def load_test_dataset(self,
filename='testDatasetWithOutNeuTwo',
vocab_name='vocabProc'):
"""
Something is wrong with this function. Does not get the same result
as before when loading in the new data...
"""
""" Load test dataset """
self.test_x, self.test_y = load_csv('datasets/' + filename,
target_column=1)
""" Get restored vocabulary processor """
self.vocabProcessor = VocabularyProcessor(self.max_words)
self.vocabProcessor.restore(vocab_name)
""" Encode pos, neu and neg to numbers """
labelEncoder = LabelEncoder()
labelEncoder.fit(self.test_y)
self.test_y = labelEncoder.transform(self.test_y)
""" Change the list of sentences to a list of sequence of words """
self.test_x = np.array(
list(self.vocabProcessor.transform([x[0] for x in self.test_x])))
""" Pad the sequences to fit the longest sentence """
self.test_x = pad_sequences(self.test_x,
maxlen=self.max_words,
value=0.)
""" Convert labels to binary vector """
self.test_y = to_categorical(self.test_y,
nb_classes=self.number_of_classes)
def load_dataset_training(self,
vocab_name,
filename='datasetWithoutNeutral'):
""" Load the dataset """
X, Y = load_csv('datasets/' + filename,
target_column=2,
columns_to_ignore=[0])
""" Count max words from the longest sentence """
self.max_words = max([len(x[0].split(" ")) for x in X])
""" Get vocabulare size from longest sentence """
self.vocabProcessor = VocabularyProcessor(self.max_words)
""" Encode pos, neu and neg to numbers """
labelEncoder = LabelEncoder()
labelEncoder.fit(Y)
Y = labelEncoder.transform(Y)
""" Change the list of sentences to a list of sequence of words """
X = np.array(list(self.vocabProcessor.fit_transform([x[0]
for x in X])))
""" Split the datasets to training set and test test """
self.X_train, self.X_test, self.Y_train, self.Y_test = train_test_split(
X, Y, test_size=0.10, random_state=7)
""" Pad the sequences to fit the longest sentence """
self.X_train = pad_sequences(self.X_train,
maxlen=self.max_words,
value=0.)
self.X_test = pad_sequences(self.X_test,
maxlen=self.max_words,
value=0.)
""" Convert labels to binary vector """
self.Y_train = to_categorical(self.Y_train,
nb_classes=self.number_of_classes)
self.Y_test = to_categorical(self.Y_test,
nb_classes=self.number_of_classes)
self.vocabProcessor.save(vocab_name)
def getData(dataframe):
# Extract the required columns for inputs and outputs
totalX = dataframe.sub_grade
totalY = dataframe.short_emp
print(dataframe.sub_grade.value_counts())
totalX = totalX.values
totalY = totalY.values
vocab_proc = VocabularyProcessor(1)
# Convert the strings in the input into integers corresponding to the dictionary positions
# Data is automatically padded so we need to pad_sequences manually
"""
totalX="I am happy today. I feel sad today."
vocab_proc = VocabularyProcessor(1)
totalX = np.array(list(vocab_proc.fit_transform(totalX)))
#totalX=totalX.transpose()
#totalX = pad_sequences(totalX, maxlen=100, value=0.)
print(totalX)
"""
totalX = np.array(list(vocab_proc.fit_transform(totalX)))
totalY = to_categorical(totalY, nb_classes=2) #totalY=[1,0,1,0,1] 需要为数组
# 分离出训练数据和测试数据
trainX, testX, trainY, testY = train_test_split(totalX,
totalY,
test_size=0.1)
return trainX, testX, trainY, testY
def __init__(self, config):
self.config = config
# load data here
# Load data from files
positive_data_file = self.config.positive_data_file
negative_data_file = self.config.negative_data_file
positive_examples = list(open(positive_data_file, "r").readlines())
positive_examples = [s.strip() for s in positive_examples]
negative_examples = list(open(negative_data_file, "r").readlines())
negative_examples = [s.strip() for s in negative_examples]
# Split by words
x_text = positive_examples + negative_examples
x_text = [clean_str(sent) for sent in x_text]
self.max_text_length = max([len(x.split(" ")) for x in x_text])
# transform words to id
vocab_processor = VocabularyProcessor(self.max_text_length)
X = np.array(list(vocab_processor.fit_transform(x_text)))
self.vocab_size = len(vocab_processor.vocabulary_)
# Generate labels
positive_labels = [[0, 1] for _ in positive_examples]
negative_labels = [[1, 0] for _ in negative_examples]
y = np.concatenate([positive_labels, negative_labels], 0)
self.train_input, self.valid_input, self.train_label, self.valid_label = train_test_split(
X, y, random_state=2018, test_size=0.1)
print('training size: {}'.format(len(self.train_input)))
def __init__(self, model_dir, char_embeddings, raw_sentence_pairs=None, save_vocab=True):
self.model_dir = model_dir
os.makedirs(self.model_dir, exist_ok=True)
if raw_sentence_pairs is None:
self.restore()
else:
raw_sentence_pairs = raw_sentence_pairs.ravel()
raw_sentence_pairs = [str(x) for x in list(raw_sentence_pairs)]
if char_embeddings:
log('Chosen char embeddings.')
