7 Ways to Use ChatGPT for Analytics | Webinar

Key Takeaways

three's buzzword chat GPT it's a word on everyone's lips and we're super grateful to welcome Alex breberg back to the channel I know that Alex's crowd are watching over on YouTube and we've also got a lot of people watching a career Foundry too so welcome to everybody whilst I'm here um I'm William events and Communications lead here at career Foundry for everybody joining let's just give a couple of moments for people to join but on Big Market you can see that we've got the chat on the right hand side maybe because this is going to be all about chat GPT just drop why you're interested in chat GPT where you're joining from and what your name is also if you're watching on LinkedIn also if you're watching on YouTube I know that Alex always brings his crowd we love to see them uh We've hosted lots of workshops in the past and presentations so uh thankful to everybody to join this evening and this is all about seven ways to use a chat GPT for data analytics as you can see on big market we've also got some emojis do press those let's know you're here we want to make this as interactive as possible before we get started let me just introduce career Foundry very very briefly um career Foundry is the online school for your career change into Tech and we guide you from complete beginner to job ready professional in data analytics and help you land your job in the field we're not any old school our programs are so flexible that you don't need to quit your day job you get regular mentorship for not one but two industry professionals so that's a mental and a tutor that's our dual mentorship model and if you don't land a job within 180 days of graduation we refund your tuition in full so that's the career foundry's job guarantee but I don't want to talk too much about career Foundry if you're watching on YouTube and you're interested in doing a career boundary program we've added a book a cool uh Link in the bottom to one of our program advisors so if you're interested in the correct term if you're interested in career Foundry do book with a program advisor and at the end of this webinar we will be having a live q a so drop your questions on big marker LinkedIn YouTube you've got a lot of team in the background and we're going to be having a great q a session at the end Alex I don't really want to say anything more this is all about you is all about gbt um I'll leave the floor over to you awesome thank you so much and yeah thank you to Career Foundry for putting the stuff on it's always a really fun this is like I think my third time my fourth time uh being here so I I just absolutely love it um we have a really important topic uh today and uh I'm of course going to talk about you know how we can use chat gbt and data analytics but also talk a little bit about some other topics around chat gbt as well and I'm sure at the end during q a I already know some of the questions that are going to come up um and and I will stay a little extra a little longer uh if we have lots of questions on that and so um let's go ahead uh let's kind of dive into it I'm going to preface this by saying I um I I definitely fall in love with chat gbt a little bit if I ramble on a little bit too long I apologize um but I'll do my best to keep it short uh well basically how we're gonna do this I'm gonna have a little a few slides walking through some of the ways that we can use it I'll talk through it and then I'll show you just a really quick demo um on Chachi BT of how you can actually do these things um I won't again I can't do like a full Deep dive demo um but I'll just show you a few things and I have a full video on how you can do that if you want to check it out on my channel as well um but this is me I'm Alex um and let's talk about chat gbt so if you don't know about Chachi BT at all you're just hearing it for the very first time uh it's pretty incredible uh it's basically uh a chat where you can talk to this computer and it's going to give you answers in in a really simple sense but to be a little bit more specific uh it's built off of a large language model uh these llms are pretty relatively new uh only going back four or five years but have just recently started booming because of you know Chachi BT back in November of last year uh it really is meant to help understand a lot of things just talking naturally to it it's been integrated to a lot of different things even chat gbts put out something called whisper AI where you can actually talk and and communicate via just using you know your voice which is pretty amazing um but most people are using it right now just kind of typing in the chat and doing it that way um and it has a ton of different uses now these three uses are like the tip of the iceberg there are literally thousands but these are three that I think everyone could you know pretty easily uh you know see um you can use it for language translation almost like a Google translate you can do that uh in Chachi with tea you can use it for things like content creation that's something I use it for um you know I kind of think you know here's a topic and then I asked chat gbd hey what other topics on this could I talk about and it just gives me ideas so it helps me helps create content and then data analytics which will of course we'll be focusing on today um let's talk about how it works so uh I'm gonna mostly talk on the user side although if you really want to like have your mind blown um you know look up how it works on the back end of um on how these large language models work because they're insane they're super cool um basically how it works is is you have this chat window and you prompt it to do something now you can ask it a question like a fact you say um you know in 1997 how many people lived in the United States and and it can you know probably retrieve that information or you can do uh something a little bit more advanced was did you give it some context you say hey you are a data analyst you are an expert in Python I want you to write this code or something like that so you're prompting it to do something you're giving it some context giving it some information now Chachi BT is going to take