# tf.keras.datasets.imdb.get_word_index

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/keras-team/keras/tree/v2.7.0/keras/datasets/imdb.py#L159-L188) |

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

#### View aliases


**Compat aliases for migration**

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

[`tf.compat.v1.keras.datasets.imdb.get_word_index`](https://www.tensorflow.org/api_docs/python/tf/keras/datasets/imdb/get_word_index)

<br />

    tf.keras.datasets.imdb.get_word_index(
        path='imdb_word_index.json'
    )

<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 />

#### Example:

    # Retrieve the training sequences.
    (x_train, _), _ = keras.datasets.imdb.load_data()
    # Retrieve the word index file mapping words to indices
    word_index = keras.datasets.imdb.get_word_index()
    # Reverse the word index to obtain a dict mapping indices to words
    inverted_word_index = dict((i, word) for (word, i) in word_index.items())
    # Decode the first sequence in the dataset
    decoded_sequence = " ".join(inverted_word_index[i] for i in x_train[0])