Impact of Technology - Collaborating Online Respectfully

Gaining support for a cause

Networks: from semaphores to the Internet

Spreadsheets

Programming essentials in Scratch: part I

Programming essentials in Scratch: part II

Design Vector Graphics

Computing systems

Development for the Web

Representations: from clay to silicon

Mobile app development

Intro to Python programming

Animations

Data Science

Cybersecurity

Representations: going audiovisual

Python programming with sequences of data

Physical Computing Programming

Computing

Y9 Computing

Key Stage 3

Year 9

UNIT

In this lesson we will be introduced to data science, and in particular, how visualising data can help us to provide insights that may not be as obvious when looking at raw data.

Delving into data science

﻿Welcome to lesson one of data science. I'm Ben, and I'm really excited that you've chosen to study this unit. 'Cause in this unit, we're going to look at how data is used to change the world around you. We'll look at global datasets, as well as local data sets that are perhaps more relevant to you in your local area. You'll learn how to visualise data, spot patterns, identify trends. So hopefully you'll feel empowered to use that data to make decisions and solve problems. So all you'll need for this lesson is a computer and a web browser, and of course a whole bunch of enthusiasm. So once you found that let's get started. Okay, so in this lesson we're actually going to explore what is meant by data science and what it actually is. We'll also explain how visualising data can help us to identify patterns and trends in order to gain some insights. Okay, so what actually is data science? Well, let's say data science is extracting meaning from large data sets in order to gain insights to support decision-making. So I think a key there is, large datasets. So we're not just talking about some data that we might see in a spreadsheet with a few rows. We're talking about large amounts of data that as a human being, if we were to look at this data it might look a bit confusing and it might take us a long time to really read through all of it to try and make an some kind of understanding of it. So data science allows us to maybe extract some meaning out of that and provide some insights or represent the data in a different way. So once those insights are being created, it'll help us to learn from the data and maybe make some decisions. So let's get started and actually give you a task to do which is to give you some data as you can see on the screen here. So task one on your worksheet I've given you this data for you to look at and what I'd like you to do is spend a little bit of time to really explore the data and look at it in a bit of depth and see if you can work out what the data is actually showing you. Can you extract any information from it and maybe is there some kind of story that's appearing when you look at the data a little bit more, okay? So what I'd like to do is I would like you to head over to your task one on your worksheet now and pause the video and see if you can just explore the data and see if you can answer the questions. Don't spend more than five minutes on this activity so if you're struggling after five minutes then unpause the video and we'll just move on. Okay, so what did you actually learn from the data? Were you able to extract any meaning from it? Or get some information or maybe even tell a story from the data? Well, actually this data comes from a really very famous example from Mancha Joseph Minard. Now Joseph Minard used these numbers in 1869 to find meaning, to tell a story with the data. So I wonder whether or not you are able to tell a story with it. Well, actually the story derives if I gave you a bit of context because obviously what you didn't have there and Joseph Minard did have was he had a bit of context which obviously helped him with this. So the data you looked up before relates to Napoleon's march on Russia in 1812. So Joseph Minard then represented this data in a different way to create what is known as what is widely regarded as the best statistical graph of all time. So, let's have a look at that now. So this is what Joseph Minard actually produced. He actually produced this visualisation a graphical representation of that data that you were looking at. Now, again, we're looking at the Napoleon's march on Europe. So with it just a little bit of a help here, we can work out what this graph's showing us. Now the width of the line represents the number of troops that were marching from France to Russia. So on the left-hand side is their starting point and the width of that beige looking line represents the number of troops they had. And then as we go towards Moscow, you might notice that the line is narrowing slightly, so what do you think that tells us? Well, that tells us that the number of troops that the French army had was diminishing. So obviously along the way, things are happening to you know, to kill off the soldiers essentially. And then what the black line represents their journey back home. We can also see some geographical information on here and we can also see the temperature as well. So this line at the bottom, the, the mini line graph at the bottom, it looks like it's going up but that actually represents the temperature dropping. So the starting at the end point, when we get to Moscow, the temperature is actually -30 degrees. So that's, I wanted to highlight some key points this graph to really highlight a couple of those things. So let's have a look at this one here. So what I've done on this slide is I've highlighted a couple of things that I wanted to point out to you, which was I'll say left their destination. They had, you can see from this a circle and arrow on the top left hand side there, there were 422,000 troops. Now, by the time they reached Moscow they only had a hundred thousand troops, which means that at that point, at least a hundred, they had at least 322,000 troops die before they even reached Moscow. And then the black line coming back we can see that by the end of that campaign they were left with only 10,000 troops. And that's all highlighted on this, on this graph, right? You know, it was not only represented in numbers but we can also see the thickness of the line, which helps. So the other thing I wanted to point out was this. So these are the geographical elements that you can see on the map and what I've done is highlighted a particular area of that. So you can see what the green circle I've zoomed it in so you can see it on the right hand side. Now what I find interesting about that is the fact that, you can see the thickness of the line, which is on the right hand side, shows you that a 50,000 troops. now that like wiggly line shows you that that's actually a river and that river, I think my presentation is not amazing but I think it's the Berezina River, which is near Minsk. So they had 50,000 troops but by the time they crossed the river they had 28,000 troops, which that suggests that there were 22,000 troops that had died crossing the river. Now, of course, that's not the only place where we can see geography on that map but that's just a highlighted part to it where we can, again, extract some meaning out of that that might have been difficult for us to determine by just looking at that initial data. So what all of this is showing us that when we did look at that initial data we found it very difficult to extract that meaning and find the story. But as soon as we visualise it, then actually once we look at that visualisation, it makes it much easier for us to interpret the data and, you know? Get some kind of insight as to what actually happened during that Napoleon's march on Moscow. Now another really famous example was John Snow's visualisation. Now in 1854, there was an outbreak of cholera in the Soho area of London. Now, the time it was widely believed that cholera was caused by pollution in the air. Now John Snow didn't quite believe the theory but he needed a way to prove it. Now we did some observations that led him to give him some evidence of discounting this belief but he couldn't prove this to other people. So your job now is to help John Snow prove his theory. Now, John Snow made a dot map of Soho. Now, essentially a dot map is finding a map and placing a dot every time something occurs. Now, the dots that you can see on the map here on the shaded parts represent where there each time there was a cholera related death and where it had occurred. And what I'd like you to do is look at the map in a bit more detail and answer the questions on the worksheet to help John Snow prove his theory. So I'd like to pause the video now, head over to