# tf.keras.datasets.reuters.get_word_index

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/keras-team/keras/tree/v2.13.1/keras/datasets/reuters.py#L164-L191) |

Retrieves a dict mapping words to their index in the Reuters dataset.

#### View aliases


**Compat aliases for migration**

See
[Migration guide](https://www.tensorflow.org/guide/migrate) for
more details.

\`tf.compat.v1.keras.datasets.reuters.get_word_index\`

<br />

    tf.keras.datasets.reuters.get_word_index(
        path='reuters_word_index.json'
    )

Actual word indices starts from 3, with 3 indices reserved for:
0 (padding), 1 (start), 2 (oov).

E.g. word index of 'the' is 1, but the in the actual training data, the
index of 'the' will be 1 + 3 = 4. Vice versa, to translate word indices in
training data back to words using this mapping, indices need to substract 3.

<br />

<br />

<br />

| ## Args ||
|---|---|
| `path` | where to cache the data (relative to `~/.keras/dataset`). |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| The word index dictionary. Keys are word strings, values are their index. ||

<br />