self.sentences_lengths = [len(list(str(x))) for x in list(raw_sentence_pairs)]
else:
log('Chosen word embeddings.')
self.sentences_lengths = [len(str(x).split(' ')) for x in list(raw_sentence_pairs)]
max_sentence_length = max(self.sentences_lengths)
log('Maximum sentence length : {}'.format(max_sentence_length))
if char_embeddings:
log('Processing sentences with char embeddings...')
self.vocabulary = VocabularyProcessor(
max_document_length=max_sentence_length,
tokenizer_fn=char_tokenizer,
)
else:
log('Processing sentences with word embeddings...')
self.vocabulary = VocabularyProcessor(
max_document_length=max_sentence_length,
)
log('Sentences have been successfully processed.')
self.vocabulary.fit(raw_sentence_pairs)
if save_vocab:
self.vocabulary.save('{}/vocab'.format(self.model_dir))
def load_vocab_processor(name,max_length,min_frequency):
'''
load model
'''
print('Loading vocabulary model from {}'.format(name))
vp = VocabularyProcessor(max_length, min_frequency=min_frequency)
vp = vp.restore(name)
return vp
def do_vocabulary_table():
x, y = load_data()
vp = VocabularyProcessor(max_document_length=max_document_length,
min_frequency=0)
x = vp.fit_transform(x, unused_y=None)
x = np.array(list(x))
return x, y
def __init__(self, raw_sentence, model_dir, save_vocab=True):
os.makedirs(model_dir, exist_ok=True)
raw_sentence = raw_sentence.ravel()
raw_sentence = [str(x) for x in list(raw_sentence)]
self.sentence_length = [
len(str(x).split(' ')) for x in list(raw_sentence)
]
max_sentence_length = max(self.sentence_length)
self.vocabulary = VocabularyProcessor(max_sentence_length)
if save_vocab:
self.vocabulary.save('{}/vocab'.format(model_dir))
def make_vocab_processor(name,text,max_length,min_frequency):
''''
generate vocab model
'''
print('Making vocabulary model...')
vp = VocabularyProcessor(max_length, min_frequency=min_frequency)
vp = vp.fit(text)
if name == None:
return vp
else:
print('Saving vocabulary model to {}'.format(name))
vp.save(name)
return vp
def predict_one_sentence(self, sentence=[['']], vocab_name='vocabProc'):
""" Load vocabulary processor """
self.vocabProcessor = VocabularyProcessor(self.max_words)
self.vocabProcessor.restore(vocab_name)
""" Transorm sentence to matrix of numbers """
sentence = np.array(
list(self.vocabProcessor.transform([x[0] for x in sentence])))
sentence = pad_sequences(
sentence,
max_len=self.vocabProcessor.max_document_length,
value=0.)
""" Predict sentence """
pred_score = self.model.predict(sentence)
return pred_score
def _create_vocab(min_count=3):
"""
创建词汇表
需要训练样本
"""
def gen_documents():
for path in (TRAIN_POS_PATH, TRAIN_NEG_PATH):
with codecs.open(path, 'r', 'utf-8') as file:
for line in file:
yield line[:-1]
vocab = VocabularyProcessor(SEQUENCE_LEN,
min_count - 1,
tokenizer_fn=chinese_tokenizer)
vocab.fit(gen_documents())
return vocab
def build_model(vocabFile, model_type='bilstm'):
processor = VocabularyProcessor.restore(vocabFile)
n_words = len(processor.vocabulary_)
net = tflearn.input_data([None, 300])
net = tflearn.embedding(net, input_dim=n_words, output_dim=200)
if model_type == 'bilstm':
net = tflearn.bidirectional_rnn(net, tflearn.BasicLSTMCell(200),
tflearn.BasicLSTMCell(200))
net = dropout(net, 0.5)
elif model_type == 'lstm':
net = tflearn.lstm(net, 200, dropout=0.5)
net = dropout(net, 0.5)
elif model_type == 'cnn':
net = conv_model(net)
net = tflearn.fully_connected(net, 2, activation='softmax')
net = tflearn.regression(net,
optimizer='adam',
learning_rate=0.05,
loss='categorical_crossentropy')
return net
def __init__(self, model_dir, raw_sentence_pairs=None, save_vocab=True):
self.model_dir = model_dir
os.makedirs(self.model_dir, exist_ok=True)
if raw_sentence_pairs is None:
self.restore()
else:
raw_sentence_pairs = raw_sentence_pairs.ravel()
raw_sentence_pairs = [str(x) for x in list(raw_sentence_pairs)]
self.sentences_lengths = [
len(str(x).split(' ')) for x in list(raw_sentence_pairs)
