±à¼ÍƼö: |
±¾ÎÄÀ´×Ôcnblogs£¬Ö÷Òª½éÉÜÁËDense È«Á¬½Ó²ã£¬Ç¶Èë²ã Embedding£¬LSTM²ã£¬Êý¾ÝÔ¤´¦Àí£ºÎı¾Ô¤´¦Àí£¬ÐòÁÐÔ¤´¦Àí£¬Êý¾Ý¼ÓÔØ£¬Êý¾ÝÇåÏ´£¬Keras´î½¨ÍøÂçÏà¹ØÄÚÈÝ¡£
|
|
Keras ÊÇÒ»¸öÓà Python ±àдµÄ¸ß¼¶Éñ¾ÍøÂç API£¬ËüÄܹ»ÒÔ
TensorFlow, CNTK, »òÕß Theano ×÷Ϊºó¶ËÔËÐС£Keras µÄ¿ª·¢ÖصãÊÇÖ§³Ö¿ìËÙµÄʵÑé¡£Äܹ»ÒÔ×îСµÄʱÑÓ°ÑÄãµÄÏ뷨ת»»ÎªÊµÑé½á¹û£¬ÊÇ×öºÃÑо¿µÄ¹Ø¼ü¡£
±¾ÎÄÒÔKaggleÉϵÄÏîÄ¿:IMDBÓ°ÆÀÇé¸Ð·ÖÎöΪÀý,ѧϰÈçºÎÓÃKeras´î½¨Ò»¸öÉñ¾ÍøÂç,´¦Àíʵ¼ÊÎÊÌâ.ÔĶÁ±¾ÎÄÐèÒª¶ÔÉñ¾ÍøÂçÓлù´¡µÄÁ˽â.
ÎÄÕ·ÖΪÁ½¸ö²¿·Ö:
KerasÖеÄһЩ»ù±¾¸ÅÄî.ApiÓ÷¨.ÎÒ»á¸ø³öһЩ¼òµ¥µÄʹÓÃÑùÀý,»òÊǸø³öÏà¹ØÖªÊ¶Á´½Ó.
IMDBÓ°ÆÀÇé¸Ð·ÖÎöʵս.Óõ½µÄ¶¼ÊǵÚÒ»²¿·ÖÖн²µ½µÄ֪ʶµã.
Model
Dense È«Á¬½Ó²ã
keras.layers.core.Dense(units,
activation=None, use_bias=True, k
ernel_initializer='glorot_uniform', bias_initializer='zeros',
ke
rnel_regularizer=None, bias_regularizer=None,
activity_regulariz
er=None, kernel_constraint=None, bias_constraint=None) |
# as first layer
in a sequential model:
# as first layer in a sequential model:
model = Sequential()
model.add(Dense(32, input_shape=(16,)))
# now the model will take as input arrays of shape
(*, 16)
# and output arrays of shape (*, 32)
# after the first layer, you don't need to specify
# the size of the input anymore:
model.add(Dense(32)) |
ǶÈë²ã Embedding
keras.layers.embeddings.Embedding (input_dim,
output_dim, embeddi
ngs_initializer='uniform', embeddings_regularizer=None,
activity
_regularizer=None, embeddings_constraint=None,
mask_zero=False,
input_length=None) |
ÓÐÐËȤµÄ¿´Õâ¸öÁ´½Ó
Æäʵ¾ÍÊÇword to vector¡£ ÕâÒ»²ãµÄ×÷ÓþÍÊǵõ½ÓôÊÏòÁ¿±íʾµÄÎı¾.
input_dim: ´Ê±íµÄ´óС.¼´²»Í¬µÄ´ÊµÄ×ܸöÊý.
output_dim:ÏëÒª°Ñ´Êת»»³É¶àÉÙάµÄÏòÁ¿.
input_length: ÿһ¾äµÄ´ÊµÄ¸öÊý
±ÈÈçÈçÏ´ú±í:ÎÒÃÇÊäÈëÒ»¸öM*50µÄ¾ØÕó,Õâ¸ö¾ØÕóÖв»Í¬µÄ´ÊµÄ¸öÊýΪ200,ÎÒÃÇÏë°Ñÿ¸ö´Êת»»Îª32άÏòÁ¿.
·µ»ØµÄÊÇÒ»¸ö(M,50,32)µÄÕÅÁ¿.
Ò»¸ö¾ä×Ó50¸ö´Ê,ÿ¸ö´ÊÊÇ32άÏòÁ¿,¹²M¸ö¾ä×Ó. ËùÒÔÊÇe.shape=(M,50,32)
e = Embedding(200,
32, input_length=50) |
LSTM²ã.
