effectus: a cause-effect library


effectus tells you which causes provoke which effects:

>>> from effectus import Effects
>>> Effects([789, 621, 109, 65, 45, 30, 27, 15, 12, 9])
<pareto present [0.707]: 1/5 causes => 4/5 effects [total ∆: 1.9 % points]>


Few values of high intensity distort the result of the arithmetic mean for most values of low intensity and vice versa.

Guided by the arithmetic mean one regularly misunderstands it as something like the most likely value where it would be better called the most unlikely value.


A cause-effect relationship is easier to communicate yet preciser. As it unveils the true power behind things, it transforms resistance into pleasure for action. If you want to achieve more with less, this might be something for you.

effectus operationalises the entropy() model proposed by Ronen et al. [2007]. It adds a routine to approximate the most relevant cause-effect relationship. Its main class Effects provides methods to return any effect or cause for any given cause or effect. Interval functions allow to intersect and subtract values of two different attributes. You can intersect results and effort to increase the effectiveness by orders of magnitude.

It comes with an Excel interface and binaries to parse CSV files directly.

Is all that too complicated for you?

Then just paste your data into this web service and get instant results (summary only).

[2007]Grosfeld-Nir, A.; Ronen, B.; Kozlovsky, N. The Pareto managerial principle: when does it apply?, International Journal of Production Research, Vol. 45, No. 10, 15 May 2007, 2317—2325