ctfidf_config.json

{
  "ctfidf_model": {
    "bm25_weighting": false,
    "reduce_frequent_words": true
  },
  "vectorizer_model": {
    "params": {
      "analyzer": "word",
      "binary": false,
      "decode_error": "strict",
      "encoding": "utf-8",
      "input": "content",
      "lowercase": true,
      "max_df": 1.0,
      "max_features": null,
      "min_df": 1,
      "ngram_range": [
        1,
        1
      ],
      "stop_words": "english",
      "strip_accents": null,
      "token_pattern": "(?u)\\b\\w\\w+\\b",
      "vocabulary": null
    },
    "vocab": {
      "gun": 1,
      "drug": 0,
      "people": 2
    }
  }
}