34:["$","title",null,{"children":"Analyzing a dataset: Is an expensive college worth it | Jazmine | Observable"}] 3c:T11da,3d:T477,const loadData = () => { const url = "https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2020/2020-03-10/tuition_cost.csv"; // Download the data. Then, after it's downloaded, process it as // described in the function inside "then". return d3.csv(url, d3.autoType).then((data) => data.map(d => ({ ...d, room_and_board: d['room_and_board'] === 'NA' ? NaN : d['room_and_board'], state: Object.keys(nonStates).includes(d['state_code']) ? nonStates[d['state_code']] : d['state'] })) ) } const tuitionData = await loadData(); const incomeData = (await d3.csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2020/2020-03-10/salary_potential.csv', d3.autoType)) .map(d => ({ name: d.name, state: d.state_name, early_career_pay: d.early_career_pay, mid_career_pay: d.mid_career_pay, make_world_better_percent: d.make_world_better_percent })); // From inside out: use map to get a list of states, then put them in a Set to get unique names, // then turn it back into an array. const states = Array.from(new Set(tuitionData.map(d => d.state)));3e:[] 38:{"id":"4404cb3326e9d64f","slug":"analyzing-a-dataset-is-an-expensive-college-worth-it","title":"Analyzing a dataset: Is an expensive college worth it","thumbnail":"e5cd4035542f764735cbe2c25657ce4030481228e7176e96785c503ff99f0ec6","access_level":"public","create_time":"$D2026-10-13T00:02:16.218Z","update_time":"$D2026-10-21T00:25:40.929Z","view_time":null,"first_public_time":"$D2026-10-21T00:27:08.526Z","has_unpublished_edits":null,"fork":true,"stars":0,"starred":false,"owner":{"type":"team","id":"f9794693d27004e3","login":"jhazzy","name":"Jazmine","avatar_url":null,"tier":"starter_2024","bio":"","following":false},"version":674,"publish_version":674,"role":null,"authored":false,"authors":[{"type":"individual","id":"542eace3fbc752f9","login":"jhazzy","name":"Jazmine","avatar_url":null,"tier":null,"bio":"","following":false}],"members":[{"type":"team","id":"f9794693d27004e3","login":"jhazzy","name":"Jazmine","avatar_url":null,"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":"Analyzing a dataset: Is an expensive college worth it","cells":[{"id":1,"value":"# Analyzing a dataset: Is an expensive college worth it","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":5,"value":"Today's lesson is all about using array functions (some familiar, some new) to do a realistic data analysis. We're going to take a data-driven perspective to answer the question: **_Is an expensive college worth it?_**","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":27,"value":"First, let's try to state how we're going to answer this question. What would make that expensive college \"worth it\"? For that matter, what counts as \"expensive\"? What data would you need to answer these questions?\n\nWrite your answer (briefly) in the cell below.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":28,"value":"- Housing\n- Transportation\n- tuition\n - or financial aid\n - housing etc. room and board\n- offers your major\n- employment rate\n - average salary\n- student happiness\n- facilities\n- location: distance from home, distance from a big city\n- teachers/staff\n- study abroad/other programmes\n- networking/research opportunities","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":30,"value":"$${vspace(150)}\n## Getting started\n\nWe'll start with [a dataset](https://rfordatascience.github.io/tidytuesday/data/2020/2020-03-10/readme.html) of college tuition amounts and survey responses from graduates, collected and cleaned from various sources as part of the [_Tidy Tuesday_](https://rfordatascience.github.io/tidytuesday/about.html) project.\n\nThe data is from the 2018–2019 academic year.\n\nHere's what it looks like in tabular form.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":6,"value":"Inputs.table(tuitionData, { rows: 5, sort: 'degree_length', reverse: true })","pinned":false,"hidden":false,"mode":"ts","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":9,"value":"As before, it's an array of objects.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":10,"value":"tuitionData","pinned":true,"hidden":false,"mode":"ts","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":85,"value":"## Warm up\n\nLet's start by getting to know the data little better.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":86,"value":"_Can you find the record for Cal Poly?_ You can use the [`find`](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Array/find) function here.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":87,"value":"tuitionData.find(c => c.name.includes('California') && c.name.includes('Polytechnic'))","pinned":true,"hidden":false,"mode":"ts","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":88,"value":"_Does this table include only 4-year institutions?_ I.e., `degree_length === \"4 Year\"` true for _all_ schools? You can use the [`every`](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Array/every) function here.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":89,"value":"// Your code here.\n// tuitionData.filter((school) => school[\"degree_length\"] !