heatmap = Plot.plot({
width: 600,
height: 500,
marginTop: 20,
marginBottom: 60,
marginLeft: 70,
padding: 0,
style: {fontFamily: "system-ui", fontSize: "15px", overflow: "visible" },
// y: {
// tickFormat: Plot.formatMonth()
// },
color: {
scheme: "ylgnbu",
legend: true
},
x: {tickRotate: -40, fontweight: "bold", label: "Publication Year"},
y:{label: "Citation Year"},
marks: [
Plot.cell(publicationCitaionCount.filter(d =>
(selectedYear === "All Years" || d.publicationYear === selectedYear) && // NEW CONDITION
yr.includes(d.publicationYear) // EXISTING CONDITION
),//(d=>selectedYears.includes(year_mapping.get(d.publicationYear))),
{
x: "publicationYear",
y: "citationYear",
// stroke: "black",
// strokeWidth: 1,
fill: "citingPolicyCount",
inset: 0.5,
title: (d) =>`Publication year ${d.publicationYear}\n\tCitaion Year ${d.citationYear}\n Policy citations ${d.citingPolicyCount}`
})
]
})
totalPlot = Plot.plot({
width: 600,
height: 500,
marginTop: 60,
marginBottom: 80,
marginLeft: 70,
x:{tickRotate: -40},
y:{tickFormat: d3.format("~s"), label: "↑ Count" },
// inset: 15,
grid: false,
style: {fontFamily: "system-ui", fontSize: "18px", overflow: "visible", fill: "red" },
color: {
legend: true
},
marks: [
Plot.ruleY([0],{stroke: "currentColor", strokeWidth:3}),
// Plot.tickX({fill:"red"}),
Plot.dot(publicationCitaionCount.filter(d =>
(selectedYear === "All Years" || d.publicationYear === selectedYear) && // NEW CONDITION
yr.includes(d.publicationYear) // EXISTING CONDITION
),//(d=>selectedYears.includes(year_mapping.get(d.publicationYear))),
{
x: "publicationYear",
y: "totalCitingPolicyCount",
// r: "totalCitingPolicyCount",
// fill: "totalCitingPolicyCount",
fill: colorScale('Total policy citations'),
// sort:"publicationYear",
title: (d) =>`Publication year: ${d.publicationYear}\nTotal policy citations: ${d.totalCitingPolicyCount}`
}),
// \n makes a new line}),
//stroke: "citationYear"
Plot.line(publicationCitaionCount.filter(d=>yr.includes(d.publicationYear)),//(d=>selectedYears.includes(year_mapping.get(d.publicationYear))),
{x: "publicationYear", y: "totalCitingPolicyCount", stroke: colorScale('Total policy citations'), strokeWidth: 1}),
Plot.dot(publicationCitaionCount.filter(d=>yr.includes(d.publicationYear)),//(d=>selectedYears.includes(year_mapping.get(d.publicationYear))),
{
x: "publicationYear",
y: "publicationCount",
// r: "publicationCount",
//fill: "publicationCount",
fill: "blue",
// sort:"publicationYear",
title: (d) =>`Publication Year: ${d.publicationYear}\nTotal Publications: ${d.publicationCount}`}), // \n makes a new line}),
//stroke: "citationYear"
Plot.line(publicationCitaionCount.filter(d=>yr.includes(d.publicationYear)),//(d=>selectedYears.includes(year_mapping.get(d.publicationYear))),
{x: "publicationYear", y: "publicationCount", stroke: colorScale("Total publications"), strokeWidth: 1})
]
})
// plot 4
boxPlot = Plot.plot({
width: 600,
height: 500,
marginTop: 60,
marginBottom: 60,
marginLeft: 60,
x: {tickRotate: -40},
color: {
type: 'categorical',
scheme: 'category10',//'tableau10',
legend: true,
},
// color: {
