2a:null 2b:["$","title",null,{"children":"TORCHLITE: HTRC Extracted Features API | Janet Swatscheno | Observable"}] 30:T5f4, | Name | Workset ID | # of Volumes | Description | | ------ | -------- | --------| --------| | Native-authored Workset | 6408a5e930000067055ce2e8 |919|A list of works authored by Native Americans in HathiTrust| | Comparative Literature Workset | 6408a63a30000067055ce2e9 |927|A list of works authored by non-Native Americans in HathiTrust on the similar subjects as the Native-authored workset during similar time period with similar language representation | | **Native-authored Workset Sample** | **640e74be300000d90b5ce31b** | **10** | **10 volume sample from the list of works author by Native Americans in HathiTrust**| | The Black Fantastic Workset | 642720e53300008d02a5dc9c |90 |90 volumes, including duplicates, of Black Fantastic fiction, identified by Dr. Seretha Williams and Dr. Clarissa West-White, as part of HTRC's SCWAReD project | | History of Black Writers Workset | 6407a1ec300000a4045ce2e7 | 2166 | Volumes found in HathiTrust written by African-American authors, as identified by the University of Kansas's Project on the History of Black Writing, released as part of the SCWAReD project| | **History of Black Writers Workset Sample** | **640ba4bf300000440a5ce31a** | **25** | **25 volume sample of volumes found in HathiTrust written by African-American authors, as identified by the University of Kansas's Project on the History of Black Writing, released as part of the SCWAReD project**|31:T115c,// Copyright 2021 Observable, Inc. // Released under the ISC license. // https://observablehq.com/@d3/beeswarm function BeeswarmChart(data, { value = d => d, // convenience alias for x label, // convenience alias for xLabel type = d3.scaleLinear, // convenience alias for xType domain, // convenience alias for xDomain x = value, // given d in data, returns the quantitative x value title = null, // given d in data, returns the title group, // given d in data, returns an (ordinal) value for color groups, // an array of ordinal values representing the data groups colors = d3.schemeTableau10, // an array of color strings, for the dots radius = 10, // (fixed) radius of the circles padding = 10, // (fixed) padding between the circles marginTop = 30, // top margin, in pixels marginRight = 20, // right margin, in pixels marginBottom = 30, // bottom margin, in pixels marginLeft = 20, // left margin, in pixels width = 640, // outer width, in pixels height = 400, // outer height, in pixels xType = type, // type of x-scale, e.g. d3.scaleLinear xLabel = label, // a label for the x-axis xDomain = domain, // [xmin, xmax] xRange = [marginLeft, width - marginRight] // [left, right] } = {}) { // Compute values. const X = d3.map(data, x).map(x => x == null ? NaN : +x); const T = title == null ? null : d3.map(data, title); const G = group == null ? null : d3.map(data, group); // Compute which data points are considered defined. const I = d3.range(X.length).filter(i => !isNaN(X[i])); // Compute default domains. if (xDomain === undefined) xDomain = d3.extent(X); if (G && groups === undefined) groups = d3.sort(G); // Construct scales and axes. const xScale = xType(xDomain, xRange); const xAxis = d3.axisBottom(xScale).tickSizeOuter(0); // had to add .tickFormat(d3.timeFormat("%Y")) to make it display years properly!! const color = group == null ? null : d3.scaleOrdinal(groups, colors); // Compute the y-positions. const Y = dodge(I.map(i => xScale(X[i])), radius * 2 + padding); // Compute the default height; if (height === undefined) height = d3.max(Y) + (radius + padding) * 2 + marginTop + marginBottom; // Given an array of x-values and a separation radius, returns an array of y-values. function dodge(X, radius) { const Y = new Float64Array(X.length); const radius2 = radius ** 2; const epsilon = 1e-3; let head = null, tail = null; // Returns true if circle ⟨x,y⟩ intersects with any circle in the queue. function intersects(x, y) { let a = head; while (a) { const ai = a.index; if (radius2 - epsilon > (X[ai] - x) ** 2 + (Y[ai] - y) ** 2) return true; a = a.next; } return false; } // Place each circle sequentially. for (const bi of d3.range(X.length).sort((i, j) => X[i] - X[j])) { // Remove circles from the queue that can’t intersect the new circle b. while (head && X[head.index] < X[bi] - radius2) head = head.next; // Choose the minimum non-intersecting tangent. if (intersects(X[bi], Y[bi] = 0)) { let a = head; Y[bi] = Infinity; do { const ai = a.index; let y = Y[ai] + Math.sqrt(radius2 - (X[ai] - X[bi]) ** 2); if (y < Y[bi] && !intersects(X[bi], y)) Y[bi] = y; a = a.next; } while (a); } // Add b to the queue. const b = {index: bi, next: null}; if (head === null) head = tail = b; else tail = tail.next = b; } return Y; } const svg = d3.create("svg") .attr("width", width) .attr("height", height) .attr("viewBox", [0, 0, width, height]) .attr("style", "max-width: 100%; height: auto; height: intrinsic;"); svg.append("g") .attr("transform", `translate(0,${height - marginBottom})`) .call(xAxis) .call(g => g.append("text") .attr("x", width) .attr("y", marginBottom - 