Patrick Perry (@ptrckprry) profile picture

Statistician

Joined October 2013
Replying to @ssfarouk
Opioid is the inclusive umbrella term for drugs that bind the opioid receptor (including synthetics like fentanyl and dilaudid). Opiates are the opium poppy derived subset (incl morphine, codeine). If you say "opioid" you'll always be correct. #NephMadness
1
4
1
11
Patrick Perry retweeted
On Hamilton's birthday, listen to some Hamilton, check out @ptrckprry corpus package #Rstats. cran.r-project.org/web/packa… containing Federalist Papers - a case of disputed authorship. Apropos, cool data set for a #tidytuesday? #textanalysis
1
1
8
Patrick Perry retweeted
The Federalist Papers, a case of disputed authorship, is a fun starting point to think about what preprocessing might shed the most light on authorship. Ready to use in @ptrckprry R "corpus" package. evangelinereynolds.netlify.c…
I've been seeing a lot of Hot Takes on authorship identification today from very smart, well-meaning folks that aren't very well informed about the field. 1) Topic models do not tell you about authorship 2) Stop words are generally the best features (Burrows 1987)
2
3
Politicians are more boring than they used to be, right? NOPE! #MPSA2018 ppr w @ptrckprry models "interestingness" of UK backbench MPs post-1935 by looking at how distinctive their word use is: nyu.edu/projects/spirling/do…. Average boringness is constant! BUT.. (1/n)
1
2
2
8
Patrick Perry retweeted
A framework for the economic study of the technological elements of machine-learning-driven artificial intelligence, from @MattTaddy nber.org/papers/w24301
13
29
Patrick Perry retweeted
"Scaling Text with the Class Affinity Model", new paper with @ptrckprry arxiv.org/abs/1710.08963. It's Wordscores 2017. #textasdata #nlp
1
4
New vers of STM pkg w @mollyeroberts @b_m_stewart, spectral speed, heldout predict, interop w other pkgs. goo.gl/JVXXhw #rstats
2
13
1
22
Patrick Perry retweeted
Practical Data Science for Stats A @PeerJPreprints Collection, edited w/@hadleywickham. https://teapawt.net/t.co/AHzSMBe0M8 #rstats
6
187
36
408
Patrick Perry retweeted
Wow , this thread is worth your time teapawt.net/conspirator0/status/90…
Replying to @conspirator0
A pattern you may have noticed: many bot and troll accounts have usernames that end in 8 random digits.
189
7,776
462
11,610
Patrick Perry retweeted
If you work in data analysis, this could be the most useful 30m video on data communication you watch this year youtube.com/watch?v=fSgEeI2X…
2
44
1
167
Quick reminder that the paper deadline for the 2017 "text as data" conference is *July 31*. Get your proposals in! q-aps.princeton.edu/news/tex…
1
32
2
34
Patrick Perry retweeted
Nice contribution by @ptrckprry on speech modelling at #tbd3
1
1
Patrick Perry retweeted
Promising new package 'corpus' by @ptrckprry reads NDJSON 7x faster than jsonlite (but manipulation is a bit slower) github.com/jeroen/ndjson-ben…
1
10
1
33
Patrick Perry retweeted
I worry about over-interpreting t-SNE plots. Here is its behavior on 1 dimensional data gist.github.com/mikelove/74b…
7
108
1
200
Patrick Perry retweeted
Seems like 2017 will go down as the year we realize we need to incorporate a little more uncertainty in our predictions
8
163
17
335
Patrick Perry retweeted
If you have a common last name & don't clean up your google scholar profile, you'll get a crazy # of citations/year scholar.google.com/citations…
3
5
A photo to visualize my daughter's color preference in drawings: warmer colors over cooler colors.
4
5
Pretty much the best Venn diagram ever. |
34
1,257
861