Discover and read the best of Twitter Threads about #dataviz

Most recents (24)

No because it is not at all true. If the UK were in a customs union with the EU, nothing the EU negotiated with the US with regard to public services would have any impact on the UK because the UK would not be party to the EU’s free trade agreement with the US.
Even if the UK is in a customs union with the EU, the UK still needs to negotiate its own free trade agreements. The constraint a customs union placed on the UK’s ability to do so is that its offer on tariff concessions must be the same as the EU. Everything else up to UK.
This stuff is complicated, I get it. But everyone on all sides of the debate must do better.
Read 4 tweets
New project:

A “Bar Chart Race” animation showing the changing ranks of the 10 biggest cities in the world since 1500.

Fascinating to watch giant cities vanish after falling in conquests, and amazing that three UK cities were in the top 8 in the late 1800s.
• Full code for the animation here on @observablehq…
• I’ve tried to build this in a fairly reproducible way, such that you give it a dataset containing entity, year, value, and it does the rest
• Feedback welcome!
• Pre-1900 I’m using @nasaearthdata’s “Historical Urban Population, 3700 BC  to  2000”…
• Post-1900 it’s that merged with data from the UN and Demographia on urban agglomerations…
Read 7 tweets
[football #dataviz thread]
La 23ème journée de @Ligue1Conforama se terminait sur un choc entre @OL vs @PSG_inside hier soir pour la première défaite parisienne de la saison.
Retour en visuels sur ce match ⬇️
Bien que ce soit plus marqué côté parisien, les deux équipes ont penché sur la gauche dans leur animation offensive. Depay pour Lyon et MBappé pour Paris étant les joueurs recherchés.
Traoré peu touché et Cavani trouvé très bas, en général dos au but.
#xGtimeline : Paris a vite marqué par #DiMaria mais a ensuite été incapable de tirer à nouveau avant que Lyon n'égalise par @MDembele_10. Lyon a pris le jeu à son compte et profité d'un penalty pour passer devant.
Le modèle #xG donne Lyon vainqueur 72% du temps sur ce match.
Read 9 tweets
Hello all #dataviz fanatics! It’s time to kick off our #datavizbook #epibookclub for @kjhealy’s new book, Data Visualization.

Remember, if your book hasn’t arrived yet or you’re waiting on the library, you can read it here:

#epitwitter #datascience
This week, we’re reading the Preface and Chapter 1: Look at Data.

I’ll post some highlights from each and then I hope you’ll chime in with your thoughts, comments, questions, etc.
In the Preface we get a nice overview of the goal of this book: the why and how of good data visualization for beginners, including practical applications in R with ggplot2.

The book doesn’t assume any prior knowledge of R, & covers everything #dataviz from scatterplots to maps.
Read 18 tweets
This morning I attacked my problem of showing hierarchical clusters without just making a dendrogram tree (left pic). Lots of plots were made in through the course of the day to get to the plot on the right, so I decided to show the whole process #dataviz 1/5
First approach was putting the unclustered graph into Large Graph Layout. I have to consult my own blogpost to run the program, so I guess write for yourself The graph is too dense for even the magic bullet of LGL to get good separation w/o clustering 2/5
Next series of plots in R with ggraph, still using unclustered graph. The graph is too dense to all of these, but they look cool. 3/5
Read 7 tweets

I’m feeling festive! I want to spread the cheer this holiday season by giving the #GiftOfCode for making beautiful figures! #EpiTwitter #StatsTwitter

When I was starting out, I remember how it would take HOURS to get my figures looking just right.

Nothing was more valuable than example code for learning different #DataViz options 🎁
First up:

These options in #stata for making this graph presentation-ready!

adjustrcspline, link(logit) scheme(vg_palec) ///
ylabel(, nogrid angle(horizontal)) ///
xtitle("X (Units)", size(medium)) ytitle("Outcome Risk (%)", size(medium)) ///
Read 7 tweets
Não deu pra ir no #codabr18? Foi, mas queria mesmo era se clonar pra ver as muitas atividades simultâneas? A gente reuniu quase 40 apresentações e recursos didáticos usados nas mesas, bootcamps e workshops! Conhecimento bom é conhecimento aberto! #ddj…
Vamos revisitar aos poucos as apresentações do #CodaBr18 :

Na abertura, o @albertocairo abordou a democratização da visualização de dados, falando de sua busca para que esta prática se torne uma linguagem universal 🌐…
@viegasf falou de suas pesquisas sobre inteligência artificial, #dataviz e inovação no Google. Aqui, você confere a oficina que ela deu sobre Interpretação e Fairness em Machine Learning
Read 37 tweets
✨🧠 The ecosystem that has grown up around @TensorFlow in the last few years blows my mind. There's just so much functionality, compared to some of the other, newer frameworks.