// scheme: "ylgnbu",
// legend: true
// },
style: {fontFamily: "system-ui", fontSize: "15px", overflow: "visible" },
y: {
grid: false,
inset: 0,
label: "Citation Lag ↑"
},
marks: [
Plot.ruleY([1],{stroke: "currentColor", strokeWidth:3}),
Plot.boxY(filteredArticles2.filter(d =>
(selectedYear === "All Years" ||
d3.timeFormat("%Y")(d["Article publication date"]) === selectedYear) && // NEW CONDITION
yr.includes(d3.timeFormat("%Y")(d["Article publication date"])) // EXISTING CONDITION
),
//(d=>selectedYears.includes(year_mapping.get( d3.timeFormat("%Y")((d["Article publication date"]))))), //.filter(d=> d.citationSerial==1),
{
y: d=>{if (selectedCitationLagType=="Month") {return Math.ceil(d.citationLag/30)} else if (selectedCitationLagType=="Year") {return Math.ceil(d.citationLag/365)} else return d.citationLag},
// x: d=> d3.timeFormat("%Y")(d["Article publication date"]),
x: "citationSerial" , // stroke :change color scale
// fill: "citationSerial",
title: (d) =>`Publication Year: ${d3.timeFormat("%Y")(d["Article publication date"])}\nCitation Serial: ${d.citationSerial}`}
)
]
})
tkn=0;
heatPubYear=0
barPlot = Plot.plot({
// style:
// { fontFamily: "system-ui", fontSize: "40px", overflow: "visible" },
width: 400,
height: 400,
marginTop: 40,
marginBottom: 80,
marginLeft: 180, // space to the left of the chart
color: {legend: true, type: 'categorical',
scheme: "paired" ,
},
style: {fontFamily: "system-ui", fontSize: "14px", overflow: "visible" },
x: {
type: "band",
tickRotate: -40, // rotates x-axis tick labels (dates)
},
y:{tickFormat: d3.format("~s")},
marks: [
Plot.barY(filteredArticles2.filter(d =>
(selectedYear === "All Years" ||
d3.timeFormat("%Y")(d["Article publication date"]) === selectedYear) && // NEW CONDITION
yr.includes(d3.timeFormat("%Y")(d["Article publication date"])) // EXISTING CONDITION
),//(d=>selectedYears.includes(year_mapping.get( d3.timeFormat("%Y")((d["Article publication date"]))))),
Plot.groupX(
{y: "count"},
{
x: "Cited by type",
fill: "Cited by subtype",
sort:"Cited by subtype",
title: (d) =>`${d["Cited by subtype"]}`}
)),
Plot.ruleY([1],{stroke: "currentColor", strokeWidth:3}),
]
})
articlesWithUsaPolicyCitations
articlesWithUsaPolicyCitations.forEach((d,i)=>{d["Article publication date"] = new Date (d["Article publication date"]); d["Policy citation date"] = (new Date (d["Policy citation date"]));})
function filterByYear(data, selectedYear) {
if (selectedYear === "All Years") return data;
return data.filter(d =>
d3.timeFormat("%Y")(d["Article publication date"]) === selectedYear
);
}
filteredArticles={
const articles=articlesWithUsaPolicyCitations.filter(d=>{var t= d3.timeFormat("%Y")(d["Policy citation date"]); var t1= d3.timeFormat("%Y")(d["Article publication date"]); return (t>=2010 && t<2022 && t1>=2010 && t1<2022 && t>=t1 )});
return articles;
}
filteredArticles.sort((a,b)=>a["Article publication date"]-(b["Article publication date"]) || a["Policy citation date"]-(b["Policy citation date"]))
// calculating and assigning citation lag of each policy citation
