IMDB 数据集探索

代码参考：

https://www.tensorflow.org/tutorials/keras/basic_text_classification

https://my.oschina.net/u/3800567/blog/2887156

代码存放：https://colab.research.google.com/drive/1vpo6LSRfvnUj3G4JGEKsqGCl6HGevIaK#scrollTo=b2H9UBT4qXay

import tensorflow as tf
from tensorflow import keras

imdb = keras.datasets.imdb
(X_train,y_train),(X_test,y_test) = imdb.load_data(num_words=10000)

这里需要注意的是，num_words的设定，如果为None，后面训练模型有一个参数词向量大小的设置，会报错：

InvalidArgumentError: indices[64,51] = 32616 is not in [0, 5000) [[{{node embedding/embedding_lookup}}]]

X_train[:10],y_train[:10]
output:(array([list([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, 2, 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, 2, 8, 4, 107, 117, 5952, 15, 256, 4, 2, 7, 3766, 5, 723, 36, 71, 43, 530, 476, 26, 400, 317, 46, 7, 4, 2, 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]),
        list([1, 194, 1153, 194, 8255, 78, 228, 5, 6, 1463, 4369, 5012, 134, 26, 4, 715, 8, 118, 1634, 14, 394, 20, 13, 119, 954, 189, 102, 5, 207, 110, 3103, 21, 14, 69, 188, 8, 30, 23, 7, 4, 249, 126, 93, 4, 114, 9, 2300, 1523, 5, 647, 4, 116, 9, 35, 8163, 4, 229, 9, 340, 1322, 4, 118, 9, 4, 130, 4901, 19, 4, 1002, 5, 89, 29, 952, 46, 37, 4, 455, 9, 45, 43, 38, 1543, 1905, 398, 4, 1649, 26, 6853, 5, 163, 11, 3215, 2, 4, 1153, 9, 194, 775, 7, 8255, 2, 349, 2637, 148, 605, 2, 8003, 15, 123, 125, 68, 2, 6853, 15, 349, 165, 4362, 98, 5, 4, 228, 9, 43, 2, 1157, 15, 299, 120, 5, 120, 174, 11, 220, 175, 136, 50, 9, 4373, 228, 8255, 5, 2, 656, 245, 2350, 5, 4, 9837, 131, 152, 491, 18, 2, 32, 7464, 1212, 14, 9, 6, 371, 78, 22, 625, 64, 1382, 9, 8, 168, 145, 23, 4, 1690, 15, 16, 4, 1355, 5, 28, 6, 52, 154, 462, 33, 89, 78, 285, 16, 145, 95]),
        list([1, 14, 47, 8, 30, 31, 7, 4, 249, 108, 7, 4, 5974, 54, 61, 369, 13, 71, 149, 14, 22, 112, 4, 2401, 311, 12, 16, 3711, 33, 75, 43, 1829, 296, 4, 86, 320, 35, 534, 19, 263, 4821, 1301, 4, 1873, 33, 89, 78, 12, 66, 16, 4, 360, 7, 4, 58, 316, 334, 11, 4, 1716, 43, 645, 662, 8, 257, 85, 1200, 42, 1228, 2578, 83, 68, 3912, 15, 36, 165, 1539, 278, 36, 69, 2, 780, 8, 106, 14, 6905, 1338, 18, 6, 22, 12, 215, 28, 610, 40, 6, 87, 326, 23, 2300, 21, 23, 22, 12, 272, 40, 57, 31, 11, 4, 22, 47, 6, 2307, 51, 9, 170, 23, 595, 116, 595, 1352, 13, 191, 79, 638, 89, 2, 14, 9, 8, 106, 607, 624, 35, 534, 6, 227, 7, 129, 113]),