4) .attr("fill", "currentColor") .attr("text-anchor", "end") .text(xLabel)); const dot = svg.append("g") .selectAll("circle") .data(I) .join("circle") .attr("cx", i => xScale(X[i])) .attr("cy", i => height - marginBottom - radius - padding - Y[i]) .attr("r", radius); if (G) dot.attr("fill", i => color(G[i])); if (T) dot.append("title") .text(i => T[i]); return svg.node(); }32:[] 2e:{"id":"ed0723b050ddb6f3","slug":"torchlite-ef-api","title":"TORCHLITE: HTRC Extracted Features API","thumbnail":"991c2fd397295ef8049052b75a1713bbe4a62cfebd2a2f5945d661c4718c18e8","access_level":"public","create_time":"$D2023-01-24T22:54:24.052Z","update_time":"$D2024-05-21T15:44:57.076Z","view_time":null,"first_public_time":"$D2023-01-24T22:54:24.052Z","fork":false,"stars":1,"starred":false,"owner":{"type":"team","id":"c3a8dbb1a887251a","login":"jswatsch","name":"Janet Swatscheno","avatar_url":"https://avatars-next.observableusercontent.com/304a19f602cd1fcc4f9c56978a6ae85e3b378ff8dad530cc1b2ce1dfe34a18c8","tier":"starter_2024"},"version":1336,"publish_version":null,"role":null,"authored":false,"authors":[{"type":"individual","id":"0e8491e0251e2955","login":"jswatsch","name":"Janet Swatscheno","avatar_url":"https://avatars-next.observableusercontent.com/bb6f24281a7b6eba1aa3ce8b18f98fbde9107877f5fa74828fda69afb582b2de","tier":null}],"members":[{"type":"individual","id":"0e8491e0251e2955","login":"jswatsch","name":"Janet Swatscheno","avatar_url":"https://avatars-next.observableusercontent.com/bb6f24281a7b6eba1aa3ce8b18f98fbde9107877f5fa74828fda69afb582b2de","tier":null,"role":"editor"},{"type":"individual","id":"331b1ab1e362f154","login":"rdubnicek","name":"Ryan Dubnicek","avatar_url":"https://avatars-next.observableusercontent.com/8b127c182b725fcb6080e659fe0053a0b5248fb8794c37e22315dd6524d25a10","tier":null,"role":"editor"}],"comments":[{"id":"b9f18ea1028bf367","reply_to_id":null,"content":"I should probably change this and/or additionally show the GET workset volumes metadata by workset id method instead which in theory should give the same results","create_time":"$D2023-03-06T02:32:36.915Z","update_time":"$D2023-03-06T02:32:45.401Z","resolved":true,"user":{"type":"individual","id":"0e8491e0251e2955","login":"jswatsch","name":"Janet Swatscheno","avatar_url":"https://avatars-next.observableusercontent.com/bb6f24281a7b6eba1aa3ce8b18f98fbde9107877f5fa74828fda69afb582b2de","tier":null}},{"id":"74ac3fe3bd9dd2b0","reply_to_id":null,"content":"Change the workset chart to have smaller worksets","create_time":"$D2023-03-09T21:28:16.013Z","update_time":null,"resolved":true,"user":{"type":"individual","id":"0e8491e0251e2955","login":"jswatsch","name":"Janet Swatscheno","avatar_url":"https://avatars-next.observableusercontent.com/bb6f24281a7b6eba1aa3ce8b18f98fbde9107877f5fa74828fda69afb582b2de","tier":null}}],"custom_thumbnail":true,"trashed":false,"subscribed":null,"forks":9,"collection":null,"type":"notebook","body":{"title":"TORCHLITE: HTRC Extracted Features API","cells":[{"id":307,"value":"# TORCHLITE: HTRC Extracted Features API","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":1163,"value":"## ❓ Helpful Links\n* [Observable Documentation](https://observablehq.com/@observablehq/documentation)\n* [Extracted Features API](https://htrc.stoplight.io/docs/ef-api/8xpvh96ani2e0-ef-api)\n* [D3 Examples Gallery](https://observablehq.com/@d3/gallery)\n* [HathiTrust Digital Library](https://www.hathitrust.org/)","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":640,"value":"## 📗 Exploring a single volume","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":577,"value":"In order to explore a single volume, we need a HathiTrust id. HathiTrust ids can be found in various ways. If you're looking for a specific book, you can search on the [HathiTrust Digital Library](https://www.hathitrust.org/). The HT ID is the permanent HathiTrust item identifier. Each item identifier is unique.\n\nThis identifier can be used to construct a persistent handle url or other link that directs users to the item. For example, mdp.39015013764785 is the HT ID in this URL: [https://hdl.handle.net/2027/mdp.39015013764785](https://hdl.handle.net/2027/mdp.39015013764785).\n\nHere are some additional HathiTrust IDs you can experiment with:\n\n| HT ID | Title | Year Published | Author |\n| ------ | -------- | --------| --------|\n| uva.x001016358\t | The children of Sisyphus | 1964 | Patterson, Orlando 1940- |\n| mdp.39015016452230 | Trumbull park, a novel. | 1959 | Brown, Frank London |","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":1296,"value":"htid2 = \"uva.x001016358\"","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":257,"value":"htid = 'mdp.39015067702061'; //assigning the HathiTrust ID to the variable htid","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":606,"value":"### 🛀 Cleaning the HathiTrust id","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":582,"value":"Not all of the HathiTrust ids are formatted in a way we can easily use because they include special characters. We created this cleanId function that will replace special characters and we can run it against our HathiTrust id.