14 lines
274 B
TOML
14 lines
274 B
TOML
# Более длинные n-граммы и больше признаков: риск переобучения.
|
|
|
|
[cv]
|
|
folds = 5
|
|
repeats = 3
|
|
seed = 42
|
|
|
|
[features]
|
|
char_ngram_range = [2, 6]
|
|
char_max_features = 8000
|
|
pos_ngram_range = [1, 4]
|
|
pos_max_features = 800
|
|
min_df = 2
|