Topic modeling for Spice Girls lyrics
30:29
Пікірлер
@MattBirch
@MattBirch 9 күн бұрын
I have been using the tidyverse and came here for tidymodels. Then 6 minutes in I learn about fct_reorder(). That is awesome! I always order mine manually before the graph, but this is so much cleaner!
@umber_wall
@umber_wall 9 күн бұрын
Thank you, learned so much!
@AaonLee
@AaonLee 9 күн бұрын
can it use the “dev containers” remote extension like vscode?
@JuliaSilge
@JuliaSilge 9 күн бұрын
The VS Code implementation of this is proprietary so we can't use it directly, but we have an issue here tracking interest in this feature: github.com/posit-dev/positron/issues/4691
@juriand
@juriand 10 күн бұрын
I learned more from this video in 30 minutes than hours upon hours of conversing with ChatGPT. Thank you.
@sarpdoracebeci
@sarpdoracebeci 16 күн бұрын
dear julia, I came across with the new ide, through your video yesterday. I should say I am fascinated by the work you guys did. I hope it can be sustainable for some time. thanks!
@benardmugisha9751
@benardmugisha9751 Ай бұрын
I looooveeeee this.
@benardmugisha9751
@benardmugisha9751 Ай бұрын
Hello Julia. I love your experience in Data science. I'm an agriculturalist, whose first data analysis software is R and RStudio is the best IDE i have ever used. I look forward to keeping updated on anything that has to do with R and RStudio. Thanks for the work you are doing. I love your voice and looks too.
@pattheitguy
@pattheitguy Ай бұрын
How is this not the most popular YT channel?
@a-sadeghi-md
@a-sadeghi-md Ай бұрын
I didn't get a response on the other video so here is my comment😁: Your video casts are great. I even got a job with the things I learned from you! Thank you BIG TIME! I wish there was a way to give back to those who teach us these amazing skills. I noticed that you haven't been doing more videos for some time. Please do more.
@djangoworldwide7925
@djangoworldwide7925 Ай бұрын
Too bad copilot can't work with it. It's the main thing that keeps me from using it, especially when I work with python, which is not my main language. Please implement CoPilot :)
@MannyBernabe
@MannyBernabe Ай бұрын
What is the upgrade versus Rstudio? E.g., why is this better than Rstudio?
@JuliaSilge
@JuliaSilge Ай бұрын
You may be interested in reading our FAQs: positron.posit.co/faqs.html
@dinohadjiyannis3225
@dinohadjiyannis3225 Ай бұрын
this is fantastic.. A small note is to maybe give the user the ability to choose the colors for the distributions on the left, we might get tired of blue. I'm sure color option will be there since its in all IDEs
@jalepezo
@jalepezo Ай бұрын
Hi, statistics major here. Is positron going to replace R studio? If so, when it is going to be ready? Does it also have a studen free version for single user? Thank u very much for your work. Statistics student from Peru
@JuliaSilge
@JuliaSilge Ай бұрын
The desktop version is in fact free, and always will be. You can read more about the license here: github.com/posit-dev/positron/wiki/Licensing In terms of the relationship with RStudio, you may want to check out our FAQs: github.com/posit-dev/positron/wiki/Frequently-Asked-Questions
@brittnyfreeman3650
@brittnyfreeman3650 Ай бұрын
What does this mean for Rstudio? Is it going to be depreciated soon?
@JuliaSilge
@JuliaSilge Ай бұрын
You can read more about that in our FAQs: github.com/posit-dev/positron/wiki/Frequently-Asked-Questions
@nicholasgrant1111
@nicholasgrant1111 Ай бұрын
The plot pop-out feature is not visible in the latest version (2024.11.0-49). How do I enable the pop-out feature?
@JuliaSilge
@JuliaSilge Ай бұрын
Ah, apologies, yep! You need to find "Positron Plots In Editor Tab" in the settings and turn it on. It is currently considered experimental!