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":266,"value":"function cleanId(id) {\n const i = id.indexOf('.');\n if (i == -1) throw `Invalid clean htid: ${id}`;\n const lib = id.substring(0, i);\n const libId = id.substring(i+1);\n return `${lib}.${libId.replaceAll(':', '+').replaceAll('/', '=').replaceAll('.', ',')}`;\n}","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":264,"value":"cleanHTID = cleanId(htid); //Now we pass our HathiTrust ID throught he clean id function so we can use it in our API calls","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":585,"value":"### ☎️ API Calls","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":591,"value":"Now that we have a clean HathiTrust ID, we can use it to the make a call to the Extracted Features API. In Observable, making a JavaScript fetch call to an API is super easy! Just click the plus sign to insert a cell.\n\nA dropdown will appear with lots of handy options, including \"Fetch from URL\".\n\nSelect \"Fetch from URL\", then we can grab and paste the URL we want to use from the [Extracted Features API](https://htrc.stoplight.io/docs/ef-api/8xpvh96ani2e0-ef-api).","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":1298,"value":"data1 = fetch(`https://data.htrc.illinois.edu/ef-api/volumes/${cleanHTID}`).then((response) => response.json())","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":269,"value":"response = fetch(`https://data.htrc.illinois.edu/ef-api/volumes/${cleanHTID}`).then(resp => resp.json()) //In our API call, we're passing the cleanHTID into the URL for the API call using ${cleanHTID}. Must use back tick ` aroundd the url","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":604,"value":"### ⛏️ Let's dig into the response we got from the API","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":611,"value":"In our API response, we get back two pieces of information:\n * **code: 200**: This indicates that the HTTP status code of the response is \"200 OK,\" which means that the request was successful and the server is returning data. (yay!)\n * **data**: This is the body of the response, which contains the data being returned.\n\nWe can now look directly at just the data being returned. This will remove the status code, and only show us the data property.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":271,"value":"data = response.data //looking specifically at the data property","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":625,"value":"### 🔍 A closer look at the data","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":628,"value":"Even for a single volume, Extracted Features gives us a lot of information.\n\nAs you can see in the data property, there are a number of other properties nested below it. What you're probably most interested in is either **metadata** or **features**. Both of these properties give us different facets of the data we can explore. For example, in the features property, we can explore individual pages:","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":285,"value":"hd = data.features.pages //looking specifically at the pages within the features property","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":659,"value":"When we dig into data > features > pages we get an array that contains each page of our volume. For each page, we get really handy statistics like token counts, sentence counts, empty line counts, etc. That's what we'll use to visualize our data!","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":668,"value":"### 📊 Let's visualize something!","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":1176,"value":"One of the really nice features of Observable is they provide some preloaded visualizations we can add. The Plot visualizations are super simple, and great for quick analysis. To select a Plot visualization to use, we can click the plus button to add another cell and then simply select the type of chart we want to use.\n\nThese preloaded charts come with some standard data already loaded that we will swap out with our data.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":346,"value":"### Token Counts Per Page","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":337,"value":"chart1 = Plot.plot({\n marks: [\n Plot.ruleY([0]),\n Plot.lineY(hd, {x: \"seq\", y: \"tokenCount\"}) //here is where we can swap out the preloaded data and put in our hd array and plot the token count You can swap out tokenCount for lineCount, sentenceCount, etc.!\n ]\n})","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":1200,"value":"In this chart, we are plotting the token count for each page of this book on the y-axis. The x-axis is the sequence, aka the page number. This gives us a general overview of how many words our on each page of this book. \n\n**Do you notice anything odd?**","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":1196,"value":"### 📊 Customize and Compare\nWe can also customize things like the color of the plot lines and add some comparison data. Below we'll define another variable with a comparison book so we can plot it on top of our first book.