        list([1, 4, 2, 2, 33, 2804, 4, 2040, 432, 111, 153, 103, 4, 1494, 13, 70, 131, 67, 11, 61, 2, 744, 35, 3715, 761, 61, 5766, 452, 9214, 4, 985, 7, 2, 59, 166, 4, 105, 216, 1239, 41, 1797, 9, 15, 7, 35, 744, 2413, 31, 8, 4, 687, 23, 4, 2, 7339, 6, 3693, 42, 38, 39, 121, 59, 456, 10, 10, 7, 265, 12, 575, 111, 153, 159, 59, 16, 1447, 21, 25, 586, 482, 39, 4, 96, 59, 716, 12, 4, 172, 65, 9, 579, 11, 6004, 4, 1615, 5, 2, 7, 5168, 17, 13, 7064, 12, 19, 6, 464, 31, 314, 11, 2, 6, 719, 605, 11, 8, 202, 27, 310, 4, 3772, 3501, 8, 2722, 58, 10, 10, 537, 2116, 180, 40, 14, 413, 173, 7, 263, 112, 37, 152, 377, 4, 537, 263, 846, 579, 178, 54, 75, 71, 476, 36, 413, 263, 2504, 182, 5, 17, 75, 2306, 922, 36, 279, 131, 2895, 17, 2867, 42, 17, 35, 921, 2, 192, 5, 1219, 3890, 19, 2, 217, 4122, 1710, 537, 2, 1236, 5, 736, 10, 10, 61, 403, 9, 2, 40, 61, 4494, 5, 27, 4494, 159, 90, 263, 2311, 4319, 309, 8, 178, 5, 82, 4319, 4, 65, 15, 9225, 145, 143, 5122, 12, 7039, 537, 746, 537, 537, 15, 7979, 4, 2, 594, 7, 5168, 94, 9096, 3987, 2, 11, 2, 4, 538, 7, 1795, 246, 2, 9, 2, 11, 635, 14, 9, 51, 408, 12, 94, 318, 1382, 12, 47, 6, 2683, 936, 5, 6307, 2, 19, 49, 7, 4, 1885, 2, 1118, 25, 80, 126, 842, 10, 10, 2, 2, 4726, 27, 4494, 11, 1550, 3633, 159, 27, 341, 29, 2733, 19, 4185, 173, 7, 90, 2, 8, 30, 11, 4, 1784, 86, 1117, 8, 3261, 46, 11, 2, 21, 29, 9, 2841, 23, 4, 1010, 2, 793, 6, 2, 1386, 1830, 10, 10, 246, 50, 9, 6, 2750, 1944, 746, 90, 29, 2, 8, 124, 4, 882, 4, 882, 496, 27, 2, 2213, 537, 121, 127, 1219, 130, 5, 29, 494, 8, 124, 4, 882, 496, 4, 341, 7, 27, 846, 10, 10, 29, 9, 1906, 8, 97, 6, 236, 2, 1311, 8, 4, 2, 7, 31, 7, 2, 91, 2, 3987, 70, 4, 882, 30, 579, 42, 9, 12, 32, 11, 537, 10, 10, 11, 14, 65, 44, 537, 75, 2, 1775, 3353, 2, 1846, 4, 2, 7, 154, 5, 4, 518, 53, 2, 2, 7, 3211, 882, 11, 399, 38, 75, 257, 3807, 19, 2, 17, 29, 456, 4, 65, 7, 27, 205, 113, 10, 10, 2, 4, 2, 2, 9, 242, 4, 91, 1202, 2, 5, 2070, 307, 22, 7, 5168, 126, 93, 40, 2, 13, 188, 1076, 3222, 19, 4, 2, 7, 2348, 537, 23, 53, 537, 21, 82, 40, 2, 13, 2, 14, 280, 13, 219, 4, 2, 431, 758, 859, 4, 953, 1052, 2, 7, 5991, 5, 94, 40, 25, 238, 60, 2, 4, 2, 804, 2, 7, 4, 9941, 132, 8, 67, 6, 22, 15, 9, 283, 8, 5168, 14, 31, 9, 242, 955, 48, 25, 279, 2, 23, 12, 1685, 195, 25, 238, 60, 796, 2, 4, 671, 7, 2804, 5, 4, 559, 154, 888, 7, 726, 50, 26, 49, 7008, 15, 566, 30, 579, 21, 64, 2574]),
        list([1, 249, 1323, 7, 61, 113, 10, 10, 13, 1637, 14, 20, 56, 33, 2401, 18, 457, 88, 13, 2626, 1400, 45, 3171, 13, 70, 79, 49, 706, 919, 13, 16, 355, 340, 355, 1696, 96, 143, 4, 22, 32, 289, 7, 61, 369, 71, 2359, 5, 13, 16, 131, 2073, 249, 114, 249, 229, 249, 20, 13, 28, 126, 110, 13, 473, 8, 569, 61, 419, 56, 429, 6, 1513, 18, 35, 534, 95, 474, 570, 5, 25, 124, 138, 88, 12, 421, 1543, 52, 725, 6397, 61, 419, 11, 13, 1571, 15, 1543, 20, 11, 4, 2, 5, 296, 12, 3524, 5, 15, 421, 128, 74, 233, 334, 207, 126, 224, 12, 562, 298, 2167, 1272, 7, 2601, 5, 516, 988, 43, 8, 79, 120, 15, 595, 13, 784, 25, 3171, 18, 165, 170, 143, 19, 14, 5, 7224, 6, 226, 251, 7, 61, 113]),
