Welcome to Unit 9: Data! In this unit, we are going to learn how to organize and visualize data to answer questions. We'll make charts, look for patterns, and consider the impact that data collection has on our world.

Let's get things started by asking a question.

Search tools are useful for efficiently finding information. How can we analyze our searches to discover patterns or trends? Let's find out!

When you post information to a social network, watch a video online, or simply search for information on a search engine, some of that data is collected, and you reveal what topics are currently on your mind. When a topic is quickly growing in popularity, it is often said to be trending, but there are many different trends or patterns we might find in this data, including historical trends. These patterns might help us to identify, understand, and predict how our world is changing.

We will be using Google Trends which is a tool that allows you to visualize data about search history across different times and locations. We can use it to look for interesting patterns, trends, or relationships between multiple trends and try to tell the story that pattern is showing.

This chart gives us information: a collection of facts and patterns extracted from data. We can use this information to identify trends, make connections and address problems.

There are two distinctions we need to make when looking at a chart or visualization:

• What does the data show?
• Why might that be the case?

The "what" is the facts of the matter. Chocolate searches spike in December. The "why" is an informed opinion. Chocolate searches spike around the time of the winter holidays because it's a common gift.

Using Google Trends to find patterns represents an important concept in understanding how programs are used to gain insight and knowledge from data. When you worked with the tool, there were elements of both interaction and iteration. You interacted with the tool trying out several different options, and repeated the process (iteration) until you came to a possible conclusion.

As you were determining the Why in your data stories, you may have been tempted to draw concrete connections. However, it's important to remember that correlation (similarities, patterns) does not equal causation (this thing caused that thing). There can be any number of reasons why a pattern or interesting data point may appear in a chart - and our job is to make an informed decision while recognizing that there may be multiple factors at play. Usually additional research with several data sets is necessary to understand the exact nature of the relationship between data. Did this one thing cause another thing to happen? Do more people search for chocolate because they want to give it as a gift, or could there perhaps be another reason?

In this unit we will be making charts to help answer questions:

• "I think this visualization tells me this…"
  • Something is more popular than something else
  • Something is more important than something else
  • Something has become more or less searched over time

• "... but I'm not sure because…"
  • I don't know exactly how the data was collected
  • This might tell me people searched for green more than red, but it doesn't tell me why they do that or that green is a better color
  • We need more data!

When we consider datasets, it's helpful to know as much about those datasets as possible. Where did the data come from? How much data is included? When was it collected?

All of this information is considered metadata which is defined as "data about data".

We can have metadata about any digital data. For example, this picture contains metatdata that tells us the when the picture was created, what the resolution is, and how many people have downloaded it. Datasets can also have metadata that explains more about the information in the dataset. You've seen this in App Lab!

Now let's explore metadata in App Lab in the datasets you've used in previous units. Where can we find this information? What can it tell us about the data? How can it help us organize the data?