task 2 on your worksheets and see if you can answer the questions and help John Snow disproves that theory. Okay, so when you've done that unpause the video and we'll continue. Okay, so how did he get on with that? Were you able to help John Snow in trying to work out what was going on with the cholera outbreak in Soho? Now what John Snow does he highlighted on the map the position of the water pump on Broad Street. Now that was really important because he had gone on and done some research and he worked out that so many people were dying around the Broad Street area so what was different about Broad Street compared to the other areas of Soho? And when he worked out that they were all getting their water from the same source and that was the pump that he highlighted on Broad Street. Now that visualisation helps him to prove a theory that all deaths had been people who'd used this water pump for drinking water. So John Snow created this visualisation and used it to help convince the local council to immediately remove the water pump handle. And as soon as they did that many lives were saved because people all of a sudden stopped drinking from that water source and they weren't getting cholera anymore. So that visualisation helped him prove a theory to really kind of prove the theory that he was trying to tell them that the water pump was the actual issue. Okay, so you might have heard of an infographic before or at least might have seen one before. Now, I've used the term visualisations quite a lot already in this lesson. So let's explore the differences between them and what is each one, what each one is. So data visualisations are visual representations of the data, such as what we looked at before, that John Snow had done and Joseph Minard. So they are charts and graphs intended to help an audience to process the information more easily, and maybe get a clear idea about what the data's showing just at a glance. Whereas infographics are a visual representations of data often involving pictures that reflect patterns and help tell a story. Now infographics can include visualisations, so we look at the differences data visualisations tend to be a single thing, it's about a single set of data. Whereas infographics are a collection of those single visualisations to then in order to tell more of a story. So we look at the example on the right-hand side this is participation in code clubs around the world. So you can see it's made up of a whole, whole bunch of visualisations. Put together it helps form us maybe a bigger story or easier thing first determine and make decisions about. So I thought I'd show you some visualisations that I think are really great and really creative. So here's an example of maybe more unusual ones. We've already looked at John Snow's dot matrix we lots of Joseph Minard doing that kind of visualisation with a different thickness of lines. So here's ones that also show different ways in which we can represent data so let's look at the first one. So this first one is showing us female astronauts in space. So you can see it's very simply a bar chart. And we can see that and then at the bottom we can tell what years they were going across. So it starts at 1963 and goes all the way to 2019. But also we look at this data in a bit more detail. We can see that we can work out the number of astronauts, female astronauts in space. But also what nations they come from as well. And you can see maybe if it's increasing for a country or is it a bit more random, but we can test it out by just looking at it, in a bit more detail. Now, I also, really like this one and this was done by somebody, a child at school. And what this is showing us is they recorded their use of digital technology outside of school. So you can see on the graph at the bottom we have Monday to Sunday, so it's recording their usage throughout the whole week. But actually we it's not very clear on your screen, but the key at the top shows us what kind of activities they were doing. So if it was whether or not they were listening to music or playing a game or looking at social media. And the colours actually represent how long they were spending on it as well. So again, visually, we can see that Saturday and Sunday, and is that a Thursday? They're spending the most amount of time using electronic device. But you might also be able to tell that they're using maybe playing more music on a Sunday than they do on other days. So from that visualisation, we can pull out that kind of information. And finally, I wanted to show you this one so this one's very similar. So this shows us what liquids were being consumed by a student at school throughout a whole week. So the shapes of the icons inside the bottles they represent, what day of the week it is. But also we can see straight away from here that water is the most consumed drink. And we look a bit further you might even be able to tell by the shape of the icons and the patterns inside what day of the week that was. So again, we can pick out information was we can ask questions such as are they drinking water at home, or is it just at school? Are they drinking healthily, inside and outside of school? So those are the kinds of insights that we might be able to gain from looking at that visualisation. And what decisions could we make from that? We could probably decide that we need to drink more water at home maybe, or in school we may need to drink more water, whatever it might be, but either way, we're able to extract information provide an insight so that maybe we could make a change or make some kind of decision. So I've got an activity for you to do now which involves you looking at some data and I'd like you to be really creative and create a visualisation based on this raw data that I'm going to provide you with, okay? So you're going to create, go to the worksheet and create a visualisation, but let me show you the data first of all. So you can see I've got all the planets in our solar system and I provided you with a whole bunch of data such as the mass, the time it takes for light to travel to that planet from the sun, the time it takes to orbit the sun, in earth days, the length of the day in hours, distance from the sun and the average temperature as well. Okay, so I'd like you to pick out the data that you would like from here. I'm certainly not asking you to represent all of this data in a single visualisation but what I'd like you to do is, pick out something that you think might be interesting to learn about. For example, you might just want to represent their mass. And that would be absolutely fine if you want to do that have the planet and the mass. But you also you might want to compare two of the variables that we're looking at there for example, is there a relationship between, the time it takes for light to travel from the sun to the average temperature, maybe? And that might be something that you could visualise. Now I'm going to leave it completely up to you how you visualise this data. You might want to do this electronically and you can see the link at the bottom there if you were to click on that link it will take you to this as a spreadsheet. So you can use that electronically and if you want to use spreadsheet tools to create that graph, you're more than welcome to. But equally if you want to be creative, like those students that you saw at school, you want to just get a pen and paper and draw something for me, and you think you might want to represent the size of the planets in different ways with different width or different colours, that's up to you, let's see if you can do that, okay? So I'm really looking forward to seeing what you might create with that. So I'd like to head over to your worksheet now, pause the video, have a go at that and once you're done, you can restart again. Okay, so how did he get on with that? And really, really well done if you're able to make a visualisation. I'm really looking forward to seeing what you created as well so please do share them with us. If you feel like you'd like to share them then please ask your parents or carer to share your work on Instagram and Facebook or Twitter tagging @OakNational and using the #LearnwithOak. So you've done a really great job there we've taken our first steps into data science. We've looked at maybe some more historic examples of how data has been taken from its raw form to actually make decisions and have an impact. But also we've looked at some space data where you visualised it yourself. So the next lesson we're going to look at global data sets. We're going to look at how data is used to determine and compare different countries in the world. So I'm really looking forward already so I'll see you then.