        list([1, 778, 128, 74, 12, 630, 163, 15, 4, 1766, 7982, 1051, 2, 32, 85, 156, 45, 40, 148, 139, 121, 664, 665, 10, 10, 1361, 173, 4, 749, 2, 16, 3804, 8, 4, 226, 65, 12, 43, 127, 24, 2, 10, 10]),
        list([1, 6740, 365, 1234, 5, 1156, 354, 11, 14, 5327, 6638, 7, 1016, 2, 5940, 356, 44, 4, 1349, 500, 746, 5, 200, 4, 4132, 11, 2, 9363, 1117, 1831, 7485, 5, 4831, 26, 6, 2, 4183, 17, 369, 37, 215, 1345, 143, 2, 5, 1838, 8, 1974, 15, 36, 119, 257, 85, 52, 486, 9, 6, 2, 8564, 63, 271, 6, 196, 96, 949, 4121, 4, 2, 7, 4, 2212, 2436, 819, 63, 47, 77, 7175, 180, 6, 227, 11, 94, 2494, 2, 13, 423, 4, 168, 7, 4, 22, 5, 89, 665, 71, 270, 56, 5, 13, 197, 12, 161, 5390, 99, 76, 23, 2, 7, 419, 665, 40, 91, 85, 108, 7, 4, 2084, 5, 4773, 81, 55, 52, 1901]),
        list([1, 4, 2, 716, 4, 65, 7, 4, 689, 4367, 6308, 2343, 4804, 2, 2, 5270, 2, 2315, 2, 2, 2, 2, 4, 2, 628, 7685, 37, 9, 150, 4, 9820, 4069, 11, 2909, 4, 2, 847, 313, 6, 176, 2, 9, 6202, 138, 9, 4434, 19, 4, 96, 183, 26, 4, 192, 15, 27, 5842, 799, 7101, 2, 588, 84, 11, 4, 3231, 152, 339, 5206, 42, 4869, 2, 6293, 345, 4804, 2, 142, 43, 218, 208, 54, 29, 853, 659, 46, 4, 882, 183, 80, 115, 30, 4, 172, 174, 10, 10, 1001, 398, 1001, 1055, 526, 34, 3717, 2, 5262, 2, 17, 4, 6706, 1094, 871, 64, 85, 22, 2030, 1109, 38, 230, 9, 4, 4324, 2, 251, 5056, 1034, 195, 301, 14, 16, 31, 7, 4, 2, 8, 783, 2, 33, 4, 2945, 103, 465, 2, 42, 845, 45, 446, 11, 1895, 19, 184, 76, 32, 4, 5310, 207, 110, 13, 197, 4, 2, 16, 601, 964, 2152, 595, 13, 258, 4, 1730, 66, 338, 55, 5312, 4, 550, 728, 65, 1196, 8, 1839, 61, 1546, 42, 8361, 61, 602, 120, 45, 7304, 6, 320, 786, 99, 196, 2, 786, 5936, 4, 225, 4, 373, 1009, 33, 4, 130, 63, 69, 72, 1104, 46, 1292, 225, 14, 66, 194, 2, 1703, 56, 8, 803, 1004, 6, 2, 155, 11, 4, 2, 3231, 45, 853, 2029, 8, 30, 6, 117, 430, 19, 6, 8941, 9, 15, 66, 424, 8, 2337, 178, 9, 15, 66, 424, 8, 1465, 178, 9, 15, 66, 142, 15, 9, 424, 8, 28, 178, 662, 44, 12, 17, 4, 130, 898, 1686, 9, 6, 5623, 267, 185, 430, 4, 118, 2, 277, 15, 4, 1188, 100, 216, 56, 19, 4, 357, 114, 2, 367, 45, 115, 93, 788, 121, 4, 2, 79, 32, 68, 278, 39, 8, 818, 162, 4165, 237, 600, 7, 98, 306, 8, 157, 549, 628, 11, 6, 2, 13, 824, 15, 4104, 76, 42, 138, 36, 774, 77, 1059, 159, 150, 4, 229, 497, 8, 1493, 11, 175, 251, 453, 19, 8651, 189, 12, 43, 127, 6, 394, 292, 7, 8253, 4, 107, 