def rescale(config, online_preds_fp):
online_preds = DataUtil.load_vector(online_preds_fp, 'float')
feature_name = 'graph_edge_max_clique_size'
feature_pt = config.get('DEFAULT', 'feature_pt')
test_feature_fp = '%s/%s.test.smat' % (feature_pt, feature_name)
test_features_mc = Feature.load(test_feature_fp).toarray()
feature_name = 'graph_edge_cc_size'
feature_pt = config.get('DEFAULT', 'feature_pt')
test_feature_fp = '%s/%s.test.smat' % (feature_pt, feature_name)
test_features_cc = Feature.load(test_feature_fp).toarray()
for index in range(len(online_preds)):
score = online_preds[index]
if test_features_mc[index][0] == 3.:
score = PostProcessor.adj(score, te=0.40883512, tr=0.623191)
elif test_features_mc[index][0] > 3.:
score = PostProcessor.adj(score, te=0.96503024, tr=0.972554)
else:
if test_features_cc[index][0] < 3.:
score = PostProcessor.adj(score,
te=0.05739666,
tr=0.233473)
else:
score = PostProcessor.adj(score,
te=0.04503431,
tr=0.149471)
online_preds[index] = score
DataUtil.save_vector(online_preds_fp + '.rescale', online_preds)
def run_online(self):
# load feature matrix
online_features = Feature.load_all(self.config.get('DIRECTORY', 'feature_pt'),
self.config.get('FEATURE', 'feature_selected').split(),
self.config.get('MODEL', 'online_rawset_name'),
self.config.get('FEATURE', 'will_save'))
model = Model.new(self.config.get('MODEL', 'model_name'), self.config)
model_fp = self.config.get('DIRECTORY', 'model_pt') + '/se.%s.model' % self.config.get('MODEL', 'model_name')
model.load(model_fp)
online_preds = model.predict(online_features)
online_preds_fp = '%s/se_online.%s.pred' % (self.config.get('DIRECTORY', 'pred_pt'),
self.config.get('MODEL', 'online_test_rawset_name'))
DataUtil.save_vector(online_preds_fp, online_preds, 'w')
def __generate_index(self, row_num):
index_all = [list()] * self.cv_num
for i in range(row_num):
index_all[int(random.random() * self.cv_num)].append(i)
for i in range(self.cv_num):
LogUtil.log(
'INFO',
'generate cv index, size(part%d)=%d' % (i, len(index_all[i])))
index_pt = self.config.get('DEFAULT', 'index_pt')
for i in range(self.cv_num):
fold_id = i
# train
fp = '%s/cv_tag%s_n%d_f%d_train.%s.index' % (
index_pt, self.cv_tag, self.cv_num, fold_id,
self.config.get('MODEL', 'offline_rawset_name'))
DataUtil.save_vector(fp, list(), 'w')
for j in range(self.cv_num - 2):
part_id = (i + j) % self.cv_num
DataUtil.save_vector(fp, index_all[part_id], 'a')
# valid
fp = '%s/cv_tag%s_n%d_f%d_valid.%s.index' % (
index_pt, self.cv_tag, self.cv_num, fold_id,
self.config.get('MODEL', 'offline_rawset_name'))
part_id = (fold_id + self.cv_num - 2) % self.cv_num
DataUtil.save_vector(fp, index_all[part_id], 'w')
# test
fp = '%s/cv_tag%s_n%d_f%d_test.%s.index' % (
index_pt, self.cv_tag, self.cv_num, fold_id,
self.config.get('MODEL', 'offline_rawset_name'))
part_id = (fold_id + self.cv_num - 1) % self.cv_num
DataUtil.save_vector(fp, index_all[part_id], 'w')
def generate_index_with_swap(self):
"""
Generate the index file of `train_with_swap.csv`
:return: none
"""
train_index_fp = '%s/train_311.train.index' % self.config.get('DEFAULT', 'feature_index_pt')
train_with_swap_index_fp = '%s/train_311.train_with_swap.index' % self.config.get('DEFAULT', 'feature_index_pt')
train_index = DataUtil.load_vector(train_index_fp, False)
