DL之LSTM：基于《wonderland爱丽丝梦游仙境记》小说数据集利用LSTM算法(基于keras)对word实现预测daiding

ゝ一纸荒年。 2022-10-22 10:56 111阅读 0赞

DL之LSTM：基于《wonderland爱丽丝梦游仙境记》小说数据集利用LSTM算法(基于keras)对word实现预测

**目录**

基于《wonderland爱丽丝梦游仙境记》小说数据集利用LSTM算法(基于keras)对word实现预测

输出结果

核心代码

--------------------

# 基于《wonderland爱丽丝梦游仙境记》小说数据集利用LSTM算法(基于keras)对word实现预测 #

## 输出结果 ##

rawtext_BySpaceConnect: ALICE'S ADVENTURES IN WONDERLAND  Lewis Carroll  THE MILLENNIUM FULCRUM EDITION 3.0  CHAPTER I. Down the Rabbit-Hole  Alice was beginning to get very tired of sitting by her sister on the bank, and of having nothing to do: once or twice she had peeped into the book her sister was reading, but it had no pictures or conversations in it, 'and what is the use of a book,' thought Alice 'without pictures or conversations?'  So she was considering in her own mind (as well as she could, for the hot day 
    rawtext2WordLists: ["ALICE'S", 'ADVENTURES', 'IN', 'WONDERLAND', 'Lewis', 'Carroll', 'THE', 'MILLENNIUM', 'FULCRUM', 'EDITION', '3.0', 'CHAPTER', 'I', 'Down', 'the', 'Rabbit-Hole', 'Alice', 'was', 'beginning', 'to', 'get', 'very', 'tired', 'of', 'sitting', 'by', 'her', 'sister', 'on', 'the', 'bank', 'and', 'of', 'having', 'nothing', 'to', 'do', 'once', 'or', 'twice', 'she', 'had', 'peeped', 'into', 'the', 'book', 'her', 'sister', 'was', 'reading', 'but', 'it', 'had', 'no', 'pictures', 'or', 'conversations', 'in', 'it', 'and', 'what', 'is', 'the', 'use', 'of', 'a', 'book', 'thought', 'Alice', 'without', 'pictures', 'or', 'conversations', 'So', 'she', 'was', 'considering', 'in', 'her', 'own', 'mind', 'as', 'well', 'as', 'she', 'could', 'for', 'the', 'hot', 'day', 'made', 'her', 'feel', 'very', 'sleepy', 'and', 'stupid', 'whether', 'the', 'pleasure', 'of', 'making', 'a', 'daisy-chain', 'would', 'be', 'worth', 'the', 'trouble', 'of', 'getting', 'up', 'and', 'picking', 'the', 'daisies', 'when', 'suddenly', 'a', 'White', 'Rabbit', 'with', 'pink', 'eyes', 'ran', 'close', 'by', 'her', 'There', 'was', 'nothing', 'so', 'VERY', 'remarkable', 'in', 'that', 'nor', 'did', 'Alice', 'think', 'it', 'so', 'VERY', 'much', 'out', 'of', 'the', 'way', 'to', 'hear', 'the', 'Rabbit', 'say', 'to', 'itself', 'Oh', 'dear', 'Oh', 'dear', 'I', 'shall', 'be', 'late', 'when', 'she', 'thought', 'it', 'over', 'afterwards', 'it', 'occurred', 'to', 'her', 'that', 'she', 'ought', 'to', 'have', 'wondered', 'at', 'this', 'but', 'at', 'the', 'time', 'it', 'all', 'seemed', 'quite', 'natural', 'but', 'when', 'the', 'Rabbit', 'actually', 'TOOK', 'A', 'WATCH', 'OUT', 'OF', 'ITS', 'WAISTCOAT-POCKET', 'and', 'looked', 'at', 'it', 'and', 'then', 'hurried', 'on', 'Alice', 'started', 'to', 'her', 'feet', 'for', 'it', 'flashed', 'across', 'her', 'mind', 'that', 'she', 'had', 'never', 'before', 'seen', 'a', 'rabbit', 'with', 'either', 'a', 'waistcoat-pocket', 'or', 'a', 'watch', 'to', 'take', 'out', 'of', 'it', 'and', 'burning', 'with', 'curiosity', 'she', 'ran', 'across', 'the', 'field', 'after', 'it', 'and', 'fortunately', 'was', 'just', 'in', 'time', 'to', 'see', 'it', 'pop', 'down', 'a', 'large', 'rabbit-hole', 'under', 'the', 'hedge', 'In', 'another', 