8, 4, 2826, 15, 1082, 1251, 9, 906, 42, 1134, 6, 66, 78, 22, 15, 13, 244, 2519, 8, 135, 233, 52, 44, 10, 10, 466, 112, 398, 526, 34, 4, 1572, 4413, 6706, 1094, 225, 57, 599, 133, 225, 6, 227, 7, 541, 4323, 6, 171, 139, 7, 539, 2, 56, 11, 6, 3231, 21, 164, 25, 426, 81, 33, 344, 624, 19, 6, 4617, 7, 2, 2, 6, 5802, 4, 22, 9, 1082, 629, 237, 45, 188, 6, 55, 655, 707, 6371, 956, 225, 1456, 841, 42, 1310, 225, 6, 2493, 1467, 7722, 2828, 21, 4, 2, 9, 364, 23, 4, 2228, 2407, 225, 24, 76, 133, 18, 4, 189, 2293, 10, 10, 814, 11, 2, 11, 2642, 14, 47, 15, 682, 364, 352, 168, 44, 12, 45, 24, 913, 93, 21, 247, 2441, 4, 116, 34, 35, 1859, 8, 72, 177, 9, 164, 8, 901, 344, 44, 13, 191, 135, 13, 126, 421, 233, 18, 259, 10, 10, 4, 2, 6847, 4, 2, 3074, 7, 112, 199, 753, 357, 39, 63, 12, 115, 2, 763, 8, 15, 35, 3282, 1523, 65, 57, 599, 6, 1916, 277, 1730, 37, 25, 92, 202, 6, 8848, 44, 25, 28, 6, 22, 15, 122, 24, 4171, 72, 33, 32]),
        list([1, 43, 188, 46, 5, 566, 264, 51, 6, 530, 664, 14, 9, 1713, 81, 25, 1135, 46, 7, 6, 20, 750, 11, 141, 4299, 5, 2, 4441, 102, 28, 413, 38, 120, 5533, 15, 4, 3974, 7, 5369, 142, 371, 318, 5, 955, 1713, 571, 2, 2, 122, 14, 8, 72, 54, 12, 86, 385, 46, 5, 14, 20, 9, 399, 8, 72, 150, 13, 161, 124, 6, 155, 44, 14, 159, 170, 83, 12, 5, 51, 6, 866, 48, 25, 842, 4, 1120, 25, 238, 79, 4, 547, 15, 14, 9, 31, 7, 148, 2, 102, 44, 35, 480, 3823, 2380, 19, 120, 4, 350, 228, 5, 269, 8, 28, 178, 1314, 2347, 7, 51, 6, 87, 65, 12, 9, 979, 21, 95, 24, 3186, 178, 11, 2, 14, 9, 24, 15, 20, 4, 84, 376, 4, 65, 14, 127, 141, 6, 52, 292, 7, 4751, 175, 561, 7, 68, 3866, 137, 75, 2541, 68, 182, 5, 235, 175, 333, 19, 98, 50, 9, 38, 76, 724, 4, 6750, 15, 166, 285, 36, 140, 143, 38, 76, 53, 3094, 1301, 4, 6991, 16, 82, 6, 87, 3578, 44, 2527, 7612, 5, 800, 4, 3033, 11, 35, 1728, 96, 21, 14, 22, 9, 76, 53, 7, 6, 406, 65, 13, 43, 219, 12, 639, 21, 13, 80, 140, 5, 135, 15, 14, 9, 31, 7, 4, 118, 3672, 13, 28, 126, 110]),
        list([1, 14, 20, 47, 111, 439, 3445, 19, 12, 15, 166, 12, 216, 125, 40, 6, 364, 352, 707, 1187, 39, 294, 11, 22, 396, 13, 28, 8, 202, 12, 1109, 23, 94, 2, 151, 111, 211, 469, 4, 20, 13, 258, 546, 1104, 7273, 12, 16, 38, 78, 33, 211, 15, 12, 16, 2849, 63, 93, 12, 6, 253, 106, 10, 10, 48, 335, 267, 18, 6, 364, 1242, 1179, 20, 19, 6, 1009, 7, 1987, 189, 5, 6, 8419, 7, 2723, 2, 95, 1719, 6, 6035, 7, 3912, 7144, 49, 369, 120, 5, 28, 49, 253, 10, 10, 13, 1041, 19, 85, 795, 15, 4, 481, 9, 55, 78, 807, 9, 375, 8, 1167, 8, 794, 76, 7, 4, 58, 5, 4, 816, 9, 243, 7, 43, 50])],
       dtype=object), array([1, 0, 0, 1, 0, 0, 1, 0, 1, 0]))

