Algorithm [ˈælgərIðəm]: A precise sequence of actions, used to programmatically solve problems. The results of your Google searches, your Spotify recommendations or the posts that are presented to you on your Facebook feed: all those are generated by algorithms.

Be it a cooking recipe or your car’s manual, humans do follow algorithm-like instructions many times in their daily lives, too. However, a computer algorithm has to be designed in an even more precise way, as the computer only does exactly what it is told to do.

Arithmetic mean

Arithmetic mean [əˈrɪθ.mə.tɪk miːn]: the most commonly known mean.

To get the arithmetic mean you add the values of all observations and then divide by the number of observations. In most cases this is what we mean, when we colloquially talk about the average.

Other means are: the median or the truncated mean. Which one you should chose depends on the kind of data in front of you.

The main differnce lies in the way these means are affected by extreme values – their so called robustness against anomalies. The arithmetic mean is not very robust, because it is influenced by every single value – even the extreme ones.

Back to Dictionary


BitBucket [bɪtˈbʌk.ɪt]: A web-based hosting service to upload and share code. See also Github.

It runs on the Open Source version control system Git. Developers use version control systems to organize their projects, to update and change code and to store these modifications in a central repository. Others can contribute to that repository and download and upload changes.

Git is a command-line tool. It does not have its own user interface. You use it by entering short commands into the terminal/command-line. BitBucket is the webpage where developers store their project and network with the BitBucket community. Many Open Source projects are hosted on hosting pages like BitBucket so everyone can contribute, report issues and comment. But you can create private repositories where just a few invited people have access, too.


Choropleth [ˈkɔːrəˌplɛθ] : A map with geographical areas colored in relation to a data variable.

It is used to display patterns or variation of the variable in different districts of a region. For example it’s popular to show different voting behaviour between the electoral districts of a country.

The type of data determines what color scale to pick for the map. Sequential data is often displayed with a color gradient from light to dark. Maps showing diverging data, for example the derivation from a specific comparative value, get a scale with two color gradients and a fixed color for the comparative value. If your data is qualitative, every category gets its own individual color in the map. A great tool to find a good color scale matching your data is colorbrewer.

Comma-separated values

Comma-separated values [ˈkɑː.məˈsep·əˌreɪted ˈvæl·juz]: a file format for storing tabular data, in which cells are seperated by commas.

The punctuation is not standardized though, which is why you might also come across files in which cells are seperated by semicolons or varying decimal punctuation like periods or commas. There are also some special forms that often end with .csv. For example tab-seperated or space-sperated values. Many programs allow you to specify the type of seperator, decimal point etc.

Back to Dictionary