25:["$","title",null,{"children":"Data Polyamory | Stella Holbrook's Workspace | Observable"}] 49:T4e8,This study analyzes the use of sketches, random sampling, and time series interpolation to identity correlated events in urban time series data. The paper contributes to research in the fields of data analysis and data discovery by enabling the study of large time series from a single web notebook. The author argues that specific sketching and random sampling techniques can help identify correlated data features across datasets. The paper also investigates the use of temporal sub-sampling to try to identify patterns between features which have been previously dubbed “Salient features”[cite]. The code and data used to perform this research are referenced in the report and all the code used to generate the figure used to to justify the author’s claims of sketches suitability for urban data exploration are hosted on an observable notebook. The main contributions of this paper are two-fold: to show that sketches enable statistically representative data analysis when sampling from small to medium size datasets of 1.5, and 0.5 million observations of events in cities, and to demonstrate how analysts could naively identify salient features through the use of sketches on these datasets - potentially forgoing the use of expensive compute. 4a:T492,Displaying data which represents phenomena over space and time has been the topic of previous data visualization research. Data gathered from phenomena in cities are useful for discovering patterns and correlations between events in the area[data-polygamy]. Novel research has identified phenomena which, while uncorrelated most of the time, can become correlated during time subsets which are referred to as Salient Features. The further identification of salient features can help analysts unlock new patterns and correlations between events that occur within a studied city. Cities are great locations to study the relationships between salient features of datasets because their large populations necessitate the gathering of space-time data. I refer to space-time data as any data or combination of data sets which describe phenomena that have been measured with both a location and a timestamp. Spatiotemporal data can be tricky to visualize because some spatial aggregation, temporal aggregation or both aggregations are sometimes necessary to produce a useful visualization. How can the best space-time aggregation be determined in order to visualize this data? 4b:T517,chart = { // Specify the chart’s dimensions. const width = 640; const height = 400; const marginTop = 25; const marginRight = 20; const marginBottom = 35; const marginLeft = 40; // Define the horizontal scale. const x = d3.scaleLinear() .domain(d3.extent(penguins, d => d.flipper_length_mm)).nice() .range([marginLeft, width - marginRight]); // Define the vertical scale. const y = d3.scaleLinear() .domain(d3.extent(penguins, d => d.body_mass_g)).nice() .range([height - marginBottom, marginTop]); // Create the container SVG. const svg = d3.create("svg") .attr("width", width) .attr("height", height) .attr("viewBox", [0, 0, width, height]) .attr("style", "max-width: 100%; height: auto;"); // Add the axes. svg.append("g") .attr("transform", `translate(0,${height - marginBottom})`) .call(d3.axisBottom(x)); svg.append("g") .attr("transform", `translate(${marginLeft},0)`) .call(d3.axisLeft(y)); // Append a circle for each data point. svg.append("g") .selectAll("circle") .data(penguins) .join("circle") .filter(d => d.body_mass_g) .attr("cx", d => x(d.flipper_length_mm)) .attr("cy", d => y(d.body_mass_g)) .attr("r", 3); return svg.node(); }4c:T4f2,map = { // const w = d3.min([width, 1000]) // const h = 0.625 * w // const projection = d3.geoAlbers().fitSize([w, h], BoroughsGeoJSON) // ^^ have these defined outside the box let map = d3.create("svg").attr("width", w).attr("height", h); // let stations = getSations.forEach(function (d) { // let xy = projection(d.Latitude, d.Longitude)} map.selectAll("path") .data(BoroughsGeoJSON.features) .join("path") .attr("d", path) .attr("fill", "lightgray") .attr("stroke", "#fff") .attr("stroke-width", 1); map.selectAll("circle") .data(weather_stations) .join("circle") //.attr("r", (c) => 5 * (c.population / .max_pop) ** 0.3) .attr("r", 100) .attr("fill", "black") .attr("fill-opacity", 0.5) .attr("stroke", "black") // .attr("data-name", (c) => c.name) // .attr("data-population", (c) => c.population) // .nodes() // .forEach(function (c) { // tippy(c, { // content: ` //

