gizmobench

Dot Plot Maker

Paste a list of numbers and get a dot plot that stacks one dot per observation above the value you entered, with the frequency table beside it and an SVG to download. Most makers bin the data before they draw it, which turns a dot plot into a histogram and hides the repeats a dot plot exists to show, or they cap the axis and quietly leave the far value out. This one leaves every value where you put it: rounding to whole numbers, to halves or to a step of your own is a control you switch on, an outlier stretches the axis rather than being trimmed off it, and any entry that could not be read as a number is listed under the box instead of being dropped in silence. Values can be separated by commas, semicolons, spaces, tabs or new lines, up to 5,000 dots are drawn, and the counts beside the plot are the exact counts of the values it accepted. Nothing is uploaded and there is no account.

Rounding
Dot plotone dot per value
Dots
0
Positions
0
Tallest stack
0

Paste numbers on the left to draw a dot plot.

Values can be separated by commas, semicolons, spaces, tabs or new lines, so a column copied from a spreadsheet pastes straight in. Anything that is not a number is listed under the box rather than dropped, and up to 5,000 dots are drawn. Your values and the settings on this page are kept in this browser only.

Accuracy. One dot per value, drawn at the value you entered. Nothing is binned or smoothed unless you switch rounding on, and an outlier keeps its place on the axis rather than being trimmed. The table beside the plot is the exact count of the values it accepted, and it says how many it could not read.

Common questions

What is a dot plot, and how is it different from a histogram?
A dot plot puts one dot on the number line for every observation, stacked over the value it took, so eight sevens are a column of eight dots above 7 and you can read the individual values straight off the picture. A histogram first sorts the values into intervals and draws a bar for each interval, which means the original numbers are gone by the time you see it. That is the difference this page keeps: with rounding off, 1.4 and 1.6 are two dots at two places on the axis, not one bar covering both. When every value is a whole number and the range is small the axis is labelled in whole numbers, which is the form a class or a lab notebook usually wants.
How do I enter the data?
Type or paste the numbers separated by commas, semicolons, spaces, tabs or new lines, so a column copied from a spreadsheet and a comma-separated row both work without editing. Decimals, negative numbers, a leading plus and exponent form such as 1e3 are all read. Blank lines are ignored. Anything that is not a number, a word, a unit stuck to the number such as 5px, or a stray NaN, is counted and listed under the box rather than dropped without a word. One thing to watch: a comma always separates values, so write 1200 rather than 1,200, otherwise it reads as two values, 1 and 200.
Should I turn rounding on?
Only if you want it. Rounding is off by default and every value keeps the exact place you gave it. Switch it to whole numbers when measurements such as 7.2 and 6.8 should stack together as 7, to halves when the data was collected to the nearest half, or to a step of your own for anything else: a step of 5 puts 12, 13 and 17 at 10, 15 and 15. A value exactly halfway rounds up. Rounding never changes how many dots there are, only how many positions they stand on, and the table beside the plot shows the merged counts.
What happens to an outlier?
It stays. A value of 1000 among values near 1 keeps its own dot and the axis stretches to reach it, which is usually the whole reason for drawing the plot: the gap is the finding. Nothing is trimmed, capped or moved to the edge. If the run of empty axis makes the cluster hard to read, the frequency table beside the plot gives the same information without the scale problem, and you can plot the outlier separately if it is a data-entry mistake you want to confirm.
How many values can it plot?
Up to 5,000 dots. Past that it says how many values it was given and what the limit is rather than drawing the first 5,000 and staying quiet about the rest, because a plot that is silently missing observations is worse than no plot. A very tall stack closes up so that it still fits inside the plot, which reads as a column, and the count in the table stays exact whatever the picture does.
Can I download the plot or the counts?
Both. Download SVG saves the drawing you are looking at as a vector file: it scales to any size without blurring and opens in Inkscape, Illustrator or Figma, where every dot, tick and label is a separate object you can restyle. It carries the dark background you see on the page. Copy table puts the value and count columns on the clipboard as two tab-separated columns with a header row, which pastes into a spreadsheet as two columns. The optional title and axis label you type are drawn on the plot and go into the file with it.
Is my data sent anywhere?
No. The parsing, the layout and the drawing all happen in your browser, and the SVG file is made there too and handed to the ordinary download. Nothing is uploaded and there is no account. Your values, the rounding step, the title and the axis label are kept in this browser's local storage so the plot is still there when you come back, and clearing the box clears the values.

One dot per value, drawn at the value you entered. Nothing is binned or smoothed unless you switch rounding on, and an outlier keeps its place on the axis rather than being trimmed. The table beside the plot is the exact count of the values it accepted, and it says how many it could not read.