👉Consider this an ever-expanding thread for me to take notes + wrap my brain around products. Ready?
1) @TensorFlow Extended (TFX)

It's no secret that I 💕 #TFX and all of its tooling for deploying machine learning models into production. If you care about keeping your models up-to-date and monitoring them, you should check out the product + its paper.
2) @TensorFlow Hub

If you want to train your model on a small data set, or improve generalization, you'll need to use something called transfer learning. #TFHub modules make it easy—and are available in an #OSS marketplace:

Read 40 tweets
MEL Technology Director Chris Gegenheimer discusses how to combat bad data viz by “broadening the base” ie building internal capacity to create impactful visualizations. Specifically, how did @Chemonics do this? #Eval18 @aeaweb
Cue “12 Days of Data” - an opportunity for Chemonics employees in the home and field offices to create viz out of their project or department’s data.
It doesn’t have to be 12 or days, but it should give employees an opportunity to tap into their inner data nerd and learn best practices and tips to better their #dataviz
Read 4 tweets
All available #gab posts have been indexed. Dozens of millions of posts to analyze. You can now search and sort by various fields such as score, created_utc (time), etc.

#dataviz #datascience #bigdata
The top scoring Gab post mentioning "jews":…

"For all of you who are new to Gab, don't worry about the racism. I know it can be a little weird at first, but pretty soon you're going to realize that racism is normal and the only reason you haven't ...
... seen it before is because the Jews were censoring it."
Read 5 tweets
Glad to be back at @DesignUpConf, this year as part of the organizing team, doing graphic recording and helping with the scholarship program. 🙌
Here's a thread with my #sketchnotes, photos & reflections from this year's edition: #DUp18!
Yesterday was dedicated to masterclasses, and in the morning, I got a chance to listen to @vlh highlight how animation can be a part of design systems, explain easing curves & walk us through an inspiring set of popular design systems!
(2/n) #DUp18
Next half was a masterclass on using sketching in the design process by @bencrothers (author of @prestosketching). It was great to watch him distill sketching into smaller pieces to learn through inspiring examples!
Here are my #sketchnotes from his session!
(3/n) #DUp18
Read 32 tweets
Hypothesis: university prestige shapes the flow of scientists, which determines which scientific ideas get worked on, where. In new work in @epj_ds, we show how this process can create an “epistemic advantage”, w/ @alliecmorgan D. Economou & @samfway… 1/5
Prestige predicts who hires whose graduates as faculty (…), and they carry scientific ideas with them. Via simulation, we show that ideas born at elite universities can spread exponentially further than equally good ideas from less elite places 2/5
We also tested whether hiring has influenced the spread of 5 real scientific ideas. Here's the spread of “topic modeling” (1992-2011), which we traced through the literature via expert-curated keywords, including LDA, PLSA & PLSI (#dataviz here by the fantastic @mckweller) 3/5
Read 5 tweets
OK my @medium account got "caught in the spam filter" & has been restored so let me try this #thread again. I've been working for several months on a series of blogs explaining trolling & botting tactics used by 4chan during the election. #ContentWarning:…
Several months ago @elimisteve from @PursuanceProj found a series of pastebins and sent them to me. 4chan trolls studied learned graphic design software to make memes, memetic warfare and botting to troll the election.…
The 1st part is an 8chan thread by someone who claimed to have worked in the marketing & advertising industry. The explain various components of effective graphic design & instructions for /pol/ to “normalize” their message to blend in with the normies.…
Read 36 tweets
Morning, #dataviz folks! Here comes a thread on the "streamgraph" chart type used in the @FinancialTimes graphic on Premier League shirt sponsors.

The research paper by @leeb & @wattenberg that introduced streamgraphs to the world is one of the best dataviz papers I've ever read
1/16 In November 2008, @leeb & @wattenberg published "Stacked Graphs – Geometry & Aesthetics", a wonderfully comprehensive discussion of the trade-offs between aesthetics & geometry in stacked graphs…
2/ I've been nerding out on key insights & other highlights. Here goes:

Intro: the paper followed 2 early examples of stacked, meandering graphics
- "Listening Histories": last fm listening data (pic 1)
- "The ebb and flow of movies" by @nytgraphics on box office takings (pic 2)
Read 17 tweets
I've been working on two big projects for several months, one is finally finished tonight. #QAnon network visualizations:…
#QAnon trends appear to be connected to Twitter rooms, high-volume accounts and a conservative political marketing firm called AppSame.

This is a user-to-user @gephi graph of 51,437 #QAnon tweets  from May 3 to May 11… #dataviz
I constantly find high-volume accounts in certain hashtags and they are present in #QAnon networks. These high-volume accounts are hubs in Twitter networks. Here’s what some of the high-volume hubs look like in 8 days of #QAnon tweets from May 3 to May 11…
Read 22 tweets
So it’s a Saturday afternoon, it’s 20+ degrees outside – you know what you should do?