'moment', 'down', 'went', 'Alice', 'after', 'it', 'never', 'once', 'considering', 'how', 'in', 'the', 'world', 'she', 'was', 'to', 'get', 'out', 'again', 'The', 'rabbit-hole', 'went', 'straight', 'on', 'like', 'a', 'tunnel', 'for', 'some', 'way', 'and', 'then', 'dipped', 'suddenly', 'down', 'so', 'suddenly', 'that', 'Alice', 'had', 'not', 'a', 'moment', 'to', 'think', 'about', 'stopping', 'herself', 'before', 'she', 'found', 'herself', 'falling', 'down', 'a', 'very', 'deep', 'well', 'Either', 'the', 'well', 'was', 'very', 'deep', 'or', 'she', 'fell', 'very', 'slowly', 'for', 'she', 'had', 'plenty', 'of', 'time', 'as', 'she', 'went', 'down', 'to', 'look', 'about', 'her', 'and', 'to', 'wonder', 'what', 'was', 'going', 'to', 'happen', 'next', 'First', 'she', 'tried', 'to', 'look', 'down', 'and', 'make', 'out', 'what', 'she', 'was', 'coming', 'to', 'but', 'it', 'was', 'too', 'dark', 'to', 'see', 'anything', 'then', 'she', 'looked', 'at', 'the', 'sides', 'of', 'the', 'well', 'and', 'noticed', 'that', 'they', 'were', 'filled', 'with', 'cupboards', 'and', 'book-shelves', 'here', 'and', 'there', 'she', 'saw', 'maps', 'and', 'pictures', 'hung', 'upon', 'pegs', 'She', 'took', 'down', 'a', 'jar', 'from', 'one', 'of', 'the', 'shelves', 'as', 'she', 'passed', 'it', 'was', 'labelled', 'ORANGE', 'MARMALADE', 'but', 'to', 'her', 'great', 'disappointment', 'it', 'was', 'empty', 'she', 'did', 'not', 'like', 'to', 'drop', 'the', 'jar', 'for', 'fear', 'of', 'killing', 'somebody', 'so', 'managed', 'to', 'put', 'it', 'into', 'one', 'of', 'the', 'cupboards', 'as', 'she', 'fell', 'past', 'it', 'Well', 'thought', 'Alice', 'to', 'herself', 'after', 'such', 'a', 'fall', 'as', 'this', 'I', 'shall', 'think', 'nothing', 'of', 'tumbling', 'down', 'stairs', 'How', 'brave', "they'll", 'all', 'think', 'me', 'at', 'home', 'Why', 'I', "wouldn't", 'say']
    rawtext_BySpace: ALICE'S ADVENTURES IN WONDERLAND Lewis Carroll THE MILLENNIUM FULCRUM EDITION 3.0 CHAPTER I Down the Rabbit Hole Alice was beginning to get very tired of sitting by her sister on the bank and of having nothing to do once or twice she had peeped into the book her sister was reading but it had no pictures or conversations in it and what is the use of a book thought Alice without pictures or conversations So she was considering in her own mind as well as she could for the hot day made her feel very
    words_num: 26694
    vocab_num: 3063
    dataX： 26594 100 [[19, 18, 238, 547, 278, 84, 469, 294, 160, 133, 16, 74, 227, 125, 2713, 393, 223, 31, 2932, 769, 2773, 1456, 2905, 2770, 2006, 2500, 862, 1569, 2495, 2019, 2713, 733, 660, 2006, 1543, 1988, 2773, 1144, 2020, 2035, 2841, 2434, 1513, 2091, 1663, 2713, 810, 1569, 2495, 2932, 2258, 856, 1675, 1513, 1977, 2111, 2035, 1006, 1640, 1675, 660, 2960, 1673, 2713, 2886, 2006, 594, 810, 2741, 31, 3004, 2111, 2035, 1006, 440, 2434, 2932, 996, 1640, 1569, 2051, 1897, 701, 2954, 701, 2434, 1012, 1402, 2713, 1603, 1083, 1847, 1569, 1328, 2905, 2513, 660, 2637, 2969, 2713], [18, 238, 547, 278, 84, 469, 294, 160, 133, 16, 74, 227, 125, 2713, 393, 223, 31, 2932, 769, 2773, 1456, 2905, 2770, 