that information it's going to process it it's going to do some type of reasoning on the back end it's going to generate an output and what's really great and what's become such a um an important part of chat EBT is it has uh some type of memory a working memory of previous conversations so it's not just asking it a question you're having a conversation with it and you're you're saying hey three questions ago I gave you this information I have a follow-up question on that and it keeps track of all those things and it's pretty incredible so we're going to talk about these seven ways and again I want to preface this by saying these seven ways are are very specific to data analytics the more technical side of things um I will mention at the end some more ways that I've been using it and I've been using it a lot so um I feel like you know these are good ways to really start using it things that you can definitely start using but then I'll give you some other ways you can use what use it as well the first one is just teaching yourself when you know you're first starting out and you're trying to learn you're taking courses which I highly recommend doing sometimes you get stuck and you're like I the way that this person's explaining it doesn't exactly make sense to me but you have the code um you can ask Chachi BT to kind of guide you through this walk me through how this code works and it'll explain it to you um and you can even ask it to create kind of like a lesson plan like I'm trying to learn SQL what should I start with I don't want to ask Alex he doesn't know anything I want to ask chat gbt because it knows everything so you just ask it for a personalized plan you say I'm a brand new beginner in data analytics I want to learn SQL how can I do that and it'll kind of create that for you and you can ask it for links and place is where you can study certain things and again it'll offer those links and resources pretty amazing um I'm you know sure a lot of people are are kind of getting into analytics or taking courses or doing all these things so this is just another resource to start learning um or even if you're looking at more advanced things even uh it can be really great for teaching yourself the next thing is explaining code uh this one is pretty it's really really cool honestly uh because even for me even though I feel like I'm pretty Advanced on a lot of you know writing SQL and Python and even some R like I get confused sometimes and and somebody will send me code and I'm like okay what's going on here and I'll have to really dissect the code and understand it now I do that sometimes it takes me 30 minutes an hour or I can just put the whole uh block of code into Chachi BT ask it and then I can get a much quicker overview I've noticed that sometimes I would spend 30 minutes or an hour trying to understand somebody's code that they're sending me I'll put it into here and I'll understand about five minutes or so I just it's all it's a huge Time Saver not only is it a Time Saver but when you're you know working in it and you're trying to learn it understanding like what logically is going on in your code is also just really helpful because it helps you give a it helps you have a better perspective on how the code is functioning how it's operating and what it's actually doing give me one second I need a sip of water so touch GPT also can offer other Solutions so when you ask it to the EXP to explain the code oftentimes it'll you know go above and beyond uh you know that's just something that's kind of hardwired into chat gbt is it tries to you know answer questions that maybe you didn't exactly ask but sometimes when you ask it to explain code it'll say Okay I I see your code but you know it might even be better if you do this and here's why pretty incredible it's like it's you know how uh almost like the first one it's like having your own little personal assistant who's like an expert at coding uh they're alongside you pretty pretty cool the next thing is generating code and I will say this is one that I've probably been using the most I do a lot of tutorials I also do a lot of real work um where I'm like okay here's what I want to do um here's what I want to build and I'll give it a prompt I'll say you're an expert at python you are just the best uh a python uh coder in the world and I want you to write a script that performs this function and it'll go and it'll do it now it does not always get it correct and I think I wrote it somewhere it's about it gets you about 80 80 of the way there and sometimes it even gets it wrong and I've been doing it enough to realize that you you need to know like if you're using python you need to know python to really use chat gbt well and the reason for that is it's going to spit out it's going to spit out code almost every time it's going to be like okay I understand what you're asking it's going to give you code but if you don't understand what it does and you try to implement it you try to use that code I can almost guarantee you it's it's going to be very very very tough to actually use that code um what is really beneficial is understanding already how python Works visually seeing what chat EBT is giving you so that when you put it in your script or your program or whatever you're building that you know you know what's going to happen kind of beforehand and you can make any changes or fixes to what you have um let me see uh yeah another thing uh that I want to mention is it doesn't just have to be in one programming language it could be in Excel it could be in SQL it could be an R it could be in Scala it could be in JavaScript it can be in almost any programming language and uh I didn't I don't think I mentioned this here at all but one thing that I've really been using it for a lot is is translating code I'll have a really tough really difficult MySQL code and I'm like okay I want to kind of change the pipeline I want to use python or I want to put this through somewhere else let me change it to python so I'll say you know convert this MySQL code into uh you know python code and it does a really good job or at least it gets you like 80 to 90 of the way there and just saves you a ton of time which