train_index = [int(x) for x in train_index]
offset = 404290
train_swap_index = [x + offset for x in train_index]
train_with_swap_index = train_index + train_swap_index
DataUtil.save_vector(train_with_swap_index_fp, train_with_swap_index, 'w')
def run_online(self):
# load feature matrix
online_features = Feature.load_all(
self.config.get('DIRECTORY', 'feature_pt'),
self.config.get('FEATURE', 'feature_selected').split(),
self.config.get('MODEL', 'online_rawset_name'),
self.config.get('FEATURE', 'will_save'))
model = Model.new(self.config.get('MODEL', 'model_name'), self.config)
model_fp = self.config.get(
'DIRECTORY', 'model_pt') + '/se.%s.model' % self.config.get(
'MODEL', 'model_name')
model.load(model_fp)
online_preds = model.predict(online_features)
online_preds_fp = '%s/se_online.%s.pred' % (self.config.get(
'DIRECTORY',
'pred_pt'), self.config.get('MODEL', 'online_test_rawset_name'))
DataUtil.save_vector(online_preds_fp, online_preds, 'w')
def __generate_index(self, row_num):
train_indexs = list()
valid_indexs = list()
test_indexs = list()
for i in range(row_num):
part_id = random.random() * self.se_num
if part_id < self.se_num - 2:
train_indexs.append(i)
elif part_id < self.se_num - 1:
valid_indexs.append(i)
else:
test_indexs.append(i)
index_pt = self.config.get('DEFAULT', 'index_pt')
train_fp = '%s/se_tag%s_train.%s.index' % (
index_pt, self.se_tag,
self.config.get('MODEL', 'offline_rawset_name'))
DataUtil.save_vector(train_fp, train_indexs, 'w')
valid_fp = '%s/se_tag%s_valid.%s.index' % (
index_pt, self.se_tag,
self.config.get('MODEL', 'offline_rawset_name'))
DataUtil.save_vector(valid_fp, valid_indexs, 'w')
test_fp = '%s/se_tag%s_test.%s.index' % (
index_pt, self.se_tag,
self.config.get('MODEL', 'offline_rawset_name'))
DataUtil.save_vector(test_fp, test_indexs, 'w')
def __generate_index(self, row_num):
train_indexs = list()
valid_indexs = list()
test_indexs = list()
for i in range(row_num):
part_id = random.random() * self.se_num
if part_id < self.se_num - 2:
train_indexs.append(i)
elif part_id < self.se_num - 1:
valid_indexs.append(i)
else:
test_indexs.append(i)
index_pt = self.config.get('DEFAULT', 'index_pt')
train_fp = '%s/se_tag%s_train.%s.index' % (index_pt,
self.se_tag,
self.config.get('MODEL', 'offline_rawset_name'))
DataUtil.save_vector(train_fp, train_indexs, 'w')
valid_fp = '%s/se_tag%s_valid.%s.index' % (index_pt,
self.se_tag,
self.config.get('MODEL', 'offline_rawset_name'))
DataUtil.save_vector(valid_fp, valid_indexs, 'w')
test_fp = '%s/se_tag%s_test.%s.index' % (index_pt,
self.se_tag,
self.config.get('MODEL', 'offline_rawset_name'))
DataUtil.save_vector(test_fp, test_indexs, 'w')
def generate_cv_subset_index(cf, argv):
"""
Generate index used for 5-fold cross validation
:param cf: configuration file
:param argv: parameter list
:return: none
"""
tag = argv[0]
cv_num = 5
cv_rawset_name = 'train_with_swap'
train_data_size = 404290
index_all = []
for i in range(cv_num):
index_all.append([])
for i in range(train_data_size):
index_all[int(random.random() * cv_num)].append(i)
for i in range(cv_num):
LogUtil.log('INFO', 'size(part%d)=%d' % (i, len(index_all[i])))
index_fp = cf.get('DEFAULT', 'feature_index_pt')
for i in range(cv_num):
fold_id = i
# train
fp = '%s/cv_tag%s_n%d_f%d_train.%s.index' % (
