def train_model_best(is_training=False, model_name='S2-gb', classifier=lr):
model_best = stst.Model(model_name, classifier)
model_best.add(TFFeature(type='word', convey='count', load=True))
model_best.add(TFFeature(type='char', convey='count', load=True))
model_best.add(BigramFeature(type='word', convey='count', load=True))
model_best.add(BigramFeature(type='char', convey='count', load=True))
emb_wd_50_file = config.EMB_WORD_DIR + '/embedding.50'
emb_wd_100_file = config.EMB_WORD_DIR + '/embedding.100'
emb_wd_200_file = config.EMB_WORD_DIR + '/embedding.200'
emb_wd_300_file = config.EMB_WORD_DIR + '/embedding.300'
headlines_vec = config.EMB_WORD_DIR + '/headlines.vec'
model_best.add(
MinAvgMaxEmbeddingFeature('headlines',
100,
headlines_vec,
pooling_type='avg',
load=True))
model_best.add(
MinAvgMaxEmbeddingFeature('headlines',
100,
headlines_vec,
pooling_type='all',
load=True))
if is_training:
train_nlpcc(model_best)
dev_nlpcc(model_best)
return model_best
def stack():
model_stack = stst.Model('Stack1', boosting)
model_stack.add(model_best_stack)
model_stack.add(xgb_model_best_stack)
model_stack.add(model_emb_stack)
train_nlpcc(model_stack)
model_stack.feature_list = []
model_stack.add(model_best)
model_stack.add(model_emb)
model_stack.add(xgb_model_best)
dev_nlpcc(model_stack)
word_count += len(words)
char_count += len(chars)
print(word_count / len(instances))
print(char_count / len(instances))
# Define Model
lr = stst.Classifier(stst.LIB_LINEAR_LR())
svm = stst.Classifier(stst.skLearn_svm())
xgb = stst.Classifier(stst.XGBOOST_prob())
boosting = stst.Classifier(stst.sklearn_GradientBoosting())
model = stst.Model('S-lr-expand', lr)
# model.add(FuckFeature(load=True))
model.add(TFFeature(type='word', convey='count', load=False))
model.add(TFFeature(type='char', convey='count', load=False))
model.add(BigramFeature(type='word', convey='count', load=False))
model.add(BigramFeature(type='char', convey='count', load=False))
headlines_vec = config.EMB_WORD_DIR + '/headlines.vec'
model.add(
MinAvgMaxEmbeddingFeature('headlines',
100,
headlines_vec,
pooling_type='avg',
load=False))