is pretty great the next thing is answering domain questions now I worked in healthcare for many years uh I love Healthcare I think it's fantastic and for data analysis it's actually a I would say somewhat underutilized um uh data analysis is underutilized in healthcare and what's been really great is just this this understanding that Chachi BT does not know everything but they probably know more than you uh so for example I worked with claims data and if you don't know Healthcare in the United States or you're in another country the healthcare system is it's not great but uh what I will say is you know I worked with claims data for a long long time and a lot of people would come to me and ask me hey how do you what do I need to know about claims data for data analysis because there's this data and Analyst job that's open for claims data and I would say a ton of different things like I could talk all day about health care and claims data just I know way too much about it and now you know instead of doing that I'll say you know let me real quick let me ask chat gbt I'll get us prompt and I'll say here are the actual things and here's kind of some resources and it'll provide all of those things for me um and I'll still talk with them and I'll still like help them but at the same time you know it can give you a lot of context around how a different domains use their data Healthcare is just one example but let's take Finance you can say how do you do you know stock price analysis using you know uh python or using MySQL using this kind of data or that kind of data you can really use it as just an expert in the field and again it's not perfect sometimes it gets things slightly wrong but from my uh from my messing around with it and I trying it out especially with Healthcare which I'm really knowledgeable in it's it's pretty good it's pretty accurate the next thing is commenting your code now if you're just starting out nobody's commenting their code like nobody nobody's commenting code uh that's because you're just starting out but when you get into a real workplace I promise you um people will get mad at you if you don't come at your code at least they did on my team um because we passed around code a lot you know I would write my uh stored procedure in MySQL and they get pretty Advanced um and then I would just like pass it off to a database developer and he's like what on Earth did you do he's like this is this spaghetti code over here and I'm like yeah well I'ma did it well so like you do your job and then you know he would fix it up but almost every single time like it was a requirement as part of the team to comment your code chat DBT does a really good job at this where you can put in your block of code and you can say add comments to this and it's almost like it's it when I was talking earlier about explaining the code um it's like it's instead of explaining the code to you it's now adding comments of explaining the code in your actual code so then you can just copy and paste it um again really really helpful and what I will say is you know commenting code it's kind of a it's kind of a look down upon like nobody takes it really seriously um but you know I think it's important enough to where you should look at how to do that chat dbd can do a lot of it for you um so there should be any excuses going forward right we should all be commenting our code I'm trying to really push that in the data analyst Community because I think it needs to be done more um all right let's go to the next one next one is data cleaning now data cleaning is where you're taking like raw data from a source and you're cleaning it up to make it more usable for the end product or the end analysis so if you haven't done that before it's okay it's really just taking kind of messy data making it more usable and I have genuinely spent weeks of my life cleaning one or two data sets from customers because it gets really complex um that doesn't all just come from the data being messy right it doesn't mean the data is um all misspellings and all bad formatting sometimes it's more business rules um where the client is saying yes do that except when this and these business rules are ones that typically Chachi BD can't really do it doesn't um it's not going to be able to understand those business rules like you do because you're working with the client you're understanding how they're inputting their data into the source but what it is really good for is doing the more obvious data cleaning that you're gonna have to do anyways like spelling mistakes or formatting issues those are things that you know are just time consuming to have to search through and find and and use uh are in fix and so you know right now you can do it really on a small sample of data if you're using the chat EBT window on openai.com now right now yeah I'm gonna go off on a really small tangent stay with me here I apologize because now once I get rolling I can't stop uh right now Microsoft's integrating a lot of this chat gbt into their systems I'm sure you've seen it with Bing with their search engine but they're also going to be doing a lot with Azure if you're using anything with Azure like their Azure data Factory the Azure data Lake Azure data warehouse all those things are going to have this kind of stuff integrated into it in the very near future if not uh some of those products already and so um on a small scale you can do it now all but you'll be able to do that on a large large scale in the future um probably not too long where you can say hey I have these million rows not just 10 rows which you can do in like chat GPT but I have these million or 10 million or a billion if you're working with big data and you can say hey you know what are some things I I should be identifying to clean in here and then you can ask it to clean that data um there's a lot of other factors that go into cleaning data like keeping the raw data using staging databases a lot of different things but that's a whole uh different webinar um on on that process so let's keep going let's keep I'm trying to keep it focused I have so much to get through I've already been talking for almost 20 minutes I have so much to get through