That’s right, read a thread about GOVERNMENT ORGANOGRAMS, a year on from our @instituteforgov #IfGhackday #opendata
Organograms aren’t most obvious data thing to get pulses racing. Hardly AI, blockchain (#buzzword), Citymapper etc.

Part of Cameron’s May 2010 pledges ( to open up data, they include names, salaries, professions, jobs of civil servants & units w/in depts
Maude called them ‘the most comprehensive organisation charts of the UK civil service ever released online’ Not the flashiest or sexiest datasets, but mgmt info vital both for effectiveness (understanding your workforce) and accountability.

Read 18 tweets
Yo, here's my nü #dataviz workflow:

1. Visidata for data exploration & export
2. @observablehq & d3.js to build graphic pieces
3. Export d3.js graphic as SVG from notebook
4. Finish graphic in Adobe Illustrator
5. Run ai2html to publish on the web

Interested? Keep reading 👇🏿
👉🏿 Visidata is a command-line tool for manipulating data I first learned about it from @jsvine at #NICAR18. It's a great program for working with data and can work with a ton of formats.
👉🏿 @observablehq let's you create interactive notebooks with data and code Rather than setting up a local build development for your charts, you can do it all from the browser. You can also share your work with your colleagues. Great for collaboration.
Read 8 tweets
Anyone interested in mapping the linguistic diversity of Indian states with the help of this data?…

#dataviz #Datavisualization #data #india #OpenData
Maybe, we can compare that with economic indicators and see if there is any correlation between diversity and development.
Read 4 tweets
⬇️ Thread of thoughts on this topic ⬇️

I've taught #D3js to nearly 300 faculty, staff, and students at primarily the grad/PhD level across various workshops and bootcamps.

Some key reasons behind why D3 is hard, I'll outline below (in case anyone is learning or curious)
While you DO need to understand empathy, design, color perception, visual cognition, story-telling, geometric thinking, graphical conventions, basic statistics, data structures, linear/spatial algebra, and trigonometry to do VISUALIZATION well, D3 makes all of this *EVEN HARDER*
Why? Because the CORE of D3 is in its name: 'Data Driven Documents.' Data-driven is one thing, but the 'Documents' part refers to the DOM, which is a broad term referring to the *stuff* that makes up the web:
& more - all at once
Read 11 tweets
Now comes the hard part of being an academic #opensource developer moving into industry. 😢 I need volunteers to take over some of my #rstats packages. I'm hoping to retain some but also want to pass on a few.

If you're interested, please reach out on Github about any of...
{csvy} is a package for reading and writing metadata-enhanced CSV files that include a YAML header.

The format:

The package: (on CRAN but needs some updates to match the current csvy specification).
{colourlovers} is an API client for

The package:… (on CRAN but could use an XML -> xml2 conversion and a refresh to make sure it's still up to date).
Read 13 tweets
Before you RT this catchy infographic, a thread--
#RoadSafety #VisionZero #dataviz
Infographics work. I clicked. My first response: Catchy title but the piece provides zero basis for the statement. Data-driven safety improvements are essential--so where's the data? This could have been so much more. #RoadSafety #visionzero
Dug a bit. Googled law firm credited on map. Got… telling me it's @NHTSA "accident" (sic) data for "automobiles/pedestrians". Where are bicycles/motorcycles? More Google. #CrashNotAccident #RoadSafety #VisionZero
Read 19 tweets
A J-14 du #hackinghealth, quels défi de #santé allez-vous relever ? Passage en revue de notre sparkboard 2017 :
Familien - comment mieux accompagner les familles lors d'une #hospitalisation ?…
Un outil numérique serait-il pertinent pour maintenir le lien entre enfant et patient même si les visites sont impossibles ou rares ?
Read 93 tweets
22.9.2017: <1/2 of mainland Americans know Puerto Ricans have U.S. citizenship. #Hurricane #PuertoRicoSeLevanta…
12.9.2017: "It is American land. Has been for 100 years." #Hurricane #USVirginIslands #Maria #Irma
Read 56 tweets
#Hurricane #Irma thread. Irma is category 5 - highest # on Saffir–Simpson hurricane wind scale.
A few ways to visualize the Saffir-Simpson hurricane wind scale #Hurricane #Irma
#Hurricane #Irma expected to first hit landfall in Anguilla / Leeward Islands.…
Read 28 tweets

Related hashtags

Did Thread Reader help you today?

Support us! We are indie developers!

This site is made by just three indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3.00/month or $30.00/year) and get exclusive features!

Become Premium

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal Become our Patreon

Thank you for your support!