Solve almost any machine learning problem (full translation)
Original English text: Approaching (Almost) Any Machine Learning Problem
Kaggle Team | 07.21.2016
Kaggle guru Abhishek Thakur originally published this article here on July 18, 2016.
A data scientist processes large amounts of data every day. Some say that more than 60-70% of the time is spent on data cleaning, data transfer and data acquisition so that machine learning models can be applied to this data. This article focuses on the second part, applying the machine learning model, including the preprocessing steps. The pipeline discussed in this article is the result of over a hundred machine learning competitions I have participated in. It must be noted that the discussion here is very general, but very useful, and there may also be very complex methods practiced by professionals.
We will use python!