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":1181,"value":"comparison_id = \"uiug.30112064412874\"","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":1183,"value":"comparison_htid = cleanId(comparison_id)","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":1185,"value":"comparison_response = fetch(`https://data.htrc.illinois.edu/ef-api/volumes/${comparison_htid}`).then(resp => resp.json())","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":1187,"value":"comparison_data = comparison_response.data","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":1189,"value":"comparison_hd = comparison_data.features.pages","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":1193,"value":"### Token Counts Per Page: The Raw Shark Texts vs. Anna Karenina","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":1191,"value":"chart2 = Plot.plot({\n marks: [\n Plot.ruleY([0]),\n Plot.line(hd, {x: \"seq\", y: \"tokenCount\", stroke: \"blue\"}),\n Plot.line(comparison_hd, {x: \"seq\", y: \"tokenCount\", stroke: \"#e15759\"}),\n ]\n})","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":757,"value":"### D3 Visualizations\nThe Plot charts are nice for very simple graphing, but Observable also has some handy premade D3 visualizations. Some of these visualization are available from the dropdown and in the [D3 Gallery notebook](https://observablehq.com/@d3/gallery).\n\nD3.js is a powerful JavaScript library for producing dynamic, interactive data visualizations in web browsers.\n\nFor the next visualizations we will continue to analyze the token count in our volume, this time using a Histogram from a premade [D3 Histogram notebook](https://observablehq.com/@d3/histogram).","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":1210,"value":"### Token Count Frequency","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":1220,"value":"Again, Observable makes it easy for us to use a premade D3 graph, this time using the \"import\" option.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":293,"value":"import {Histogram} from \"@d3/histogram\"","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":297,"value":"chart = Histogram(hd, { //taking this from https://observablehq.com/@d3/histogram\n value: d => d.tokenCount, \n label: \"Number of Tokens\",\n width,\n height: 400,\n color: \"steelblue\"\n})","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":1312,"value":"chart3 = Histogram(hd, {\n value: d => d.tokenCount,\n label: \"Number of Tokens\",\n width,\n height: 500,\n color: \"steelblue\"\n})","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":830,"value":"You'll notice that both graphs show something a bit unusual-- many of the pages of this book have a very low number of tokens on the page, with 85 of the pages having only 0-10 words on the page. Let's take a look at an example page from the book we're analyzing. The book we're graphing is a novel called *The Raw Shark Texts* by Steven Hall. At one point in the novel, the words are arranged to look like a shark getting closer to you, leaving a lot of whitespace and few words!\n","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":475,"value":"### 🦈 The Raw Shark Texts","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":478,"value":"![The Raw Shark Text](https://www.researchgate.net/profile/Kiene-Wurth/publication/261943465/figure/fig1/AS:296656902868995@1447739926125/The-Raw-Shark-Texts-page-375.png)","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":313,"value":"## 📚 Exploring multiple volumes (AKA a workset)","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":357,"value":"### Premade SCWAReD worksets","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":783,"value":"We have some premade worksets ready for you to use. These worksets were created by project teams who were part of our Scholar-Curated Worksets for Analysis, Reuse and Dissemination grant.\n\nThe worksets we have preloaded include \n\n* The History of Black Writing from the University of Kansas, led by co-PI Dr. Maryemma Graham, which is a workset of all African-American fiction in the HathiTrust Digital Library, based on a manually-verified list of Black authors and works at Project HBW.\n* Mining the Native American Authored Works in HathiTrust for Insights Dr. Kun Lu, Dr. Raina Heaton (University of Oklahoma), and Dr. Raymond Orr (Dartmouth)\n* The Black Fantastic: Curated Vocabularies, Artifact Analysis and Identification Dr. Clarissa West-White (Bethune-Cookman University) and Dr. Seretha Williams (Augusta University)\n\n","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":789,"value":"$30","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":366,"value":"### Get workset volumes by workset id","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":809,"value":"First, we'll set the variable **worksetid** to the workset we want to use. In this notebook, I'm using the Black Fantastic Workset because 90 volumes is easier to parse. Note: Some of the larger worksets, like the History of Black Writing can take a long time for Observable to load, depending on the API call you are making.