In this lesson, we will explore how ever-improving advances in technology have made it more feasible to collect, store, and analyse much larger datasets than previously. We will then look at global data sets.


Global data

﻿Welcome to lesson two of our data science unit. Now this lesson is called global data, because in lesson one we looked at some famous visualisations by John Snow and Joseph Menard, but in this lesson we're going to look at large data sets on a global scale. So all you'll need for this lesson is your computer and a web browser. And other than that, if you can clear away any distractions that you might have, turn off your mobile phone, and if you've got a nice quiet place to work that'd be absolutely brilliant. So when you're ready, let's get started. Okay so more specifically in this lesson, we're going to recognise examples of where large datasets are used and we can relate to it in our daily lives. Also we're going to select criteria to use on a dataset to investigate a prediction that you're going to make. Then finally, you're going to evaluate your findings to support an argument, either in favour or against your prediction. So, let's start off with an example that maybe you've come across before, because the image on the screen comes from Google Maps. So I've got three questions for you, and they are, what do the different colours on this visualisation represent? Because this image is a visualisation of data. What data is needed to show you this visualisation? And then finally, how do you think the data is collected? So I'd like to study that map in a little bit more detail and think a little bit harder about those questions. Write down the answers on your worksheet, and when you're ready, I'll be here when you get back. Okay so let's head back over to the questions and we'll have a quick look at, what we thought the answers were. Okay. So what do the different colours on this visualisation represent? Well actually we can see this blue line primarily, and that blue line is the route that um, that Google has decided to make for me. And obviously that's taking lots of data, which we'll explore in a second. The blue, essentially the routes. But you also see some other colours on there. So we see this kind of amber colour and then red colour. So what do you think that represents? Well, that actually is showing the, the real-time traffic conditions. So with amber it's maybe more than normal traffic, so slightly heavier traffic. And then the red is really kind of maybe gridlock, kind of heavy traffic. Okay? So what data is needed to show you those different colours? Well first of all, to actually create the routes in the first place, Google needs to have all the data loaded of all the different routes, all the different rows, how to get from A to B, but also an algorithm's going to be put in place to work out maybe what's the most efficient route. And if you've ever had experience at using a sat nav, or seeing one in a car, sometimes they even tell you maybe the fastest routes and maybe the most efficient routes or the most efficient for your petrol consumption or something like that. So all that data is, is there and manipulated to form this kind of route. Now, the other things that we're seeing there and you might have gathered with the traffic data how does it actually work out where the heavy traffic is? Well this is normally based on some real-time data. So the car itself might have some kind of Android operating system inside it. Or if you've got an Android mobile phone with Google services, then that might be sending location service data to Google, which is collecting all the time and analysing what the conditions are. Cause it might know that you're in a car by the speed you're travelling and where you're travelling, but then be able to work out what speed you're travelling at and compare it against what's normal. Now if we're comparing it against what's normal, then obviously it needs to have some kind of historical data in there too. So it's not just measuring that real time data, it's working out maybe the busiest times of the day and when that road is likely to be at its most busiest. Okay. So let's move on. Now again, we've already looked at a large data set. You imagine how much data Google needs to collect to produce a map in the first place, let alone the traffic data or work up the routes. It's a huge amount of data being collected from all its users that have got location services enabled. So what I wanted to do is show you another video from another service that you may have heard of before, which is Netflix. Now Netflix is an online TV and movie streaming service, but they're collecting data all the time. So this video is going to highlight to us what kind of things they do with the data, and why it's important for them to collect the data and what, how they analyse it. So just take a moment to watch this video now. Okay so I find that really fascinating stuff. And it's exactly what data science is. Netflix is taking data all the time from all of its users and working out what they're watching, when they're watching it. And it's fascinating to know that, that data science in action there is pulling all of this data out, and enabling us to have some insights, and therefore make some decisions. So clearly Netflix are using that to make a decision about what their next TV show is going to be, or they can pretty much guarantee they know what's going to be a hit or popular with their users. So that's a really great example of Netflix, also data science being used by Netflix in action. So what I might do is pause the video for a moment and then think about what other companies can you think of that might collect large sets of data. So we looked at Google, we've looked at Netflix, what other companies might be collecting huge amounts of data from us all