stackexchange-tutorial/vectorizer-params.yml

analyzer: word
binary: false
decode_error: strict
encoding: utf-8
input: content
lowercase: true
max_df: 1.0
max_features: 50000
min_df: 1
norm: l2
smooth_idf: true
stop_words: english
strip_accents: null
sublinear_tf: false
token_pattern: (?u)\b\w\w+\b
tokenizer: null
use_idf: true
vocabulary: null