filteredArticles.map(d=>d.citationLag=Math.ceil((d["Policy citation date"].getTime()-d["Article publication date"].getTime()) /(1000*3600*24)))
filteredArticles.map(d=>{if (d["Article funder(s)"]!="Not funded") {d["Article funder(s)"]="Funded"}})
groupedByTitle=d3.group(filteredArticles, d=> (d["Title"]))
journalMap={
const sortedJournals = d3.groupSort(filteredArticles, g => -g.length, v => v.Journal);
const journal= new Map();
sortedJournals.forEach((d,i)=>journal.set(d,i+1));
return journal;
}
[...groupedByTitle.keys()].map((v)=>groupedByTitle.get(v).map((v1,k)=>v1.citationSerial=(k+1)))
filteredArticles1=[].concat(...[...groupedByTitle.values()])
filteredArticles2= filteredArticles1.filter(d=>
{
if (topN!=0)
return (fund.includes(d["Article funder(s)"]) & selectedCitationSerial.includes(d["citationSerial"]-1) & journalMap.get(d["Journal"])<=topN)
else return (fund.includes(d["Article funder(s)"]) & selectedCitationSerial.includes(d["citationSerial"]-1))
})
filteredArticles2
publicationCitaionCount = {
var publicationCitaionCount = [];
const groupedByPubDate=d3.group(filteredArticles2, d=> d3.timeFormat("%Y")(d["Article publication date"]));
const groupedByPubCiteDate=d3.group(filteredArticles2, d=> d3.timeFormat("%Y")(d["Article publication date"]), d=> d3.timeFormat("%Y")(d["Policy citation date"]));
const groupedByPubDateTitle=d3.group(filteredArticles2, d=> d3.timeFormat("%Y")(d["Article publication date"]),d => d.Title);
[...groupedByPubCiteDate.keys()].forEach(d=>
[...groupedByPubCiteDate.get(d).keys()].forEach(d1=>
{
var obj = {
"publicationYear": d,
"publicationCount":groupedByPubDateTitle.get(d).size,
"totalCitingPolicyCount":groupedByPubDate.get(d).length,
"citationYear":d1 , "citingPolicyCount":groupedByPubCiteDate.get(d).get(d1).length
};
publicationCitaionCount.push(obj);
} ))
publicationCitaionCount.sort((a,b)=>a["publicationYear"]-(b["publicationYear"]) || a["citationYear"]-(b["citationYear"])) .sort((a,b)=>{return a-b});
return publicationCitaionCount
}
pub_years={
var publicationyear =["2021"]; //
publicationyear = publicationyear.concat(Array.from(new Set (publicationCitaionCount.map(d=> d.publicationYear))) )
return publicationyear
}
filteredArticles2
cite_dates=new Set();
pub_dates=new Set();
filteredArticles2.filter(d=>
{
pub_dates.add(d3.timeFormat("%Y")(d["Article publication date"]));
cite_dates.add(d3.timeFormat("%Y")(d["Policy citation date"]))
});
citing_years=Array.from(cite_dates).sort((a,b)=>{return a-b})
filteredArticles1
function getUniqueListBy(arr, key) {
return [...new Map(arr.map(item => [item[key], item])).values()]
}
array1 =[]
arr1 =getUniqueListBy(filteredArticles2, "Title")
filteredArticles2.forEach(d=> {
var obj = {
"title": d["Title"],
"pubdate": d["Article publication date"],
"citation": d["USA citation count"],
};
array1.push(obj);
}
)
year_mapping= new Map([["2010",0],["2011",1], ["2012",2], ["2013",3],["2014",4], ["2015",5],["2016",6],["2017",7], ["2018",8], ["2019",9], ["2020",10], ["2021",11]])
citationSerialMapping = new Map([["1",0],["2",1], ["3",2], ["4",3],["5",4], ["6",5],["7",6],["8",7], ["9",8], ["10",9]])
Thank You!!!