um so now we have a debugging code uh you know coaches doesn't work all the time uh I can you know if you've ever watched any of my tutorials on online I I'll do these long tutorials and throughout it I'll make mistakes and I'll have to like figure it out uh Chaturbate you can do a lot of that for you and actually it's been really helpful for me I've been doing um some a lot more advanced coding in webdev um as well as you know creating a lot more complex projects in web scraping and things like that using selenium and and a few other libraries and it's been really complex even for me I'm like I'm like okay I'm pretty good at this but pagination and there's some issues on certain types of websites and there's it's difficult it really can get complicated and I have found that when I put this really Advanced code or advance for me let me just say that it's Advanced for me when I put it in there I'm like I'm like what is wrong with this like I don't understand why I'm not getting the output or it's not working how I want I'll just ask it hey debug this code I'm I was expecting this but I'm getting I'm getting an error and here's the error code when I prompted with this information oftentimes like you know maybe 70 of the time it could actually help me fix that issue very quickly um which when you're working by yourself on these projects like typically I'm doing you know I don't have someone next to me who I can you know down the hall or on my team who I can just ask to kind of help me with this you know the chat DVD has kind of been like a little personal coder helper for me um especially with the more advanced stuff and I've been really really impressed with how it's um solved a lot of my issues that I had um and what's really interesting is also if I'm generating the code I can take that code try to implement it into my current uh code block that I have and if I get an issue I take it back and I put it back and then it debugs it and I get it back so it's I I really feel like I'm having a conversation with chat gbt generating my code explaining my code debugging my code it's really helpful it's really really fascinating um and you know if you haven't used it yet if you're just starting out coding again you know it could help you initially start learning these things but when you really start getting into these larger projects you know this is such a great resource um I I've been using the free one for a lot the free version for a long time and you can get you can get a ton done with even the free version of Chachi PT um which is just really great let's go to the next one I'm gonna take another sip of water so here's some considerations and those are the seven things again I'm doing all right on time I also have a demo to get to so uh here's some considerations is definitely not perfect um and I think that's a good thing uh because if it was perfect that'd be a bit freaky um but it's not perfect and it makes a lot of mistakes and and there are something called hallucinations and if you haven't heard of that term yet it's definitely like it's it's becoming very popular because uh chati will quote unquote hallucinate facts it'll hallucinate um numbers even basic calculations that can get wrong and that's actually something that the Chachi or uh the open AI is really working on is for it to do basic calculations because it's just it has a really tough time with it and it can't run code for you right so you have to have some type of IDE or you have there are some limitations on what Chachi BT can actually do but the hallucinations are actually really important um and I don't know if they're going to be going away anytime soon you really need to fact check uh uh fact check what what you're putting in there for example if you're asking more factual information if you're saying hey you know explain to me what uh this doesn't Sequel and it gives you an output you know I've had times where I'm even like I don't think that's correct and then I'll you know I'm I'm like because I've used it enough I'm like that's not exactly what it does and I'll go look it up and it's like just ever so slightly wrong but chat gbt has a way of writing it and the way that the the interface is where it makes you seem it makes it really believable um and so sometimes it's like 90 of the way their accuracy wise that last ten percent is wrong and and you really need to look out for that and so I I want to you know just get your expectations it's not a perfect system the next thing is don't put any sensitive information into chat gbt don't put your you know personal information don't put your company's personal information um Microsoft or not Microsoft um who was it it was some company that just had a big a big article written about them because they're putting like Trade Secrets and documents in there that they should not have been um and so you know that stuff gets potentially leaked and it gets into the system because um you know on a really simple scale it's this reinforcement learning it's learning and it has a feedback loop and it's taking in more data and it could be taking your sensitive information and use it for different information so you don't want that so uh the last thing that I want you to to think about or remember is that chat gbd is really only as good as you make it if you give it a super simple prompt like what is this it's going to give you a fairly simple answer although sometimes it can do really well but the more context you give it the more information you give it it'll actually give you a lot better responses and so the more specific you can be the more information you can feed it the better context it has as a whole and the better uh kind of um out uh output it'll give you so with that being said we're going to jump onto my screen I'm going to pull up chat GPT I'm going to show you what it looks like if you haven't seen it before um and I'm gonna give it a little bit of uh just a little demo of how to use it we're not going to go through every single thing that we talked about all seven points because I'll take way too long but let me pull up my screen really quickly all right I hope you can see my screen right now let's see if you can okay so I'm