LSTMÊÇÑ»·Éñ¾ÍøÂçµÄÒ»ÖÖÌØÊâÇé¿ö .
¼òµ¥À´Ëµ,ÎÒÃÇ´Ëǰ˵¹ýµÄÉñ¾ÍøÂç,°üÀ¨CNN,¶¼Êǵ¥ÏòµÄ,ûÓп¼ÂÇÐòÁйØÏµ,µ«ÊÇij¸ö´ÊµÄÒâÒåÓëÆäÉÏÏÂÎÄÊÇÓйصÄ,±ÈÈç"ÎÒÓÃ×ÅСÃ×ÊÖ»ú,³Ô×ÅСÃ×Öà",Á½¸öСÃ׿϶¨²»ÊÇÒ»¸öÒâ˼.ÔÚ×öÓïÒå·ÖÎöµÄʱºò,ÐèÒª¿¼ÂÇÉÏÏÂÎÄ.
Ñ»·Éñ¾ÍøÂçRNN¾ÍÊǸÉÕâ¸öÊÂÇéµÄ.»òÕß˵"ÕⲿµçÓ°ÖÊÁ¿ºÜ¸ß,µ«ÊÇÎÒ²»Ï²»¶".Õâ¸ö¾ä×ÓÀï¼ÈÓÐÕýÃæÆÀ¼Û,ÓÖÓиºÃæÆÀ¼Û,²Î¿¼ÉÏÏÂÎĵÄLSTM»áʶ±ð³ö"µ«ÊÇ"ºóÃæµÄ²ÅÊÇÎÒÃÇÏëÒªÖØµã±í´ïµÄ.
keras.layers.recurrent.LSTM (units,
activation='tanh', v recurrent_
activation='hard_sigmoid', use_bias=True, kernel_initializer='gl
orot_uniform', recurrent_initializer='orthogonal',
bias_initiali
zer='zeros', unit_forget_bias=True, kernel_regularizer=None,
rec
urrent_regularizer=None, bias_regularizer=None,
activity_regular
izer=None, kernel_constraint=None, recurrent_constraint=None,
bi
as_constraint=None, dropout=0.0, recurrent_dropout=0.0) |
³Ø»¯²ã
keras.layers.pooling.GlobalMaxPooling1D() #¶Ôʱ¼äÐźŵÄÈ«¾Ö×î´ó³Ø»¯
https://stackoverflow.com/ questions/43728235/what-is -the-difference-between -keras-maxpooling1d-and- globalmaxpooling1d-functi>
input:ÐÎÈ磨 samples£¬ steps£¬ features£© µÄ3DÕÅÁ¿
output:ÐÎÈç(samples, features)µÄ2DÕÅÁ¿
keras.layers.pooling.MaxPooling1D (pool_size=2, strides=None,
pad
ding='valid')
keras.layers.pooling.MaxPooling2D (pool_size=(2, 2),
strides=None
, padding='valid', data_format=None)
keras.layers.pooling.MaxPooling3D (pool_size=(2, 2,
2), strides=N
one, padding='valid', data_format=None)
....
Êý¾ÝÔ¤´¦Àí
Îı¾Ô¤´¦Àí
keras.preprocessing.text. text_to_word_sequence(text,
filters=base_filter(), lower=True, split=" ")
keras.preprocessing.text.one_hot (text, n,
filters=base_filter(), lower= True, split=" ")
keras.preprocessing.text.Tokenizer (num_words=None,
filters=base_
filter(),
lower=True, split=" ")
TokenizerÊÇÒ»¸öÓÃÓÚÏòÁ¿»¯Îı¾£¬ »ò½«Îı¾×ª»»ÎªÐòÁУ¨ ¼´µ¥´ÊÔÚ×ÖµäÖеÄϱ깹
³ÉµÄÁÐ±í£¬ ´Ó1ËãÆð£© µÄÀà¡£
num_words£º None»òÕûÊý£¬ ´¦ÀíµÄ×î´óµ¥´ÊÊýÁ¿¡£ Èô±»ÉèÖÃΪÕûÊý£¬ Ôò·Ö´ÊÆ÷
½«±»ÏÞÖÆÎª´¦ÀíÊý¾Ý¼¯ÖÐ×î³£¼ûµÄ num_words ¸öµ¥´Ê
²»¹Ünum_wordsÊǼ¸,fit_on_textsÒÔºó´Êµä¶¼ÊÇÒ»ÑùµÄ,È«²¿µÄ´Ê¶¼ÓжÔÓ¦µÄindex.Ö»ÊÇÔÚ×ötexts_to_sequencesʱËùµÃ½á¹û²»Í¬.