@nicholasgrant1111
@nicholasgrant1111 Ай бұрын
@@JuliaSilge Thank you!
@oldrichspacil2299
@oldrichspacil2299 Ай бұрын
@@JuliaSilge I was wondering the same as Nicholas. I am using Positron on Windows and I don't see this options in Settings. Is it possible this experimental plot pop-up feature is not yet available on the Windows build of Positron at all yet?
@JuliaSilge
@JuliaSilge Ай бұрын
@@oldrichspacil2299 I just checked the latest build of Positron (2024.11.0-49) on Windows, and I do see the setting. It is called "Positron Plots In Editor Tab" and you will need to check to opt in to the experimental behavior.
@oldrichspacil2299
@oldrichspacil2299 Ай бұрын
@@JuliaSilge You're right, of course. I had two versions of Positron installed and stupidly I was somehow using the older one! 😕 Thank you so much!
@hnagaty
@hnagaty 2 ай бұрын
Welcome back. It looks like Positron will be the "go to" and preferred IDE for data scientists. As a side question, why are you not using a dark theme :)
@JoeFaith-i6m
@JoeFaith-i6m 2 ай бұрын
This was great! Thanks for sharing. I'm very excited to try it out!
@tchamoupotindji
@tchamoupotindji 2 ай бұрын
Great video, i have a question, what are the settings to get quarto working on positron
@JuliaSilge
@JuliaSilge 2 ай бұрын
Both Quarto and the Quarto VS Code extension are bundled in Positron, so we expect Quarto to work out of the box. Please open a GH discussion if you run into problems!
@yuzaR-Data-Science
@yuzaR-Data-Science 2 ай бұрын
welcome back :) please, don't leave us for long time ;)
@TyrannosaurusSnacks
@TyrannosaurusSnacks 2 ай бұрын
Ah nice, I've installed positron, but was a bit overwhelmed. Good so see a hands on video about it. Thanks!
@HaiLeQuang
@HaiLeQuang 2 ай бұрын
Is there a timeline when it will go official, no beta?
@JuliaSilge
@JuliaSilge 2 ай бұрын
No official commitment on a timeline, but Positron will be on Posit Workbench in preview before the end of this year. I currently expect we'll move out of beta sometime next year.
@HaiLeQuang
@HaiLeQuang 2 ай бұрын
Welcome back, my favourite screencast vlogger
@brandonmartinez8558
@brandonmartinez8558 2 ай бұрын
@Julia Silge , Is it possible to work seamlessly between R and Python within the same document in Quarto without having to reload the dataset in different chunks? Can I achieve this without using reticulate, especially when working in the Poistron IDE? I'm curious if there's a way to manipulate a dataset in R and then continue working with it in Python without needing to reload it. ?
@JuliaSilge
@JuliaSilge 2 ай бұрын
You'll need to use reticulate for an approach like this. We did recently add some pretty nice support for reticulate in Positron, which you might want to check out: github.com/posit-dev/positron/discussions/3920#discussioncomment-10808127
@rayflyers
@rayflyers 2 ай бұрын
It looks pretty impressive, especially the summary panel!
@renzo.ruesta
@renzo.ruesta 2 ай бұрын
It seems that there is a lot of work behind it, congratulations and good to have you back, you really taught us a lot with Rstudio; It will be difficult to leave it. 😁
@patolobos8266
@patolobos8266 2 ай бұрын
Happy to see you back Julia 😊😊😊😊😊😊
@CaribouDataScience
@CaribouDataScience 2 ай бұрын
Yeah, don't be a stranger. 😊
@데이터의길
@데이터의길 2 ай бұрын
자주 올려 주세요. 배울 것이 참 많습니다. ^^
@flonga2302
@flonga2302 2 ай бұрын
Happy to have you back!
@mike8delta
@mike8delta 2 ай бұрын
Will there be a server version of Positron? For example, the RStudio Server version is great for working remotely and accessing powerful CPU and GPU resources from a laptop.