若想要看到对应的文字，可以使用imdb.get_word_index()

# A dictionary mapping words to an integer index
word_index = imdb.get_word_index()

# The first indices are reserved
word_index = {k:(v+3) for k,v in word_index.items()}
word_index["<PAD>"] = 0   #< PAD >: 补全字符
word_index["<START>"] = 1
word_index["<UNK>"] = 2  # unknown < UNK >: 低频词或者一些未遇到过的词等。
word_index["<UNUSED>"] = 3

reverse_word_index = dict([(value, key) for (key, value) in word_index.items()])

def decode_review(text):
    return ' '.join([reverse_word_index.get(i, '?') for i in text])

for i in range(3):
  print(decode_review(X_train[i]))

output:<START> this film was just brilliant casting location scenery story direction everyone's really suited the part they played and you could just imagine being there robert <UNK> is an amazing actor and now the same being director <UNK> father came from the same scottish island as myself so i loved the fact there was a real connection with this film the witty remarks throughout the film were great it was just brilliant so much that i bought the film as soon as it was released for <UNK> and would recommend it to everyone to watch and the fly fishing was amazing really cried at the end it was so sad and you know what they say if you cry at a film it must have been good and this definitely was also <UNK> to the two little boy's that played the <UNK> of norman and paul they were just brilliant children are often left out of the <UNK> list i think because the stars that play them all grown up are such a big profile for the whole film but these children are amazing and should be praised for what they have done don't you think the whole story was so lovely because it was true and was someone's life after all that was shared with us all
<START> big hair big boobs bad music and a giant safety pin these are the words to best describe this terrible movie i love cheesy horror movies and i've seen hundreds but this had got to be on of the worst ever made the plot is paper thin and ridiculous the acting is an abomination the script is completely laughable the best is the end showdown with the cop and how he worked out who the killer is it's just so damn terribly written the clothes are sickening and funny in equal <UNK> the hair is big lots of boobs <UNK> men wear those cut <UNK> shirts that show off their <UNK> sickening that men actually wore them and the music is just <UNK> trash that plays over and over again in almost every scene there is trashy music boobs and <UNK> taking away bodies and the gym still doesn't close for <UNK> all joking aside this is a truly bad film whose only charm is to look back on the disaster that was the 80's and have a good old laugh at how bad everything was back then
<START> this has to be one of the worst films of the 1990s when my friends i were watching this film being the target audience it was aimed at we just sat watched the first half an hour with our jaws touching the floor at how bad it really was the rest of the time everyone else in the theatre just started talking to each other leaving or generally crying into their popcorn that they actually paid money they had <UNK> working to watch this feeble excuse for a film it must have looked like a great idea on paper but on film it looks like no one in the film has a clue what is going on crap acting crap costumes i can't get across how <UNK> this is to watch save yourself an hour a bit of your life