gonna assume you are and if you aren't that's not good let's assume you are though this is the interface for chat GPT at least they're on their website chat.openai.com now these are all my previous conversations uh don't look at this one right here I was looking up uh Darth Sidious and his background information seeing what Chachi BT knew about it um I read the forums but you know I wanted to see what chat gbt said anyways uh right now I have PL I have actually paid for the plus now I have access to three different models the default and it gives you some information over here some different models now I'm going to use chat gbd4 which is their latest model I'm going to go ahead and click on that and let me hide this real quick what I'm going to do is I'm going to give you a demonstration I'm going to go over to this Excel and this is some dummy data although this is accurate data um this is some Tesla information go ahead and copy this and I'm going to not paste it just yet but I'm going to give it first some context and then I'm going to paste it now I'm going to refresh this actually really quickly just to make sure it's fresh um and it's working so here's what we're going to do I'm going to say you are a data analyst you are going to analyze data for your company Tesla so this is a data analyst at Tesla that's the context we're giving it at least um and I'm just gonna I'm gonna keep it simple because again um yeah he's gonna uh he's gonna give us a response I'm calling it a key but try gbd is going to give us a response um I'm gonna stop it's gonna keep going but I want to you know show you how you can use it now it's going to understand that that's what it does it's even to say as a data analyst for Tesla my main goal is is this it's going to give you some information now I'm going to feed it in a data set I'm going to say um here is a data set you're working with and I'm going to paste in this information and it's you know it doesn't seem formatted well let's just see what it says on this and so it's going to be given the data site we can derive some insights and perform analysis on various aspects so it's again taking on this Persona of he is a data analyst here is the data that I'm given and because as a data analyst when I'm working with data here are some things that I should be doing now oftentimes when you're working with uh you you input some information it'll build out this little table that it'll remember for future conversations so right now he's you know or he but Chachi BT is you know going to give us some output I have not prompted it to do anything besides exactly what it is doing right now which it's gonna kind of just do its thing now while it's talking or while it's typing um I'm going to talk to you about what I'm going to do in just a little bit I'm going to ask it to write some code for us and because this was in Excel also have it write some Excel formulas for us and I'm going to keep it fairly simple just so you know because if I get too advanced it will take a long time for it actually to work um it could take you know as you can see it's taking a while to write all these things out so if I give it a long prompt it could take a long time to generate the code so I'm going to go ahead and stop it here it's giving us um actually some somewhat um generalized information but also some specific information so here's what we're going to ask it we're going to say please and I always like to be kind please write a my sequel oops in my sequel query to see which vehicle made us the most profit after expenses and let me spell that right so I'm saying uh I wanted to give us this information now I'm going to let it type and I want to go back up really quickly so we have our car price the cars sold so how many cars were sold and how much it costs to produce these vehicles these are actually accurate this is actually um interesting inaccurate information I believe this is based on 2022 though um but it's going to we haven't given any information about these columns what data is in there let's scroll back down and see what it's giving us so it's going to assume that the car or the table is called Tesla sales and it's going to infer information based off the data that's in the columns as well as the column names itself so it just generated this and this profit right here is exactly how I would have done it super simple we have the car price that's how much we're selling it for minus how much it costs to produce times the amount of cars sold and that is our profit for that actual vehicle so either the model S or the three or whatever so if I plugged this in I would just copy this code I'd plug it into a SQL database if this was in SQL now let's say I had it in like a panda's data frame or a polar's data frame let's say um I wanted to convert this code into python pandas and I'm going to go ahead and run this and we're getting the same this and this happens a lot with chat gbt I'm just going to let you know this is when you're using it if you don't ask it right away it's sometimes uh doesn't work properly now this is a good example that it remembers this conversation because I had to refresh but it kept this conversation in memory and now I'm continuing this conversation saying convert this code into python pandas so it's going to go ahead and do that for us now this one's going to take a little bit it usually Imports pandas creates the data frame and then it's going to create the code using a data frame so give it just a second um but the very last thing that I'm going to do is have it convert into an Excel formula we'll take that Excel formula and we'll put it back into uh our Excel that we had and that'll be the last thing I'm going to demonstrate um again it's I can't express enough how just it's I the board is the word is pretty it's magical it's just incredible um it's pretty it's pretty awesome to watch visually it happen but also to think about how it's working on the back end it's incredible and as a data analyst using stuff like this or not using this you're going to spend a lot more time writing out this code you're going to spend a lot more time possibly understanding your data um and so it's just again it's a it's a it's