Introduction
Visualisations are everywhere—from business reports to social media. But knowing what to use and when can make all the difference. In this article, we'll break down the most common types of visualisations, like bar charts, line graphs, pie charts, and scatter plots. You'll get a quick guide on how to pick the right one for your data and make your insights really pop.
Choosing the right visualisation
Before you create a visualisation, make sure it’s the right one. Visualisations can serve a number of purposes such as:
- Showing changes over time.
- Showing how data is distributed.
- Showing how a whole is divided into its parts.
- Comparing data side by side.
- Showing a relationship between different variables.
- Showing geospatial data.
Types of data visualisations
Bar Charts
A bar chart is a simple way to visually compare different things using bars. Each bar represents a category or group, and the length of the bar shows how much or how many of something there is. The longer the bar, the bigger the value. For example, if you’re comparing sales of different products, each product gets its own bar, and the bar’s length shows how many units were sold.
Use case
Conventional bar charts are used when
- Comparing categorical or discrete data
- Ranking data
- Comparing data across time *
* Useful for comparing data over time only when there are few data points, and not displaying a continuous trend. For that purpose, use a histogram or line chart.
Stacked Bar Chart
A stacked bar chart is like a regular bar chart, but instead of each bar showing just one value, it’s divided into different parts (or "stacks"). Each stack represents a sub-category within the main category, and all the stacks add up to the total value of the bar.
Used stacked bar charts when:
- Visualising part-to-whole relationships
- Comparing sub-categories across categories
- Showing changes over time
- Highlighting proportions
Grouped Bar Chart
A grouped bar chart is an easy way to compare different categories side by side. Instead of having just one bar for each category, you have several bars grouped together for each one. Each bar in the group represents a different sub-category.
Grouped bar charts are best used when highlighting differences between categories compared to a stacked bar chart.
Histogram
A histogram is a way to show how data is distributed across different ranges, or "bins." Imagine you’ve got a bunch of numbers, like test scores, and you want to see how often certain scores pop up. A histogram groups those scores into ranges (say, 60-70, 70-80, etc.) and then uses bars to show how many numbers fall into each range. The taller the bar, the more numbers in that range.
There are a few differences between a histogram and a conventional bar chart. The X axis in a histogram can show continuous data, unlike a bar chart. To illustrate this, there are no gaps between the bars.
Lollipop chart
Lollipop charts are simply a cosmetic variant of the traditional bar chart. Instead of using bars, a lollipop chart has lines with dots at the ends. It's helpful when there are many categories with similar values. The different design makes it easier to read and understand compared to regular bar charts.
Line Charts
A line chart is a simple and clear way to show how something changes over time. It consists of a series of points connected by straight lines, making it easy to see trends and patterns. You often use line charts to track things like sales figures, temperatures, or any data that varies continuously.
Use cases
Line charts are used when:
- Plotting how one variable changes with relation to the continuous values of a second variable. This is particularly true when illustrating how a variable changes over a continuous time period.
- Illustrating the frequency distribution of multiple numeric variables. For a single variable, histogram is a better choice.
Ridgeline plot
A ridgeline plot is a twist on the standard line chart that shows multiple lines. In this type of plot, each line has its own axis, but they’re stacked slightly above or below each other instead of being completely separate. This helps save space compared to using lots of separate plots.
Pie Charts
A pie chart is a circular graphic that divides a whole into slices to show the proportions of different categories. Each slice represents a part of the total, making it easy to see how each category contributes to the whole.
This picture shows a pie chart and a corresponding donut chart.
Use Cases
Pie charts are one of the most misused charts. It’s true, there’s rarely anything simpler and more intuitive than a pie chart. However, there are many times when pie charts are simply not the best choice. Use pie charts when:
- You want to compare how categories stack up as part of a whole
- You have 5-7 segments or less
- You want to highlight dominant segments
- There are clear differences between categories
- Exact values aren’t critical
Alternatives
- If you have more than 5-7 categories, consider tree maps.
- If you want precise comparisons, or if the segment sizes are similar, use a standard or grouped bar chart.