]
max_sentence_length = max(self.sentences_lengths)
self.vocabulary = VocabularyProcessor(max_sentence_length)
self.vocabulary.fit(raw_sentence_pairs)
if save_vocab:
self.vocabulary.save('{}/vocab'.format(self.model_dir))
class SentimentLookup:
net = tflearn.input_data ([None, 40])
net = tflearn.embedding (net, input_dim=12495, output_dim=128)
net = tflearn.lstm (net, 128, dropout=0.8)
net = tflearn.fully_connected(net, 2, activation='softmax')
net = tflearn.regression (net, optimizer='adam', learning_rate=0.001,
loss='categorical_crossentropy')
model = tflearn.DNN(net, tensorboard_verbose=0)
model.load(MODEL)
vp = VocabularyProcessor.restore(VOCAB)
def _process_tweet(self, tweet = ""):
cleaned = str(tweet).upper()
cleaned = re.sub('&\w+;', '', cleaned)
cleaned = re.sub('\'', '', cleaned)
cleaned = re.sub('@\w+ ', 'USERNAME ', cleaned)
cleaned = re.sub('[^A-Z ]', '', cleaned)
cleaned = re.sub('[ ]+', ' ', cleaned)
return cleaned.strip()
def sentiment(self, data):
if isinstance(data, str):
query = [x for x in SentimentLookup.vp.transform([self._process_tweet(data)])]
bad, good = SentimentLookup.model.predict(query).tolist()[0]
return good
data = map(self._process_tweet, data)
query = [x for x in SentimentLookup.vp.transform(data)]
return SentimentLookup.model.predict(query)[:,1]
class DatasetVectorizer:
def __init__(self, raw_sentence, model_dir, save_vocab=True):
os.makedirs(model_dir, exist_ok=True)
raw_sentence = raw_sentence.ravel()
raw_sentence = [str(x) for x in list(raw_sentence)]
self.sentence_length = [
len(str(x).split(' ')) for x in list(raw_sentence)
]
max_sentence_length = max(self.sentence_length)
self.vocabulary = VocabularyProcessor(max_sentence_length)
if save_vocab:
self.vocabulary.save('{}/vocab'.format(model_dir))
@property
def max_sentence_len(self):
return self.vocabulary.max_document_length
@property
def vocabulary_size(self):
return len(self.vocabulary.vocabulary_._mapping)
def restore(self):
self.vocabulary = VocabularyProcessor.restore('{}/vocab'.format(
self.model_dir))
def vectorize(self, sentence):
return np.array(list(self.vocabulary.transform([sentence])))
def vectorize_2d(self, raw_sentence):
#num_instances, num_classes = raw_sentence.shape
num_instances = raw_sentence.shape[0]
num_classes = 1
raw_sentence = raw_sentence.ravel()
for i, v in enumerate(raw_sentence):
if v is np.nan:
print(i, v)
vectorized_sentence = np.array(
list(self.vocabulary.transform(raw_sentence)))
vectorized_sentence = vectorized_sentence.reshape(
num_instances, num_classes, self.max_sentence_len)
return vectorized_sentence[:, 0, :]
def __init__(self):
if not exists(VOCABULARY_PATH):
self._vocab = self._create_vocab()
self._vocab.save(VOCABULARY_PATH)
else:
self._vocab = VocabularyProcessor.restore(VOCABULARY_PATH)
self._model = self._create_model()
if exists(MODEL_PATH + '.meta'):
self._model.load(MODEL_PATH, True)
def __init__(self, args):
self.use_gaze = args.use_gaze
categories = ['NEGATIVE', 'POSITIVE']
if args.num_sentiments == 3:
categories.append('NEUTRAL')
dataset = load_files(container_path=DATASET_DIR,
categories=categories,
load_content=True,
encoding='utf-8')
self.sentences_, self.sentence_numbers, _, self.targets, _ = dataset.values(
)
self.sentence_numbers = [
int(re.search(r'\d{1,3}', fname).group())
for fname in dataset['filenames']
]
# adopting Hollenstein's method of building the vocab
self.sentences = [clean_str(s) for s in self.sentences_]
self.num_sentences = len(self.sentences)
self.max_sentence_length = max(
[len(s.split()) for s in self.sentences])
self.vocab_processor = VocabularyProcessor(self.max_sentence_length)
self.indexed_sentences = torch.LongTensor(
list(self.vocab_processor.fit_transform(self.sentences)))
self.vocabulary = list(
self.vocab_processor.vocabulary_._mapping.keys())
print('\n> Data set loaded. Sentiment classes:', categories)
print('> Max sentence length:', self.max_sentence_length, 'words.')