an enhancer of your ability as well as a it just can allow you to do so much more so this is the code if I just glance at this I'm going to take a look yeah this looks perfectly fine because you're taking uh you're taking this data frame you're taking that column you're saying minus the production cost times that this all looks good and then we're even it's even sorting it for us so um yeah you know it's it's going above and beyond even in this case and creating um you know this most profitable vehicle and that's printing it out I didn't ask it to do that sometimes it does that I didn't ask it but that's what it did now I'm going to say Can you convert this formula into an Excel formula I don't know if that's the best way to say it but let's see if it understands it let me take a sip of water really quick now what's really great is its ability context without you giving it context because um you know oftentimes and this is actually a really great um example of it making a mistake but um what's really great is it's going to say you know okay if it's in Excel it's starting at cell A1 so it's kind of it's just really really interesting um now okay it's it's it's giving us this really um I believe it's converting this formula from this right here which because it's using let me see we're figuring this out on the Fly this is you know this is part of using chat gbt um but it's using uh the profit let's see yeah this this formula is not 100 correct but what we're going to do is I'm going to take it anyway yeah it's okay it is it's converting actually it's converting this python code into a formula so it didn't work um exactly as I was actually hoping I was just wanting it to give it give us a really simple one um but it's let me um there we go now oh it's uh formatted run now um I'm not going to uh I'm not going to try to get this to work because I don't want to waste anybody's time but um if I had prompted it based off of the MySQL one I think it would have worked properly but it did it based off of the uh the python code so you know it keeps everything in context it keeps everything in memory I asked it to convert this formula and I'm sure it was thinking of this one so that's some of the small limitations you need to be really specific in what you're asking and how you are asking it because again if you're not very specific it can often make mistakes like this um that was my fault if I'm being honest that was completely my fault so with that being said that is you know how you can use it that's what it looks like this is just a very quick demonstration but there are lots of tutorials I have some on my channel but there's lots of ways and and you can even look at their documentation on how to use it how to prompt it all of these things let me go back really quickly I'm gonna stop screen sharing and I'm back so that was just a quick demo um I didn't show you everything I could have also asked it to comment the code which maybe I should have done really quickly um but go and try out yourself it's it's pretty incredible um we're not showing slides anymore it's just me there we go uh it's pretty incredible um and the technology is just getting better and better and better they released us back in November and it's already made leaps uh and it's already improved by Leaps and Bounds in such a short time so here's what I'll just say in a nutshell is child gbt is an amazing tool that's how I see it is is a fantastic tool and if you're not using it you're going to be wasting a lot of time that's kind of now how I would perceive it is if you're if you're in a job where you're actively a data analyst and you're not using something like this for at least the simple stuff you can input sensitive information you can't connect it to your database but if you're not using it for for template stuff that won't give away Trade Secrets or data or personal information you know I think you're you're using you're not using your resources effectively I I've just become such a big proponent of them such a big believer in it now especially after using it since November I've used it since it came out um it's just an incredible and incredible tool I know there's gonna be a thousand questions uh um in just a second so I'm not going to go deep dive into um a few other things that I could talk about um but I'm gonna pass it back over to will I'm gonna let him talk for a little bit then we'll do some q a and again I'm looking forward to the Q a because um I can talk about this all day so foreign myself thank you Alex for that great presentation and also for the live the live work on chat GPT I think it's great to see it working um but also how you just put in input one part and then the second part and the third part so you get actually far removed from what you started off with but you do see the inner workings of chap GPT so I think it was super useful there's been a lot of engagement on big marker there's also been a lot of engagement on YouTube and Linkedin um if you've got any questions it is now question time so the floor is open it's your time to ask questions about chat GPT or I know we have a lot of people watching this evening who are just starting their journey in data analytics so if you've got any intro um you know questions about data analytics the industry or career Foundry this is the time to ask the questions you got a question Alex I'd like to say one thing uh I I am going to answer any question you guys have to the best of my ability I promise you but I will say uh I am not an expert in chat gbt I actually use it a ton I would consider myself um an expert user but I don't know everything about it um but I've used it for like a thousand different things I find it amazing but you just want to put that context out there I'm not like claiming to be the sole source of Truth on this but I'll do my best to answer any questions you guys have um any questions that we can't answer we'll just refer everybody to chat GPT um to ask those questions I think actually the first question which I think is a great one to start off with because I know that Alex you showed us the different versions of a chat GPT since it's been released um Bridget had a good question do you think