Data Analytics

Collecting and storing enormous amounts of data achieves nothing on its own — the benefit appears only when someone examines that data and extracts meaning from it. Data analytics is exactly that process: the systematic examination of data sets to work out what information they contain and to draw conclusions from it. Because the data sets involved are typically far too large and complex for manual inspection, the examination is done with the aid of specialised systems and software built for the purpose.

The techniques and technologies of data analytics are gaining popularity day by day, and two broad arenas illustrate why.

• Commercial industries. Organisations analyse their data so that business decisions rest on evidence rather than guesswork. A conclusion drawn from actual data — about customers, sales, operations — makes the resulting decision better informed.
• Science and technology. Researchers use analytics to test their ideas against reality: a scientific model, theory or hypothesis can be verified or disproved by analysing the relevant data. The data acts as the referee between competing explanations.

The same logic applies in both arenas: raw data goes in, specialised software examines it, and what comes out is a conclusion a decision-maker or researcher can act on.

For students of Informatics Practices there is a directly practical entry point into this field. Pandas, a library of the Python programming language, serves as a tool that makes data analysis much simpler. Rather than writing every examining-and-summarising routine from scratch, an analyst can lean on the ready-made capabilities Pandas provides — which is why it appears again and again as the working toolkit for data analytics in Python. …