Donut Chart
A donut chart is a pie chart with a hole in the middle. For the most part, there aren’t many differences between the two. Here’s why you might want to consider a donut chart over a pie chart:
- The hole in the middle draws focus to the segments rather than the whole pie.
- The hole in the middle is also handy for placing labels, totals or other useful information inside.
- The design might be considered more aesthetic and modern.
Scatter Plots
A scatter plot is a simple yet powerful chart that helps you see the relationship between two variables. A scatter plot (also called a scatter chart or scatter graph) uses dots to show values for two different numeric variables. Each dot’s position on the horizontal and vertical axes represents a specific data point. Scatter plots are handy for spotting relationships between variables.
Use case
Scatter plots are used to:
- Show a relationship between 2 variables
- Identify outliers
- Assess distribution
- Understand data patterns
Scatter plots are primarily used when there are many data points.
Bubble charts
Bubble charts can be seen as a variant of scatter plots when there are 3 variables. Simply put, bubble charts change the point size of the data points based on the value of the 3rd variable.
Heatmaps
Heatmaps are a vibrant and intuitive way to visualize data, allowing you to quickly identify patterns, trends, and anomalies. Picture a grid filled with various colours, where each colour represents a different value. This visual approach transforms complex data into an easily digestible format, making it simple to see where things heat up—and where they cool down.
The axis variables are split into ranges, just like in a bar chart or histogram. Each cell's colour shows the value of the main variable that fits within that range.
The term heatmap is also used in a spatial context, plotting against a map rather than a grid. The map need not be geographical in nature. It could also show clicks or mouse activity on a webpage for example.
Use cases
Heatmaps are used in different ways depending on type:
- Identify correlations, similar to line charts
- Show frequency distribution while plotting against 2 other variables, like a bubble chart. Heatmaps are particularly suitable when there are a huge number of variables, which would cause overplotting issues on a line chart or bubble chart.
- Heatmaps are also used when one axis represents continuous data shown in intervals rather than discrete data points.
- Spatial heatmaps also plot data against spatial objects – any entity that has a spatial dimension or can be represented in a space.
Waterfall Charts
A waterfall chart is a visualisation which shows how a starting value is affected by various positive or negative changes over time, and how it ends up. A waterfall chart could also be used to show a detailed breakdown of a total.
Here’s how it works:
- Starting Point: You kick things off with a starting value—like your total revenue or profit at the beginning of a period.
- Positive and Negative Changes: As you go through the series of changes, some will add to that value (like profits or new sales) and some will subtract from it (like expenses or losses). Each of these changes is represented by a bar that either rises or falls from the previous level.
- Visual Flow: The bars are usually colour-coded—often green for gains and red for losses. This makes it easy to see how much each change contributes to the final result.
- Final Value: At the end of the chart, you’ll see the final value, which shows you how all those ups and downs have affected the starting point.
Use cases
Waterfall charts can be used
- To show changes over time
- To show cumulative effects
- To show how each entity contributes to a total. Unlike pie charts, waterfall charts can show negative values.
Box Plots
A box plot, often called a whisker plot, is a handy way to display the distribution of data using a five-number summary. It gives a quick visual snapshot of the median, quartiles, and any potential outliers in your dataset, making it a great tool for statistical analysis.
Here’s what you’ll find in a box plot:
- Minimum: This is the smallest value in the dataset, not counting any outliers.
- First Quartile (Q1): The value below which 25% of the data falls, marking the lower edge of the box.
- Median (Q2): The middle value that divides the dataset in half. This is shown as a line inside the box.
- Third Quartile (Q3): The value below which 75% of the data falls, forming the upper edge of the box.
- Maximum: The largest value in the dataset, excluding outliers.
The box itself represents the interquartile range (IQR), which covers the middle 50% of the data, giving you a clear visual of the data’s spread.
Whiskers extend from the box to the minimum and maximum values within a certain range (usually 1.5 times the IQR). Any data points that fall outside this range are considered outliers and are typically shown as individual dots or asterisks.
