def main():
data_sets = debates.get_for_crossvalidation()
texts = [sentence.text for sentence in data_sets[0][1]]
texts.extend([sentence.text for sentence in data_sets[0][2]])
tokenizer, word_index = create_tokenizer(texts)
create_embedding('/usr/users/oliverren/meng/check-worthy/data/glove/glove.6B.50d.txt', word_index)
import sys
sys.path.append('/usr/users/oliverren/meng/check-worthy')
import numpy as np
from sklearn.metrics import (average_precision_score, precision_score,
recall_score, roc_auc_score)
from keras.preprocessing.sequence import pad_sequences
from keras.callbacks import ModelCheckpoint
from src.data import debates
from src.models import models
from src.stats import rank_metrics as rm
from src.features.feature_sets import get_serialized_pipeline
data_sets = debates.get_for_crossvalidation()
texts = [
sentence.text for sentence in debates.read_all_debates(sep_by_deb=False)
] #debates
texts.extend([
sentence.text for sentence in debates.read_all_speeches(sep_by_deb=False)
]) #speeches
tokenizer, word_index = models.create_tokenizer(texts)
MAX_SENTENCE_LENGTH = max([len(sentence.split()) for sentence in texts])
folder = 'speeches/'
# tests: one hidden layer, dropout 0.3, softmax activation, fixed vs dynamic word embedding (300d glove)
results = []
serialize = False
if serialize:
all_debates = []
trainable_feats = counting_feat.BagOfTfIDF.FEATS + knn_similarity.TrainSearch.FEATS
for debate in DEBATES:
all_debates += read_debates(debate)
all_feats = get_experimential_pipeline(all_debates, to_matrix=False).fit_transform(all_debates)
for feat_name in all_feats[0].features.keys():
if feat_name in trainable_feats:
continue
feat_dict = {}
for _x in all_feats:
feat_dict[str(_x.id) + _x.debate.name] = _x.features[feat_name]
if os.path.isfile(CONFIG['features_dump_dir'] + feat_name):
old_dict = json.loads(open(CONFIG['features_dump_dir'] + feat_name).read())
else:
old_dict = {}
old_dict.update(feat_dict)
with open(CONFIG['features_dump_dir'] + feat_name, "w") as out:
out.write(json.dumps(old_dict))
else:
results = []
for test_deb, test, train in get_for_crossvalidation():
split_results = run(test, train)
results.append(split_results)
get_all_metrics(copy.deepcopy([split_results]), agreement=1)
get_all_metrics(results, agreement=1)