What are some of the most common data visualizations you see in newspapers, textbooks, and corporate annual reports? Graphs showing a country’s GDP growth trends or charts capturing a company’s sales growth in the last 4 quarters would be high up on the list. Essentially, these are visualizations that track time series data — the performance of an indicator over a period of time — also known as temporal visualizations.

Temporal visualizations are one of the simplest, quickest ways to represent important time series data. In this blog, we have put together 7 handy temporal visualization styles for your time series data. Explore and let us know which is your favorite!

1. Line Graph

A line graph is the simplest way to represent time series data. It is intuitive, easy to create, and helps the viewer get a quick sense of how something has changed over time.

A line graph uses points connected by lines (also called trend lines) to show how a dependent variable and independent variable changed. An independent variable, true to its name, remains unaffected by other parameters, whereas the dependent variable depends on how the independent variable changes. For temporal visualizations, time is always the independent variable, which is plotted on the horizontal axis. Then the dependent variable is plotted on the vertical axis.

In the graph below, the populations of Europe and Ireland are the dependent variables and time is the independent variable.

time series data

This graph captures the population growth in Europe and Ireland from 1740 to around 2010. It clearly highlights the sudden drop in Ireland’s population in the 1840s. History books will tell you this was the result of the devastating Irish Potato Famine, a period of mass starvation, disease, and emigration in Ireland between 1845 and 1852.

Note that this graph uses different y-axis scales for its two dependent variables — the populations of Europe and Ireland. If the viewer doesn’t pay attention to the difference in the scales, they could be led to the conclusion that until about 1920, Ireland’s population was greater than that of Europe!

Use different scales with care and only when absolutely necessary. If you need to represent multiple variables on a line graph, try to use the same y-axis for all dependent variables to avoid confusion. If you can’t do this, like in the chart above, make sure both y-axes use the same number of increments and use color to show which y-axis belongs to which line.

As a good rule of thumb, don’t represent more than four variables on a line graph. With that many variables, the axis scales can become difficult to understand.

2. Stacked Area Chart

An area chart is similar to a line chart in that it has points connected by straight lines on a two-dimensional chart. It also puts time as the independent variable on the x-axis and the dependent variable on the y-axis. However, in an area chart, multiple variables are “stacked” on top of each other, and the area below each line is colored to represent each variable.

This is a stacked area chart showing time series data of student enrollments in India from 2001-10.

time series data

Stacked area charts are useful to show how both a cumulative total and individual components of that total changed over time.

The order in which we stack the variables is crucial because there can sometimes be a difference in the actual plot versus human perception. The chart plots the value vertically whereas we perceive the value to be at right angles to the general direction of the chart. For instance, in the case below, a bar graph would be a cleaner alternative.

time series data

3. Bar Charts

Bar charts represent data as horizontal or vertical bars. The length of each bar is proportional to the value of the variable at that point in time. A bar chart is the right choice for you when you wish to look at how the variable moved over time or when you wish to compare variables versus each other. Grouped or stacked bar charts help you combine both these purposes in one chart while keeping your visualization simple and intuitive.

For instance, this grouped bar chart in this interactive visualization of number of deaths by disease type in India not only lets you compare the deaths due to diarrhea, malaria, and acute respiratory disease across time, but also lets you compare the number of deaths by these three diseases in a given year.

time series data

time series data

By switching to the stacked bar chart view, you get an intuitive sense of the proportion of deaths caused by each disease.

To avoid clutter and confusion, make sure to not use more than 3 variables in a stacked or group bar chart. It is also a good practice to use consistent bold colors and leave appropriate space between two bars in a bar chart. Also, check out our blog on 5 common mistakes that lead to bad data visualization to learn why the base axis for your bar charts should start from zero.

4. Gantt Chart

A Gantt chart is a horizontal bar chart showing work completed in a certain period of time with respect to the time allocated for that particular task. It is named after the American engineer and management consultant Henry Gantt who extensively used this framework for project management.

time series data

Assume you’re planning the logistics for a dance concert. There are lots of activities to be completed, some of which will take place simultaneously while some can be done only after another activity has been completed. For instance, the choreographers, soundtrack, and dancers need to be finalized before the choreography can begin. However, the costumes, props, and stage decor can be planned at the same time as the choreography. With careful preparation, Gantt charts can help you plan for complex, long-term projects that are likely to undergo several revisions and have various resource and task dependencies.

time series data

Gantt charts are a popular project management tool since they present a concise snapshot of various tasks spread across various phases of the project. You can show additional information such as the correlation between individual tasks, resources used in each task, overlapping resources, etc., by the use of colors and placement of bars in a Gantt chart.

5. Stream Graph

A stream graph is essentially a stacked area graph, but displaced around a central horizontal axis. The stream graph looks like flowing liquid, hence the name.

Below is a stream graph showing a randomly chosen listener’s last.fm music-listening habits over time.

time series data

Stream graphs are great to represent and compare time series data for multiple variables. Stream graphs are, thus, apt for large data sets. Remember that choice of colors is very important, especially when there are lots of variables. Variables that do not have significantly high values might tend to get drowned out in the visualization if the colors are not chosen well.

6. Heat Map

Geospatial visualizations often use heat maps since they quickly help identify “hot spots” or regions of high concentrations of a given variable. When adapted to temporal visualizations, heat maps can help us explore two levels of time in a 2D array.

This heat map visualizes birthdays for babies born in the United States between 1973 and 1999. The vertical axis represents the 31 days in a month while the horizontal axis represents the 12 months in a year. This chart quickly helps us identify that a large number of babies were born in the later half of July, August, and September.

time series data

Heat maps are perfect for a two-tiered time frame — for instance, 7 days of the week spread across 52 weeks in the year, or 24 hours in a day spread across 30 days of the month, and so on. The limitation, though, is that only one variable can be visualized in a heat map. Comparison between two or more variables is very difficult to represent.

7. Polar Area Diagram

Think beyond the straight line! Sometimes, time series data can be cyclical — a season in a year, time of the day, and so on. Polar area diagrams help represent the cyclical nature time series data cleanly. A polar diagram looks like a traditional pie chart, but the sectors differ from each other not by the size of their angles but by how far they extend out from the centre of the circle.

This popular polar area diagram created by Florence Nightingale shows causes of mortality among British troops in the Crimean War. Each color in the diagram represents a different cause of death. (Check out the the text legend for more details.)

time series data

Polar area diagrams are useful for representing seasonal or cyclical time series data, such as climate or seasonal crop data. Multiple variables can be neatly stacked in the various sectors of the pie.

It is crucial to clarify whether the variable is proportional to the area or radius of the sector. It is a good practice to have the area of the sectors proportional to the value being represented. In that case, the radius should be proportional to the square root of the value of the variable (since area of a circle is proportional to the square of the radius).

Polar area diagrams, or pie charts in general, must be made with a lot of care to avoid misrepresentation. For more tips, check out this blog on 5 things you should know before you make a pie chart.

Go ahead… It’s “time” you made some cool temporal visualizations of your own!


Learn how our data intelligence platform can help you find hidden trends across years of data and analyze the interaction between multiple parameters over time using simple visualizations here.

rE