index_fp, tag, cv_num, fold_id, cv_rawset_name)
for j in range(cv_num - 2):
part_id = (i + j) % cv_num
DataUtil.save_vector(fp, index_all[part_id], 'a')
for j in range(cv_num - 2):
part_id = (i + j) % cv_num
DataUtil.save_vector(
fp,
[index + train_data_size
for index in index_all[part_id]], 'a')
# valid
fp = '%s/cv_tag%s_n%d_f%d_valid.%s.index' % (
index_fp, tag, cv_num, fold_id, cv_rawset_name)
part_id = (fold_id + cv_num - 2) % cv_num
DataUtil.save_vector(fp, index_all[part_id], 'w')
# test
fp = '%s/cv_tag%s_n%d_f%d_test.%s.index' % (
index_fp, tag, cv_num, fold_id, cv_rawset_name)
part_id = (fold_id + cv_num - 1) % cv_num
DataUtil.save_vector(fp, index_all[part_id], 'w')
def __generate_index(self, row_num):
index_all = [list()] * self.cv_num
for i in range(row_num):
index_all[int(random.random() * self.cv_num)].append(i)
for i in range(self.cv_num):
LogUtil.log('INFO', 'generate cv index, size(part%d)=%d' % (i, len(index_all[i])))
index_pt = self.config.get('DEFAULT', 'index_pt')
for i in range(self.cv_num):
fold_id = i
# train
fp = '%s/cv_tag%s_n%d_f%d_train.%s.index' % (index_pt,
self.cv_tag,
self.cv_num,
fold_id,
self.config.get('MODEL', 'offline_rawset_name'))
DataUtil.save_vector(fp, list(), 'w')
for j in range(self.cv_num - 2):
part_id = (i + j) % self.cv_num
DataUtil.save_vector(fp, index_all[part_id], 'a')
# valid
fp = '%s/cv_tag%s_n%d_f%d_valid.%s.index' % (index_pt,
self.cv_tag,
self.cv_num,
fold_id,
self.config.get('MODEL', 'offline_rawset_name'))
part_id = (fold_id + self.cv_num - 2) % self.cv_num
DataUtil.save_vector(fp, index_all[part_id], 'w')
# test
fp = '%s/cv_tag%s_n%d_f%d_test.%s.index' % (index_pt,
self.cv_tag,
self.cv_num,
fold_id,
self.config.get('MODEL', 'offline_rawset_name'))
part_id = (fold_id + self.cv_num - 1) % self.cv_num
DataUtil.save_vector(fp, index_all[part_id], 'w')
def run_offline(self):
LogUtil.log('INFO', 'cv_tag(%s)' % self.cv_tag)
# load feature matrix
offline_features = Feature.load_all(
self.config.get('DIRECTORY', 'feature_pt'),
self.config.get('FEATURE', 'feature_selected').split(),
self.config.get('MODEL', 'offline_rawset_name'),
self.config.get('FEATURE', 'will_save'))
# load labels
offline_labels = DataUtil.load_vector(
'%s/%s.label' % (self.config.get('DIRECTORY', 'label_pt'),
self.config.get('MODEL', 'offline_rawset_name')),
True)
# generate index file
if '' == self.cv_tag:
self.cv_tag = self.out_tag
self.__generate_index(offline_features.shape[0])
# cross validation
offline_valid_preds_all = [0.] * offline_features.shape[0]
offline_test_preds_all = [0.] * offline_features.shape[0]
for fold_id in range(self.cv_num):
LogUtil.log('INFO', 'cross validation fold_id(%d) begin' % fold_id)
# generate training data set
offline_train_pos_rate = float(
self.config.get('MODEL', 'train_pos_rate'))
offline_train_indexs_fp = '%s/cv_tag%s_n%d_f%d_train.%s.index' % (
self.config.get('DIRECTORY',
'index_pt'), self.cv_tag, self.cv_num, fold_id,
self.config.get('MODEL', 'offline_rawset_name'))
offline_train_indexs = DataUtil.load_vector(
offline_train_indexs_fp, 'int')
offline_train_features, offline_train_labels, offline_train_balanced_indexs = \
CrossValidation.__generate_data(offline_train_indexs,
offline_labels,
offline_features,
offline_train_pos_rate)
