Python and Pandas with Reuven Lerner
Do you use Python, Pandas, and Seaborn to collect, analyze, and plot data? Then you’ll be amazed by what ChatGPT can do, when using ChatGPT+, GPT-4 model, and the plugin for Noteable’s version of Jupyter notebooks.
[UPDATE/NOTE: This was my first summary of Noteable and ChatGPT. I have done more experiments, which you can see here: https://www.youtube.com/watch?v=2WUZ0b-hUDU]
In this video, I show you how I got things set up for using Noteable (and world headlines), then put together a query, You’ll see how it goes well, where it goes wrong, and what sort of code I can create using just English-language descriptions of my plans. And I show you what’s happening behind the scenes, as we see the JSON being written.
This is all brand new and exciting, and I hope that you’ll post suggestions and ideas in the comments for how we can take this even further!
And if you’re interested in analyzing data with Pandas, check out Bamboo Weekly at https://www.BambooWeekly.com/, where I look at current events through the eyes of data analysis.
Awesome Alpha brother! New Sub right here..
Awesome.. waiting for another project. Thanks brother.
Wonderful for initial, explorative analysis, especially in conjuring up relationships that are less obvious. Gets a bit sticky where accountabilities are concerned, especially for mission/life-critical decision-making analysis. For now, this will make a wonderful assistant. The next step is to connect it to my coffee machine. Cheers and thank you from Sydney – Dave 🙂
You guys don’t get it, LLM’s are so dumb and easy there trained on words, don’t you get it yet? It’s not smart at all just word play nothing else , auto-regressive LLM’s will be a thing of the past soon, and your paying to be the human in the middle lmao. Even this guys is a commercial
I think chatgpt is still like stack overflow. You can't blindly source from it and assume you have a correct working solution. Chatgpt can be wrong, can hallucinate, can misunderstand the prompting. Also it's still a somewhat constrained data set, though the plugins help expand its capabilities. So it's not yet going to replace a data scientist or coding
Mind blowing? Well, the good news is that the majority of people don't have much mind to lose. The bad news is that the centralization of thinking via A.I. will be the final link in the people's chains of socioeconomic slavery. Centralization of the people's powers into the hands of the few is a socioeconomic cancer.
ok i just watched up to the part where notable suddenly writing code itself and kinda scrape the webs?! I have been trying to ask gpt3.5 to write code to help scrape some sites for me to no avail! wow wow wow, ok let me continue watching and come back in a lil bit
Can you use notable for R?
Programming will be automated for sure.
Thank you for this video!
Nice video..🎉 I think what you did is very helpful in literature review / research. I m sure you can do video before anyone else how to use these tools to automate using csv / Excel, then send it to notable, then apply the magic og Gpt by analyzing data . This will revolutionize the field . Please soon
Holy white theme. Can't see anything. Fix yourself
6 months? …. dude… you mean like 4 years+
Interesting stuff all around……but what a mess. Little evidence of preparation that I could see. Scope way too broad. Lack of focus. No objective apparent. On the positive side, I think your knowledge has high potential. Best of luck to you.
can you check, if any sample program, say java spring boot project, is completely downloaded and saved in notebook as a folder?
free sign up because they get access to your data
and seriously go dark screen mate
I think Chat-GPT has gotten worse lately. Literally it will be a gamble whether or not it will even be able to read my project and sometimes it just doesn't want to send the code to Noteable. I spent an hour describing every detail of how I wanted to plan my code, I divided it up in lists and everything and then, as soon as it went on to actually write code, it didn't even use the regex pattern I had literally provided it. So weird…
Watching in June and there are now 143 pages of plugins!
when I tell noteable to download dataset for me. it returns 'I'm sorry for the confusion, but as an AI developed by OpenAI, I don't have the capability to directly download files from external websites or platforms like Kaggle.' it does not trigger NOTEABLE. I called noteable in my prompt.
Super fantastic mash-up possibilities! Thanks for the cool vid!
Great intro to both Notable and GPT+ capabilities! Thanks. Your enthusiastic approach is contagious. We'll try to follow up on this.
how to process large data?
🐍 + 🐼 with Reuven Lerner.
Hi, this is your first video I've seen, and I just subbed! I've seen videos listed about Notable, but had no idea it was related to Jupyter 😂
impossible to read. Please use a larger font size. Noteable is not available any more.
I don’t understand why I don’t have it. I’m Plus user since it’s been released. How do I get an access to it?
What at terrible click-bait image for this talk. This talk deserves better.
So what is the point of learning Data Analysis anymore to prepare for a job if ChatGPT can do all the entry level work anyways?
Question-01: There is limit to Token size sent to chatGPT, does that also account of size of the file downloaded (or considered) for the Analysis
For example in your DEMO your CSV file was 2GB or 200+ MB, will the size of those files impact in ChapGPT limits set for your account?
Question-02: You mentioned 4000 odd tokens allowed for upto 3 hours, where can I find how-much is available since last use
Question-03: Tokens if NOT used in 3 hours window, will it get carried-forward to next 3 hours window?
I do not think so but still curious
Pressing Ctrl+ several times before video recording might be a good path to take.
so basically you are doing web scrapping and using joins like the sql query… to get data.
comment
One issue I keep having with trying to process data with Noteable from ChatGPT 4 is errors that keep popping up on the ChatGPT side. In the middle of processing I often get errors that stop the processing like "There was an error generating a response" or "Network Error". I've watched around many videos on YouTube with others tinkering around with ChatGPT/Noteable and no one seems to have this issue – any ideas what might be causing this?