»áÈ¡×î³£³öÏÖµÄ(num_words - 1)¸ö´Ê¶ÔÓ¦µÄindexÀ´´ú±í¾ä×Ó.
×¢Òânum_words²»Í¬Ê±,×¼»»ºóX_tµÄ²»Í¬. ֻȡ´ÊµäÖгöÏÖ×î¶àµÄnum_words - 1´ú±í¾ä×Ó.Èç¹ûÒ»¸ö¾ä×ÓÖгöÏÖÌØ±ðÉúƧµÄ´Ê,¾Í»á±»¹ýÂ˵ô.±ÈÈçÒ»¸ö¾ä×Ó="x
y z".y,z²»ÔڴʵäÖÐ×î³£³öÏÖµÄtop num_words-1µÄ»°,×îºóÕâ¸ö¾ä×ÓµÄÏòÁ¿ÐÎʽÔòΪ[x_index_in_dic]
t1="i love
that girl"
t2='i hate u'
texts=[t1,t2]
tokenizer = Tokenizer(num_words=None)
tokenizer.fit_on_texts(texts) #µÃµ½´Êµä ÿ¸ö´Ê¶ÔÓ¦Ò»¸öindex.
print( tokenizer.word_counts) #OrderedDict([('i',
2), ('love', 1), ('that', 1), ('girl', 1), ('hate',
1), ('u', 1)])
print( tokenizer.word_index) #{'i': 1, 'love':
2, 'that': 3, 'girl': 4, 'hate': 5, 'u': 6}
print( tokenizer.word_docs) #{'i': 2, 'love':
1, 'that': 1, 'girl': 1, 'u': 1, 'hate': 1})
print( tokenizer.index_docs) #{1: 2, 2: 1, 3:
1, 4: 1, 6: 1, 5: 1}
tokennized_texts = tokenizer.texts_to_sequences(texts)
print(tokennized_texts) #[[1, 2, 3, 4], [1, 5,
6]] ÿ¸ö´ÊÓÉÆäindex±íʾ
X_t = pad_sequences(tokennized_texts, maxlen=None)
#ת»»Îª2d array ¼´¾ØÕóÐÎʽ. ÿ¸öÎı¾µÄ´ÊµÄ¸öÊý¾ùΪmaxlen. ²»´æÔڵĴÊÓÃ0±íʾ.
print(X_t)#[[1 2 3 4][0 1 5 6]] |
ÐòÁÐÔ¤´¦Àí
keras.preprocessing.sequence.pad_sequences
(sequences, maxlen=None
, dtype='int32',
padding='pre', truncating='pre', value=0.)
·µ»ØÒ»¸ö2½×ÕÅÁ¿
keras.preprocessing.sequence.skipgrams
(sequence, vocabulary_size
,
window_size=4, negative_samples=1.,
shuffle=True,
categorical=False, sampling_table=None)
keras.preprocessing.sequence.make
_sampling_table (size, sampling_
factor=1e-5)
kerasʵս:IMDBÓ°ÆÀÇé¸Ð·ÖÎö
Êý¾Ý¼¯½éÉÜ
labeledTrainData.tsv/imdb_master.csv Ó°ÆÀÊý¾Ý¼¯ ÒѾ±ê×¢¶ÔµçÓ°ÊÇÕýÃæ/¸ºÃæÆÀ¼Û
testData.tsv ²âÊÔ¼¯ ÐèÒªÔ¤²âÆÀÂÛÊÇÕýÃæ/¸ºÃæ
Ö÷Òª²½Öè
Êý¾Ý¶ÁÈ¡
Êý¾ÝÇåÏ´ Ö÷Òª°üÀ¨È¥³ýÍ£´Ê,È¥³ýhtml tag,È¥³ý±êµã·ûºÅ
Ä£Ð͹¹½¨
ǶÈë²ã:Íê³É´Êµ½ÏòÁ¿µÄת»»
LSTM
³Ø»¯²ã:Íê³ÉÖØÒªÌØÕ÷³éÈ¡
È«Á¬½Ó²ã£º·ÖÀà
Êý¾Ý¼ÓÔØ
import pandas
as pd
import matplotlib.pyplot as plt
import numpy as np
df_train = pd.read_csv("./dataset/word2vec-nlp-tutorial/labeledTrainData.tsv",
header=0, delimiter="\t", quoting=3)
df_train1=pd.read_csv("./dataset/imdb-review-dataset/imdb_master.csv",encoding="latin-1")
df_train1=df_train1.drop(["type",'file'],axis=1)
df_train1.rename(columns={'label':'sentiment',
'Unnamed: 0':'id',
'review':'review'},
inplace=True)
df_train1 = df_train1[df_train1.sentiment != 'unsup']
df_train1['sentiment'] = df_train1['sentiment'].map({'pos':
1, 'neg': 0})
new_train=pd.concat([df_train,df_train1]) |
Êý¾ÝÇåÏ´
ÓÃbs4´¦ÀíhtmlÊý¾Ý
¹ýÂ˳öµ¥´Ê
È¥³ýÍ£ÓôÊ