paying for plus is worth it as a beginner now I I don't recommend it and in fact I didn't pay for it until about a maybe two months maybe it's a month ago uh it was recent and I only did that because I wanted access to chat gpd4 because I was doing more advanced things um the the big one of the big benefits of Chachi B4 is it has a lot better responses let me let me rephrase that does have a lot better response have slightly improved responses um it understands a little bit more of the context for 90 of people out there I think that using the free one is perfectly fine now if you really want consistency in there and when you're using the free version there's some data caps there they if they have a high influx of volume you won't be able to access it that's a problem um but it's not is not required I I really don't think it is but um you know I think if you're going to use it enough if you're using it once or twice a day me personally I use it multiple times a day um for for different things and it's been extremely worth the money so yeah I think I I don't think it's necessary but it's helpful if you have extra 20 bucks a month and you use it often great honestly great answer um and another question is coming through and I think this is a question which comes through specifically um from people who are thinking about um you know transitioning into data analytics um making the leap into the field um do you think that um chat GPT will replace the data analyst that's also a question that's come through on big marker yeah this is a question that I've been asking myself a lot recently um and I I take this question extremely seriously I I in no way have I taken this question lightly because it affects a lot of people and it's not just data analysis it's data science data engineering database developers it's going to affect every every single piece of software users in some way genuinely so I take this question extremely to heart I have a huge community and and I want to do right by them and giving them a good response I've been looking into this um I think more than the average person uh and and here's my take on it as of today as of April 18 2023. as of right now I've used enough to understand a lot of its limitations I've done enough for research to understand its limitations I think there are some very genuine limitations in what it can and will be able to do in the future um and I think at least I'm quite confident that the data that's going to be generated from these systems the data that's actually going to be more usable because these systems I believe and again this is my personal belief based off my research is that it's actually going to cause people a lot more companies be more uh data focused because they have to be not because they want to be but because they're going to be left in the dust if they don't so millions of companies out there that have never had a data analytics team are now vying for data analysts who can come in and use their data because they have never done it before I think larger larger companies who have the infrastructure to actually really utilize it well will at least for the next 10 to 15 years as my estimate again hard to say with how fast things have been improving I don't think you'll see any real decrease or Automation in jobs just because of a lot of um ethical issues a lot of data sensitivity data protection issues I think um there will eventually be regulations from the gov a lot of governments around the world on use of this and within um a lot of databases public health information there again I've I've done dove into this too much to go into all the aspects but there's some there's a lot more that is going on than I think what people think when they think automation they're just like could it do it's their job my general genuine answer is right now it can't um and even if it could I think there's going to be a lot more issues than just can it do your job but how well can it do it is it legal what are the ethical ramifications um there's there's a lot of things to consider so um again I'm trying to give you the best answer I can without um without being too confident my gut my research tells me that no I don't think data analysis is going to be automated in fact I do think to an extent it'll actually be and it maybe for a short time but even for an extent I think it's going to be actually more in demand than before that's my feeling of it now you could take that however you'd like I work in data analysis I'm a huge proponent of data analysis everybody knows that and you could you can take that how you'd like it but that is my genuine belief um as of today and has been for the past uh probably about a month since I really started diving into it that's a great answer and I think that aligns also with what we also invite other guests to talk a career Foundry a doctor who mayor I think also subscribes to that being too and for those watching also Dr Gamera is doing an intro to data analytics Workshop tomorrow just gonna shamelessly plug that one there um I'm just going to pick up on the regulation point that you you made Alex because we've had a great question coming on LinkedIn from Cynthia um what restrictions might be put in place regarding open AI in the future I think it's not even I think I know a lot of companies and even countries are starting to ban it um completely because they're having major data leaks they're having data uh misinformation they're having these hallucinations that are causing issues I'm there are so many positive and I again before I talk a little further the positives for it to AI are are massive they have a lot of implications for a lot of different things um there's so much upside but there's also some downside um and some of those downsides especially looking at a company level companies using this and where they don't have specific safeguards in place there's a lot of there could be data leaks there can be um you know you're opening up your systems to you know really Advanced software and and sometimes even people at chat gbt or open AI are like we don't know exactly how this is working there are countries like Italy as well as some other countries are starting to ban or