2006, 2500, 862, 1569, 2495, 2019, 2713, 733, 660, 2006, 1543, 1988, 2773, 1144, 2020, 2035, 2841, 2434, 1513, 2091, 1663, 2713, 810, 1569, 2495, 2932, 2258, 856, 1675, 1513, 1977, 2111, 2035, 1006, 1640, 1675, 660, 2960, 1673, 2713, 2886, 2006, 594, 810, 2741, 31, 3004, 2111, 2035, 1006, 440, 2434, 2932, 996, 1640, 1569, 2051, 1897, 701, 2954, 701, 2434, 1012, 1402, 2713, 1603, 1083, 1847, 1569, 1328, 2905, 2513, 660, 2637, 2969, 2713, 2144], [238, 547, 278, 84, 469, 294, 160, 133, 16, 74, 227, 125, 2713, 393, 223, 31, 2932, 769, 2773, 1456, 2905, 2770, 2006, 2500, 862, 1569, 2495, 2019, 2713, 733, 660, 2006, 1543, 1988, 2773, 1144, 2020, 2035, 2841, 2434, 1513, 2091, 1663, 2713, 810, 1569, 2495, 2932, 2258, 856, 1675, 1513, 1977, 2111, 2035, 1006, 1640, 1675, 660, 2960, 1673, 2713, 2886, 2006, 594, 810, 2741, 31, 3004, 2111, 2035, 1006, 440, 2434, 2932, 996, 1640, 1569, 2051, 1897, 701, 2954, 701, 2434, 1012, 1402, 2713, 1603, 1083, 1847, 1569, 1328, 2905, 2513, 660, 2637, 2969, 2713, 2144, 2006], [547, 278, 84, 469, 294, 160, 133, 16, 74, 227, 125, 2713, 393, 223, 31, 2932, 769, 2773, 1456, 2905, 2770, 2006, 2500, 862, 1569, 2495, 2019, 2713, 733, 660, 2006, 1543, 1988, 2773, 1144, 2020, 2035, 2841, 2434, 1513, 2091, 1663, 2713, 810, 1569, 2495, 2932, 2258, 856, 1675, 1513, 1977, 2111, 2035, 1006, 1640, 1675, 660, 2960, 1673, 2713, 2886, 2006, 594, 810, 2741, 31, 3004, 2111, 2035, 1006, 440, 2434, 2932, 996, 1640, 1569, 2051, 1897, 701, 2954, 701, 2434, 1012, 1402, 2713, 1603, 1083, 1847, 1569, 1328, 2905, 2513, 660, 2637, 2969, 2713, 2144, 2006, 1851], [278, 84, 469, 294, 160, 133, 16, 74, 227, 125, 2713, 393, 223, 31, 2932, 769, 2773, 1456, 2905, 2770, 2006, 2500, 862, 1569, 2495, 2019, 2713, 733, 660, 2006, 1543, 1988, 2773, 1144, 2020, 2035, 2841, 2434, 1513, 2091, 1663, 2713, 810, 1569, 2495, 2932, 2258, 856, 1675, 1513, 1977, 2111, 2035, 1006, 1640, 1675, 660, 2960, 1673, 2713, 2886, 2006, 594, 810, 2741, 31, 3004, 2111, 2035, 1006, 440, 2434, 2932, 996, 1640, 1569, 2051, 1897, 701, 2954, 701, 2434, 1012, 1402, 2713, 1603, 1083, 1847, 1569, 1328, 2905, 2513, 660, 2637, 2969, 2713, 2144, 2006, 1851, 594]]
    dataY： 26594 [2144, 2006, 1851, 594, 1074]
    Total patterns: 26594
    X_train.shape (26594, 100, 1)
    Y_train.shape (26594, 3063)
    _________________________________________________________________
    Layer (type)                 Output Shape              Param #   
    =================================================================
    lstm_1 (LSTM)                (None, 256)               264192    
    _________________________________________________________________
    dropout_1 (Dropout)          (None, 256)               0         
    _________________________________________________________________
    dense_1 (Dense)              (None, 3063)              787191    
    =================================================================
    Total params: 1,051,383
    Trainable params: 1,051,383
    Non-trainable params: 0
    _________________________________________________________________
    LSTM_Model 
     None
    
