search

ai-se / SMOTE

0 stars 0 forks source link

what do the params tune tune for? #15

Open WeiFoo opened 8 years ago

WeiFoo commented 8 years ago

alpha : float, optional (default=1.0) Additive (Laplace/Lidstone) smoothing parameter (0 for no smoothing). fit_prior : boolean Whether to learn class prior probabilities or not. If false, a uniform prior will be used.

More details

alpha is to prevent 0 likelihood of some features. usually, alpha in[0,1]

N{yi} is the number of times feature(word) i appear in documents of class y N{y} is total number of all features(words) in documents of class y n is the number of features(number of columns )

nulti

WeiFoo commented 8 years ago

need to check scikit learn for details.........