数据的类别两者是平衡的，可以使用

from collections import Counter

Counter(y_train)
output:Counter({0: 12500, 1: 12500})

 

训练模型的每个句子的长度要求一致，所以需要设置一个maxlen，maxlen的设置，可以通过分析训练数据字数的占比，小于等于291个数字占训练数据的75%（可使用pandas 的describe()）

train_data = keras.preprocessing.sequence.pad_sequences(X_train,
                                                        value=word_index["<PAD>"],
                                                        padding='post',
                                                        maxlen=400)

test_data = keras.preprocessing.sequence.pad_sequences(X_test,
                                                       value=word_index["<PAD>"],
                                                       padding='post',
                                                       maxlen=400)

模型的构建

vocab_size=10000

model = keras.Sequential()
model.add(keras.layers.Embedding(vocab_size, 16,name="embedding"))  # 构造词嵌入层
model.add(keras.layers.Conv1D(filters=250,kernel_size=3,strides=1
                                  ,activation=keras.activations.relu,name="conv1d"))   # 基于词向量的堆叠方式做卷积

model.add(keras.layers.GlobalAveragePooling1D())  # 对每一个卷积出的特征向量做最大池化

model.add(keras.layers.Dense(250, activation=tf.nn.relu)) # 输入是250维，输出是hidden_dims
model.add(keras.layers.Activation(activation=keras.activations.relu,name="relu1"))

model.add(keras.layers.Dense(1, activation=tf.nn.sigmoid))  # 二分类问题，输出维度为1
model.add(keras.layers.Activation(activation=keras.activations.sigmoid,name="sigmod"))  # 二分类问题，使用sigmod函数做分类器
model.summary()

output:

Model: "sequential_1"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
embedding (Embedding)        (None, None, 16)          160000    
_________________________________________________________________
conv1d (Conv1D)              (None, None, 250)         12250     
_________________________________________________________________
global_average_pooling1d_1 ( (None, 250)               0         
_________________________________________________________________
dense_2 (Dense)              (None, 250)               62750     
_________________________________________________________________
relu1 (Activation)           (None, 250)               0         
_________________________________________________________________
dense_3 (Dense)              (None, 1)                 251       
_________________________________________________________________
sigmod (Activation)          (None, 1)                 0         
=================================================================
Total params: 235,251
Trainable params: 235,251
Non-trainable params: 0
_________________________________________________________________

keras 的回调函数，可以查看历史的损失值

https://keras-cn.readthedocs.io/en/latest/other/callbacks/

history = LossHistory()
train_history = model.fit(
                x=train_data, 
                y=y_train, 
                batch_size=128, 
                epochs=20, 
                verbose=0, 
                validation_data=(test_data,y_test),
                callbacks=[history])

train_history.history.keys()  # dict_keys(['loss', 'acc', 'val_loss', 'val_acc'])

print(train_history.history['acc'])
print(train_history.history['loss'])

output:
[0.50008, 0.56868, 0.65532, 0.70892, 0.75084, 0.78016, 0.80296, 0.8196, 0.83096, 0.83884, 0.84528, 0.85484, 0.8608, 0.87096, 0.87644, 0.88596, 0.88872, 0.89476, 0.89572, 0.8996]
[0.6828569381332398, 0.5650574667358399, 0.5439573343276978, 0.5355715534973144, 0.5302316103935242, 0.5272521385383606, 0.5255409695434571, 0.5236049571609497, 0.5221833774375916, 0.521118473520279, 0.5208271135044098, 0.5204424796676635, 0.5200169047927856, 0.5205016284370423, 0.5204848652267456, 0.5205531217956543, 0.5199918963241578, 0.5194626947784424, 0.5192412329483033, 0.5196685311508179]

model.evaluate(test_data, y_test)
output:[0.5636490060424805, 0.84652]

model.save(filepath=".imdb.m")