// Plot.plot({
// width: 960,
// height: 560,
// x: {
// axis: "top",
// grid: true,
// domain: [1, 10]
// },
// fy: {
// grid: true,
// tickFormat: (d) => d ?? "N/A",
// label: null,
// padding: 0
// },
// facet: {
// data:filteredArticles2.filter(d=>yr.includes( d3.timeFormat("%Y")(d["Article publication date"]))),
// y: d=> d3.timeFormat("%Y")(d["Article publication date"]),
// marginLeft: 120
// },
// marks: [
// Plot.dot(
// filteredArticles2.filter(d=>yr.includes( d3.timeFormat("%Y")(d["Article publication date"]))),
// Plot.dodgeY(
// {
// anchor: "middle",
// padding: -2
// },
// {
// x: "citationSerial",
// stroke: d=> d3.timeFormat("%Y")(d["Article publication date"]),
// r: 2.5
// }
// )
// )
// ]
// })
// citePlot =
// // bar plot for citation year
// Plot.plot({
// width: 600,
// height: 400,
// marginTop: 40,
// marginBottom: 80,
// marginLeft: 60,
// inset: 15,
// grid: false,
// color: {
// // scheme: "ylgnbu",
// legend: true
// },
// marks: [
// Plot.ruleY([0]),
// Plot.barY(publicationCitaionCount.filter(d=>selectedYears.includes(year_mapping.get(d.publicationYear))),//.filter(d=>d.publicationYear=="2010"),
// {
// x: "citationYear",
// y: "citingPolicyCount",
// // r: "citingPolicyCount",
// fill: "publicationYear",
// sort:"publicationYear",
// title: (d) =>` year of publication: ${d.publicationYear} \n\t citation year: ${d.citationYear}\n\tpolicy citations: ${d.citingPolicyCount}`})
// ]
// })
// //line plot
// citePlot = Plot.plot({
// width: 600,
// height: 540,
// marginTop: 40,
// // marginBottom: 10,
// marginLeft: 60,
// inset: 15,
// grid: false,
// // y: {
// // type: "log"
// // },
// // color: {
// // legend: true,
// // },
// marks: [
// Plot.ruleY([0]),
// Plot.dot(publicationCitaionCount.filter(d=>selectedYears.includes(year_mapping.get(d.publicationYear))), //.filter(d=>d.publicationYear=="2015"),
// {
// x: "citationYear",
// y: "citingPolicyCount",
// r: "citingPolicyCount",
// fill: "publicationYear",
// sort:"publicationYear",
// title: (d) =>` Publication year: ${d.publicationYear} \n\t Citation year: ${d.citationYear}\n\tPolicy citations: ${d.citingPolicyCount}`}), // \n makes a new line}),
// //stroke: "citationYear"
// Plot.line(publicationCitaionCount.filter(d=>selectedYears.includes(year_mapping.get(d.publicationYear))), //.filter(d=>d.publicationYear=="2015"),
// {x: "citationYear", y: "citingPolicyCount",stroke: "publicationYear" ,
// sort:"publicationYear"})
// ]
// })
// pubPlot =
// // bar plot for citation year
// Plot.plot({
// width: 600,
// height: 400,
// marginTop: 40,
// marginBottom: 80,
// marginLeft: 60,
// inset: 15,
// grid: false,
// color: {
// // scheme: "ylgnbu",
// legend: true
// },
// marks: [
// Plot.ruleY([0]),
// Plot.barY(publicationCitaionCount.filter(d=>selectedYears.includes(year_mapping.get(d.publicationYear))),//.filter(d=>d.publicationYear=="2010"),
// {
// x: "publicationYear",
// y: "citingPolicyCount",
// // r: "citingPolicyCount",
// fill: "citationYear",
// sort:"citationYear",
// title: (d) =>` year of publication: ${d.publicationYear} \n\t citation year: ${d.citationYear}\n\tpolicy citations: ${d.citingPolicyCount}`})
// ]
// })
// pubPlot = Plot.plot({
// width: 600,
// height: 400,
// marginTop: 40,
// marginBottom: 80,
// marginLeft: 60,
// inset: 15,
// grid: false,
// color: {
// legend: true,
// },
// marks: [
// Plot.ruleY([0]),
// Plot.dot(publicationCitaionCount.filter(d=>selectedYears.includes(year_mapping.get(d.publicationYear))),//.filter(d=>d.citationYear=="2015"),
// {
// x: "publicationYear",
// y: "citingPolicyCount",
// r: "citingPolicyCount",
