In the beginning, I am not a big fan of data exploration. However, after a while I think it is very important to get some shallow knowledge from the data. After all, we don't really need to find a true but subtle knowledge from the things we learn, like random forest or other advanced techniques of machine learning.
1. scatter matrix plot Where to call: from pandas.tools.plotting import scatter_matrix How to use: scatter_matrix(df, alpha=0.2, figsiz=(3,3), diagonal='kde') # kde means: kernel density estimation, which is an non-parametric method to get a smoothed distribution for density function from finite number of data. |
AuthorShaowu Pan Archives
December 2017
Categories
All
|