@JuliaSilge
@JuliaSilge 2 ай бұрын
Not a server version, but instead remote SSH sessions. You can read a bit more here: github.com/posit-dev/positron/discussions/4936
@respanol1970
@respanol1970 2 ай бұрын
Nice, thax Julia
@blaisepascal3905
@blaisepascal3905 2 ай бұрын
The View() function in positron look really nice. Is there a future project to make the results appear just bellow a chunck like in RStudio?
@JuliaSilge
@JuliaSilge 2 ай бұрын
Currently, that type of behavior is only supported in `.ipynb` notebooks, not for Quarto files.
@blaisepascal3905
@blaisepascal3905 2 ай бұрын
@@JuliaSilge Thank you for your answer!
@Kasenkow
@Kasenkow 2 ай бұрын
Why does Positron look so much like VS Code?
@JuliaSilge
@JuliaSilge 2 ай бұрын
Because it is a fork of Code OSS! You can read more here and in our wiki: github.com/posit-dev/positron?tab=readme-ov-file#get-started-using-positron
@sr4823
@sr4823 2 ай бұрын
I was worried that you were done with the screencasts. Glad to see you're back. 😊
@stefanodidonato1284
@stefanodidonato1284 2 ай бұрын
Literally, made my day!!
@BFGHDF
@BFGHDF 2 ай бұрын
Does python cell blocks work in Positron?
@JuliaSilge
@JuliaSilge 2 ай бұрын
Yep, sure does! If you run into problems getting started with it, please let us know.
@atiqullah2396
@atiqullah2396 2 ай бұрын
Nice to see you madam. I am following you book "text as data" and "supervised machine learning ....." for my thesis data . Love your methods of NLP and topic modeling ...
@learning_boson
@learning_boson 2 ай бұрын
Thanks for the video, Julia! Can you please list the most prominent features of Positron which are not available in RStudio? Which ones are the most important for you?
@JuliaSilge
@JuliaSilge 2 ай бұрын
You can read a bit here about who Positron may be a good fit for, and for who it may not be: github.com/posit-dev/positron/wiki#is-positron-for-me
@a-sadeghi-md
@a-sadeghi-md 2 ай бұрын
Your video casts are great. I even got a job with the things I learned from you! Thank you BIG TIME! I wish there was a way to give back to those who teach us these amazing skills. I noticed that you haven't been doing more videos for some time. Please do more.
@nikolaostziokas6847
@nikolaostziokas6847 3 ай бұрын
Great work, please keep it up! As an idea for another video, it would be nice to use the package bonsai to train a lightgbm regression model and perhaps show the differences against an XGB and a RF model.
@enicay7562
@enicay7562 3 ай бұрын
Thank you
@YannC-p1q
@YannC-p1q 4 ай бұрын
Would be amazing if you do a video using nested data (instead of having a nominal variable, nest it and generate a model for each of the levels for example), also using the map_workflow etc.. great as always!
@rafaelcallejo8367
@rafaelcallejo8367 4 ай бұрын
buenos días, sus videos son excelentes, solo pedirle para futuros videos poder enfocar mas la cámara al código ya que se ve muy pequeño, disculpas por la sugerencia.
@dinohadjiyannis3225
@dinohadjiyannis3225 6 ай бұрын
Julia, if I'm using a topic model on KZbin comments to determine which video best explains topic modeling, how can I decide if your video or another video should be suggested? I see the model ranks comments with "gamma." If each comment is linked to a video ID, and based on gamma some or all comments rank highly in a hypothetical "topic modeling" topic, what then ? can we infer that your video is the best ?
@JuliaSilge
@JuliaSilge 6 ай бұрын
HAHA I can't tell if this is serious or not 🙈 In case it is, I will say that since topic modeling is unsupervised ML, it can't be used in a straightforward way to evaluate better/worse (you are not predicting a label). Instead, like you say, you could compare the relative proportion of certain topics (like, say, a topic that seems to be mostly about topic modeling) in one video's comments compared to others, and make an evaluation of videos based on that.
