logger = create_logger(__name__)
environment.reproducible()
theano.config.floatX = 'float32'
if not os.path.exists(WORD_EMBEDDING_NN):
raise EnvironmentError("Can't find NN model. File {} doesn't exist {}."
"Probably you haven't train it yet. "
"Run `train_word_embedding_nn.py` script.")
logger.info("Reading data")
data = pd.read_csv(REVIEWS_FILE, sep='\t')
logger.info("Loading word embedding NN")
word2vec = WordEmbeddingNN.load(WORD_EMBEDDING_NN)
prepare_data_pipeline = Pipeline([
('tokenize_texts', TokenizeText(ignore_stopwords=False)),
('ignore_unknown_words', IgnoreUnknownWords(dictionary=word2vec.vocab)),
('word_embedding', word2vec),
])
classifier = algorithms.RPROP(
[
layers.Relu(100),
layers.Relu(200),
layers.Sigmoid(50),
layers.RoundedOutput(1),
],
error='binary_crossentropy',
import pandas as pd
from neupy import utils
from src.word_embedding_nn import WordEmbeddingNN
from src.preprocessing import TokenizeText
from src.utils import create_logger, REVIEWS_FILE, WORD_EMBEDDING_NN
logger = create_logger(__name__)
utils.reproducible()
if not os.path.exists(REVIEWS_FILE):
raise EnvironmentError("Cannot find reviews.csv file. Probably you "
"haven't run `loadata.py` script yet.")
data = pd.read_csv(REVIEWS_FILE, sep='\t')
train_data = data[data.type == 'train']
documents = train_data.text.values
logger.info("Tokenizing train data")
text_tokenizer = TokenizeText(ignore_stopwords=False)
word2vec = WordEmbeddingNN(size=100, workers=4, min_count=5, window=10)
text = text_tokenizer.transform(documents)
logger.info("Building vocabulary")
word2vec.build_vocab(text)
word2vec.train(text, n_epochs=10)
logger.info("Saving model into the {} file".format(WORD_EMBEDDING_NN))
word2vec.save(WORD_EMBEDDING_NN)
logger = create_logger(__name__)
environment.reproducible()
theano.config.floatX = 'float32'
if not os.path.exists(WORD_EMBEDDING_NN):
raise EnvironmentError("Can't find NN model. File {} doesn't exist {}."
"Probably you haven't train it yet. "
"Run `train_word_embedding_nn.py` script.")
logger.info("Reading data")
data = pd.read_csv(REVIEWS_FILE, sep='\t')
logger.info("Loading word embedding NN")
word2vec = WordEmbeddingNN.load(WORD_EMBEDDING_NN)
prepare_data_pipeline = Pipeline([
('tokenize_texts', TokenizeText(ignore_stopwords=False)),
('ignore_unknown_words', IgnoreUnknownWords(dictionary=word2vec.vocab)),
('word_embedding', word2vec),
])
classifier = algorithms.RPROP(
[
layers.Relu(100),
layers.Relu(200),
layers.Sigmoid(50),
layers.RoundedOutput(1),
],
error='binary_crossentropy',
from neupy import environment
from src.word_embedding_nn import WordEmbeddingNN
from src.preprocessing import TokenizeText
from src.utils import create_logger, REVIEWS_FILE, WORD_EMBEDDING_NN
logger = create_logger(__name__)
environment.reproducible()
if not os.path.exists(REVIEWS_FILE):
raise EnvironmentError("Cannot find reviews.csv file. Probably you "
"haven't run `loadata.py` script yet.")
data = pd.read_csv(REVIEWS_FILE, sep='\t')
train_data = data[data.type == 'train']
documents = train_data.text.values
logger.info("Tokenizing train data")
text_tokenizer = TokenizeText(ignore_stopwords=False)
word2vec = WordEmbeddingNN(size=100, workers=4, min_count=5, window=10)
text = text_tokenizer.transform(documents)
logger.info("Building vocabulary")
word2vec.build_vocab(text)
word2vec.train(text, n_epochs=10)
logger.info("Saving model into the {} file".format(WORD_EMBEDDING_NN))
word2vec.save(WORD_EMBEDDING_NN)