the time and using it to provide some kind of insights or make decisions with that data. Okay so pause the video and then un-pause when you've got a couple of examples. Okay so what examples did you come up with? Now there are lots of examples you could have used. The one that really kind of sticks out in my mind, I think like social media companies who might be collecting data about what kind of things you like and dislike and the kind of groups that you might join. But maybe also there are things out there called smart cities. Smart cities are really fascinating things, because what they're doing is collecting data all the time about maybe things like people's movements around the city. And they use that to determine maybe, what bus routes are going to be most popular, or where do we need to have bus routes? Maybe there aren't bus routes. So all those kinds of data is being collected in those cities to help, you know, improve people's lives. So now we're going to look at a global data set that you're going to take action on, and you're going to have a go and play around with and experiment with. So what we're going to do is decide, look at some global data and I'd like to decide or predict in advance where you think the best place is in the world to live. So we're going to look at this large data set that compared countries across the world, in order to help us work out the answer to the following question, where is the best place in the world to live? Now I've already got a thought on that. And I wonder whether or not some things or countries are kind of going around in your head now. Now I picked a picture of a really nice place that I'd like to live. This is actually Fiji, but I've got an idea in my head. I would really like to live in Barbados. Because I think Barbados sounds like a wonderful place to live. Now most of us, we like the idea of living somewhere like Fiji or Barbados, but would it actually really be the best place to spend the rest of your life? So in order for us to gain an answer for this, we need to really think about, what the things are that are important to us, of a place that we'd like to live. And what conditions would we like to live in? For example what's the life expectancy in the country that we'd like to live. Maybe what's the average income or the wealth of people there. What's the health conditions of them, if they've good health care. And maybe also one thing that's important to me is CO2 emissions. You know is it low CO2 emissions and not many people using their cars? So those kinds of things are important. Can you think of any other things, other than life expectancy, income, wealth, health, and CO2 emissions that might be important to you? Well I've come up with a list of extra things, but if you've got some extra criteria that's not on my list then that's fine, but try when you can to pick three from, from this list, cause these are the ones that we can explore using the software we're going to look at and the data set that we have. Okay. So I've got life expectancy, average health- income, health, CO2 emissions, but the new ones I've now added, maybe the average temperature, because I wouldn't want it too hot. I want it hot, but not too hot. Inequality, is it a fair society? Unemployment levels, population density, do they allow freedom of speech, and what's the crime rate there, you know, what's the number of murders per hundred thousand people. Okay? Cause we won't want that to be very high, because I certainly want to live, won't want to live in a dangerous place. Okay so just pause the video for a moment, and then see if you can pick three from this list. And then un-pause when you've got three that you feel comfortable with. Okay so I wonder if your three were the same as, as mine. Anyway. So what we're going to do is going to use a website called Gapminder. Okay so we're going to use a data visualisation tool called Gapminder to help you decide where the best place to live is based on the criteria that you've set. So your criteria should be those three, three things that you thought were most important. Okay so you're going to use that criteria to investigate your prediction. Okay and you're going to document your findings on your worksheet. But before we do that, I'm going to give you, I'm going to head over now to Gapminder, and give you a bit of a demonstration about how to use the software so we can confirm or deny our, our opinions on that. Okay so this is what your worksheet is going to look like, when you get to it. Now the first thing we have to do is list down or we're going to, going to ask you to list down the three sets of criteria that you think are most important. Okay and then underneath that, you're going to make a prediction of where you think the best place in the world is to live. Now like I say, I hope that Barbados is the best place to live, and I'm going to pack my bags and go move. Okay now the two websites I'd like to use, and please ask permission from your parents or carer before you access these websites, but they are Gapminder and Berkeley Earth. Okay so first we're going to look at Gapminder, and then I'll show you the second one as well. So I'm going to head over to Gapminder now. And this is what Gapminder looks like. Now each one of these little bubbles represents a different country in the world. And on the right hand side, we can see a list of countries. So all you need to do is search. You can do a little search for your country there, or you can scroll down til you find it. So I'm going to click on Barbados here, so I'm going to get that little tick, and see what that does once I tick that, I go and put the wrong one there, I seem to have got rid of, I've got Bangladesh. I going to see if I can de-select that, I was going to click de-select. Right okay so I'm going to click Barbados. So Barbados is now