# TfidfTransformer

### *class* cuml.dask.feature_extraction.text.TfidfTransformer(, client=None, verbose=False, \*\*kwargs)[[source]](https://github.com/NVIDIA/cuml/blob/93418baf5/python/cuml/cuml/dask/feature_extraction/text/tfidf_transformer.py#L44)

Distributed TF-IDF transformer

### Methods

| [`fit`](#cuml.dask.feature_extraction.text.TfidfTransformer.fit)(X[, y])           | Fit distributed TFIDF Transformer                                                  |
|------------------------------------------------------------------------|------------------------------------------------------------------------------------|
| [`fit_transform`](#cuml.dask.feature_extraction.text.TfidfTransformer.fit_transform)(X[, y]) | Fit distributed TFIDFTransformer and then transform the given set of data samples. |
| [`transform`](#cuml.dask.feature_extraction.text.TfidfTransformer.transform)(X[, y])     | Use distributed TFIDFTransformer to transform the given set of data samples.       |

### Examples

```python
>>> import cupy as cp
>>> from sklearn.datasets import fetch_20newsgroups
>>> from sklearn.feature_extraction.text import CountVectorizer
>>> from dask_cuda import LocalCUDACluster
>>> from dask.distributed import Client
>>> from cuml.dask.common import to_sparse_dask_array
>>> from cuml.dask.naive_bayes import MultinomialNB
>>> import dask
>>> from cuml.dask.feature_extraction.text import TfidfTransformer

>>> # Create a local CUDA cluster
>>> cluster = LocalCUDACluster()
>>> client = Client(cluster)

>>> # Load corpus
>>> twenty_train = fetch_20newsgroups(subset='train',
...                         shuffle=True, random_state=42)
>>> cv = CountVectorizer()
>>> xformed = cv.fit_transform(twenty_train.data).astype(cp.float32)
>>> X = to_sparse_dask_array(xformed, client)

>>> y = dask.array.from_array(twenty_train.target, asarray=False,
...                     fancy=False).astype(cp.int32)

>>> multi_gpu_transformer = TfidfTransformer()
>>> X_transformed = multi_gpu_transformer.fit_transform(X)
>>> X_transformed.compute_chunk_sizes()
dask.array<...>

>>> model = MultinomialNB()
>>> model.fit(X_transformed, y)
<cuml.dask.naive_bayes.naive_bayes.MultinomialNB object at 0x...>
>>> result = model.score(X_transformed, y)
>>> print(result)
array(0.93264981)
>>> client.close()
>>> cluster.close()
```

<!-- !! processed by numpydoc !! -->

#### fit(X, y=None)[[source]](https://github.com/NVIDIA/cuml/blob/93418baf5/python/cuml/cuml/dask/feature_extraction/text/tfidf_transformer.py#L111)

Fit distributed TFIDF Transformer

* **Parameters:**
  **X**
* **Returns:**
  cuml.dask.feature_extraction.text.TfidfTransformer instance

<!-- !! processed by numpydoc !! -->

#### fit_transform(X, y=None)[[source]](https://github.com/NVIDIA/cuml/blob/93418baf5/python/cuml/cuml/dask/feature_extraction/text/tfidf_transformer.py#L158)

Fit distributed TFIDFTransformer and then transform
the given set of data samples.

* **Parameters:**
  **X**
* **Returns:**
  dask.Array with blocks containing transformed sparse cupy arrays

<!-- !! processed by numpydoc !! -->

#### get_combined_model()[[source]](https://github.com/NVIDIA/cuml/blob/93418baf5/python/cuml/cuml/dask/common/base.py#L57)

Return single-GPU model for serialization

* **Returns:**
  **model**
  : yet been trained.

<!-- !! processed by numpydoc !! -->

#### transform(X, y=None)[[source]](https://github.com/NVIDIA/cuml/blob/93418baf5/python/cuml/cuml/dask/feature_extraction/text/tfidf_transformer.py#L176)

Use distributed TFIDFTransformer to transform the
given set of data samples.

* **Parameters:**
  **X**
* **Returns:**
  dask.Array with blocks containing transformed sparse cupy arrays

<!-- !! processed by numpydoc !! -->