Digging Deeper Using the Rows and Columns Shelves

Loading...

Из курса от партнера Duke University

Data Visualization and Communication with Tableau

1729 оценок

Duke University

Data Visualization and Communication with Tableau

1729 оценок

Курс 3 из 5 — Specialization Excel to MySQL: Analytic Techniques for Business

One of the skills that characterizes great business data analysts is the ability to communicate practical implications of quantitative analyses to any kind of audience member. Even the most sophisticated statistical analyses are not useful to a business if they do not lead to actionable advice, or if the answers to those business questions are not conveyed in a way that non-technical people can understand. In this course you will learn how to become a master at communicating business-relevant implications of data analyses. By the end, you will know how to structure your data analysis projects to ensure the fruits of your hard labor yield results for your stakeholders. You will also know how to streamline your analyses and highlight their implications efficiently using visualizations in Tableau, the most popular visualization program in the business world. Using other Tableau features, you will be able to make effective visualizations that harness the human brain’s innate perceptual and cognitive tendencies to convey conclusions directly and clearly. Finally, you will be practiced in designing and persuasively presenting business “data stories” that use these visualizations, capitalizing on business-tested methods and design principles.

Из урока

Data Visualization with Tableau

Welcome to week 2! This week you'll install Tableau Desktop to learn how visualizing data helps you figure out what your data mean efficiently, and in the process of doing so, helps you narrow in on what factors you should take into consideration in your statistical models or predictive algorithms. Over the next two weeks, we’re going to learn how to use Tableau to implement this type of visualization and to help you find, and communicate, answers to business questions, as well as work with the Tableau functions that all data analysts should be familiar with. You will learn to install Tableau Desktop and learn to use the program by working with two data sets. In addition, through a series of practice exercises, you will use a data set to do example analyses and to answer specific sample questions about salaries for certain data-related jobs across the United State. Then for graded exercises, you will use a different data set to work out analyses and questions that will require you to directly apply the Tableau skills you have acquired through practice. <p>By the end of this week, you will be able to: <ul><li>Create the most important graphs used in business analysis and transform data in Tableau </li></ul><p>Once you have watched the "Why Tableau" video, review the "Written Instructions to install Tableau Desktop" and install the software. Remember to refer back to the Salary Data Set and to the Dognition Data Set resources posted on the course site this week. You will also complete a graded quiz at the end of the week. <p>As always, if you have any questions, post them to the <b>Discussions</b>.<p>To get started, please begin with the video “Use Data Visualization to Drive Your Analysis" and then review the "Written Instructions to install Tableau Desktop.<p>I hope you enjoy this week's materials!

Salaries of Data-Related Jobs: Your First Graph11:37

Formatting and Exporting Your First Graph6:49

Digging Deeper Using the Rows and Columns Shelves13:10

Познакомьтесь с преподавателями

Daniel Egger
Executive in Residence and Director, Center for Quantitative Modeling
Pratt School of Engineering, Duke University
Jana Schaich Borg
Assistant Research Professor
Social Science Research Institute

In the last video,

we got an idea for how much you might make in different data related fields.

Especially for those of you who live outside of the US, our next question

is whether those salaries might change depending on the visa you apply for.

It turns out that green cards cost quite a bit more to sponsor than visas.

So you might first check hypothesize that companies will sponsors less green cards

than they will sponsor visas.

On the other hand, because the green cards cost so much more,

companies might have a higher bar for the people they sponsor with green cards.

Therefore, they might also work harder to try to recruit those people.

So it seems possible that the salaries for people who are sponsored with green cards

might be higher in our data set than those who are sponsored with H1B visas.

Let's test those hypotheses in this video,

and in the process, learn what happens when you put different variables, or

more than one variable, in either the Column shelf or the Rows shelf.

Let's begin by making the same graph we did last time one last time.

And this time I'm gonna give you one extra tip since we've already learned how to

change the aggregation when a variable's on the rows shelf.

When you have a variable over her in the variables cards,

you can click on the drop down and go to Default Properties.

Here is where you can change the default aggregation.

So if you go to Aggregation,

you can see that the default aggregation right now is Sum.

We can make it Median.

So now, any time you bring Paid Wage Per Year to the Rows column,

it will automatically be Median, which will make our life a little easier.

Let's go ahead and put it on the Rows column, you see it's Median.

