1. The differences between PCA and LDA:
a.PCA has a bad discriminability between different classes, but it has high variance in one class.
b.LDA has a good discriminability between different classes, but it has low variance in one class.
2.The similarities between PCA and LDA:
a.Both rank the new axis in order of importance.
b.Both can let you dig in and see which features are driving the new axis.
c.Both try to reduce dimensions.