Tensorflow2.0学習(18):Embedding前処理-ワードテーブルインデックスの構築
12602 ワード
Embedding
データセットの読み込みと用語集インデックスの構築
import matplotlib as mpl
import matplotlib.pyplot as plt
%matplotlib inline
import numpy as np
import sklearn
import pandas as pd
import os
import sys
import time
import tensorflow as tf
from tensorflow import keras
print(tf.__version__)
print(sys.version_info)
for module in mpl, np ,pd, sklearn, tf, keras:
print(module.__name__, module.__version__)
2.1.0
sys.version_info(major=3, minor=7, micro=4, releaselevel='final', serial=0)
matplotlib 3.1.1
numpy 1.16.5
pandas 0.25.1
sklearn 0.21.3
tensorflow 2.1.0
tensorflow_core.python.keras.api._v2.keras 2.2.4-tf
# keras
imdb = keras.datasets.imdb
#
vocab_size = 10000
# id
index_from = 3
# ,
(train_data, train_labels),(test_data, test_labels) = imdb.load_data(
num_words = vocab_size, index_from = index_from)
Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/imdb.npz
17465344/17464789 [==============================] - 4s 0us/step
#
print(train_data[0], train_labels[0])
#
print(train_data.shape, train_labels.shape)
#
print(len(train_data[0]), len(train_data[1]))
[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] 1
(25000,) (25000,)
218 189
print(test_data.shape, test_labels.shape)
(25000,) (25000,)
#
word_index = imdb.get_word_index()
print(len(word_index))
print(list(word_index.items())[:5])
# print(word_index)
88584
[('fawn', 34701), ('tsukino', 52006), ('nunnery', 52007), ('sonja', 16816), ('vani', 63951)]
# index_from = 3, id + 3
word_index = {k:(v+3) for k, v in word_index.items()}
# id 3 ,
word_index['' ] = 0
word_index['' ] = 1
word_index['' ] = 2
word_index['' ] = 3
reverse_word_index = dict(
[(value, key) for key, value in word_index.items()])
# id
def decode_review(text_ids):
return " ".join(
[reverse_word_index.get(word_id,"" ) for word_id in text_ids])
decode_review(train_data[0])
" 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 is an amazing actor and now the same being director 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 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 to the two little boy's that played the of norman and paul they were just brilliant children are often left out of the 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"