highlighted for me. Okay so you can see that Barbados is there, okay you can still see the other colours in the background, which is kind of helpful to us because it does help us to compare the different countries. But if you wanted to kind of get it so that it only showed Barbados and, and because it's such a small dot because they thought, so represent in comparison to population size. So the bigger the dot means the larger the population. Barbados has got quite a small population, that tells me something for a start, but it's a bit kind of disappeared there behind China. So if I wanted to get rid of those dots, I can use a slide at the bottom left there, and move it down so I can only see Barbados. But like I say, it might actually be helpful for us to compare it cause of the country. So I'm just going to move them an ounce, a slice. So you can still see it. First of all, this is comparing life expectancy and income. Okay now life expectancy was one of my criteria goals. So let's have a look at that. Now if we look at Barbados there, you can see it kind of makes up the dotted line and actually the average, the life expectancy of Barbados is 77.3, okay. Now we might want to compare that against where we live now. So let me scroll down and find the United Kingdom. Okay so I'm also going to put United Kingdom. So it compares Barbados to maybe where I live now. So I can see that that is 77.3, and this is 81.1. So I'm going to live on average there's more of a chance I'm going to live longer if I live in the United Kingdom. Okay so, it's up to you, whether or not you think that's a good thing or a bad thing, but either way it allows us to make that comparison. So let's say we're looking at something that's not life expectancy. What we can do is click on this arrow here. Okay and then we can pick something out. For example if you go through all these things, these are all the different categories. So you need to find the one that you saw, selected as your category on this list, but let's say it's CO2 emissions. Okay so again I'm going to click on this now, and it will get rid of life expectancy now, and it should put in a CO2 emissions in a second. There we go. Right. So CO2 emissions in Bar- in Barbados here, okay is three- Oh, that's Mexico sorry. See if we can get Barbados. There we go. So 2014 was the last time it was measured and it was 4.47. Okay where's the United Kingdom? It's 6.42. So it's definitely higher in the United Kingdom. Okay so maybe that's a, that, that proves that maybe that would be a better place to live, the United kingdom. But clearly there were dots on the right-hand side, which are much much better such as Luxembourg and Singapore. Okay so anyway, we can, we can check that out and think, you know, is that a good thing or a bad thing. Now so that's an example of how we can use Gapminder. The other one was this one which is Berkeley Earth, and that's going to show what the average temperature is only. Okay so let's just find Barbados. So let's select Barbados. Okay and it should show me this graph. Okay perfect. Now so I can see the graph is going to show the average temperature, and obviously the last time it was recorded was 2019, which is 27.8. Okay now what other information can we get from this graph? That's really interesting, isn't it? Because it is showing this trend line here, and you can clearly see the trend line is going up. Okay so once we've picked these different criteria for us to explore, what I'd like to do is continue to complete your worksheets, by taking each of those three criteria, I'd like to tell me what criteria you've investigated, I'd like to maybe take a screenshot if you can, of the graph that you've found. And then write just a little short something about what your findings are, and does that support your prediction. And let me give you an example. If I ever had back over to the slides. Okay, what I've got here that you can see I've taken a picture of the average temperature. So I'll put the criteria investigated was the average temperature. And what I thought my findings were I said, the average temperature was 27.65 degrees Celsius in 2019. So this is an, I think this is a nice temperature but I wouldn't want it any hotter than that. So the graph shows that the trend is going upwards, so therefore it's likely to get hotter in the coming years. So does that make it the best place to live or would I want to live somewhere that's going to be slightly cooler or maybe more of a stable temperature. Okay so that's your task now, so if I head back over to, I'd like to pause this now, go to task two, so remember I'd like to write in your criteria that you want to investigate, and then I'd like to document your findings by taking a screenshot and then writing just a small amount of text to see whether or not that graph, that visualisation, helps support or disprove your theory. Okay so un-pause when you've done that, and we'll carry on with the rest of the lesson. Okay so well done on completing that. What's the country you predicted the best place in the world to live? I'm not so sure Barbados actually was the best place in the world to live but, certainly a great place to visit on holiday. I think looking at the data maybe Singapore looked like a nice place to live but, you know what? I'm really happy here in my office and my shed in the United Kingdom right now. So well done in completing that anyway. I hope you enjoyed that lesson and really look to see the work that you've done. And if you found the best place to live in the world, then definitely prove it to me. Okay so if you'd like to share that with us then please do, ask your parents or carers to share your work on Instagram, Facebook, or Twitter tagging @oaknational and using the #learnwithoak. Okay so that's all for me, I'm looking forward to seeing you next lesson. Okay. Bye!