// fill: "citationYear",
// sort:"citationYear",
// title: (d) =>` Publication year: ${d.publicationYear} \n\tCitation year: ${d.citationYear}\n\tPolicy citations: ${d.citingPolicyCount}`}),
// //stroke: "citationYear"
// Plot.line(publicationCitaionCount.filter(d=>selectedYears.includes(year_mapping.get(d.publicationYear))),//.filter(d=>d.citationYear=="2015"),
// {x: "publicationYear", y: "citingPolicyCount",stroke: "citationYear" ,
// sort:"citationYear"})
// ]
// })
// Hexabin
// Plot.plot({
// color: {
// scheme: "ylgnbu",
// legend: true
// },
// marks: [
// Plot.hexagon(
// filteredArticles1,
// Plot.hexbin(
// { r: "count", fill: "count" },
// {
// x: d=>d3.timeFormat("%Y")(d["Article publication date"]),
// y: d=>d3.timeFormat("%Y")(d["Policy citation date"]) ,
// stroke: "black",
// strokeWidth: 1
// }
// )
// )
// ]
// })
// // bar plot for citation year
// Plot.plot({
// width: 600,
// height: 400,
// marginTop: 40,
// marginBottom: 80,
// marginLeft: 60,
// inset: 15,
// grid: false,
// color: {
// // scheme: "ylgnbu",
// legend: true
// },
// marks: [
// Plot.ruleY([0]),
// Plot.barY(publicationCitaionCount,//.filter(d=>d.publicationYear=="2010"),
// {
// x: "citationYear",
// y: "citingPolicyCount",
// // r: "citingPolicyCount",
// fill: "publicationYear",
// sort:"publicationYear",
// title: (d) =>` year of publication: ${d.publicationYear} \n\t citation year: ${d.citationYear}\n\tpolicy citations: ${d.citingPolicyCount}`})
// ]
// })
// // alter total plot
// Plot.plot({
// inset: 10,
// grid: true,
// // x: {
// // label: "publicationYears →"
// // },
// y: {
// label: "↑ Counts"
// },
// marks: [
// Plot.line(publicationCitaionCount, {x: "publicationYear", y: "totalCitingPolicyCount", curve: "catmull-rom", marker: "circle", stroke: "red", strokeWidth: 2}),
// Plot.text(publicationCitaionCount, {x: "publicationYear", y: "totalCitingPolicyCount", text: d => `${d.totalCitingPolicyCount}`, dy: -8, fill:'black'}),
// Plot.line(publicationCitaionCount, {x: "publicationYear", y: "publicationCount", curve: "catmull-rom", marker: "circle", stroke: "green", strokeWidth: 2}),
// Plot.text(publicationCitaionCount, {x: "publicationYear", y: "publicationCount", text: d => `${d.publicationCount}`, dy: -8, fill:'black'})
// ]
// })
// // hist
// Plot.plot({
// grid: true,
// marks: [
// Plot.frame(),
// Plot.rectY(publicationCitaionCount, Plot.binX(
// {y: "count"},
// {x: "x",
// fill: "steelblue",
// strokeWidth: .5, // linewidth = 0.5
// stroke: "white", // equivalent of edgecolor="white"
// thresholds: 8 // equivalent of "bins=8"
// }
// ))
// ]
// })
// publicationCitaionCount.map(d=>filteredArticles2.map(d1=>{
// if ((d3.timeFormat("%Y")(d1["Article publication date"]) == d["publicationYear"]) && (d3.timeFormat("%Y")(d1["Policy citation date"]) == d["citationYear"]))
// {
// d1["publicationYear"]=d["publicationYear"];
// d1["citationYear"]=d["citationYear"];
// d1["publicationCount"]=d["publicationCount"]
// d1["totalCitingPolicyCount"]= d["totalCitingPolicyCount"];
// d1["citingPolicyCount"]= d["citingPolicyCount"]
// }
// }))
//totalCount=[]
// pub_years.map(d=> {
// var obj = {
// "publicationYear": d,
// "publicationCount": groupedByPubDateTitle.get(d).size,
// "totalCitingPolicyCount":groupedByPubDate.get(d).length,
// };
// totalCount.push(obj);
// })
// // "publicationCount": groupedByPubDateTitle.get(d).size,
// // "totalCitingPolicyCount":groupedByPubDate.get(d).length,
// {
// //const adjmatx = d3.select(adjMatrix).selectAll("rect");
// const tlines = d3.select(totalPlot)
// const brush = d3.brush()
// // set the space that the brush can take up
