1. 数据集2. 模型设计3. 训练

from keras.datasets import imdb(X_train, y_train), (X_test, y_test) = imdb.load_data(path="imdb_full.pkl",                                                      nb_words=None,                                                      skip_top=0,                                                      maxlen=None,                                                      test_split=0.1)                                                      seed=113,                                                      start_char=1,                                                      oov_char=2,                                                      index_from=3) 1. path：如果你在本机上已有此数据集（位于‘~/.keras/datasets/‘+path），则载入。否则数据将下载到该目录下2. nb_words：整数或None，要考虑的最常见的单词数，任何出现频率更低的单词将会被编码到0的位置。3. skip_top：整数，忽略最常出现的若干单词，这些单词将会被编码为04. maxlen：整数，最大序列长度，任何长度大于此值的序列将被截断5. seed：整数，用于数据重排的随机数种子6. start_char：字符，序列的起始将以该字符标记，默认为1因为0通常用作padding7. oov_char：字符，因nb_words或skip_top限制而cut掉的单词将被该字符代替8. index_from：整数，真实的单词（而不是类似于start_char的特殊占位符）将从这个下标开始

X_train和X_test：序列的列表，每个序列都是词下标的列表。如果指定了nb_words，则序列中可能的最大下标为nb_words-1。如果指定了maxlen，则序列的最大可能长度为maxleny_train和y_test：为序列的标签，是一个二值list

X_train[0][1, 14, 22, 16, 43, 530, 973, 1622, 1385, 65, 458, 4468, 66, 3941, 4, 173, 36, 256, 5, 25, 100, 43, 838, 112, 50, 670, 2, 9, 35, 480, 284, 5, 150, 4, 172, 112, 167, 2, 336, 385, 39, 4, 172, 4536, 1111, 17, 546, 38, 13, 447, 4, 192, 50, 16, 6, 147, 2025, 19, 14, 22, 4, 1920, 4613, 469, 4, 22, 71, 87, 12, 16, 43, 530, 38, 76, 15, 13, 1247, 4, 22, 17, 515, 17, 12, 16, 626, 18, 19193, 5, 62, 386, 12, 8, 316, 8, 106, 5, 4, 2223, 5244, 16, 480, 66, 3785, 33, 4, 130, 12, 16, 38, 619, 5, 25, 124, 51, 36, 135, 48, 25, 1415, 33, 6, 22, 12, 215, 28, 77, 52, 5, 14, 407, 16, 82, 10311, 8, 4, 107, 117, 5952, 15, 256, 4, 2, 7, 3766, 5, 723, 36, 71, 43, 530, 476, 26, 400, 317, 46, 7, 4, 12118, 1029, 13, 104, 88, 4, 381, 15, 297, 98, 32, 2071, 56, 26, 141, 6, 194, 7486, 18, 4, 226, 22, 21, 134, 476, 26, 480, 5, 144, 30, 5535, 18, 51, 36, 28, 224, 92, 25, 104, 4, 226, 65, 16, 38, 1334, 88, 12, 16, 283, 5, 16, 4472, 113, 103, 32, 15, 16, 5345, 19, 178, 32]y_train[0]1

if ngram_range > 1:    print(‘Adding {}-gram features‘.format(ngram_range))    # Create set of unique n-gram from the training set.    ngram_set = set()    for input_list in X_train:        for i in range(2, ngram_range + 1):            set_of_ngram = create_ngram_set(input_list, ngram_value=http://www.mamicode.com/i)            ngram_set.update(set_of_ngram)    print(‘ngram_set.pop‘)    print(ngram_set.pop())

X_train shape: (2500, 400)X_test shape: (2500, 400)

https://github.com/fchollet/keras/blob/master/examples/imdb_fasttext.py

model.add(Embedding(max_features,                    embedding_dims,                    input_length=maxlen))

model.add(GlobalAveragePooling1D())

https://keras-cn.readthedocs.io/en/latest/layers/embedding_layer/http://www.cnblogs.com/bzjia-blog/p/3415790.htmlhttps://keras-cn.readthedocs.io/en/latest/layers/pooling_layer/

