})
}
md`This is our most important linked visualization where the slider for the year will control the years. The following data is selectable, can be filted through brushing, are linked and details can be displayed through the delection.`
VegaLite({
data: { values: allDataUnion },
width: 300,
height: 300,
columns:2,
vconcat: [
{
transform: [
{filter: {field: "year", lte: range[1]}},
{filter: {field: "year", gte: range[0]}},
],
selection: {
area: { type: "interval" }
},
mark: { type: "circle", clip: true },
encoding: {
x: {
field: "gasPrice",
type: "quantitative",
},
y: {
field: "parkVisits",
type: "quantitative",
},
size: {
condition: {
selection: "area",
value: 20,
},
value: 5
},
color: {
condition: {
selection: "area",
value: "green",
},
value: "lightgray"
},
}
},
{
transform: [
{filter: {field: "year", lte: range[1]}},
{filter: {field: "year", gte: range[0]}},
],
selection: {
area: { type: "interval" }
},
mark: { type: "circle", clip: true },
encoding: {
x: {
field: "income",
type: "quantitative",
scale: {
domain: [40000, 80000]
}
},
y: {
field: "parkVisits",
type: "quantitative",
scale: {
domain: [200000000, 400000000]
}
},
size: {
condition: {
selection: "area",
value: 20,
},
value: 5
},
color: {
condition: {
selection: "area",
value: "green",
},
value: "lightgray"
},
}
}
,
{
transform: [
{filter: {field: "year", lte: range[1]}},
{filter: {field: "year", gte: range[0]}},
],
selection: {
area: { type: "interval" }
},
mark: { type: "circle", clip: true },
encoding: {
x: {
field: "tourist",
type: "quantitative",
scale: {
domain: [350000000, 500000000]
}
},
y: {
field: "parkVisits",
type: "quantitative",
scale: {
domain: [200000000, 400000000]
}
},
size: {
condition: {
selection: "area",
value: 20,
},
value: 5
},
color: {
condition: {
selection: "area",
value: "green",
},
value: "lightgray"
},
}
}
,
{
transform: [
{filter: {field: "year", lte: range[1]}},
{filter: {field: "year", gte: range[0]}},
],
selection: {
area: { type: "interval" }
},
mark: { type: "circle", clip: true },
encoding: {
x: {
field: "population",
type: "quantitative",
scale: {
domain: [200000000, 350000000]
}
},
y: {
field: "parkVisits",
type: "quantitative",
scale: {
domain: [200000000, 400000000]
}
},
size: {
condition: {
selection: "area",
value: 20,
},
value: 5
},
color: {
condition: {
selection: "area",
value: "green",
},
value: "lightgray"
},
}
}
,
{
transform: [
{filter: {field: "year", lte: range[1]}},
{filter: {field: "year", gte: range[0]}},
],
selection: {
area: { type: "interval" }
},
mark: { type: "circle", clip: true },
encoding: {
y: {
field: "parkVisits",
type: "quantitative",
scale: {
domain: [1000000, 400000000]
}
},
x: {
field: "numberOfParks",
type: "quantitative",
scale: {
domain: [0, 400]
}
},
size: {
condition: {
selection: "area",
value: 20,
},
value: 5
},
color: {
condition: {
selection: "area",
value: "green",
},
value: "lightgray"
},
}
}
]
})
md`After looking at the previous visualization, we think if would be interesting to see how number of parks change over time and so on so we decided to create another visualization set.`
viewof range2 = rangeSlider({
min: d3.min(allDataUnion, d => d.year),
max: d3.max(allDataUnion, d => d.year),
title: 'Year',
step: 1,
description: 'filtering by year'
})
VegaLite({
data: { values: allDataUnion },
width: 300,
height: 300,
columns:2,
vconcat: [
{
transform: [
{filter: {field: "year", lte: range2[1]}},
{filter: {field: "year", gte: range2[0]}},
],
selection: {
area: { type: "interval" }
},
mark: { type: "bar", clip: true },
encoding: {
x: {
field: "year",
type: "quantitative",
scale: {
domain: [1900, 2018]
}
},
y: {
field: "numberOfParks",
type: "quantitative",
scale: {
domain: [0, 400]
}
},
size: {
condition: {
selection: "area",
value: 20,
},
value: 5
},
color: {
condition: {
selection: "area",
value: "green",
},
value: "lightgray"
},
}
}
,
{
transform: [
{filter: {field: "year", lte: range2[1]}},
{filter: {field: "year", gte: range2[0]}},
],
selection: {
area: { type: "interval" }
},
mark: { type: "bar", clip: true },
encoding: {
x: {
field: "year",
type: "quantitative",
scale: {
domain: [1900, 2018]
}
},
y: {
field: "gasPrice",
type: "quantitative",
},
size: {
condition: {
selection: "area",
value: 20,
},
value: 5
},
color: {
condition: {
selection: "area",
value: "green",
},
value: "lightgray"
},
}
}
,
{
transform: [
{filter: {field: "year", lte: range2[1]}},
{filter: {field: "year", gte: range2[0]}},
],
selection: {
area: { type: "interval" }
},
mark: { type: "bar", clip: true },
encoding: {
x: {
field: "year",
type: "quantitative",
scale: {
domain: [1900, 2018]
}
},
y: {
field: "population",
type: "quantitative",
},
size: {
condition: {
selection: "area",
value: 20,
},
value: 5
},
color: {
condition: {
selection: "area",
value: "green",
},
value: "lightgray"
},
}
}
,
]
})
md`Sources`
md`https://data.world/inform8n/us-national-parks-visitation-1904-2016-with-boundaries
https://github.com/rfordatascience/tidytuesday/tree/master/data/2019/2019-09-17
https://stats.oecd.org/Index.aspx?DataSetCode=TOURISM_INBOUND
https://fred.stlouisfed.org/series/MEHOINUSA672N
`
md`Libraries`
md`We used the d3 and Vegalite library.`
import {rangeSlider} from '@mootari/range-slider'
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.