// .extent([[0+60, 0+40], [600, 400-90]])
// // handle events
// .on('brush', onBrush)
// // .on('end', onEnd);
// tlines.call(brush);
// const x = d3.scaleBand()
// .domain(pub_years)
// .range([0+60, 600]);
// const y = d3.scaleSequential()
// .domain([1, d3.max(publicationCitaionCount, d => d["totalCitingPolicyCount"])])
// .range([400-80, 0+40]);
// function onBrush(event) {
// // event.selection gives us the coordinates of the
// // top left and bottom right of the brush box
// const [[x1, y1], [x2, y2]] = event.selection;
// console.log(event.currentTarget)
// d3.select(this).selectAll("circle").attr("stroke", "orange").attr("stroke-width", "5px")
// .classed('selected', true)
// // return true if the dot is in the brush box, false otherwise
// // tlines.attr('stroke', d => isBrushed(d) ? "blue" : 'gray');
// // function isBrushed(d) {
// // const cx = x(d["publicationYear"]);
// // const cy = y(d["citingPolicyCount"])
// // return cx >= x1 && cx <= x2 && cy >= y1 && cy <= y2;
// // }
// // update the data that appears in the cars variable
// //svg.property('value', cars.filter(isBrushed)).dispatch('input');
// }
// // function onEnd(event) {
// // // if the brush is cleared
// // if (event.selection === null) {
// // // reset the color of all of the dots
// // dots.attr('stroke', d => carColor(d.Origin));
// // gridMap.node().property('value', initialValue).dispatch('input');
// // }
// // }
// }
// // adjmatx
// // .on("pointerover", cellHighlight)
// // .on("pointerout", cellRestore)
// // lines
// // .on("pointerover", lineHighlight)
// // .on("pointerout", lineRestore)
// // tlines
// // .call( d3.brush() // Add the brush feature using the d3.brush function
// // .extent( [ [0,0], [width,height] ] ) // initialise the brush area: start at 0,0 and finishes at width,height: it means I select the whole graph area
// // .on("start brush", updateChart) // Each time the brush selection changes, trigger the 'updateChart' function
// // )
// // Function that is triggered when brushing is performed
// // function updateChart() {
// // extent = d3.event.selection
// // myCircle.classed("selected", function(d){ return isBrushed(extent, x(d.Sepal_Length), y(d.Petal_Length) ) } )
// // }
// // // A function that return TRUE or FALSE according if a dot is in the selection or not
// // function isBrushed(brush_coords, cx, cy) {
// // var x0 = brush_coords[0][0],
// // x1 = brush_coords[1][0],
// // y0 = brush_coords[0][1],
// // y1 = brush_coords[1][1];
// // return x0 <= cx && cx <= x1 && y0 <= cy && cy <= y1; // This return TRUE or FALSE depending on if the points is in the selected area
// // }
// // }
//import {vl} from "@vega/vega-lite-api-v5"
//V = require("@observablehq/vega-lite@0.2")
lda = require( 'https://cdn.jsdelivr.net/gh/stdlib-js/nlp-lda@umd/browser.js' )
simpleStatistics = require("simple-statistics@7")
{
var model;
var docs;
docs = [
'I loved you first',
'For one is both and both are one in love',
'You never see my pain',
'My love is such that rivers cannot quench',
'See a lot of pain, a lot of tears'
];
model = lda( docs, 2 );
model.fit( 1000, 100, 10 );
// returns {}
var words = model.getTerms( 0, 3 );
/* returns
[
{ 'word': 'both', 'prob': 0.06315008476532499 },
{ 'word': 'pain', 'prob': 0.05515729517235543 },
{ 'word': 'one', 'prob': 0.05486669737616135 }
]
*/
return words
}
Purpose-built for displays of data
Observable is your go-to platform for exploring data and creating expressive data visualizations. Use reactive JavaScript notebooks for prototyping and a collaborative canvas for visual data exploration and dashboard creation.
