The gap between 0 and 1? It's there because there are no values that fall into that range. Each of the bins contains values starting at the left endpoint, so the number 1 falls into the bin from 1 to 3. Good luck on your test!

Most welcome! Glad it helped 😄

Oh no! It didn’t click? One other thing to keep in mind is that I described precision and recall for the apple class. We could also define precision and recall for the orange class. Any other questions?

ALL-SI-ome! 😁

So glad you enjoyed it! Yes, hopefully some new videos soon!

So glad to hear that! 😁

You can reach out to me via my company email address: hello at drkimdata dot com 👍

Thanks for the encouragement! 😁

!ls for Mac and Linux, !dir for Windows 👍

Thank you so much! Glad you enjoyed it 😀

Thanks! 🙏

Hello! 👋🏼 So glad you enjoyed it!

​@@KimberlyFessel Yeah, I'm coding some lines to help one of my teachers at the university. He has to use several data about economics (he has an economy PhD), like the exchange rate ARS-USD, investment rate, etc. And is so useful to automatize the data collecting ,as much as putting this data in graphs. I'll keep watching your videos

@@ZerokCDM Interesting! Yes, automation is the way to go, and I always love a good graph! Thanks for watching, and feel free to reach out with questions along the way. Cheers! 😄

Such a great question! 🙌 With a binary problem like this one where there are only two classes to predict, you will use precision/recall for just the minority class (the side with the fewest observations) to report the success of the model. For a multiclass problem where there are 3 or more types of outcomes, you would typically choose an aggregation strategy (micro-, macro-, or weighted averaging). And there's an article all about multiclass metrics in my new Classification Metrics course if you're interested (kimberly-s-site-0700.thinkific.com/courses/classification-metrics)! 👍

Unfortunately, no, not with Seaborn. The KDE gives you a numerical estimation of the PDF but not an analytic expression. The theory is based on adding up Gaussians, however. So I suppose if you worked out the bandwidth, you could have an analytical expression with one Gaussian term for each datapoint, given that you use a Gaussian kernel.

@@KimberlyFessel thank you!

Hi! Thanks so much! Glad you like them 😁

Thanks, Tom! Glad you’re enjoying the series. I don’t have a video on loc and iloc yet, but that’s a great idea. The main difference is that loc references the index names and iloc references the integer positions. I’ll consider making this video soon!

@@KimberlyFessel Hi Kimberly, That would be great. Thank you. Just finished your Panda's tips course (for the second time. SUPERB. Really enjoyed it. I will go again, no doubt, just to get the code under my belt.🤔). On to Seaborn now. I have watched quite a few of these. I do wonder, given the number of videos you have on Seaborn, which ones you would consider most important from a data analysis perspective. Also, did i see on your githubpage that you had a similar tips couse for python? Apologies for all the questions. I am starting my DA course in September, so i am trying to cover as much ground as i can Pandas, Matplotlib & Seaborn wise before it starts. Thanks again. Tom

@tombschannel Hey Tom - thanks for your message and so glad you're finding value in my videos. For Seaborn, my top go-to visuals are histplot, scatterplot, pairplot, and heatmap. I find I can get quite a lot of great EDA done with those visuals. I might also throw KDEplot and regplot if I get a couple of extra picks. I don't have many videos about Python (yet!), though that's always a good topic. For example, knowing the difference between a property, method, and function seems to escape a lot of people despite how important that is for understanding Python code. Best of luck on your DA course! Kim

Thanks so much! My pleasure!

You got it! The tricky bit comes when trying to combine precision and recall for multiclass into one number. Lots of options!

Most welcome! Glad you found it helpful!

Oh how I wish I knew Spanish! Glad to hear you like the videos though!

@@KimberlyFessel Thank you. Use an AI translator to translate your videos from English to Spanish.

Most welcome! 😁

Oh noes! Did plt.savefig() itself not work or was bbox_inches = 'tight' the culprit? If the later, you might try removing that and added the line, plt.tight_layout() just before your plt.savefig() line. That's a nice alternative that I use often.

So glad to hear that! I remember making that animation and thinking, “yeah, this makes total sense!” 😁

Hi there - say you have a dataframe called df and the column with those values is called "col", you could probably do something like this: df = df[df["col"] != "[x]"] That overwrites your current dataframe with a dataframe that excludes rows with "[x]" values in the "col" column.

Glad to hear it was useful! Cheers 😁

Most welcome! 👍

Right on! Glad you liked it 😊

You're so welcome! 😃

Awesome! Yes, I find both the strip plot and the swarm plot to be super useful for getting a sense of the distribution of points. And they look nice too 😊

Thanks! Glad you liked it! 😁

You are most welcome - glad it helped!

So glad to hear you found my videos valuable! Wishing you all the best on your wind data project 😀

Haha - glad you liked the video. The table is supposed to be “distressed.” But it looked even worse after my duct tape modeling 😆

You’re very welcome! Thanks for the support - cheers! 😀

Most welcome - cheers! 😀

I do love a good talking head segment! 😆

Of course! Glad you liked it 😁

Most welcome! So happy you’re enjoying my content 😀

Excellent! Glad you found it useful 😀

Really appreciate the support - thanks so much! 😀

Awesome! Welcome aboard! 👍

Thanks so much for supporting my channel! Wishing you all the best 😁

Oh yeah! 👍 This is honestly my go to but if it doesn’t work, then I switch my approach.

Thanks so much for your purchase, and I am beyond thrilled to hear my channel has helped with your data visualization skills. Wishing you all the best! 👍

Thanks! I'm not sure exactly what you're seeing. I don't remember having problems with this in the past. So my only guess that I might try is saving as a SVG file instead of a PDF and converting it later.

Thanks so much! 😊

Wow - it sure is. I attempted to update it, but that doesn't appear to be working. Hopefully will get fixed soon!

Thanks for the feedback! I’ll keep that one in mind for future videos 👍

Awww - thanks so much! So glad to hear you find my content helpful 😀

Right on! Happy you liked it!