LogUtil.log('INFO', 'offline train data generation done')
# generate validation data set
offline_valid_pos_rate = float(
self.config.get('MODEL', 'valid_pos_rate'))
offline_valid_indexs_fp = '%s/cv_tag%s_n%d_f%d_valid.%s.index' % (
self.config.get('DIRECTORY',
'index_pt'), self.cv_tag, self.cv_num, fold_id,
self.config.get('MODEL', 'offline_rawset_name'))
offline_valid_indexs = DataUtil.load_vector(
offline_valid_indexs_fp, 'int')
offline_valid_features, offline_valid_labels, offline_valid_balanced_indexs = \
CrossValidation.__generate_data(offline_valid_indexs,
offline_labels,
offline_features,
offline_valid_pos_rate)
LogUtil.log('INFO', 'offline valid data generation done')
# generate test data set
offline_test_pos_rate = float(
self.config.get('MODEL', 'test_pos_rate'))
offline_test_indexs_fp = '%s/cv_tag%s_n%d_f%d_test.%s.index' % (
self.config.get('DIRECTORY',
'index_pt'), self.cv_tag, self.cv_num, fold_id,
self.config.get('MODEL', 'offline_rawset_name'))
offline_test_indexs = DataUtil.load_vector(offline_test_indexs_fp,
'int')
offline_test_features, offline_test_labels, offline_test_balanced_indexs = \
CrossValidation.__generate_data(offline_test_indexs,
offline_labels,
offline_features,
offline_test_pos_rate)
LogUtil.log('INFO', 'offline test data generation done')
model = Model.new(self.config.get('MODEL', 'model_name'),
self.config)
model_fp = self.config.get('DIRECTORY', 'model_pt') + '/cv_n%d_f%d.%s.model' % \
(self.cv_num,
fold_id,
self.config.get('MODEL', 'model_name'))
model.save(model_fp)
offline_train_preds, offline_valid_preds, offline_test_preds = model.fit(
offline_train_features, offline_train_labels,
offline_valid_features, offline_valid_labels,
offline_test_features, offline_test_labels)
offline_train_score = Evaluator.evaluate(
self.config.get('MODEL', 'evaluator_name'),
offline_train_labels, offline_train_preds)
offline_valid_score = Evaluator.evaluate(
self.config.get('MODEL', 'evaluator_name'),
offline_valid_labels, offline_valid_preds)
offline_test_score = Evaluator.evaluate(
self.config.get('MODEL', 'evaluator_name'),
offline_test_labels, offline_test_preds)
score_fp = '%s/%s.score' % (self.config.get(
'DIRECTORY', 'score_pt'), 'cv')
score_file = open(score_fp, 'a')
score_file.write('fold:%d\ttrain:%s\tvalid:%s\ttest:%s\n' %
(fold_id, offline_train_score,
offline_valid_score, offline_test_score))
score_file.close()
# merge prediction results
for index in range(len(offline_valid_balanced_indexs)):
offline_valid_preds_all[offline_valid_balanced_indexs[
index]] = offline_valid_preds[index]
for index in range(len(offline_test_balanced_indexs)):
offline_test_preds_all[offline_test_balanced_indexs[
index]] = offline_test_preds[index]
LogUtil.log('INFO', 'cross test fold_id(%d) done' % fold_id)
# save prediction results
offline_valid_preds_all_fp = '%s/cv_n%d_valid.%s.pred' % (
self.config.get('DIRECTORY', 'pred_pt'), self.cv_num,
self.config.get('MODEL', 'offline_rawset_name'))
DataUtil.save_vector(offline_valid_preds_all_fp,
offline_valid_preds_all, 'w')
offline_test_preds_all_fp = '%s/cv_n%d_test.%s.pred' % (
self.config.get('DIRECTORY', 'pred_pt'), self.cv_num,
self.config.get('MODEL', 'offline_rawset_name'))
DataUtil.save_vector(offline_test_preds_all_fp, offline_test_preds_all,
'w')