Let's put, Job Title Subgroup in Columns, and

let's order it using the quick order button.

So this is basically the same chart we had last time.

I'm gonna show you one more thing before we get started.

Let's first of all, let's change our sheet name.

So let's call this

Median Wage Per Subgroup.

Now, we can actually make different worksheets so

that you can have multiple different graphs going at the same time.

So if you right-click say Copy Sheet, and now go ahead and say Paste Sheet.

Now because it has to connect to the data source, again,

sometimes this can take a little bit of time.

But once the query is finished,

you will see a duplicate of the worksheet you had before.

So now that we have this graph, let's see what happens or

how we would break each one of these subcategories up according to the salaries

you would make if you were applying for different visa categories.

Now the variable that refers to different visa categories over here is called

Visa Class.

So it's actually very simple.

The way you would break these bars up into Visa Class is actually very simple.

You drag Visa Class, over, behind Job Title Subgroup on the Columns bar.

So, you can see immediately,

it broke up each of the Job Title Subgroups into the different Visa Classes.

Now also this is a good point to remind you

how long this would have taken to do in Excel.

So this is the power of Tableau,

how quickly it allows you to look at these types of visualizations.

Now let me show you what would happen if you changed the order of

these two different pills.

If we drag Job Title Subgroup behind Visa Class.

Now, the main category you see up here is Visa Class and

it breaks each each Visa Class up into Job Title Subgroups.

Now as we examine this data, it looks like the hypotheses probably aren't supported.

Looks like attorney always makes the most, or

at least makes a very high amount in these visa subcategories.

Teachers usually make the least.

It's not obvious that there's a clear pattern between the different

visa classes.

But perhaps you aren't satisfied with that and you want to know your data more.

You want to find some more details and really make sure you understand it.

Well the first thing you can do, is you can hover over each bar and

it will actually tell you the exact value of the bar.

So if it's hard to see from just the axis, you can see here that it says 185,000

is the median paid wage for an attorney who's applying for an E-3 Australian visa.

You can actually get more details from that, so

if you right-click Go to View Data.

Now the summary page is what we just saw when we hovered over the bar.

But if you go to Underlying data, it will actually give you the raw data

that is used to calculate and compute the median for that particular bar.

So it has every single field shown.

You can also unclick this to show just specific fields.

But let's keep all fields shown for right now.

And as we scroll through, we can look to see if there's anything that catches our

eye that might be a little weird.

And one thing you might notice, especially when you get here,

is that there seems to be a lot of New York listed as the cities that

people are applying to work for for this particular visa.

You might begin to wonder, well is this true for the other attorney classes, and

other visa classes?

Cuz when we go back to our chart here,

you see that this particular bar is particularly high compared to the others.

So, we might wanna keep this in the back of our mind for later.

Now another think I want you to notice, is down here in this corner,

it shows you how many rows were included in that bar.

So how many rows in our entire data set we're in the visa class of

E-3 Australian and we're also in the sub group category of attorney.

You can see when you come back to Summary,

it's only one row because according to that aggregation, you only have one row.

So this would be one way that you can find out more about

the data that's going in each one of these bars.

There's some things that you'll likely only pick up by scrolling through

the broad data itself.

But there are other things you might want to know that Tableau can tell you in

a much quicker way.

For example, there's a quicker way to know how many items go into each bar.

Look at what happens when you put the number of records onto the Row shelf.

Number of Records is a measure that Tableau automatically makes for you.

If we put it behind median of the paid wage on rows,

you can see that down here first of all,

it automatically makes another graph right underneath the Visa Class.

And this gives you the number of records in each one of these bars.

So if you hover over one of these bars,

it will tell you exactly how many records went into this particular bar.

Now, an interesting interesting feature of Tableau is that, once you have these

variables in your workspace, it will put that information in what they call

the tooltip, which is the information you get when you hover over the data point.

So you can see now that, just because we made this graph with a number of records,

you now see the number of records when you hover over this particular bar in

the paid wage per year graph.

So there's another way to get this information on the tool tip.

Even if you don't want to make the number of records on the graph itself.

So to show you how to do this, fist of all, let's take this off of the graph, and

we do that by simply taking it off the shelf.

And, instead, we're gonna put Number of Records on this icon here,

which is the Detail.

They call it the property.

Looks like a button to me, but they call it the property, of the marks card.

So put Numbers of Records on the Detail.

