I am using PCA from sklearn for data reduction with 27 features and 3558 rows data and I got the following result
I have read a lot of articles but they just explain the correlation between variables and each principal component (loadings), but here I want to know what does negative and positive value means in each cell (PC1 PC2 PC3) in each data row in the final result?
You can't really deduce much from the sign of a value in the principal components. Remember that the principal components are linear combinations of initial features. Thus, a negative component just means that a linear combination gave a negative number. For example you could have the first component equal to 5*feature_1-7*feature_2=x where x<0.
Not sure what you are trying to achieve here but if you want to understand more deeply what those components mean, I suggest to look at the code at the very bottom of this page.
Negative value means the component is not significant. Positive value means the component is significant.