import re
from bs4 import BeautifulSoup
from nltk.corpus import stopwords
def review_to_words( raw_review ):
review_text = BeautifulSoup (raw_review, 'lxml').get_text()
letters_only = re.sub("[^a-zA-Z]", "
", review_text)
words = letters_only.lower().split()
stops = set (stopwords.words("english"))
meaningful_words = [w for w in words if not w
in stops]
return( " ".join ( meaningful_words
))
new_train['review']= new_train['review'].apply(review_to_words)
df_test["review"]= df_test["review"].apply(review_to_words) |
Keras´î½¨ÍøÂç
Îı¾×ª»»Îª¾ØÕó
- Tokenizer×÷ÓÃÓÚlist(sentence)µÃµ½´Êµä.½«´ÊÓôÊÔڴʵäÖеÄIndex×öÌæ»»,µÃµ½Êý×Ö¾ØÕó
- pad_sequences×ö²¹0. ±£Ö¤¾ØÕóÿһÐÐÊýÄ¿ÏàµÈ.
¼´Ã¿¸ö¾ä×ÓÓÐÏàͬÊýÁ¿µÄ´Ê.
list_classes
= ["sentiment"]
y = new_train[list_classes].values
print(y.shape)
list_sentences_train = new_train["review"]
list_sentences_test = df_test["review"]
max_features = 6000
tokenizer = Tokenizer (num_words=max_features)
tokenizer.fit_on_texts (list(list_sentences_train))
list_tokenized_train = tokenizer.texts_to_sequences (list_sentences_train)
list_tokenized_test = tokenizer.texts_to_sequences (list_sentences_test)
print (len(tokenizer.word_index))
totalNumWords = [len(one_comment) for one_comment
in list_tokenized_train]
print(max(totalNumWords), sum(totalNumWords)
/ len(totalNumWords))
maxlen = 400
X_t = pad_sequences( list_tokenized_train, maxlen=maxlen)
X_te = pad_sequences (list_tokenized_test, maxlen=maxlen) |
Ä£Ð͹¹½¨
´ÊתÏòÁ¿
inp = Input(shape=(maxlen,
))
print(inp.shape) # (?, 400) #ÿ¸ö¾ä×Ó400¸ö´Ê
embed_size = 128 #ÿ¸ö´Êת»»³É128άµÄÏòÁ¿
x = Embedding(max_features, embed_size)(inp)
print(x.shape) #(?, 400, 128) |
LSTM 60¸öÉñ¾Ôª
GlobalMaxPool1D Ï൱ÓÚ³éÈ¡³ö×îÖØÒªµÄÉñ¾ÔªÊä³ö
DropOut ¶ªÆú²¿·ÖÊä³ö ÒýÈëÕýÔò»¯,·ÀÖ¹¹ýÄâºÏ
Dense È«Á¬½Ó²ã
Ä£ÐͱàÒëʱָ¶¨Ëðʧº¯Êý,ÓÅ»¯Æ÷,Ä£ÐÍЧ¹ûÆÀ²â±ê×¼
x = LSTM(60,
return_sequences=True,name='lstm_layer')(x)
print(x.shape)
x = GlobalMaxPool1D()(x)
print(x.shape)
x = Dropout(0.1)(x)
print(x.shape)
x = Dense(50, activation="relu")(x)
print(x.shape)
x = Dropout(0.1)(x)
print(x.shape)
x = Dense(1, activation="sigmoid")(x)
print(x.shape)
model = Model(inputs=inp, outputs=x)
model.compile(loss='binary_crossentropy',
optimizer='adam',
metrics=['accuracy']) |
Ä£ÐÍѵÁ·
batch_size =
32
epochs = 2
print(X_t.shape,y.shape)
model.fit(X_t,y, batch_size=batch_size, epochs=epochs,
validation_split=0.2) |
ʹÓÃÄ£ÐÍÔ¤²â
prediction =
model.predict(X_te)
y_pred = (prediction > 0.5) |
|