are looking to ban it completely because of this this exact issue and so companies are doing the exact same thing I've looked at I've read a lot of companies I read about a lot of larger companies that are like okay it's here's there's a lot of upsides but we're now starting to realize all the potential downsides by you know um integrating these into our systems that we're not actually we're not actually sure if it's worth it because of the potential lawsuits the potential um data issues the potential misinformation just within their company um so yeah there's going to be it's I'm talking about the US government specifically they're so slow to act I think it'll be several years before we have any real regulatory systems in place at a federal level um but certain countries are already starting to enact restrictions on it um you know again there's a lot of upside but there actually is a lot of downside as well and and most people like myself when I first started using it I was like there's no downside this is amazing but I I consult with a lot of large companies I work I have worked with large companies and I've talked to a lot of experts in the industry who work at these large companies and a lot of them have said the same thing they're managers they're even seed levels that I've talked to and they're like yeah our company's decided not to use it I'm like oh not use it at all they're like no we banned it on all company computers you cannot have it on so I know personally somebody who's already done that um and I think it's only it just it's a matter of time before people start trusting it or not trusting it and there's so many implications um again I'm trying not to be crazy crazy specific but there's a lot of positive and negative implications of using it in a company so companies need to be very very careful on how they would integrate it how they use it whether it's actually helpful with their current data infrastructure um and Business Systems set up in place and data pipelines like you know it's it's a lot more it's not as easy as people make it seem to even Implement it's extremely complex um into actual data infrastructure I think that's a great answer and also reading between the lines of what you've been seeing this evening Alex um I think it's worthwhile before people jump into using chat GPT also to read Around the subject to like check out blog posts um you know check in the Press read about the implications of chat GPT um whilst you're using it simultaneously and I think that will put you in a much better position to understand not just um you know how it works but also some of the security concerns and maybe some of the ethical issues also around it too so I think that's a great answer Alex I love it when we invite you on we always get your crowd on YouTube and they love data cleaning they're obsessed with data cleaning I find it's fantastic we love to see that um we love the data cleaning uh crowd there's room for everybody but there's a great question on YouTube are there any specific prompts for data cleaning uh how can chat GPT help with the data cleaning yeah that's a great question I uh I was mentioning I did a video earlier on like some ways that you can use Chachi between data analytics and I showed data cleaning it was a very very simple prompt um which was you know how can I clean this data that is that is kind of my example of you're giving it no context you're giving it no information the more information you give it now I haven't I'm no I'm not an expert nor am I like uh uh like I don't I'm not trying to push chat gbt on anybody so I'm not like a chat gbt a list or whatever you want to call me um I just I really like it so I don't I haven't like developed prompts for this but here's what I will say um I've used it I've used it a few times for actual data cleaning um for some projects that I was doing and what I would personally do is I would say okay you are a a lead data analyst here is the data that you're working with you're also an expert in I think I was working with um oh what was that I'm trying to think there's an I'm gonna say Healthcare data but it wasn't that it was something else I was working with but I was like you're an expert Healthcare data analyst I was like here's the data that you've been given but you found some issues like the formatting and I would try to prompt it their formatting in this seems to be off in this specific column here's the format that I want it in what it would do is it would generate the code from all these different formats that was there and it would it would say here's how you can generate the code to actually fix it and so then I would I would try it it wouldn't work exactly right I'll say this format isn't working with the code you generated can you also fix this type so I don't have a prompt but the more information you give it uh the better it does and especially with data cleaning I like to be I have been very specific like this column I believe needs to be formatted like this how can I do that um and and it does pretty well it does a pretty good job thanks Alex I hope that appease the data cleaning crowd um I feel like we I feel like we should do maybe a live event just on data cleaning in the future I think I do a whole webinar in data cleaning I I data cleaning is like I did that in my job for like three years straight so I'm I'm a big fan awesome awesome um another question coming through on YouTube and I suppose with everything that we've spoken about this evening um Alex in your opinion is if I was going to say today is now the right time to start thinking about a career as a data analyst in light of everything that we've spoken about this evening yes another really good question um I so I'm gonna I'm gonna take you back to five years ago or no I'm getting older six years ago now when I first became a data analyst um you know when I was when I was there the the there was not this huge I mean data analysis was still very popular but there's nothing that I I think in recent years about probably the past two or three years the analysis become more popular because data science has become slightly less popular if that makes sense um so data analysis has had this hug