== \"4 Year\").length === 0\n\n// tuitionData\n// .map((school) => school['degree_length'] === \"4 Year\")\n// .reduce((acc, curr) => acc && curr)\n\ntuitionData.every((school) => school[\"degree_length\"] === \"4 Year\")","pinned":true,"hidden":false,"mode":"ts","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":93,"value":"_How many **unique** schools are in this table?_ There are **${tuitionData.length}** records in our table. Are any schools repeated?","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":94,"value":"// Your code here.\nconst uniqueNames = new Set(\n tuitionData.map((school) => school.name)\n)\ndisplay(uniqueNames)","pinned":true,"hidden":false,"mode":"ts","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":95,"value":"_How many states are represented in this data?_","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":97,"value":"const uniqueNames = new Set(\n tuitionData.map((school) => school.name)\n)\ndisplay (uniqueNames)\n","pinned":true,"hidden":false,"mode":"ts","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":98,"value":"new Set(tuitionData.map((school) => school.state))","pinned":true,"hidden":false,"mode":"ts","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":31,"value":"$${vspace(150)}\n## What does college cost, typically?\n\nWhat's the average cost of college?","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":38,"value":"// Find the average here\n\ndisplay(school)","pinned":true,"hidden":false,"mode":"ts","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":35,"value":"Is that number, alone, representative of what college costs? What other factors should we consider to paint a fuller picture?","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":45,"value":"We'll start by doing this for a single state.\n\nWrite a function called `stateAverage`.\n- It should take one parameter: a `string` representing the name of a state (e.g., `\"California\"`).\n- It should return an `object` representing the state's tuition averages. For example, here's what we want for California:\n\n```txt\n{\n state: \"California\",\n in_state: 14721.625984251968, // average in-state tuition\n out_of_state: 20166.937007874014, // average out-of-state tuition\n out_of_state_premium: 5445.3110236220455 // difference between the two averages\n}\n```","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":47,"value":"function stateAverage(stateName) {\n const schools = tuitionData.filter(d => d.state === stateName);\n\n const in_state = schools.reduce((sum, d) => sum + d.in_state_tuition, 0) / schools.length;\n const out_of_state = schools.reduce((sum, d) => sum + d.out_of_state_tuition, 0) / schools.length;\n\n return {\n state: stateName,\n in_state: in_state,\n out_of_state: out_of_state,\n out_of_state_premium: out_of_state - in_state\n };\n}","pinned":true,"hidden":false,"mode":"ts","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":49,"value":"$${vspace(200)}\nLet's use our function from above to produce a _new table_ (i.e. array of objects) that contains state averages. That is, we want to call our `stateAverage` function _for each state_. We can then use that new table in further analyses.\n\nHint: you can use the `states` array that I've prepared for this.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":53,"value":"states.map(state => stateAverage(state))","pinned":true,"hidden":false,"mode":"ts","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":54,"value":"With that done, which state has the biggest out of state premium?\n\nWe'll use a new function for this: [`d3.maxIndex`](https://d3js.org/d3-array/summarize#maxIndex). It gives back an index, which we can then use to find the whole object with the highest premium.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":55,"value":"states.map(state => stateAverage(state))[\n d3.maxIndex(states.map(state => stateAverage(state)), d => d.out_of_state_premium)\n]","pinned":true,"hidden":false,"mode":"ts","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":58,"value":"$${vspace(400)}\n## Salary potential\nWhat's the \"return on investment\"? In an ideal world, a college education is inexpensive and available to everyone who wants it, and your choice of whether or for what to attend college should be based solely on your academic interests.\n\nHowever, in our current world it can be very expensive. It's worth asking how much that investment in yourself tends to \"pay off\".\n\nFor that analysis, we'll bring in another dataset. (Shown in tabular form and array form below).","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":63,"value":"Inputs.table(incomeData, { rows: 6 })","pinned":false,"hidden":false,"mode":"ts","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":64,"value":"incomeData","pinned":true,"hidden":false,"mode":"ts","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":90,"value":"And here's the first tuition data set again.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":91,"value":"tuitionData","pinned":true,"hidden":false,"mode":"ts","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":66,"value":"callout(\"What do you notice about the income data? What's different between it and the tuition data?\", { type: \"ponder\" })","pinned":false,"hidden":false,"mode":"ts","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":99,"value":"\"The more income the more expensive tutuio will be\"","pinned":true,"hidden":false,"mode":"ts","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":67,"value":"$${vspace(200)}\n### Joining the datasets","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":65,"value":"$3c","pinned":false,"hidden":false,"mode":"html","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":92,"value":"vspace(75)","pinned":false,"hidden":false,"mode":"ts","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":59,"value":"// For each record in the incomeData (using map)...