@dinohadjiyannis3225
@dinohadjiyannis3225 5 ай бұрын
​@@JuliaSilge If I can "cluster" comments related to topic modeling and find that the most relevant ones are linked to your video ID (based on beta, which will give you the top word probabilities), your video will appear with the highest relevance to that topic (based on gamma). This means your video is the most representative of that specific topic. But wait.. Then, if I manually compare, say, the top 10 most relevant videos and see that your video (which is at the top) also has a lot of likes, comments, engagement, and perhaps a great sentiment (after computing it) compared to the other 9, I can conclude that your video is the "best" and would recommend it. Does this make sense, or am I misinterpreting the gamma/beta. ***Assume I have concatenated all comments into 1 corpora. Each corpora is linked to a video ID.
@JuliaSilge
@JuliaSilge 5 ай бұрын
@@dinohadjiyannis3225 I think that makes sense! Sounds to me like you are interpreting correctly. 👍
@dinohadjiyannis3225
@dinohadjiyannis3225 5 ай бұрын
@@JuliaSilge A big thanks to you for replying, given that this video is 6 years old. 🥇
@rosiedavies7708
@rosiedavies7708 6 ай бұрын
does this work in the same way with regression problems?
@rosiedavies7708
@rosiedavies7708 6 ай бұрын
also thanks for this video, its very helpful and clear
@JuliaSilge
@JuliaSilge 6 ай бұрын
Yep, you would use `set_mode("regression")` in that case
@mxm8900
@mxm8900 6 ай бұрын
Wow great video. I have nothing to do with text analysis, but I still watched the whole video
@smomar
@smomar 6 ай бұрын
All Hail the Dino! Now quickly get it some food, or else ... Thanks for the video. It was very informative.
@andreacierno4642
@andreacierno4642 7 ай бұрын
Thank you Julia. Can this work if my version of 'type' has 5-8 categories? Where the final output is More like 'X' where 'X' is each category label? Is there a way to get more words in each prediction fold? So in the final output it could look like 3 words for each more like? Thank you, again.
@JuliaSilge
@JuliaSilge 7 ай бұрын
I recommend that you check out this chapter of my book with Emil Hvitfeldt: smltar.com/mlclassification#mlmulticlass
@andreacierno4642
@andreacierno4642 7 ай бұрын
@@JuliaSilge Will do and thank you.
@emredunder9108
@emredunder9108 7 ай бұрын
You are the queen of data analysis. Thanks for the video!
@kevingiang
@kevingiang 7 ай бұрын
Hi @JuliaSilge - thanks for your wonderful and helpful videos. I am trying to replicate your code with my own dataset and I am getting the following error when trying to initiate the tuning of the model: > xgb_rs <- + tune_race_anova( + object = xgb_wf, + resamples = dens_folds, + grid = 15, + control = control_race(verbose_elim = TRUE) + ) ℹ Evaluating against the initial 3 burn-in resamples. i Creating pre-processing data to finalize unknown parameter: mtry Error in `tune::tune_grid()`: ! Package install is required for xgboost. Run `rlang::last_trace()` to see where the error occurred. It says that a package install is required. Any idea about what package may be missing? I installed the 'tune' package and still gives me the same error. Any thoughts are appreciated. Thanks, Kevin
@JuliaSilge
@JuliaSilge 7 ай бұрын
It's the xgboost package that needs to be installed: CRAN.R-project.org/package=xgboost
@kevingiang
@kevingiang 7 ай бұрын
@@JuliaSilge I just figured it out... thanks much for answering back! You rock!
@gsonbiswas9765
@gsonbiswas9765 7 ай бұрын
Nice explanation. You could have used the searchK() function to show us how to select the range for K.