# evaluate
offline_valid_score = Evaluator.evaluate(
self.config.get('MODEL', 'evaluator_name'), offline_labels,
offline_valid_preds_all)
offline_test_score = Evaluator.evaluate(
self.config.get('MODEL', 'evaluator_name'), offline_labels,
offline_test_preds_all)
score_fp = '%s/%s.score' % (self.config.get('DIRECTORY',
'score_pt'), 'cv')
score_file = open(score_fp, 'a')
score_file.write('cross_validation\tvalid:%s\ttest:%s\n' %
(offline_valid_score, offline_test_score))
score_file.close()
def run_offline(self):
# load feature matrix
offline_features = Feature.load_all(
self.config.get('DIRECTORY', 'feature_pt'),
self.config.get('FEATURE', 'feature_selected').split(),
self.config.get('MODEL', 'offline_rawset_name'),
self.config.get('FEATURE', 'will_save'))
# load labels
offline_labels = DataUtil.load_vector(
'%s/%s.label' % (self.config.get('DIRECTORY', 'label_pt'),
self.config.get('MODEL', 'offline_rawset_name')),
True)
# generate index file
if '' == self.se_tag:
self.se_tag = self.out_tag
self.__generate_index(offline_features.shape[0])
index_pt = self.config.get('DIRECTORY', 'index_pt')
# generate training data set
offline_train_pos_rate = float(
self.config.get('MODEL', 'train_pos_rate'))
offline_train_indexs_fp = '%s/se_tag%s_train.%s.index' % (
index_pt, self.se_tag,
self.config.get('MODEL', 'offline_rawset_name'))
offline_train_indexs = DataUtil.load_vector(offline_train_indexs_fp,
'int')
offline_train_features, offline_train_labels, offline_train_balanced_indexs = \
SingleExec.__generate_data(offline_train_indexs,
offline_labels,
offline_features,
offline_train_pos_rate)
LogUtil.log('INFO', 'offline train data generation done')
# generate validation data set
offline_valid_pos_rate = float(
self.config.get('MODEL', 'valid_pos_rate'))
offline_valid_indexs_fp = '%s/se_tag%s_valid.%s.index' % (
index_pt, self.se_tag,
self.config.get('MODEL', 'offline_rawset_name'))
offline_valid_indexs = DataUtil.load_vector(offline_valid_indexs_fp,
'int')
offline_valid_features, offline_valid_labels, offline_valid_balanced_indexs = \
SingleExec.__generate_data(offline_valid_indexs,
offline_labels,
offline_features,
offline_valid_pos_rate)
LogUtil.log('INFO', 'offline valid data generation done')
# generate test data set
offline_test_pos_rate = float(self.config.get('MODEL',
'test_pos_rate'))
offline_test_indexs_fp = '%s/se_tag%s_test.%s.index' % (
index_pt, self.se_tag,
self.config.get('MODEL', 'offline_rawset_name'))
offline_test_indexs = DataUtil.load_vector(offline_test_indexs_fp,
'int')
offline_test_features, offline_test_labels, offline_test_balanced_indexs = \
SingleExec.__generate_data(offline_test_indexs,
offline_labels,
offline_features,
offline_test_pos_rate)
LogUtil.log('INFO', 'offline test data generation done')
model = Model.new(self.config.get('MODEL', 'model_name'), self.config)
model_fp = self.config.get(
'DIRECTORY', 'model_pt') + '/se.%s.model' % self.config.get(
'MODEL', 'model_name')
model.save(model_fp)
offline_train_preds, offline_valid_preds, offline_test_preds = model.fit(
offline_train_features, offline_train_labels,
offline_valid_features, offline_valid_labels,
offline_test_features, offline_test_labels)
offline_train_score = Evaluator.evaluate(
self.config.get('MODEL', 'evaluator_name'), offline_train_labels,
