2Vh.dZddlZddlZddlmZddlmZddlm Z ed d dZ edd d Z ed d Z y)z%Reuters topic classification dataset.N) keras_export)get_file)remove_long_seqz keras.datasets.reuters.load_datac Pd} t|| dzd}tj|d5} | d| d} } d d d tjj |} tj t  }| j|| |}  |} |'| Dcgc]}|g|Dcgc]}||z c}z} }}n$|r"| Dcgc]}|Dcgc]}||z c}} }}|rt|| | \} } |std | D}|0| Dcgc]"}|Dcgc]}||cxkr|krnn|n|c}$} }}n.| Dcgc]!}|Dcgc]}||cxkr|ksnn|c}#} }}tt | d |z z}tj| d |d tj| d |}}tj| |d d tj| |d }}||f||ffS#1swYxYwcc}wcc}}wcc}wcc}}wcc}wcc}}wcc}wcc}}w)a7 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`. 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. 0 means no words are skipped. Defaults to `0`. maxlen: int or None. Maximum sequence length. Any longer sequence will be truncated. None means no truncation. Defaults to `None`. test_split: Float between `0.` and `1.`. Fraction of the dataset to be used as test data. `0.2` means that 20% of the dataset is used as test data. Defaults to `0.2`. seed: int. Seed for reproducible data shuffling. start_char: int. The start of a sequence will be marked with this character. 0 is usually the padding character. Defaults to `1`. 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. 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. zload_data..qs+1A+sobject)dtype) rnploadrandom RandomStatearangelenshufflerrintarray)path num_wordsskip_topmaxlen test_splitseed start_charoov_char index_from origin_folderfxslabelsrngindicesrwidxx_trainy_trainx_testy_tests r load_datar6 s:T G }, N  D D )$QsVQsVF$ ))   %CiiB GKK GB G_FBD EQzla8a*n88 E E 35 6aq)!q:~) 6 6 $VR8 F +++  DE Ea(a+)+Q 9 E  DF Fa!9Qx18y8q9 F F c"gZ( )C DS* GXXbhh7&,9OFF W / //M$$9 E) 6 F : Fsq G/ H( G<4H H  H H  HH 2H H" H H !H"/G9<HH HH"z%keras.datasets.reuters.get_word_indexcd}t||dzd}t|5}tj|cdddS#1swYyxYw)a[Retrieves a dict mapping words to their index in the Reuters dataset. 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 subtract 3. Args: path: where to cache the data (relative to `~/.keras/dataset`). Returns: The word index dictionary. Keys are word strings, values are their index. rreuters_word_index.json 4d44cc38712099c9e383dc6e5f11a921)r r N)ropenjsonr)r!r*r+s rget_word_indexr<sS& G  884 D dqyy|s >Az&keras.datasets.reuters.get_label_namescy)zReturns labels as a list of strings with indices matching training data. Reference: - [Reuters Dataset](https://martin-thoma.com/nlp-reuters/) ).cocoagrainzveg-oilearnacqwheatcopperhousingz money-supplycoffeesugartradereservesshipcottoncarcasscrudeznat-gascpizmoney-fxinterestgnpz meal-feedalumoilseedgoldtinzstrategic-metal livestockretailipiz iron-steelrubberheatjobsleibopzincorangezpet-chemdlrgassilverwpihogleadrdrget_label_namesrfs/ re) rNrNg?qr)r8) __doc__r;numpyrkeras.src.api_exportrkeras.src.utils.file_utilsrkeras.src.utils.python_utilsrr6r<rfrdrerros+ -/801     x02x0v567:67686re