${c.getAttribute("data-name")}

Population: ${c.getAttribute("data-population")}

`, // theme: "light-border", // allowHTML: true // }); // }); return map.node(); }4d:[{"id":"8cf10fb4b1ac231770a970beac6874ac9b9e505c4e8af5953426e24e68a66e9210f956932cddfa3e9dfc75e5d5444436010d824c12d0af6b47a5e0bac69bdc51","href":"https://static.observableusercontent.com/files/8cf10fb4b1ac231770a970beac6874ac9b9e505c4e8af5953426e24e68a66e9210f956932cddfa3e9dfc75e5d5444436010d824c12d0af6b47a5e0bac69bdc51","name":"data_part_1.csv","type":"text/csv","lastModified":1714711394010.105,"size":36050461},{"id":"c8f4806b4a6a614ea9c93b627cccdc30e8e315b2da719a008779b9a1d3cb3ac3131aed5f3bc29b99437ec78bab4c2e6eadbe92f01a5e609e58618b291afb21c6","href":"https://static.observableusercontent.com/files/c8f4806b4a6a614ea9c93b627cccdc30e8e315b2da719a008779b9a1d3cb3ac3131aed5f3bc29b99437ec78bab4c2e6eadbe92f01a5e609e58618b291afb21c6","name":"weather_new_york_2016-2017.csv","type":"text/csv","lastModified":1714754488504.729,"size":4679984},{"id":"9baf08baa0f21ff8e9518f24c4047cfc466e86b2053ee64a0dbbe2fc91fbf7784b91a5bbe3e661cfcba48adcfdd0dd5b2e73805cae18589b3070bba5ad097f1e","href":"https://static.observableusercontent.com/files/9baf08baa0f21ff8e9518f24c4047cfc466e86b2053ee64a0dbbe2fc91fbf7784b91a5bbe3e661cfcba48adcfdd0dd5b2e73805cae18589b3070bba5ad097f1e","name":"Borough Boundaries.geojson","type":"application/geo+json","lastModified":1714770087993.437,"size":3244474}] 29:{"id":"0041d57e1a9d355c","slug":null,"title":"Data Polyamory","thumbnail":"a6d86a2f6eaa4d431566b34672e8acc0c18170bb885f647d14dd7ecbe8bf13eb","access_level":"public","create_time":"$D2023-10-23T04:56:13.759Z","update_time":"$D2024-05-08T18:46:21.854Z","view_time":null,"first_public_time":"$D2023-10-23T04:56:13.759Z","has_unpublished_edits":null,"fork":{"id":"6d7c773a6d3673b0","slug":"d3-scatterplot","title":"D3 scatterplot","owner":{"id":"f35c755083683fe5","login":"observablehq","name":"Observable"}},"stars":0,"starred":false,"owner":{"type":"team","id":"2153b76901ba6ce0","login":"stella-holbrook-ws","name":"Stella Holbrook's Workspace","avatar_url":"https://avatars-next.observableusercontent.com/a28ff56d55268b10ce00cbf7804f508962786ecbfd89a64f4403c268e8ff9e56","tier":"starter_2024","bio":"","following":false},"version":277,"publish_version":null,"role":null,"authored":false,"authors":[{"type":"individual","id":"666f8f22e6c30342","login":"stella-holbrook","name":"Stella Holbrook","avatar_url":"https://avatars-next.observableusercontent.com/0322684e66d136dd7f58b84d004815dd665eea17f3fca7aa62e2ce6bb9ca20c8","tier":null,"bio":"","following":false}],"members":[{"type":"individual","id":"666f8f22e6c30342","login":"stella-holbrook","name":"Stella Holbrook","avatar_url":"https://avatars-next.observableusercontent.com/0322684e66d136dd7f58b84d004815dd665eea17f3fca7aa62e2ce6bb9ca20c8","tier":null,"role":"editor"},{"type":"team","id":"2153b76901ba6ce0","login":"stella-holbrook-ws","name":"Stella Holbrook's Workspace","avatar_url":"https://avatars-next.observableusercontent.com/a28ff56d55268b10ce00cbf7804f508962786ecbfd89a64f4403c268e8ff9e56","tier":"starter_2024","role":"editor"}],"comments":[],"custom_thumbnail":false,"trashed":false,"lapsed":null,"subscribed":null,"forks":0,"collection":null,"type":"notebook","body":{"titling":"auto","title":"Data Polyamory","cells":[{"id":0,"value":"# Data Polyamory \n\nVisualizing the Many to Many relationships in urban spatio-temporal datasets\n\nStella Holbrook - Information Visualization - May 3rd 2024","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":274,"value":"$49","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"","database":"$undefined"},{"id":276,"value":"$4a","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"","database":"$undefined"},{"id":104,"value":"// load dataset (cleaned) -mention it is cleaned - include picture of pyhton script for transparency && link to original dataset. \nweather = (await FileAttachment(\"weather_new_york_2016-2017.csv\").csv())\n.map(weather_d => ({\n 'Station' : weather_d.STATION,\n 'Name' : weather_d.NAME,\n 'Latitude' : Number(weather_d.LATITUDE), \n 'Longitude' : weather_d.LONGITUDE,\n 'Elevation' : Number(weather_d.ELEVATION),\n 'Date' : parseTime(weather_d.DATE),\n 'Precipitation' : Number(weather_d.PRCP),\n 'Snow' : weather_d.SNOW,\n 'Cloudiness' : weather_d.ACSH,\n 'Wind_Speed' : weather_d.AWND,\n 'Max_Temp' : weather_d.TMAX,\n 'Min_Temp' : weather_d.TMIN\n}))\n","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":127,"value":"weather_by_date = d3.group(weather, (d) => d.Date)","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":112,"value":"// helper function to parse date-times\nparseTime = d3.utcParse(\"%Y-%m-%d\");","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":108,"value":"// load in the taxi trip dataset:\ntaxis = (await FileAttachment(\"data_part_1.csv\").csv())\n.map(taxi_d => ({\n 'id' : taxi_d.id,\n 'vendor_id' : taxi_d.vendor_id,\n 'pickup_datetime' : parseDateTime(taxi_d.pickup_datetime),\n 'dropoff_datetime' : parseDateTime(taxi_d.dropoff_datetime),\n 'pickup_longitude' : taxi_d.pickup_longitude,\n 'pickup_latitude' : taxi_d.pickup_latitude,\n 'dropoff_longitude' : taxi_d.dropoff_longitude,\n 'dropoff_latitude' : taxi_d.dropoff_latitude,\n 'trip_duration' : taxi_d.trip_duration,\n 'trip_date' : formatDate(parseDateTime(taxi_d.pickup_datetime))\n}))","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":139,"value":"formatDate = d3.timeFormat(\"%Y-%m-%d\");","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":121,"value":"dayAggregate = {\n // need to make sure dates aren't strings\n const tripsPerDay = d3.flatRollup(taxis, (v) => v.length, d => parseTime(d.trip_date));\n // const tripsPerDate = tripsPerDay.map(days => ({\n // 'Date' : tripsPerDay[0],\n // 'Count' : tripsPerDay[1]\n // }))\n //const sorted = d3.sort(tripsPerDay, (d) => d.trip_date)\n //return sorted\n return tripsPerDay\n}; ","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":170,"value":"tripsPerDay = d3.flatRollup(taxis, (v) => v.length, d => parseTime(d.trip_date)).sort()","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":123,"value":"parseDateTime = d3.timeParse(\"%Y-%m-%d %H:%M:%S\");","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":119,"value":"// sort the data by the taxi time.\n\n(function(){\n if (typeof Object.defineProperty === 'function'){\n try{Object.defineProperty(Array.prototype,'sortBy',{value:sb}); }catch(e){}\n }\n if (!Array.prototype.sortBy) Array.prototype.sortBy = sb;\n\n function sb(f){\n for (var i=this.length;i;){\n var o = this[--i];\n this[i] = [].concat(f.call(o,o,i),o);\n }\n this.sort(function(a,b){\n for (var i=0,len=a.length;i`;\n yield container;\n const map = L.map(container).setView([40.7299, -73.9923], 13);\n L.tileLayer(\"https://{s}.tile.openstreetmap.org/{z}/{x}/{y}.png\", {\n attribution: \"© OpenStreetMap contributors\"\n }).addTo(map);\n}","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":101,"value":"// not sure what this does yet\nL = {\n const L = await require(\"leaflet@1/dist/leaflet.js\");\n if (!L._style) {\n const href = await require.resolve(\"leaflet@1/dist/leaflet.css\");\n document.head.appendChild(L._style = html``);\n }\n return L;\n}","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":191,"value":"getSations = {\n var stations = d3.flatRollup(weather,\n v => ({\n Latitude : d3.median(v, d => d.Latitude),\n Longitude : d3.median(v, d => d.Longitude)\n }),\n d => d.Name\n )\n return stations\n} ","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":264,"value":"// when in doubt, javascript map.\nweatherStations_json = {\n let stations = getSations.map((row) => ({\n name : row[0],\n lat : row[1].Latitude,\n lon : row[1].Longitude\n }))\n return stations\n}","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":200,"value":"BoroughsGeoJSON = FileAttachment(\"Borough Boundaries.geojson\").json()","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":230,"value":"path = d3.geoPath().projection(projection)","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":232,"value":"projection = d3.geoAlbers().fitSize([w, h], BoroughsGeoJSON)","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":235,"value":"w = d3.min([width, 1000])","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":237,"value":"h = 0.625 * w","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":198,"value":"$4c","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":269,"value":"aggregated_data_weather_stations = {\n var stations = d3.flatRollup(weather,\n v => ({\n Latitude : d3.median(v, d => d.Latitude),\n Longitude : d3.median(v, d => d.Longitude),\n meanMaxTemp : d3.mean(v, d => d.Max_temp),\n meanMinTemp : d3.mean(v, d => d.Min_Temp)\n }),\n d => d.Name\n )\n return stations // see about each of these summarizes and then you can aggregate multiple into 1 map\n\n \n \n let aggregate = getSations.map((row) => ({\n name : row[0],\n lat : row[1].Latitude,\n lon : row[1].Longitude\n }))\n return aggregate \n}\n\n","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"}],"files":"$W4d","stdlib":"1"}} 24:null