    
    ……
    
    Epoch 00005: loss improved from 6.26403 to 6.26198, saving model to hdf5/word-weights-improvement-05-6.2620.hdf5
    Epoch 6/10
    
      128/26594 [..............................] - ETA: 2:09 - loss: 6.8378
      256/26594 [..............................] - ETA: 2:06 - loss: 6.4136
      384/26594 [..............................] - ETA: 2:01 - loss: 6.3299
      512/26594 [..............................] - ETA: 1:57 - loss: 6.4469
      640/26594 [..............................] - ETA: 1:57 - loss: 6.4133
    
    ……
    
    Epoch 00008: loss improved from 6.25725 to 6.25487, saving model to hdf5/word-weights-improvement-08-6.2549.hdf5
    Epoch 9/10
    
      128/26594 [..............................] - ETA: 1:57 - loss: 6.2336
      256/26594 [..............................] - ETA: 2:02 - loss: 6.1897
      384/26594 [..............................] - ETA: 2:04 - loss: 6.3229
      512/26594 [..............................] - ETA: 2:01 - loss: 6.3550
      640/26594 [..............................] - ETA: 2:02 - loss: 6.3279
      768/26594 [..............................] - ETA: 2:05 - loss: 6.2614
      896/26594 [>.............................] - ETA: 2:06 - loss: 6.2433
     1024/26594 [>.............................] - ETA: 2:07 - loss: 6.2477
    ……
    
    25216/26594 [===========================>..] - ETA: 6s - loss: 6.2456
    25344/26594 [===========================>..] - ETA: 6s - loss: 6.2469
    25472/26594 [===========================>..] - ETA: 5s - loss: 6.2477
    25600/26594 [===========================>..] - ETA: 4s - loss: 6.2486
    25728/26594 [============================>.] - ETA: 4s - loss: 6.2480
    25856/26594 [============================>.] - ETA: 3s - loss: 6.2483
    25984/26594 [============================>.] - ETA: 2s - loss: 6.2487
    26112/26594 [============================>.] - ETA: 2s - loss: 6.2485
    26240/26594 [============================>.] - ETA: 1s - loss: 6.2483
    26368/26594 [============================>.] - ETA: 1s - loss: 6.2482
    26496/26594 [============================>.] - ETA: 0s - loss: 6.2485
    26594/26594 [==============================] - 129s 5ms/step - loss: 6.2499
    
    Epoch 00009: loss improved from 6.25487 to 6.24987, saving model to hdf5/word-weights-improvement-09-6.2499.hdf5
    Epoch 10/10
    
      128/26594 [..............................] - ETA: 1:56 - loss: 6.4864
      256/26594 [..............................] - ETA: 2:04 - loss: 6.2577
      384/26594 [..............................] - ETA: 2:07 - loss: 6.2857
      512/26594 [..............................] - ETA: 2:10 - loss: 6.3230
    ……
    
    25856/26594 [============================>.] - ETA: 3s - loss: 6.2426
    25984/26594 [============================>.] - ETA: 3s - loss: 6.2447
    26112/26594 [============================>.] - ETA: 2s - loss: 6.2446
    26240/26594 [============================>.] - ETA: 1s - loss: 6.2449
    26368/26594 [============================>.] - ETA: 1s - loss: 6.2467
    26496/26594 [============================>.] - ETA: 0s - loss: 6.2461
    26594/26594 [==============================] - 135s 5ms/step - loss: 6.2465
    
    
    
    Epoch 00010: loss improved from 6.24987 to 6.24646, saving model to hdf5/word-weights-improvement-10-6.2465.hdf5
    LSTM_Pre_word.shape: 
     (3, 3063)
    
    
    
    
    
    LSTM_Model，Seed:
    " cheerfully he seems to grin How neatly spread his claws And welcome little fishes in With gently smiling jaws I'm sure those are not the right words said poor Alice and her eyes filled with tears again as she went on I must be Mabel after all and I shall have to go and live in that poky little house and have next to no toys to play with and oh ever so many lessons to learn No I've made up my mind about it if I'm Mabel I'll stay down here It'll be no use their putting their heads "
    199 100
    
     Generated Sequence:
    the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the the
    
     Done.

## 核心代码 ##

LSTM_Model = Sequential()
    LSTM_Model.add(LSTM(256, input_shape=(X_train.shape[1], X_train.shape[2])))
    LSTM_Model.add(Dropout(0.2))
    LSTM_Model.add(Dense(Y_train.shape[1], activation='softmax'))
    LSTM_Model.compile(loss='categorical_crossentropy', optimizer='adam')
    print('LSTM_Model \n',LSTM_Model.summary())