Published
Edited
Dec 5, 2019
1 fork
Importers
md`# Park Data Wrangling`
d3 = require('d3@5')
VegaLite = require('vega-embed@5')
gasPrice = d3.csv("https://www.sfu.ca/~ridgez/ParkData/gas_price.txt", d => {
return {
year: d.year,
price: d.gas_constant,
}
})
income = d3.csv("https://www.sfu.ca/~ridgez/ParkData/MEHOINUSA672N.txt", d => {
return {
year: d.DATE.split("/")[2],
income: +d["Income (2018 Adjusted Dollars)"]
}
})
parkRaw = d3.csv("https://www.sfu.ca/~ridgez/IAT355FinalData/All%20National%20Parks%20Visitation%201904-2016.txt")
park = d3.csv("https://www.sfu.ca/~ridgez/IAT355FinalData/All%20National%20Parks%20Visitation%201904-2016.txt", d => {
if (d["YearRaw"].includes("Total")) return undefined;
return {
year:d.YearRaw,
state: d.State,
region:d.Region,
type: d.Unit_Type,
parkname:d.Unit_Name,
visitors: d.Visitors,
count: d.Number_of_Records,
}
})
centroidRaw = d3.csv("https://www.sfu.ca/~ridgez/IAT355FinalData/National_Park_Service__Park_Unit_Centroids.txt")
centroid = d3.csv("https://www.sfu.ca/~ridgez/IAT355FinalData/National_Park_Service__Park_Unit_Centroids.txt", d => {
return {
id:d.OBJECTID,
x: d.X,
y: d.Y,
parkname: d.PARKNAME,
type:d.UNIT_TYPE,
state: d.STATE,
region: d.REGION,
UUID: d.GlobalID,
}
})
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,
}
})
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,
}
})
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,
}
})
centroidGeoJson2 = d3.json("https://www.sfu.ca/~ridgez/IAT355FinalData/centroid.geojson")
filter = function(oldType) {
let type = null;
if (oldType.includes("Battlefield") ||
oldType.includes("Memorial") ||
oldType.includes("Military")) {
type = "Memorial";
} else if (oldType.includes("River") ||
oldType.includes("Seashore") ||
oldType.includes("Lakeshore")) {
type = "Waters";
} else if (oldType.includes("Historic") ||
oldType.includes("Monument")) {
type = "Historic";
} else {
type = "Park";
}
return type;
}
centroidGeoJson = d3.csv("https://www.sfu.ca/~ridgez/IAT355FinalData/National_Park_Service__Park_Unit_Centroids.txt");
centroidGeoJsonFiltered = {
let filtered = centroidGeoJson.filter(d => allDataUnion.filter(v => v.parkName === d.UNIT_NAME).length > 0);
let geoJson = {
type: "FeatureCollection",
features: filtered.map(d => {
let currentParkData = allDataUnion.filter(v => v.parkName === d.UNIT_NAME);
return {
type: "Feature",
geometry: {
type: "Point",
coordinates: [d.X, d.Y]
},
properties: {
name: d.UNIT_NAME,
state: d.STATE,
id: d.GlobalID,
yearMin: d3.min(currentParkData.map(d => d.year)),
yearMax: d3.max(currentParkData.map(d => d.year)),
type: currentParkData[0].parkType,
}
}
})
}
return geoJson;
}
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 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 parkVisits = park.filter(d => d.year == year);
// if (parkVisits.length > 0) parkVisits = d3.sum(parkVisits.map(d => d.visitors))
// else parkVisits = 0;
let tempList = [];
for (let c = 0; c < parkVisits.length; c++) {
let type = filter(parkVisits[c].type);
if (type === null) {
continue;
}
let d = {
year: year,
parkVisits: parseFloat(parkVisits[c].visitors),
parkState: parkVisits[c].state,
parkType: type,
parkName: parkVisits[c].parkname,
gasPrice: gasPriceThisYear,
income: incomeThisYear,
population: populationThisYear,
tourist: tourismThisYear,
numberOfParks: numberOfParksThisYear
}
tempList.push(d);
}
let typeCount = d3.nest()
.key(d => d.parkType)
.rollup(v => v.length)
.entries(tempList);
let typeVisitorsCount = d3.nest()
.key(d => d.parkType)
.rollup(v => {
return v.reduce((acc, d) => acc += d.parkVisits, 0)
})
.entries(tempList);
for (let c = 0; c < tempList.length; c++) {
let parkTemp = tempList[c];
let typeCountTemp = typeCount.filter(d => d.key == parkTemp.parkType)[0].value;
let typeVisitorsCountTemp = typeVisitorsCount.filter(d => d.key == parkTemp.parkType)[0].value;
parkTemp["percentPerTypePerYear"] = typeCountTemp/tempList.length*100;
parkTemp["perTypePerYearRatioWithVisitor"] = typeVisitorsCountTemp/tempList.filter(
d => d.parkType == parkTemp.parkType
).length;
}
array = array.concat(tempList);
}
array.filter(d => d.parkVisits > 0);
return array;
}
data = {
let c = {
unionByYear: allDataUnion,
unionCentroid: centroidGeoJsonFiltered,
unionInbound: tourismIn,
};
return c;
}
bob = [1,2,3,4]
md`sources`
md`
visitor amount
https://data.world/inform8n/us-national-parks-visitation-1904-2016-with-boundaries
centroids
https://public-nps.opendata.arcgis.com/datasets/national-park-service-park-unit-centroids/data?geometry=-140.367%2C39.851%2C-84.864%2C50.632
GAS prices
https://www.energy.gov/eere/vehicles/fact-915-march-7-2016-average-historical-annual-gasoline-pump-price-1929-2015
USA state population
https://fred.stlouisfed.org/release/tables?rid=118&eid=259194&od=1900-01-01#
inbound tourism
https://stats.oecd.org/Index.aspx?DataSetCode=TOURISM_INBOUND
income
https://fred.stlouisfed.org/series/MEHOINUSA672N
`
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.