Use Cases
Box plots are primarily used to show distributions of numeric data values, particularly when comparing with multiple groups. When just a single group is involved, it makes more sense to use a histogram instead. Box plots tell us about:
- Skewness of data
- Minimum and maximum values
- Interquartile range
- Median
- Outliers
When plotting multiple box plots on a graph, you can compare these details between different groups
Violin Plot
A violin plot could be seen as a variation of the box plot. A violin plot can be seen as a combination of a box plot and a density curve. Consider one side of a (vertical) violin plot to be a density curve, and the other side, its mirror image.
The symmetry rule does not apply when there are 2 categories involved:
Violin plots are a more complex, detailed alternative to box plots if you want to highlight density distribution.
Tree Maps
A tree map is a type of data visualisation that displays hierarchical data using nested rectangles. Each rectangle represents a category or subcategory, and the size of the rectangle corresponds to the value or importance of that category. Tree maps are useful for showing how different parts make up a whole. Tree maps can be visualised in a number of ways, as you will see.
Elements
A tree map is comprised of 3 elements:
Rectangles
A tree map chart uses rectangles to show data. Each rectangle represents a piece of information, with its size showing how important it is. Bigger rectangles mean more important data. The rectangles are grouped together like branches on a tree, with smaller rectangles inside larger ones. This makes it easy to see patterns and differences in the data.
Hierarchy
Tree maps can show data in a layered way. They group data into different levels, like a tree with branches and leaves. Bigger rectangles represent the main groups, while smaller ones are inside them and show smaller groups. This makes it easy to see how different groups are connected.
Colour Mapping and Rectangle Size
Tree maps use colors and sizes to show different data values. The size of a rectangle shows how much of something it represents, while the color tells you what kind of data it is. Bigger rectangles mean more of something, and different colors show different categories.
The rectangles are arranged from biggest to smallest, starting at the top left and going to the bottom right. This makes it easy to see which groups are most important. Tree maps are a good way to show a lot of data in a small space and make it easy to understand.
Use Cases
Tree maps are an excellent choice when you want to see proportions within a hierarchy, which is not easily shown in a pie chart or a stacked bar chart. Tree maps are also much better at showing a large number of categories.
Gantt Charts
A Gantt chart is a handy tool that helps you keep track of tasks and timelines in a visual way. Imagine it as a bar chart, but instead of just numbers, it shows the start and end dates of tasks in a project, all laid out on a timeline. It's like having a bird’s-eye view of everything that needs to get done, and when it needs to happen.
Whether you're managing a big construction project, planning a marketing campaign, or organising a wedding, a Gantt chart breaks everything down into bite-sized tasks so you can see how they all fit together. Plus, it helps you spot which tasks depend on others, so you know exactly what needs to be done first and what can wait.
Use Cases
The most typical use of Gantt charts is for Project management, whether it be events, products, construction, marketing campaigns, research and development etc.
While Gantt charts are typically used for planning, they could also be used for recording historical events
Funnel Charts
A funnel chart is a type of visualisation that helps you track a process that involves several stages, especially when you’re interested in seeing how the number of items reduces as they move from one stage to the next. Think of it as looking at a sales or marketing funnel—where lots of people might start at the top, but fewer make it through each subsequent step until only a small number remain at the end.
The chart looks like an inverted pyramid, with the widest part at the top (the first stage with the largest number of items) and each section below getting progressively narrower. It's great for showing things like sales pipelines, customer conversion rates, or any process where there's drop-off between stages.
Conclusion
To wrap things up, getting familiar with different types of visualisations—like bar charts, line graphs, pie charts, Gantt charts, and funnel charts—can really boost how you share and make sense of data. Each chart has its own special role, and the key is picking the right one to tell your story or highlight important trends. Whether you’re planning a project with Gantt charts or tracking customer conversions with funnel charts, these tools help you turn raw data into something clear and meaningful. Once you get the hang of them, visualisations make it so much easier to communicate ideas and make smarter, data-driven decisions in any field.