a Sic @sldZddlZddlZddlmZddlmZddlm Z ddl m Z e ddddZ e ddddZdS)z%Reuters topic classification dataset.N)_remove_long_seq)get_file) tf_logging) keras_exportz keras.datasets.reuters.load_data reuters.npz皙?qc  sd| vrtd| d| r2tdt| d} t|| ddd}tj|dd "} | d | d } } Wd n1s~0Ytj |}t t | }| || |} | |} d urڇfd d| D} nrfdd| D} |rt || | \} } stdd| Dd ur@fdd| D} nfdd| D} tt | d|}tj| d |ddt| d |}}tj| |d ddt| |d }}||f||ffS)a* Loads the Reuters newswire classification dataset. This is a dataset of 11,228 newswires from Reuters, labeled over 46 topics. This was originally generated by parsing and preprocessing the classic Reuters-21578 dataset, but the preprocessing code is no longer packaged with Keras. See this [GitHub discussion](https://github.com/keras-team/keras/issues/12072) for more info. Each newswire is encoded as a list of word indexes (integers). For convenience, words are indexed by overall frequency in the dataset, so that for instance the integer "3" encodes the 3rd most frequent word in the data. This allows for quick filtering operations such as: "only consider the top 10,000 most common words, but eliminate the top 20 most common words". As a convention, "0" does not stand for a specific word, but instead is used to encode any unknown word. Args: path: where to cache the data (relative to `~/.keras/dataset`). num_words: integer or None. Words are ranked by how often they occur (in the training set) and only the `num_words` most frequent words are kept. Any less frequent word will appear as `oov_char` value in the sequence data. If None, all words are kept. Defaults to None, so all words are kept. skip_top: skip the top N most frequently occurring words (which may not be informative). These words will appear as `oov_char` value in the dataset. Defaults to 0, so no words are skipped. maxlen: int or None. Maximum sequence length. Any longer sequence will be truncated. Defaults to None, which means no truncation. test_split: Float between 0 and 1. Fraction of the dataset to be used as test data. Defaults to 0.2, meaning 20% of the dataset is used as test data. seed: int. Seed for reproducible data shuffling. start_char: int. The start of a sequence will be marked with this character. Defaults to 1 because 0 is usually the padding character. oov_char: int. The out-of-vocabulary character. Words that were cut out because of the `num_words` or `skip_top` limits will be replaced with this character. index_from: int. Index actual words with this index and higher. **kwargs: Used for backwards compatibility. Returns: Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`. **x_train, x_test**: lists of sequences, which are lists of indexes (integers). If the num_words argument was specific, the maximum possible index value is `num_words - 1`. If the `maxlen` argument was specified, the largest possible sequence length is `maxlen`. **y_train, y_test**: lists of integer labels (1 or 0). Note: The 'out of vocabulary' character is only used for words that were present in the training set but are not included because they're not making the `num_words` cut here. Words that were not seen in the training set but are in the test set have simply been skipped. nb_wordszDThe `nb_words` argument in `load_data` has been renamed `num_words`.z Unrecognized keyword arguments: (load_data...rrr)r start_charrrrrzload_data..csg|]}fdd|DqS)csg|] }|qSrrrrrrrrrrrrrrrrcss|]}t|VqdS)N)maxrrrr rzload_data..cs"g|]}fdd|DqS)cs,g|]$}|krkr$nn|nqSrrr num_wordsoov_charskip_toprrrrrrrr"rrrscs g|]}fdd|DqS)cs(g|] }|krkrnq|qSrrrr#r%rrrrrrrr&rrrrr object)dtype)loggingwarningpop TypeErrorstrrnploadrandom RandomStatearangelenshufflerr intarray)pathr#r%maxlen test_splitseedrr$rkwargs origin_folderfxslabelsrngindicesidxx_trainy_trainx_testy_testr)rr#r$r%rr load_datasPL 0    *rGz%keras.datasets.reuters.get_word_indexreuters_word_index.jsoncCsLd}t||ddd}t|}t|WdS1s>0YdS)aRetrieves a dict mapping words to their index in the Reuters dataset. Args: path: where to cache the data (relative to `~/.keras/dataset`). Returns: The word index dictionary. Keys are word strings, values are their index. r rHZ 4d44cc38712099c9e383dc6e5f11a921rN)ropenjsonr/)r7r<r=rrrget_word_indexs  rK) rNrNrrr r r )rH)__doc__rJnumpyr.Zkeras.preprocessing.sequencerkeras.utils.data_utilsrtensorflow.python.platformrr) tensorflow.python.util.tf_exportrrGrKrrrrs(