6biu SrSSKrSSKrSSKJr SSKJr SSKJ r SSK J r \ "S5S Sj5r \ "S 5SS j5r\ "S 5S 5rg)z%Reuters topic classification dataset.N)_remove_long_seq)get_file) tf_logging) keras_exportz keras.datasets.reuters.load_datac :SU ;a'[R"S5 U RS5nU (a[S[ U 535eSn [ UU S-SS9n[ R"USS 9n U S U S pS S S 5 [ RRU5n[ R"[W 55nURU5 Xn W Un Ub-U VVs/sHnU/UVs/sHnUU-PM sn-PM n nnO/U(a(U VVs/sHnUVs/sHnUU-PM snPM n nnU(a[Xload_data..s+1Asobject)dtype)loggingwarningpop TypeErrorstrrnploadrandom RandomStatearangelenshufflerrintarray)path num_wordsskip_topmaxlen test_splitseed start_charoov_char index_fromkwargs origin_folderfxslabelsrngindicesrwidxx_trainy_trainx_testy_tests r load_datar?sXV , JJz*  :3v;-HII G  }, N  D D )QsVQsVF * ))   %CiiB GKK B G_FBD E"Qzla8aa*na88" E 35 62aq)q!q:~q)2 6 %f&9  +++  DE E1a(a+)+Q 91 E   DF F2a!9!Qx18y8q8q!92 F c"gZ( )Cxx4C9288t <WGXXbhh7&,9OFF W / //K * )9 E) 6 F : Fsx1 I# I6/I1> I6 J!I< 0J0 J :J J ( J2J J J J I.1I6<JJ Jz%keras.datasets.reuters.get_word_indexcSn[UUS-SS9n[U5n[R"U5sSSS5 $!,(df  g=f)a0Retrieves 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 substract 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. r reuters_word_index.json 4d44cc38712099c9e383dc6e5f11a921r N)ropenjsonr!)r)r3r4s rget_word_indexrEsH& G  884 D dqyy| s < A z&keras.datasets.reuters.get_label_namescg)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-chemdlrgassilverwpihogleadrmrget_label_namesros/ rn) r NrNg?qr)rA)__doc__rDnumpyr #tf_keras.src.preprocessing.sequencertf_keras.src.utils.data_utilsrtensorflow.python.platformrr tensorflow.python.util.tf_exportrr?rErormrnrrys, @2=901     C02C0L567:67686rn