官方比赛链接:https://www.kaggle.com/c/quora-question-pairs
here is some tips:
pandas读取数据的问题
dataframe=pd.read_csv('csvfile')
question1=list(dataframe['question1'])
question1中某些数据会被转换为float格式,需要转为str格式。加上下面这句:
question1=[str(i) for i in question1]
keras分词器Tokenizer
Tokenizer是一个用于向量化文本,或将文本转换为序列(即单词在字典中的下标构成的列表,从1算起)的类。
示例程序:
import keras.preprocessing.text as T
from keras.preprocessing.text import Tokenizer
text1='some thing to eat'
text2='some thing to drink'
texts=[text1,text2]
print T.text_to_word_sequence(text1) #['some', 'thing', 'to', 'eat']
print T.one_hot(text1,10) #[7, 9, 3, 4]
print T.one_hot(text2,10) #[7, 9, 3, 1]
tokenizer = Tokenizer(num_words=10)
tokenzier.fit_on_text(texts)
print tokenizer.word_count #[('some', 2), ('thing', 2), ('to', 2), ('eat', 1), ('drink', 1)]
print tokenizer.word_index #{'some': 1, 'thing': 2,'to': 3 ','eat': 4, drink': 5}
print tokenizer.word_docs #{'some': 2, 'thing': 2, 'to': 2, 'drink': 1, 'eat': 1}
print tokenizer.index_docs #{1: 2, 2: 2, 3: 2, 4: 1, 5: 1}
print tokenizer.text_to_sequences(texts) #[[1, 2, 3, 4], [1, 2, 3, 5]]
print tokenizer.text_to_matrix(texts) #
[[ 0., 1., 1., 1., 1., 0., 0., 0., 0., 0.],
[ 0., 1., 1., 1., 0., 1., 0., 0., 0., 0.]]
保存数组为numpy的npy二进制格式
np.save(npyfile, array)
array=np.load(npyfile)
with open(jsonfile, 'w') as f:
json.dump({'nb_words': nb_words}, f)
with open(NB_WORDS_DATA_FILE, 'r') as f:
nb_words = json.load(f)['nb_words']