Now you can see here that the pill is in the marks card but

they didn't make any type of graph on the worksheet.

However, when you hover over each one of these bars,

now the number of records is included in the tool tip.

So the Detail button is a way that you can use the marks card

to include more details in your graph.

We'll come back to this later.

This is a good preview of how the marks card works and

how it can do some interesting and weird things,

in addition to just changing the formatting of your graph.

Now, what if you want to get a quick sense of how variable the salaries

are within each category?

Cuz, that might give you an idea of how reliable each one of these medians are.

One way to do that would be to use a standard deviation calculation.

The standard deviation is a measure of the spread of the values within a certain

variable.

Any idea how to do that?

This is gonna be a little tricky, you would have had to pay very close

attention to something I didn't point out in previous videos.

Okay, the way to do this,

is to use a different type of aggregation over Paid Wage Per Year.

So go ahead and drag Paid Wage per Year to Rows and

this time change the aggregation to standard deviation.

Now there are two different types of standard deviation that you're gonna

see here.

There is the standard deviation that has in parenthesis POP, that stands for

population.

This is the population standard deviation.

And you can use this in two different cases.

I'm not gonna go through the math here of how the standard deviation is calculated,

by the way.

I'm just gonna tell you which one you would use to report

the dispersion of the data in different circumstances.

So the population standard deviation is used when you either have a really,

really large sample of the general population that

you think represents the general population very well.

Or, when you don't care if the sample you have relates to the general population.

So if all you wanna do is describe your specific data set and you don't care how

that relates to other data sets, you can use the population standard deviation.

If on the other hand,

you want to interpret your data as if it does represent the general population.

And you think that you probably have some type of biased sample or

it may not be the perfect representation of the general population.

Then you use the standard deviation, the normal one.

So that's the one we're gonna use here, because we want to interpret our data

as if it would apply to us, even though we know we are not in this data set.

So let's go ahead and click on that.

So now you see here that we have the standard deviation for

each one of these bars in this plot underneath it.

Now, in terms of interpretation, I told you before that the standard deviation

represents the spread of the values within each one of these bars up here.

So, if the standard deviation is really large,

like in these cases here, that usually means something's up.

In other words, it probably means you have some extreme outliers in your data.

Outliers are values that are very, very different from the rest of your data.

They're usually much larger or much smaller.

I've posted a link to a great video online that will show you how even one outlier in

your data set can really affect, especially your average values and

your standard deviation values.

In the meantime, let's take these standard deviation plots as a warning signal that

we might have outliers in our data.

And so, let's add check for outliers to our analysis plan.

Since, these outliers might include many include many other aspects of

our analysis, we'll want to address these outliers or their possibility very soon.

Now, I'd like to show you two last things before we finish this video.

The first is a reminder about how we can take this graph off and

still get the information and the tools.

One way to do that is what I showed you before.

You can simply take this pill off and then move the Paid Wage Per Year to

the Detail and change the aggregation again, but that takes a lot of steps.

One way you can do that faster is if you press the Shift key,

you can move this pill directly to the Detail bar.

So now the graph is gone, but if you hover over each bar,

you'll see that standard deviation of Paid Wage Per Year is in the tool tip.

So that's an easy way to get more information quickly.

The last thing I wanted to show you, is that there's

one other way you can save your data without exporting it that's very useful,

so we don't have to make the graphs each time.

Go ahead and go to File > Save As.

And this time save it as a Tableau Workbook and

save it in some place that you'll know where to find there.

So if you save it as a workbook you won't have to make the charts each time.

So this will be useful for later.

Great job.

We learned a couple things today.

First of all,

we learned from our data analysis that the type of visa you apply for probably

doesn't affect the salary you would make in these different job subcategories.

So as we move forward with our analysis,

we aren't gonna worry about visa class anymore.

In analyzing this, we also learned about Tableau.

We learned what happens when you put multiple different variables

in either the Column shelf or the Row shelf.

We also learned how you can use tool tips

to get more information about the data you're looking at.

Ознакомьтесь с нашим каталогом

Присоединяйтесь бесплатно и получайте персонализированные рекомендации, обновления и предложения.

Coursera делает лучшее в мире образование доступным каждому, предлагая онлайн-курсы от ведущих университетов и организаций.

© Coursera Inc., 2018 Все права защищены.

Загрузить из App Store

Загрузить в Google Play