if self.use_gaze:
self.et_features = EyeTrackingFeatures(self.max_sentence_length)
print('> Loaded eye-tracking features.\n')
else:
self.et_features = np.zeros(self.num_sentences)
def build_vocabulary(inFile, dtype, vocabFile):
# 文本长度 200
MAX_LENGTH = 300
NB_CLASSES = 2
# 读入分词后文本
doc = MySentences(inFile, dtype, 'get_content')
# 把原始文本映射到index
processor = VocabularyProcessor(MAX_LENGTH, min_frequency=5)
processor.fit(doc)
processor.save(vocabFile)
class DatasetVectorizer:
def __init__(self, model_dir, raw_sentence_pairs=None, save_vocab=True):
self.model_dir = model_dir
os.makedirs(self.model_dir, exist_ok=True)
if raw_sentence_pairs is None:
self.restore()
else:
raw_sentence_pairs = raw_sentence_pairs.ravel()
raw_sentence_pairs = [str(x) for x in list(raw_sentence_pairs)]
self.sentences_lengths = [
len(str(x).split(' ')) for x in list(raw_sentence_pairs)
]
max_sentence_length = max(self.sentences_lengths)
self.vocabulary = VocabularyProcessor(max_sentence_length)
self.vocabulary.fit(raw_sentence_pairs)
if save_vocab:
self.vocabulary.save('{}/vocab'.format(self.model_dir))
@property
def max_sentence_len(self):
return self.vocabulary.max_document_length
@property
def vocabulary_size(self):
return len(self.vocabulary.vocabulary_._mapping)
def restore(self):
self.vocabulary = VocabularyProcessor.restore('{}/vocab'.format(
self.model_dir))
def vectorize(self, sentence):
return np.array(list(self.vocabulary.transform([sentence])))
def vectorize_2d(self, raw_sentence_pairs):
num_instances, num_classes = raw_sentence_pairs.shape
raw_sentence_pairs = raw_sentence_pairs.ravel()
for i, v in enumerate(raw_sentence_pairs):
if v is np.nan:
print(i, v)
vectorized_sentence_pairs = np.array(
list(self.vocabulary.transform(raw_sentence_pairs)))
vectorized_sentence_pairs = vectorized_sentence_pairs.reshape(
num_instances, num_classes, self.max_sentence_len)
vectorized_sentence1 = vectorized_sentence_pairs[:, 0, :]
vectorized_sentence2 = vectorized_sentence_pairs[:, 1, :]
return vectorized_sentence1, vectorized_sentence2
def text2npy(inFile, outFile, vocabFile, dtype):
processor = VocabularyProcessor.restore(vocabFile)
doc = MySentences(inFile, dtype, 'get_content')
train_doc = list(processor.transform(doc))
# 可以使用 to_categorical 来实现onehot编码
# to_categorical(np.array(lable), NB_CLASSES))
if dtype == 'train':
# 把标签做变换
lable = []
for y in MySentences(inFile, dtype, 'get_info'):
lable.append(int(y))
y = np.array(lable)
# 保存到文件
np.save(outFile, np.column_stack([train_doc, y]))
elif dtype == 'test':
np.save(outFile, train_doc)
fw = open(outFile + "_doc.txt", 'w')
for y in MySentences(inFile, dtype, 'get_info'):
fw.write(y.encode('utf8') + "\n")
fw.close()
save_model = 1
dataframe = pd.read_csv('ign.csv').ix[:, 1:3]
# Fill null values with empty strings
dataframe.fillna(value='', inplace=True)
# score phrase and title
print(dataframe.columns.values)
# Extract the required columns for inputs and outputs
totalX = dataframe.title
totalY = dataframe.score_phrase
# Convert the strings in the input into integers corresponding to the dictionary positions
# Data is automatically padded so we need to pad_sequences manually
vocab_proc = VocabularyProcessor(15) # max document length
totalX = np.array(list(vocab_proc.fit_transform(totalX)))
# totalX contains a matrix with the word idi (indexes) of the sentences
# We will have 11 classes in total for prediction, indices from 0 to 10
vocab_proc2 = VocabularyProcessor(1)
totalY = np.array(list(vocab_proc2.fit_transform(totalY))) - 1
# here totalY is numbered dictionary entries (0, 1, ... to 10)
print(totalY[5])
# Convert the indices into 11 dimensional vectors
totalY = to_categorical(totalY, 11)
# here totalY is a binary matrix
print(totalY[5])
class DatasetVectorizer:
def __init__(self, model_dir, char_embeddings, raw_sentence_pairs=None, save_vocab=True):
self.model_dir = model_dir
os.makedirs(self.model_dir, exist_ok=True)
if raw_sentence_pairs is None:
self.restore()
else:
raw_sentence_pairs = raw_sentence_pairs.ravel()
raw_sentence_pairs = [str(x) for x in list(raw_sentence_pairs)]
if char_embeddings:
log('Chosen char embeddings.')
