Learn how to perform analysis for prediction using Tableau and how to interpret the results.
- [Narrator] So, we have our Tableau environment loaded. And we've connected to our data source. Something to point out here is at this point and time, Tableau does not offer a predictive analytics function. But there's definitely some things we can do to visualize the potential influence of our predictors, here in Tableau. Tableau does offer a tree map which isn't the same as a decision tree but it can help tell a story. Now, let's navigate into our workspace by selecting sheet one, at the bottom of the Tableau screen. And let's select weather from our list of measures.
And let's bring that over to the column shelf. Now I want to transform this data into a dimension. So the way I do that is I come up to the column shelf. I identify what's called the pill for weather. And I'm going to drop down this arrow and select dimension. So we can see that weather's organized by these different classifiers. Now next, let's grab our dependent variable, sales. And we'll bring that over to our row shelf. So we can see that Tableau provides a line graph of our data.
Let's take a look for a moment. So, what I can ascertain from this line graph is that the stores with the weather classification or the stores that experience a weather classification of one, tend to have the most sales. A weather classification of five seems to be the number two spot. And weather classification of three the number three spot there. Now, like I mentioned before, we can use our Show Me palette to apply a different visual to our data. So I'm going to select the Show Me palette dropdown.
And I'm going to come, one, two, three, four visualizations down on this left side column and that's our tree map. And let's go ahead and select that. So let's take a minute and review what this shows us. And so the larger block here, with the darker color, appears to be showing us weather classification one, and the sales amount. And then, this next bigger block, is showing us weather number five. So what I would ascertain from this is that the larger the block, the larger the sales.
And then we can see this little tool tip that we have on each of these blocks, which shows the weather classification. Now, let's bring some additional context to this visualization. And grab our unemployment measure, for the list of measures in the data set. And I'm just going to drop that measure right on top of our color marks card. And, so what we see now, is a spectrum of color to represent our unemployment rate. So we see a size of each section, which represents total sales.
In other words, the bigger the section, means the more the sales were for that group of stores. And we see our weather classification, so that this classification can mean a few different things. We'd have to really refer to our meta data to understand exactly what those classifications means. But there's definitely a story to be told here. So, because of Tableau's lack of predictive modeling functionality, at this point, we're really performing exploratory analysis. Which could inform our predictive modeling in R and in Python. But again, this type of analysis is great for helping us to establish some intuition about what those models should, potentially, take into account.
Which can definitely save us some time.
In this course, discover how to gain valuable insights from large data sets using specific languages and tools. Follow Chris DallaVilla as he walks through how to use R, Python, and Tableau to perform data modeling and assess performance. As Chris dives into these concepts, he shares specific case studies that come directly from his own work with clients. Plus, he shares three essential—and practical—best practices for data-driven marketing that you can use to bolster your organization's marketing performance.
- Installing R, Python, and Tableau
- Navigating the UI for R, Python, and Tableau
- Using R, Python, and Tableau
- Exploratory analysis
- Performing regression analysis
- Performing a cluster analysis
- Performing a conjoint assessment
- Stakeholder alignment