# CosineSimilarityClassifier **`class CosineSimilarityClassifier(config)`** Bases: [`Classifier`](squirro.lib.nlp.steps.classifiers.Classifier.md#squirro.lib.nlp.steps.classifiers.Classifier) The cosine similarity [`Classifier`](squirro.lib.nlp.steps.classifiers.Classifier.md#squirro.lib.nlp.steps.classifiers.Classifier) uses the [cosine similarity](https://scikit-learn.org/stable/modules/generated/sklearn.metrics.pairwise.cosine_similarity.html) to decide which text fragment is closest to which class. **Input** - the input field need to be of type [`list`](https://docs.python.org/3.11/library/stdtypes.html#list) [ [`float`](https://docs.python.org/3.11/library/functions.html#float) or [`int`](https://docs.python.org/3.11/library/functions.html#int) ] or `numpy.ndarray` **Output** - the output field is filled with data of type [`dict`](https://docs.python.org/3.11/library/stdtypes.html#dict) { [`str`](https://docs.python.org/3.11/library/stdtypes.html#str) : [`float`](https://docs.python.org/3.11/library/functions.html#float) }. The key of the [`dict`](https://docs.python.org/3.11/library/stdtypes.html#dict) is the predicted class name and the value is the cosine distance to the closest reference data point. Parameters `type` ([`str`](https://docs.python.org/3.11/library/stdtypes.html#str)) – cosine_similarity **Example** ```json { "step": "classifier", "type": "cosine_similarity", "label_field": "label", "input_field": "embedded_extract", "output_field": "prediction", } ``` Methods SummaryMethods Documentation **`load()`** Load a step **`process(docs)`** Process a set of documents Parameters `docs` (`generator``(`[`Document`](../technical/libnlp/base.md#squirro.lib.nlp.document.Document)`)`) – Generator of documents Returns Generator of processed documents Return type generator([Document](../technical/libnlp/base.md#squirro.lib.nlp.document.Document)) **`process_batch(batch)`** Process a batch of documents. If not defined will default to using self.process_doc for each document in the batch. Parameters `batch` ([`list`](https://docs.python.org/3.11/library/stdtypes.html#list)`(`[`Document`](../technical/libnlp/base.md#squirro.lib.nlp.document.Document)`)`) – List of documents Returns List of processed documents Return type [list](https://docs.python.org/3.11/library/stdtypes.html#list)([Document](../technical/libnlp/base.md#squirro.lib.nlp.document.Document)) **`save()`** Save a step **`train(docs)`** Train on a step of a set of documents Parameters `docs` (`generator``(`[`Document`](../technical/libnlp/base.md#squirro.lib.nlp.document.Document)`)`) – Generator of documents Returns Generator of processed documents Return type generator([Document](../technical/libnlp/base.md#squirro.lib.nlp.document.Document))