def prepare_data(self, dataset):
trainFeaturesExtractor = FeaturesExtractor(
self.configFileFeaturesExtractor,
self.trainFeaturesSerializationFile,
self.trainLabelsSerializationFile,
self.languageModel,
dataset,
sentiment_features=True)
trainFeaturesExtractor.ExtractNumTfFeatures(init_dicts())
maxid = max([max(i.keys()) for i in trainFeaturesExtractor.features])
X = []
Y = []
for i, item in enumerate(trainFeaturesExtractor.features):
itemx = [0 for _ in range(maxid)]
l = [0, 0, 0]
l[trainFeaturesExtractor.labels[i] - 1] = 1
for j in trainFeaturesExtractor.features[i]:
v = trainFeaturesExtractor.features[i][j]
itemx[j - 1] = v
X.append(itemx)
Y.append(trainFeaturesExtractor.labels[i])
trainFeaturesExtractor.dataset = []
trainFeaturesExtractor.features = []
trainFeaturesExtractor.labels = []
return X, Y
def prepare_data(self, dataset): trainFeaturesExtractor = FeaturesExtractor(self.configFileFeaturesExtractor, self.trainFeaturesSerializationFile, self.trainLabelsSerializationFile, self.languageModel, dataset, sentiment_features=True) trainFeaturesExtractor.ExtractNumTfFeatures(sentiment_dict=init_dicts(), sparse=True) X= trainFeaturesExtractor.sparse_features Y = np.array(trainFeaturesExtractor.labels) trainFeaturesExtractor.dataset = [] trainFeaturesExtractor.features = [] trainFeaturesExtractor.labels = [] return X, Y