Size of embedding for categorical variables

knesgood · April 2, 2019, 1:51pm

So it looks like it changed since I last looked. Previously, it was:

def emb_sz_rule(n_cat:int)->int: return min(50, (n_cat//2)+1)

Now it looks like it’s the following:

def emb_sz_rule(n_cat:int)->int: return min(600, round(1.6 * n_cat**0.56))

I’m not sure of the reason why, but you can dig into the source code here:

github.com

fastai/fastai/blob/master/fastai/tabular/data.py#L14


from ..basic_data import *
from ..data_block import *
from ..basic_train import *
from .models import *
from pandas.api.types import is_numeric_dtype, is_categorical_dtype


__all__ = ['TabularDataBunch', 'TabularLine', 'TabularList', 'TabularProcessor', 'tabular_learner']


OptTabTfms = Optional[Collection[TabularProc]]


#def emb_sz_rule(n_cat:int)->int: return min(50, (n_cat//2)+1)
def emb_sz_rule(n_cat:int)->int: return min(600, round(1.6 * n_cat**0.56))


def def_emb_sz(classes, n, sz_dict=None):
"Pick an embedding size for `n` depending on `classes` if not given in `sz_dict`."
sz_dict = ifnone(sz_dict, {})
n_cat = len(classes[n])
sz = sz_dict.get(n, int(emb_sz_rule(n_cat)))  # rule of thumb
return n_cat,sz


class TabularLine(ItemBase):