In this lesson, we will learn about the investigative cycle PPDAC (problem, plan, data, analyse, conclusion) and apply part of this cycle to a data set about roller coasters.

Statistical state of mind

In this lesson, we will investigate a problem that we can solve by ourselves. We will take our first steps towards this by working through the earlier stages of the PPDAC investigative cycle.

Data for action

In this lesson, we will continue to develop our understanding of the investigative cycle by working through the data and analysis steps of the PPDAC cycle. We will upload and cleanse our data before uploading it into the CODAP platform to start our analyses.

Clean it up

In this lesson, we will complete work through the final steps of the PPDAC cycle (analysis and conclusions) and by the end of the lesson we will have used data to make a case for positive change where we live.

Make a change

﻿Hello, and welcome to lesson six of our data science unit. I'm Ben, and this lesson is all to do with finishing off that analysis work that we started last lesson. But more importantly, we're going to start drawing some conclusions and making some recommendations, and hopefully making a change in your local area. So, all you'll need for this lesson is your computer, a web browser, and access to that dataset that you downloaded in lesson five. And then other than that, if you can clear away any distractions that you might have, maybe turn off your mobile phone, and hopefully, you've got a nice quiet place to work. So once you're ready, let's get started. Okay, so in this lesson, you're going to continue with the analysis section. Because last lesson, you analysed one of the questions that you posed, so this lesson is all about analysing the second question. So you're going to use the CODAP platform to do that. You're going to use that to visualise your data. And then hopefully, once you've done that visualisation, you'll be able to spot patterns, identify trends, and some outliers maybe, okay? And then once we've done that, we'll have analysed both of our questions. So we should be in a position to start drawing our conclusions, and maybe making some recommendations. Now, let's have a look at something of a related context, which is litter in schools. So I'm going to show you a visualisation to do with litter in schools, and I want you to just answer a few questions for me. So here's the visualisation, okay? Now, first of all, I'd like to pause the video and just think about these two questions. So, what do you notice about the data in this visualisation? And more importantly, what does it make you wonder, okay? So pause the video and then unpause when you've got some answers to that. Okay, now hopefully, once you've looked at this and identified that it is the recyclable waste and where it is found within a school, hopefully it's made you wonder something, okay? It's maybe made you think of some extra questions that you might have, okay? So let's narrow down the questions slightly. What I'd like to decide is, can you draw any conclusions from this visualisation? Does it warrant any further investigation? And what other information would be useful here, okay? So I'd like to pause the video again, see if you can get answers to those questions, and then we'll move on. Okay, so can we draw any conclusions from this visualisation? Well, possibly. I mean, we're hopefully looking at this thinking "Well, isn't it interesting how the PE corridor "does not have any non-recyclable waste, "it's all recyclable waste?" So that's made me wonder what that waste is. We could possibly say that there's a lot of litter in the dining hall, so we might want to investigate how many bins are in the in the dining hall? Can we do anything about that? Maybe it's some people's habits that we need to look at changing. But one thing I've also noticed is the IT corridor has a lot of non-recyclable waste in there, as does the languages corridor. So, does this warrant any further investigation? Well, yeah, I think so. I mean, I'd like to know why is there so much litter in the, particularly the dining hall? Why is there so much litter in the IT corridor, okay? Now, was there any other information that you think might be useful? Well, for me personally, I want to know where the bins are, I need to know whether or not there are bins near these places. Are there any bins in the dining hall? There's a lot of litter there, so maybe there's not. And the IT corridor as well, is there any bins nearby there, okay? So, I'm going to show you a very similar visualisation, but there's something slightly different about it. Okay, so from this visualisation, what data has been added to this visualisation? Now, now that we've added this extra data to the visualisation, what insights can we draw from this visualisation? And also, could you make a new recommendation to school management as a result of this extra data that you're looking at? Okay, so the final time, can you pause this video and see if you can come up with some answers to these questions. Okay, so hopefully you've seen that the data that's been added means the same visualisation, but with a bit more extra information, which is the distance from the nearest bin. Now you notice that's got a key underneath, and now the colours have gone to this green, but different shades of green. So the darker the green, the further away that corridor is, or the litter was found to have been, but the lighter it is, it means that there's a bin nearby. So actually, now I can see from this visualisation that if we look at the IT corridor in particular, none of the waste was found anywhere near a bin. So what should that tell us? Maybe that we need a bin on the IT corridor. So that could be some kind of recommendation that we can make to the school management. I think it's really interesting that the PE corridor