\nconst joined = incomeData.map((incomeRow) => {\n // Find the matching record in the tuitionData (where the school names match)\n const matchingRow = tuitionData.find((tuitionRow) => tuitionRow.name === incomeRow.name);\n return matchingRow !== undefined // If a match is found...\n ? { ...matchingRow, ...incomeRow } // return a joined record combining the two records\n : undefined; // otherwise return undefined\n })\n .filter((row) => row !== undefined); // Then filter out all undefined values","pinned":true,"hidden":false,"mode":"ts","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":70,"value":"With our combined dataset in hand, we can ask some questions that draw on information from _both_ sources.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":71,"value":"_What's the average early and mid-career pay for public vs. private schools?_","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":72,"value":"// your code here\ninterface SchoolPaySummary {\n type: string;\n avg_early_career: number;\n avg_mid_career: number;\n}\n\nconst publicSchools = joined.filter((d) => d.type === \"Public\");\nconst privateSchools = joined.filter((d) => d.type === \"Private\");\n\nconst schoolPayComparison: SchoolPaySummary[] = [\n {\n type: \"Public\",\n avg_early_career: d3.mean(publicSchools, (d) => d.early_career_pay) ?? 0,\n avg_mid_career: d3.mean(publicSchools, (d) => d.mid_career_pay) ?? 0\n },\n {\n type: \"Private\",\n avg_early_career: d3.mean(privateSchools, (d) => d.early_career_pay) ?? 0,\n avg_mid_career: d3.mean(privateSchools, (d) => d.mid_career_pay) ?? 0\n }\n];\n\nschoolPayComparison;\n\ndisplay(schoolPayComparison);","pinned":true,"hidden":false,"mode":"ts","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":73,"value":"_What's the mean early career pay for graduates from expensive vs. less expensive schools?_ To answer this, we need to decide what \"expensive\" means! Below, update the value of `costThreshold` to some meaningful value of your choosing. After all, this is your analysis.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":74,"value":"const costThreshold = 25000;","pinned":true,"hidden":false,"mode":"ts","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":76,"value":"In the following cells, find the mean `early_career_pay` for schools whose `in_state_tuition` is under that threshold, and for schools whose `in_state_tuition` is greater than or equal to that threshold.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":79,"value":"const lessExpensiveSchools = joined.filter((d) => d.in_state_tuition < costThreshold);\nconst expensiveSchools = joined.filter((d) => d.in_state_tuition >= costThreshold);\n\nconst meanEarlyPayLessExpensive = d3.mean(lessExpensiveSchools, (d) => d.early_career_pay);\nconst meanEarlyPayExpensive = d3.mean(expensiveSchools, (d) => d.early_career_pay);\n\ndisplay({\n costThreshold: costThreshold,\n lessExpensiveMeanEarlyPay: meanEarlyPayLessExpensive,\n expensiveMeanEarlyPay: meanEarlyPayExpensive\n});","pinned":true,"hidden":false,"mode":"ts","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":80,"value":"_Which schools have the worst return-on-cost?_\n\nIn this part, we're going to compute a `return_on_cost` measure for each school, computed as follows:\n\n`early_career_pay / in_state_tuition`\n\nProduce a new table that includes that information for each school.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":81,"value":"const withCostIndex = joined.map(d => ({\n ...d,\n return_on_cost: d.early_career_pay / d.in_state_tuition\n}));\n\ndisplay(withCostIndex);","pinned":true,"hidden":false,"mode":"ts","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":83,"value":"With that information, which schools have the worst return on cost? Sort the table by `return_on_cost` and inspect the top 10 rows.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":84,"value":"const worstSchools = d3.sort(withCostIndex, d => d.return_on_cost).slice(0, 10);\ndisplay(worstSchools)","pinned":true,"hidden":false,"mode":"ts","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":11,"value":"---","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":12,"value":"## Appendix","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":3,"value":"$3d","pinned":true,"hidden":false,"mode":"ts","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":51,"value":"const nonStates = {\n DC: \"Washington, DC\",\n PR: \"Puerto Rico\",\n GU: \"Guam\",\n VI: \"U.S. Virgin Islands\",\n AS: \"American Samoa\",\n MP: \"Northern Mariana Islands\",\n FM: \"Federated States of Micronesia\",\n MH: \"Marshall Islands\",\n PW: \"Palau\"\n}","pinned":true,"hidden":false,"mode":"ts","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":14,"value":"import { utils, stylesheet, vspace, callout } from 'observable:@ayaankazerouni/utils'","pinned":true,"hidden":false,"mode":"ts","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":15,"value":"","pinned":false,"hidden":false,"mode":"html","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"}],"files":"$W3e","stdlib":"2"}} 33:null