‘‘‘This example demonstrates the use of fasttext for text classificationBased on Joulin et al‘s paper:Bags of Tricks for Efficient Text Classificationhttps://arxiv.org/abs/1607.01759Results on IMDB datasets with uni and bi-gram embeddings:    Uni-gram: 0.8813 test accuracy after 5 epochs. 8s/epoch on i7 cpu.    Bi-gram : 0.9056 test accuracy after 5 epochs. 2s/epoch on GTX 980M gpu.‘‘‘from __future__ import print_functionimport numpy as npnp.random.seed(1337)  # for reproducibilityfrom keras.preprocessing import sequencefrom keras.models import Sequentialfrom keras.layers import Densefrom keras.layers import Embeddingfrom keras.layers import GlobalAveragePooling1Dfrom keras.datasets import imdbdef create_ngram_set(input_list, ngram_value=2):    """    Extract a set of n-grams from a list of integers.    >>> create_ngram_set([1, 4, 9, 4, 1, 4], ngram_value=http://www.mamicode.com/2)    {(4, 9), (4, 1), (1, 4), (9, 4)}    >>> create_ngram_set([1, 4, 9, 4, 1, 4], ngram_value=http://www.mamicode.com/3)    [(1, 4, 9), (4, 9, 4), (9, 4, 1), (4, 1, 4)]    """    return set(zip(*[input_list[i:] for i in range(ngram_value)]))def add_ngram(sequences, token_indice, ngram_range=2):    """    Augment the input list of list (sequences) by appending n-grams values.    Example: adding bi-gram    >>> sequences = [[1, 3, 4, 5], [1, 3, 7, 9, 2]]    >>> token_indice = {(1, 3): 1337, (9, 2): 42, (4, 5): 2017}    >>> add_ngram(sequences, token_indice, ngram_range=2)    [[1, 3, 4, 5, 1337, 2017], [1, 3, 7, 9, 2, 1337, 42]]    Example: adding tri-gram    >>> sequences = [[1, 3, 4, 5], [1, 3, 7, 9, 2]]    >>> token_indice = {(1, 3): 1337, (9, 2): 42, (4, 5): 2017, (7, 9, 2): 2018}    >>> add_ngram(sequences, token_indice, ngram_range=3)    [[1, 3, 4, 5, 1337], [1, 3, 7, 9, 2, 1337, 2018]]    """    new_sequences = []    for input_list in sequences:        new_list = input_list[:]        for i in range(len(new_list) - ngram_range + 1):            for ngram_value in range(2, ngram_range + 1):                ngram = tuple(new_list[i:i + ngram_value])                if ngram in token_indice:                    new_list.append(token_indice[ngram])        new_sequences.append(new_list)    return new_sequences# Set parameters:# ngram_range = 2 will add bi-grams featuresngram_range = 2max_features = 5000maxlen = 400batch_size = 32embedding_dims = 50nb_epoch = 120print(‘Loading data...‘)(X_train, y_train), (X_test, y_test) = imdb.load_data(    path="/home/zhenghan/keras/imdb_full.pkl",    nb_words=max_features)# truncate the datasettruncate_rate = 0.4X_train = X_train[:int(len(X_train) * truncate_rate)]y_train = y_train[:int(len(y_train) * truncate_rate)]X_test = X_test[:int(len(X_test) * truncate_rate)]y_test = y_test[:int(len(y_test) * truncate_rate)]print("X_train[0]")print(X_train[0])print(‘y_train[0]‘)print(y_train[0])print(len(X_train), ‘train sequences‘)print(len(X_test), ‘test sequences‘)print(‘Average train sequence length: {}‘.format(np.mean(list(map(len, X_train)), dtype=int)))print(‘Average test sequence length: {}‘.format(np.mean(list(map(len, X_test)), dtype=int)))if ngram_range > 1:    print(‘Adding {}-gram features‘.format(ngram_range))    # Create set of unique n-gram from the training set.    ngram_set = set()    for input_list in X_train:        for i in range(2, ngram_range + 1):            set_of_ngram = create_ngram_set(input_list, ngram_value=http://www.mamicode.com/i)            ngram_set.update(set_of_ngram)    print(‘ngram_set.pop‘)    print(ngram_set.pop())    # Dictionary mapping n-gram token to a unique integer.    # Integer values are greater than max_features in order    # to avoid collision with existing features.    start_index = max_features + 1    token_indice = {v: k + start_index for k, v in enumerate(ngram_set)}    indice_token = {token_indice[k]: k for k in token_indice}    # max_features is the highest integer that could be found in the dataset.    max_features = np.max(list(indice_token.keys())) + 1    print(‘max_features: ‘)    print(max_features)    # Augmenting X_train and X_test with n-grams features    X_train = add_ngram(X_train, token_indice, ngram_range)    X_test = add_ngram(X_test, token_indice, ngram_range)    print("X_train[0]")    print(X_train[0])    print(‘X_test[0]‘)    print(X_test[0])    print(‘Average train sequence length: {}‘.format(np.mean(list(map(len, X_train)), dtype=int)))    print(‘Average test sequence length: {}‘.format(np.mean(list(map(len, X_test)), dtype=int)))print(‘Pad sequences (samples x time)‘)X_train = sequence.pad_sequences(X_train, maxlen=maxlen)X_test = sequence.pad_sequences(X_test, maxlen=maxlen)print(‘X_train shape:‘, X_train.shape)print(‘X_test shape:‘, X_test.shape)print(‘Build model...‘)model = Sequential()# we start off with an efficient embedding layer which maps# our vocab indices into embedding_dims dimensionsmodel.add(Embedding(max_features,                    embedding_dims,                    input_length=maxlen))# we add a GlobalAveragePooling1D, which will average the embeddings# of all words in the documentmodel.add(GlobalAveragePooling1D())# We project onto a single unit output layer, and squash it with a sigmoid:model.add(Dense(1, activation=‘sigmoid‘))model.compile(loss=‘binary_crossentropy‘,              optimizer=‘adam‘,              metrics=[‘accuracy‘])model.fit(X_train, y_train,          batch_size=batch_size,          nb_epoch=nb_epoch,          validation_data=(X_test, y_test))

https://keras-cn.readthedocs.io/en/latest/other/datasets/https://keras-cn.readthedocs.io/en/latest/preprocessing/sequence/