has no recyclable waste, but is actually still reasonably far from a bin. So maybe I would like to investigate, well, what actually exactly is that waste? Maybe... Well, for a start, we should put a bin there, maybe just a recycling bin, but It'd be interesting to investigate this further and find out exactly what type of litter is that. For example, is it all plastic bottles? And if it was all plastic bottles, maybe we could put a plastic bottle bin there. I think the dining hall's a really interesting one there, because clearly a lot of the litter dropped in the dining hall is actually quite near a bin. So I wonder what's causing that litter. Is it a behavioural thing? Is it something that we can change? But we certainly might want to investigate that part further, okay? So hopefully this has given us an idea now that the visualisations, when we put more data into it, we can start drawing some conclusions, but also give us an extra thought, extra questions that we might have. Now, this is a really important part of this PPDAC investigative cycle that we've been talking about. Because it's not just one cycle. The idea is it keeps going around. So it may well be by the end of your investigation, you have some recommendations that you could make, but equally, there are also some further questions that you might have that might warrant further investigation, okay? So let's now move on to the actual data analysis that you started last lesson, okay? So if you remember, we used the CODAP platform to do this. So we used CODAP to upload our data that we had previously downloaded as a spreadsheet. And once we've uploaded it, we then started using the tools available to us to make our visualisations to answer one of your questions that you posed. So in this lesson, it's a case of you taking the second question and doing some analysis based on that one, okay? So what I'm going to do, if you can't remember, I'm going to show you a little reminder about how we worked with CODAP and uploaded our data and created our visualisations, okay? So if you're very comfortable with this, you might just want to watch it just to make sure you do remember. But equally, you might just want to pause the video now and start doing your analysis, okay? So I'm going to show you how to do it. So if you remember, and this link is on your worksheet, we have the link to CODAP. So that will take you to a website that looks like this, okay? Now, this is the homepage for the website, so what you have to do, is you have to click on Try CODAP, which is at the top right hand side there, you can't quite see it on my screen 'cause you can't see my cursor. But at the top right hand side, you can click Try CODAP, and that will open up this, okay? What you need to do is click on CREATE NEW DOCUMENT. Alternatively, if you saved your work from last week, you can click on OPEN DOCUMENT and just upload or open that document that you saved. But if you didn't save it, don't worry, you can just click CREATE NEW DOCUMENT. And once you go CREATE NEW DOCUMENT, to import the data, you go to that, and then you go Import and you drag your CSV file or click on here and select the CSV file that you downloaded last lesson, okay, in lesson five. Once you've done that, you'll get a window that looks a little bit like this. And here's my data that I collected. Now, you may want to resize this window, you can click on the bottom right hand side, that little green triangle there with the three lines inside, you can move your clicker and drag it down and go, it creates quite a bit of width. Now in this menu on the top left hand side, what you need to do is click on the word Graph. And when you click on the word Graph, it opens up like an empty... Well, it won't be an empty graph. It's a graph showing all the instances that you have inside your data, but this in itself, remember, the visualisation here is not useful to you. What we have to do is compare at least two variables. So I'm just going to, again, drag the bottom right hand corner out to make it a bit bigger. And if we want to put our variables into the X and Y icon, all we need to do, go to our data and hold down our mouse over the top of the title of the variable, okay? So can you see the way my mouse is over distance... Well, actually, let's just recreate the visualisation that we had before. So the visualisation we had was location. So I'm going to put location, I'm going to click my mouse over the title and then drag that into the X axes at the bottom. Okay, and there we go, it shows me the location. And the other question I had on my visualisation was, was it recyclable waste? So I'm going to put my mouse over the title, where it says Recyclable waste, I'm going to hold down my left mouse button and drag that onto the Y axes here, okay? And there we go, and it's recreated that visualisation. Now the other thing that I had in my visualisation was distance from nearest bin. Okay, so I'm going to find that, so distance to nearest bin. And this time because the X and Y axes are being used, I'm just going to put this into the middle of the graph. So I'm going to put it right in the middle of my visualisation there. Drop, let go of my mouse button, and you can see it makes the visualisation for me, puts those colours in, okay? So at that point, once you're happy with that, you can... Let me just make this a bit wider so we can see it properly. Okay. Make it nice and big, and then once you're happy with that, you can take your screenshot, you print screen, place that into your worksheet and then you can start doing some kind of mini analysis there, where you can write down a few sentences about what you think you can learn from this visualisation, okay? So this shouldn't take you too long. Make sure you select... Go back to lesson four, and in lesson four, that's where you posed your two questions. So