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":316,"value":"worksetid = '66477bae2600005807132b25';","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":816,"value":"Next, we will use the fetch function to make a GET request for the workset volumes. Notice the response we get includes all the data for each volume, meaning it sends both the **metadata** and the **features**.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":378,"value":"workset_response = fetch(`https://data.htrc.illinois.edu/ef-api/worksets/${worksetid}/volumes`).then(resp => resp.json())","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":381,"value":"### Get workset volume metadata by workset id","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":824,"value":"You might be interested in only getting the metadata for volumes for your analysis. \n\nIn that case, we can just request the **metadata** which will make the amount data we get back a lot smaller than requesting both the metadata and features.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":321,"value":"workset_metadata_response = fetch(`https://data.htrc.illinois.edu/ef-api/worksets/${worksetid}/metadata`).then(resp => resp.json())","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":1231,"value":"This returns all the metadata for our volumes. If we're interested in specific fields, we can construct the API call to just return those fields. In the below call, we're returning the volume title and the publication data by adding the following the end of our call: \n\n?fields=metadata.title%2Cmetadata.pubDate","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":408,"value":"workset_pubdates_response = fetch(`https://data.htrc.illinois.edu/ef-api/worksets/${worksetid}/metadata?fields=metadata.title%2Cmetadata.pubDate`).then(resp => resp.json())","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":1236,"value":"This returns an object with containing an array with the metadata for our volumes, with titles and publication dates nested in the metadata. In the next line, we pull out that metadata using .data as we did earlier in this notebook.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":453,"value":"wprd = workset_pubdates_response.data","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":1245,"value":"And finally we use the **JavaScript map function** to create an array of just the titles and dates.\n\n*Note: The map() function is a built-in method in JavaScript that allows you to iterate over an array and apply a function to each element of the array, creating a new array with the results of the function calls.*","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":481,"value":"pubDates = wprd.map(obj => obj.metadata);","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":522,"value":"// import {BeeswarmChart} from \"@d3/beeswarm\"","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":1259,"value":"### 📅 Timeline of Workset Publication Dates","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":526,"value":"PubDateTimeline = BeeswarmChart(pubDates, {\n x: d => d3.timeParse(\"%Y\")(d.pubDate), // d3.timeParse(\"%Y\")(d.pubDate) this needed to be added for the dates to show up correctly\n label: \"Year\",\n type: d3.scaleTime,\n title: d => d.title,\n range: [0, width]\n})","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":1261,"value":"Here again, we use a premade D3 visualization, but instead of importing the chart, we copied and pasted it directly from the [Beeswarm Notebook](https://observablehq.com/@d3/beeswarm). This allows us to customize the visualization in anyway we want.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":702,"value":"$31","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":1333,"value":"Another type of API call we can make, \"GET volumes aggregated by workset id\", will give us all the token data for each volume aggregated at the volume level rather than the page level.\n\nThe advantage to using the aggregated data is that it's much faster at retrieving tokens, so if I have an application or visualization that doesn't need parts of speech, or page level token data, I can use the aggregated data for a more performant visualization.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":1335,"value":"agg_data = fetch(`https://data.htrc.illinois.edu/ef-api/worksets/${worksetid}/volumes/aggregated`).then((response) => response.json())","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":1083,"value":"## More Extracted Features Notebooks to Explore","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"},{"id":1265,"value":"* [Word Cloud](https://observablehq.com/@jswatsch/torchlite-workset-word-cloud)\n * Displays the most used words within a workset, with the ability to input a maximum number of tokens to display at once\n* [Contributor Map](https://observablehq.com/d/e69a3c5185393caa) by Deren Kudecki\n * Uses metadata from the Extracted Features API and geographical information from Wikidata to plot country data about contributors in a workset","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined"}],"files":"$W32","stdlib":"1","titling":"auto"}} 2f:"$2e:body"