self.sentences_lengths = [len(list(str(x))) for x in list(raw_sentence_pairs)]
else:
log('Chosen word embeddings.')
self.sentences_lengths = [len(str(x).split(' ')) for x in list(raw_sentence_pairs)]
max_sentence_length = max(self.sentences_lengths)
log('Maximum sentence length : {}'.format(max_sentence_length))
if char_embeddings:
log('Processing sentences with char embeddings...')
self.vocabulary = VocabularyProcessor(
max_document_length=max_sentence_length,
tokenizer_fn=char_tokenizer,
)
else:
log('Processing sentences with word embeddings...')
self.vocabulary = VocabularyProcessor(
max_document_length=max_sentence_length,
)
log('Sentences have been successfully processed.')
self.vocabulary.fit(raw_sentence_pairs)
if save_vocab:
self.vocabulary.save('{}/vocab'.format(self.model_dir))
@property
def max_sentence_len(self):
return self.vocabulary.max_document_length
@property
def vocabulary_size(self):
return len(self.vocabulary.vocabulary_._mapping)
def restore(self):
self.vocabulary = VocabularyProcessor.restore('{}/vocab'.format(self.model_dir))
def vectorize(self, sentence):
return np.array(list(self.vocabulary.transform([sentence])))
def vectorize_2d(self, raw_sentence_pairs):
num_instances, num_classes = raw_sentence_pairs.shape
raw_sentence_pairs = raw_sentence_pairs.ravel()
for i, v in enumerate(raw_sentence_pairs):
if v is np.nan:
print(i, v)
vectorized_sentence_pairs = np.array(list(self.vocabulary.transform(raw_sentence_pairs)))
vectorized_sentence_pairs = vectorized_sentence_pairs.reshape(num_instances, num_classes,
self.max_sentence_len)
vectorized_sentence1 = vectorized_sentence_pairs[:, 0, :]
vectorized_sentence2 = vectorized_sentence_pairs[:, 1, :]
return vectorized_sentence1, vectorized_sentence2
def restore(self):
self.vocabulary = VocabularyProcessor.restore('{}/vocab'.format(self.model_dir))
from tflearn.data_utils import VocabularyProcessor
vocab = {'hello':3, '.':5, 'world':20, '/' : 10}
sentences = ['hello world . / hello', 'hello']
vocab_processor = VocabularyProcessor(max_document_length=6, vocabulary=vocab)
encoded = list(vocab_processor.transform(sentences))
print(encoded)
def run_on_ign():
df_dataset = pd.read_csv(ign_dataset_path)
df_dataset.set_index(['index'], inplace=True)
# fill null values with empty strings
df_dataset.fillna(value='', inplace=True)
# extract the required columns for inputs and outputs
data_X = df_dataset.title
# data_X[0]
label_Y = df_dataset.score_phrase
# label_Y[5]
# convert the strings in the input into integers corresponding to the dictionary positions
# maps documents to sequences of word ids
# data is automatically padded so we need to pad_sequences manually
vocab_proc = VocabularyProcessor(15)
total_X = np.array(list(vocab_proc.fit_transform(data_X)))
# total_X[0]
# we will have 11 classes in total for prediction, indices from 0 to 10
# vocabulary processor for single word
vocab_proc2 = VocabularyProcessor(1)
total_Y = np.array(list(vocab_proc2.fit_transform(label_Y))) - 1
# total_Y[5]
# len(total_Y)
# as we have 11 unique score_phrase
# convert the indices into 11 dimensional vectors
# This is wrong as it generate same array for different score_phrase
# total_Y = to_categorical(total_Y, nb_classes=11)
array_list = []
for array in total_Y:
array_list.append(get_categorical(array, 11))
total_Y = np.array(array_list)
# total_Y[4]
# split into training and testing data
train_X, test_X, train_Y, test_Y = train_test_split(total_X,
total_Y,
test_size=0.1)
# build the network for classification
# each input has length of 15
net = tflearn.input_data([None, 15])
# the 15 input word integers are then casted out into 256 dimensions each creating a word embedding.
# we assume the dictionary has 10000 words maximum
net = tflearn.embedding(net, input_dim=10000, output_dim=256)
# each input would have a size of 15x256 and each of these 256 sized vectors are fed into the LSTM layer one at a time.
# all the intermediate outputs are collected and then passed on to the second LSTM layer.
net = tflearn.gru(net, 256, dropout=0.9, return_seq=True)
# using the intermediate outputs, we pass them to another LSTM layer and collect the final output only this time
net = tflearn.gru(net, 256, dropout=0.9)
# the output is then sent to a fully connected layer that would give us our final 11 classes
net = tflearn.fully_connected(net, 11, activation='softmax')
# we use the adam optimizer instead of standard SGD since it converges much faster
net = tflearn.regression(net,
optimizer='adam',
learning_rate=0.001,
loss='categorical_crossentropy')
model = tflearn.DNN(net, tensorboard_verbose=0)
if check_file_exist(ign_model_path):
model.load(ign_model_path)
model.fit(train_X,
train_Y,
validation_set=(test_X, test_Y),
show_metric=True,
batch_size=32,
n_epoch=20)
if save_model:
print("Saving model as './ign_model.tfl'")
model.save(ign_model_path)
return 0
class CNN(object):
def __init__(self, batch_size=64):
self.batch_size = batch_size
self.number_of_classes = 2
self.X_train = []
self.X_test = []
self.Y_train = []
self.Y_test = []
self.max_words = None
self.vocabProcessor = None
self.cnn_model = None
self.model = None
self.test_x = []
self.test_y = []
def load_dataset_training(self,
vocab_name,
filename='datasetWithoutNeutral'):
""" Load the dataset """
X, Y = load_csv('datasets/' + filename,
target_column=2,
columns_to_ignore=[0])
""" Count max words from the longest sentence """
self.max_words = max([len(x[0].split(" ")) for x in X])
""" Get vocabulare size from longest sentence """
self.vocabProcessor = VocabularyProcessor(self.max_words)
""" Encode pos, neu and neg to numbers """
labelEncoder = LabelEncoder()
labelEncoder.fit(Y)
Y = labelEncoder.transform(Y)
""" Change the list of sentences to a list of sequence of words """
X = np.array(list(self.vocabProcessor.fit_transform([x[0]
for x in X])))
""" Split the datasets to training set and test test """
self.X_train, self.X_test, self.Y_train, self.Y_test = train_test_split(
X, Y, test_size=0.10, random_state=7)
""" Pad the sequences to fit the longest sentence """
self.X_train = pad_sequences(self.X_train,
maxlen=self.max_words,
value=0.)
self.X_test = pad_sequences(self.X_test,
maxlen=self.max_words,
value=0.)
""" Convert labels to binary vector """
self.Y_train = to_categorical(self.Y_train,
nb_classes=self.number_of_classes)
self.Y_test = to_categorical(self.Y_test,
nb_classes=self.number_of_classes)
self.vocabProcessor.save(vocab_name)
def create_cnn_architecture_two_layers(
self,
model_name,
outputDim=300,
number_of_filters=60,
filterSize=[3, 4],
padding='same',
activation_function_convLayer='relu',
regularizer='L2',
dropouts=0.5,
activation_function_fc='softmax',
optimizer='adam',
learning_rate=0.001,
loss_function='categorical_crossentropy'):
if len(filterSize) == 0:
filterSize = [3, 4]
""" Define input shape and create word embedding """
self.cnn_model = input_data(shape=[None, self.max_words], name='input')
self.cnn_model = tflearn.embedding(
self.cnn_model,
input_dim=len(self.vocabProcessor.vocabulary_),
output_dim=outputDim)
""" Add three/two convolutional layer. Set number of filters and filter sizes and then merge together """
conv1 = conv_1d(self.cnn_model,
nb_filter=number_of_filters,
filter_size=filterSize[0],
padding=padding,
activation=activation_function_convLayer,
regularizer=regularizer)
conv2 = conv_1d(self.cnn_model,
nb_filter=number_of_filters,
filter_size=filterSize[1],
padding=padding,
activation=activation_function_convLayer,
regularizer=regularizer)
#conv3 = conv_1d(cnn_model, nb_filter = 128, filter_size = 5, padding = 'same',
# activation = 'relu', regularizer = 'L2')
self.cnn_model = merge([conv1, conv2], mode='concat', axis=1)
""" Expand one dimension to fit the max_pooling layer """
self.cnn_model = tf.expand_dims(self.cnn_model, 1)
self.cnn_model = global_max_pool(self.cnn_model)
""" Instantiate dropout layer and specify dropout parameter """
self.cnn_model = dropout(self.cnn_model, dropouts)
""" Instantiate fully connected layer and regression layer. """
self.cnn_model = fully_connected(self.cnn_model,
self.number_of_classes,
activation=activation_function_fc)
self.cnn_model = regression(self.cnn_model,
optimizer=optimizer,
learning_rate=learning_rate,
loss=loss_function,
name='models/' + model_name)
def train_and_save(self,
model_name,
tensorboard_verbose=0,
tensorboard_dir='/logs/',
nb_epochs=5,
shuffle=True,
show_metric=True):
""" Instantiate Deep neural network model and start the training """
self.model = tflearn.DNN(self.cnn_model,
tensorboard_verbose=tensorboard_verbose,
tensorboard_dir=tensorboard_dir)
self.model.fit(self.X_train,
self.Y_train,
n_epoch=nb_epochs,
validation_set=(self.X_test, self.Y_test),
shuffle=shuffle,
show_metric=show_metric,
batch_size=self.batch_size,
run_id=model_name)
""" Save the model """
self.model.save('models/' + model_name)
def load_model(self,
model_name,
outputDim=300,
number_of_filters=60,
filterSize=[3, 4],
padding='same',
activation_function_convLayer='relu',
regularizer='L2',
dropouts=0.5,
activation_function_fc='softmax',
optimizer='adam',
learning_rate=0.001,
loss_function='categorical_crossentropy',
tensorboard_verbose=0,
tensorboard_dir='/logs/'):
"""
Has to pass the same values that the models were trained with. If the
model was trained on default values, the parameters will pass it automatically.
"""
self.create_cnn_architecture_two_layers(
model_name, outputDim, number_of_filters, filterSize, padding,
activation_function_convLayer, regularizer, dropouts,
activation_function_fc, optimizer, learning_rate, loss_function)
self.model = tflearn.DNN(self.cnn_model,
tensorboard_verbose=tensorboard_verbose,
tensorboard_dir=tensorboard_dir)
self.model.load('models/' + model_name)
def load_test_dataset(self,
filename='testDatasetWithOutNeuTwo',
vocab_name='vocabProc'):
"""
Something is wrong with this function. Does not get the same result
as before when loading in the new data...
"""
""" Load test dataset """
self.test_x, self.test_y = load_csv('datasets/' + filename,
target_column=1)
""" Get restored vocabulary processor """
self.vocabProcessor = VocabularyProcessor(self.max_words)
self.vocabProcessor.restore(vocab_name)
""" Encode pos, neu and neg to numbers """
labelEncoder = LabelEncoder()
labelEncoder.fit(self.test_y)
self.test_y = labelEncoder.transform(self.test_y)
""" Change the list of sentences to a list of sequence of words """
self.test_x = np.array(
list(self.vocabProcessor.transform([x[0] for x in self.test_x])))
""" Pad the sequences to fit the longest sentence """
self.test_x = pad_sequences(self.test_x,
maxlen=self.max_words,
value=0.)
""" Convert labels to binary vector """
self.test_y = to_categorical(self.test_y,
nb_classes=self.number_of_classes)
def evaluate_model_performance(self):
metrix_score = self.model.evaluate(self.test_x,
self.test_y,
batch_size=self.batch_size)
return metrix_score
def predict_one_sentence(self, sentence=[['']], vocab_name='vocabProc'):
""" Load vocabulary processor """
self.vocabProcessor = VocabularyProcessor(self.max_words)
self.vocabProcessor.restore(vocab_name)
""" Transorm sentence to matrix of numbers """
sentence = np.array(
list(self.vocabProcessor.transform([x[0] for x in sentence])))
sentence = pad_sequences(
sentence,
max_len=self.vocabProcessor.max_document_length,
value=0.)
""" Predict sentence """
pred_score = self.model.predict(sentence)
return pred_score
def predict_list(self,
list_of_sentences=[[''], ['']],
vocab_name='vocabProc'):
""" Load vocabulary processor """
self.vocabProcessor = VocabularyProcessor(self.max_words)
self.vocabProcessor.restore(vocab_name)
""" Transorm sentence to matrix of numbers """
sentence = np.array(
list(self.vocabProcessor.transform([x[0] for x in sentece])))
sentence = pad_sequences(
sentence,
max_len=self.vocabProcessor.max_document_length,
value=0.)
""" Predict sentence """
pred_score = self.model.predict(list_of_sentences)
return pred_score
from tflearn.data_utils import pad_sequences, to_categorical, load_csv
from tflearn.layers.core import input_data, dropout, fully_connected
from tflearn.layers.conv import conv_1d, global_max_pool, max_pool_1d
from tflearn.layers.merge_ops import merge
from tflearn.layers.estimator import regression
batch_size = 64
""" Load the dataset """
#X, Y = load_csv('datasetFullList', target_column = 2, columns_to_ignore = [0])
X, Y = load_csv('datasetWithoutNeutral',
target_column=2,
columns_to_ignore=[0])
""" Count max words from the longest sentence """
max_words = max([len(x[0].split(" ")) for x in X])
""" Get vocabulare size from longest sentence """
vocab = VocabularyProcessor(max_words)
""" Encode pos, neu and neg to numbers """
labelEncoder = LabelEncoder()
labelEncoder.fit(Y)
Y = labelEncoder.transform(Y)
""" Change the list of sentences to a list of sequence of words """
X = np.array(list(vocab.fit_transform([x[0] for x in X])))
""" Split the datasets to training set and test test """
X_train, X_test, Y_train, Y_test = train_test_split(X,
Y,
test_size=0.10,
random_state=7)
""" Pad the sequences to fit the longest sentence """
X_train = pad_sequences(X_train, maxlen=max_words, value=0.)
X_test = pad_sequences(X_test, maxlen=max_words, value=0.)
""" Convert labels to binary vector """
data.loc[data["score_phrase"] == "Disaster", "score_phrase"] = 0 data.loc[data["score_phrase"] == "Unbearable", "score_phrase"] = 0 data.loc[data["score_phrase"] == "Painful", "score_phrase"] = 0 data.loc[data["score_phrase"] == "Bad", "score_phrase"] = 0 data.loc[data["score_phrase"] == "Mediocre", "score_phrase"] = 0 data.loc[data["score_phrase"] == "Awful", "score_phrase"] = 0 data.loc[data["score_phrase"] == "Amazing", "score_phrase"] = 1 data.loc[data["score_phrase"] == "Great", "score_phrase"] = 1 data.loc[data["score_phrase"] == "Okay", "score_phrase"] = 1 data.loc[data["score_phrase"] == "Masterpiece", "score_phrase"] = 1 data.loc[data["score_phrase"] == "Good", "score_phrase"] = 1 # tokenize title # data["token_title"] = data["title"].apply(nltk.word_tokenize) word_processor = VocabularyProcessor(100) tmp = np.array(list(word_processor.fit_transform(data["title"]))) # split into train and test data train_data, test_data = model_selection.train_test_split(data, train_size=0.9) trainX = np.array(list(word_processor.fit_transform(train_data["title"]))) trainY = train_data.loc[:, ["score_phrase"]].as_matrix() testX = np.array(list(word_processor.fit_transform(test_data["title"]))) testY = test_data.loc[:, ["score_phrase"]].as_matrix() # Converting labels to binary vectors trainY = to_categorical(trainY, nb_classes=2) testY = to_categorical(testY, nb_classes=2) # Network building net = tflearn.input_data([None, 100])
'\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\' ) # print(type(df.num.apply(str))) # print(type(df.text)) text = df['text'].astype(str) # num = df['num'].astype(str) # print(type(text)) # print(text) # Extract the required columns for inputs and outputs totalX = text totalY = df.num # # Convert the strings in the input into integers corresponding to the dictionary positions # # Data is automatically padded so we need to pad_sequences manually vocab_proc = VocabularyProcessor(10) totalX = np.array(list(vocab_proc.fit_transform(totalX))) seed = np.array(list(vocab_proc.fit_transform(seed))) # # We will have 11 classes in total for prediction, indices from 0 to 10 vocab_proc2 = VocabularyProcessor(1) totalY = np.array(list(vocab_proc2.fit_transform(totalY))) - 1 # # Convert the indices into 11 dimensional vectors totalY = to_categorical(totalY, nb_classes=10) # Split into training and testing data # trainX, testX, trainY, testY = train_test_split(totalX, totalY, test_size=0.1) totalX = pad_sequences(totalX, maxlen=100, value=0.) seed = pad_sequences(seed, maxlen=100, value=0.) # testX = pad_sequences(testX, maxlen=100, value=0.) # print(trainX) # print(trainY)
def chinese_tokenizer(documents):
"""
把中文文本转为词序列
"""
for document in documents:
# 繁体转简体
text = HanziConv.toSimplified(document)
# 英文转小写
text = text.lower()
# 分词
yield list(cut(text))
# 序列长度填充或截取到100，删除词频<=2的词
vocab = VocabularyProcessor(100, 2, tokenizer_fn=chinese_tokenizer)
# 创建词汇表，创建后不能更改
vocab.fit(DOCUMENTS)
# 保存和加载词汇表
vocab.save('vocab.pickle')
vocab = VocabularyProcessor.restore('vocab.pickle')
# 文本转为词ID序列，未知或填充用的词ID为0
id_documents = list(vocab.transform(DOCUMENTS))
for id_document in id_documents:
print(id_document)
# [2 3 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
# 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
# 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0]
save_model = 0
# Select only the two columns we require. Game title and its corresponding emotion
dataframe = pd.read_csv('ign.csv').ix[:, 1:3]
# Fill null values with empty strings
dataframe.fillna(value='', inplace=True)
# print(dataframe.score_phrase.value_counts())
# Extract the required columns for inputs and outputs
totalX = dataframe.title
totalY = dataframe.score_phrase
# Convert the strings in the input into integers corresponding to the dictionary positions
# Data is automatically padded so we need to pad_sequences manually
vocab_proc = VocabularyProcessor(15)
totalX = np.array(list(vocab_proc.fit_transform(totalX)))
# We will have 11 classes in total for prediction, indices from 0 to 10
vocab_proc2 = VocabularyProcessor(1)
totalY = np.array(list(vocab_proc2.fit_transform(totalY))) - 1
# Convert the indices into 11 dimensional vectors
totalY = to_categorical(totalY, nb_classes=11)
# Split into training and testing data
trainX, testX, trainY, testY = train_test_split(totalX, totalY, test_size=0.1)
# Build the network for classification
# Each input has length of 15
net = tflearn.input_data([None, 15])
# The 15 input word integers are then casted out into 256 dimensions each creating a word embedding.
