People are often surprised when they find out that I majored in philosophy as an undergraduate. They think that philosophy has nothing to do with the career I am trying to build in data science, or even that the technical knowledge required for data science would be insufficient.While I think they are quite reasonable in their skepticism, I think that philosophy education is very useful for learning data science. For this purpose, in this first post of this series, I will talk about some data science topics that are related to philosophy.
First of all, philosophy trains students to think critically and logically, which is an essential skill for data scientists when analyzing data, making predictions, and forming conclusions. The lack of the ability to think critically and logically can lead to some problems that you can encounter in every discussion and production. One example of these problems is called logical fallacies.
A logical fallacy is an error in reasoning that results in an argument being invalid or unsound. Logical fallacies are often used in arguments to mislead or persuade an audience, rather than providing a valid and logical support for a conclusion. There are many logical fallacies associated with data science studies, although there are many more that are irrelevant. Knowing these fallacies is the best way to avoid falling into them. For this purpose, I prepared some of these fallacies in this repository and illustrated them.
In this repository, you will see the following fallacies with examples and explanations:
-
Cherry Picking
-
Hasty Generalization
-
Data Dredging
-
Post Hoc
-
Survivorship Bias
-
Cobra Effect
-
Gambler's Fallacy
-
Simpson's Paradox