Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

...

Example of workflow:

Code Block
languagejson
{
    "dataset": {
        "infer": {
            "count": 1000,
            "query_string": "NOT ml_terms_version:1"
        },
        "train": {
            "count": 2500,
            "query_string": "*"
        }
    },
    "pipeline": [
        {
            "fields": [
                "body",
                "keywords.ml_terms_version",
                "keywords.terms"
            ],
            "batch_size": 100,
            "step": "loader",
            "type": "squirro_query"
        },
        {
            "fields": [
                "body"
            ],
            "step": "filter",
            "type": "empty"
        },
        {
            "fields": [
                "keywords.terms"
            ],
            "step": "filter",
            "type": "clear"
        },
        {
            "add_lemmization": false,
            "cache_lemmas": false,
            "filter_list": [],
            "input_field": [
                "body"
            ],
            "max_chunk_len": 2,
            "min_word_len": 4,
            "output_field": "keywords.terms",
            "p_significant_terms": 0.2,
            "save_model": true,
            "step": "embedder",
            "type": "terms_extraction"
        },
        {
            "fields": [
                "keywords.terms"
            ],
            "step": "saver",
            "tracking_facet_name": "ml_terms_version",
            "tracking_facet_value": "1",
            "type": "squirro_item"
        }
    ]
}

...