σ ίΖχXc @@sˆddlmZddlmZddlmZddlZddlZddl Z ddddddd dd d „ Z d d „Z dS(i(tabsolute_importi(tget_file(tzipNs reuters.npzgš™™™™™Ι?iqiic K@sZd| kr+tjdƒ| jdƒ}n| rJtdt| ƒƒ‚nt|ddƒ}tj|ƒ} | d} | d} | jƒtj j |ƒtj j | ƒtj j |ƒtj j | ƒ|d k rg| D]*} |gg| D]}||^qο^qά} n9|rHg| D]#} g| D]}||^q)^q} n|rΈg}g}xLt | | ƒD];\} }t| ƒ|krj|j| ƒ|j|ƒqjqjW|} |} n|sζtg| D]} t| ƒ^qΘƒ}n|d k r?g| D]=} g| D]*}||ks$||kr*|n|^q^qω} nig}xZ| D]R} g}x6| D].}||ks}||kr_|j|ƒq_q_W|j|ƒqLW|} tj| tt| ƒd|ƒ ƒ}tj| tt| ƒd|ƒ ƒ}tj| tt| ƒd|ƒƒ}tj| tt| ƒd|ƒƒ}||f||ffS( s7Loads the Reuters newswire classification dataset. # Arguments path: where to cache the data (relative to `~/.keras/dataset`). num_words: max number of words to include. Words are ranked by how often they occur (in the training set) and only the most frequent words are kept skip_top: skip the top N most frequently occuring words (which may not be informative). maxlen: truncate sequences after this length. test_split: Fraction of the dataset to be used as test data. seed: random seed for sample shuffling. start_char: The start of a sequence will be marked with this character. Set to 1 because 0 is usually the padding character. oov_char: words that were cut out because of the `num_words` or `skip_top` limit will be replaced with this character. index_from: index actual words with this index and higher. # Returns Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`. Note that 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. tnb_wordssDThe `nb_words` argument in `load_data` has been renamed `num_words`.s Unrecognized keyword arguments: torigins2https://s3.amazonaws.com/text-datasets/reuters.npztxtyiN(twarningstwarntpopt TypeErrortstrRtnptloadtclosetrandomtseedtshuffletNoneRtlentappendtmaxtarraytint(tpatht num_wordstskip_toptmaxlent test_splitRt start_chartoov_chart index_fromtkwargstnpzfiletxstlabelsRtwtnew_xst new_labelsRtnxtx_trainty_traintx_testty_test((s5/tmp/pip-build-X4mzal/keras/keras/datasets/reuters.pyt load_data sX      :3  ( M  ''''sreuters_word_index.jsoncC@s;t|ddƒ}t|ƒ}tj|ƒ}|jƒ|S(sΜRetrieves the dictionary mapping word indices back to words. # Arguments path: where to cache the data (relative to `~/.keras/dataset`). # Returns The word index dictionary. Rs>https://s3.amazonaws.com/text-datasets/reuters_word_index.json(RtopentjsonR R(Rtftdata((s5/tmp/pip-build-X4mzal/keras/keras/datasets/reuters.pytget_word_indexes   ( t __future__Rtutils.data_utilsRt six.movesRtnumpyR R.RRR,R1(((s5/tmp/pip-build-X4mzal/keras/keras/datasets/reuters.pyts     Y