lesson five, you analysed one of the questions, so this lesson is all about analysing that second question. So go back to lesson four, find your second question, and then you've got to create the visualisation based on that second question. And then once you've done that and you've taken your screenshot and you've written a couple of sentences about it, we're then ready to move on to the final part of the lesson, which is to start making our conclusions and making some recommendations, okay? Okay, so you finish up. Big well done, because now you finished a huge proportion of our challenge, which was to go through all the steps of the PPDAC investigative cycle. So you have identified what the problem was, and you came up with your questions, you came up with a plan for how you're going to collect the data, you collected the data, you've now analysed it. So the only thing left for us to do now is to come up with a conclusion, and hopefully make some recommendations. So the next part of this lesson is to go over to your worksheets and answer the questions that you can see on the screen now. So they are to find out what are the answers to your questions. And don't just come up with a solution, backup anything you say with the data, 'cause you have the data to prove it. So how does that data help prove the answer? Is the answer reliable? Do you think you'd need more data to really back up your argument or make a case? Or do you think that maybe when you went and collected data, it was just a bad day? Or maybe it was a good day? Do you think going out and collecting data on different days might help support your arguments? Most importantly, what can we now do with the results? So I'd like you to use the data to make a case for action, or do you think that maybe it's led to further questions that need to be answered? And it may well be you come up with a halfway house there, it may well be that you were able to answer one of your questions fully, but the second one really does require further investigation, okay? So with this, I'd like you to head over to task two on your worksheet, and I'd like to answer questions and make a recommendation to your local council about what the next step should be. And that might be to take direct action, or it might be to recommend that you found a problem but actually, this needs investigating further and what they need to do to investigate that further, okay? So pause the video now, and then complete your work sheet on task two, sorry. And when you've completed that, I'll be here when you get back. Okay, so well done, and now you've come through all the steps in the first iteration of our investigative cycle. I wonder whether or not you feel like you were in a position where you're able to make a recommendation to your local council, and if not, why not go and do that? That would be great if you could send your report to the local council and feel confident that you're not just complaining about something, but you're actually backing up something with data and making a recommendation that is fully supported by that work that you've done. Now, now that you've done that relating to litter in your local area, this was a topic area that we recommended that you did. But I wonder if there's any other areas of your life that you think investigating data could help bring around change, okay? Are there any issues that directly affect you that data could help you understand better? And how could data help you bring around that change? Now, I've got some examples on the screen here, so it could be tracking carbon emissions in your local area. It may well be you've got lots of traffic going past your school and you're worried about carbon emissions there, so why not going to take the first steps and investigate that. You could find out the registration plates for cars, and if you search registration plates on the internet, it will tell you what their CO2 emissions are. That's open data that you can investigate. You might want to bring it more personal to your life. For example, tracking your own mobile phone usage. It may well be that you're worried about your mobile phone usage and think you might be too addicted to your phone. But why don't you note down every time you've used your mobile phone and what you were using it for, and that might give you an indication of how you're using it. And maybe again, you could make a recommendation to yourself about maybe limit the amount of time that you're going to use on certain apps or certain times of the day, for example. And then finally, you could make a case for more cycle lanes in your local area. Now those are of course, just three of my suggestions, but hopefully, this whole process, this whole six lessons has got you thinking about things that maybe you think you could bring around change for, and the way you could do that and backup your argument, or learn more about that problem, is to investigate that data. So that's all for this lesson and it's all for this unit, and I really, really hope you've enjoyed it. And I've used that word empowered before. I do feel hope that you feel empowered to go out and investigate data and solve some problems out there that really could affect you and your future, okay? Now I also would really love to see some of the work that you did, I'd love to see the investigation that you've done, and if you were able to make a recommendation to your local council. Then why not let us know what your local council responded with, okay? Now if you'd like to do that, if you'd like to share your work with us, then please ask your parent or carer to share your work on Instagram, Facebook or Twitter, tagging @OakNational and using the hashtag #LearnwithOak. Okay, so that's all from me. I'm Ben and I really hope you've enjoyed it and look forward to seeing you next time, bye.

Unit Overview: Data Science

Lessons: