def only_text(a):
nr = len(a)
text = []
for i in xrange(0, nr):
t = re.sub("[^a-zA-Z]", " ", a[i].get_text())
#t = t.encode('ascii')
words = t.split()
text.append(" ".join(words))
return text
def clean_text(a):
nr = len(a)
text = []
for i in xrange(0, nr):
letters = re.sub("[^a-zA-Z]", " ", a[i].get_text())
words = letters.lower().split()
stops = set(stopwords.words("english"))
meaningful_words = [w for w in words if not w in stops]
text.append(" ".join(
map(lambda x: lemmatizer.lemmatize(x), meaningful_words)))
return (text)
def create_text_column(df):
#create copy to modify
text_df = df.copy()
#store processed text
text = []
# for each file (row) in the df, read in the file
for row_i in df.index:
filename = df.iloc[row_i]['response']
file_text = process_file(str(filename))
#append processed text to list
text.append(file_text)
#add column to the copied dataframe
text_df['text'] = text
return text_df
imagePath = '/media/zxq/zxq/COCO/resized/'
savePath = './TextImageEmbedding.h5'
# Load caption file
with open(captionPath,'r') as f:
data = json.load(f)
text = []
imageName = []
labels = []
trainVector = []
instanceSize = 340000
print('Train model in {} instances'.format(instanceSize))
validationSize = 10000
#Load captions and images' name
for i in range(0,instanceSize):
text.append(data[i]['caption'])
imageName.append(data[i]['image_name'])
labels.append(data[i]['label'])
#Load tokenizer from file
with open('./tokenizerV2.pickle','rb') as handle:
Tokenizer=pickle.load(handle)
#Pre-processing of labels and texts
max_caption_length=400
text = Tokenizer.texts_to_sequences(text)
text = np.asarray(text)
labels = np.asarray(labels)
text = sequence.pad_sequences(text, maxlen=max_caption_length)
labels = to_categorical(labels,num_classes=90)
#Get the train label and validation label
trainLabels = labels[:instanceSize-validationSize]
valLabels = labels[instanceSize-validationSize:]
def tokenize(max_features,
max_len,
on='train',
train_path='f:/avito/train.csv',
test_path=None,
tokenizer=None,
clean_text=False,
return_tokenizer=False,
return_full_train=False):
"""
Tokenize text.
Read train and test data, process description feature, tokenize it.
Parameters:
- on: fit tokenizer on train or train + test;
- train_path: path to train file;
- test_path: past to test file;
- max_features: tokenizer parameter;
- max_len: tokenizer parameter;
- tokenizer: can pass tokenizer with different parameters or use a default one;
- clean_text: apply text cleaning or not;
"""
# check that "on" has a correct value.
assert on in ['train', 'all']
print('Reading train data.')
train = pd.read_csv(train_path, index_col=0)
labels = train['deal_probability'].values
train = train['description'].astype(str).fillna('')
text = train
# define tokenizer
if tokenizer:
tokenizer = tokenizer
else:
tokenizer = Tokenizer(num_words=max_features)
if on == 'all':
print('Reading test data.')
test = pd.read_csv(test_path, index_col=0)
test = test['description'].astype(str).fillna('')
text = text.append(test)
# clean text
if clean_text:
pass
# print('Cleaning.')
print('Fitting.')
tokenizer.fit_on_texts(text)
# split data
X_train, X_valid, y_train, y_valid = train_test_split(train,
labels,
test_size=0.1,
random_state=23)
print('Converting to sequences.')
X_train = tokenizer.texts_to_sequences(X_train)
X_valid = tokenizer.texts_to_sequences(X_valid)
if test_path:
test = tokenizer.texts_to_sequences(test)
print('Padding.')
X_train = sequence.pad_sequences(X_train, maxlen=max_len)
X_valid = sequence.pad_sequences(X_valid, maxlen=max_len)
if test_path:
test = sequence.pad_sequences(test, maxlen=max_len)
data = {}
data['X_train'] = X_train
data['X_valid'] = X_valid
data['y_train'] = y_train
data['y_valid'] = y_valid
if test_path:
data['test'] = test
if return_tokenizer:
data['tokenizer'] = tokenizer
if return_full_train:
X = np.concatenate([X_train, X_valid])
y = np.concatenate([y_train, y_valid])
data['X'] = X
data['y'] = y
return data