offline_train_preds)
offline_valid_score = Evaluator.evaluate(
self.config.get('MODEL', 'evaluator_name'), offline_valid_labels,
offline_valid_preds)
offline_test_score = Evaluator.evaluate(
self.config.get('MODEL', 'evaluator_name'), offline_test_labels,
offline_test_preds)
score_fp = '%s/%s.score' % (self.config.get('DIRECTORY',
'score_pt'), 'cv')
score_file = open(score_fp, 'a')
score_file.write(
'single_exec\ttrain:%s\tvalid:%s\ttest:%s\n' %
(offline_train_score, offline_valid_score, offline_test_score))
score_file.close()
# save prediction results
offline_valid_preds_fp = '%s/se_valid.%s.pred' % (self.config.get(
'DIRECTORY',
'pred_pt'), self.config.get('MODEL', 'offline_rawset_name'))
DataUtil.save_vector(offline_valid_preds_fp, offline_valid_preds, 'w')
offline_test_preds_fp = '%s/se_test.%s.pred' % (self.config.get(
'DIRECTORY',
'pred_pt'), self.config.get('MODEL', 'offline_rawset_name'))
DataUtil.save_vector(offline_test_preds_fp, offline_test_preds, 'w')
def run_offline(self):
LogUtil.log('INFO', 'cv_tag(%s)' % self.cv_tag)
# load feature matrix
offline_features = Feature.load_all(self.config.get('DIRECTORY', 'feature_pt'),
self.config.get('FEATURE', 'feature_selected').split(),
self.config.get('MODEL', 'offline_rawset_name'),
self.config.get('FEATURE', 'will_save'))
# load labels
offline_labels = DataUtil.load_vector('%s/%s.label' % (self.config.get('DIRECTORY', 'label_pt'),
self.config.get('MODEL', 'offline_rawset_name')),
True)
# generate index file
if '' == self.cv_tag:
self.cv_tag = self.out_tag
self.__generate_index(offline_features.shape[0])
# cross validation
offline_valid_preds_all = [0.] * offline_features.shape[0]
offline_test_preds_all = [0.] * offline_features.shape[0]
for fold_id in range(self.cv_num):
LogUtil.log('INFO', 'cross validation fold_id(%d) begin' % fold_id)
# generate training data set
offline_train_pos_rate = float(self.config.get('MODEL', 'train_pos_rate'))
offline_train_indexs_fp = '%s/cv_tag%s_n%d_f%d_train.%s.index' % (self.config.get('DIRECTORY', 'index_pt'),
self.cv_tag,
self.cv_num,
fold_id,
self.config.get('MODEL',
'offline_rawset_name'))
offline_train_indexs = DataUtil.load_vector(offline_train_indexs_fp, 'int')
offline_train_features, offline_train_labels, offline_train_balanced_indexs = \
CrossValidation.__generate_data(offline_train_indexs,
offline_labels,
offline_features,
offline_train_pos_rate)
LogUtil.log('INFO', 'offline train data generation done')
# generate validation data set
offline_valid_pos_rate = float(self.config.get('MODEL', 'valid_pos_rate'))
offline_valid_indexs_fp = '%s/cv_tag%s_n%d_f%d_valid.%s.index' % (self.config.get('DIRECTORY', 'index_pt'),
self.cv_tag,
self.cv_num,
fold_id,
self.config.get('MODEL',
'offline_rawset_name'))
offline_valid_indexs = DataUtil.load_vector(offline_valid_indexs_fp, 'int')
offline_valid_features, offline_valid_labels, offline_valid_balanced_indexs = \
CrossValidation.__generate_data(offline_valid_indexs,
offline_labels,
offline_features,
offline_valid_pos_rate)
LogUtil.log('INFO', 'offline valid data generation done')
# generate test data set
offline_test_pos_rate = float(self.config.get('MODEL', 'test_pos_rate'))
offline_test_indexs_fp = '%s/cv_tag%s_n%d_f%d_test.%s.index' % (self.config.get('DIRECTORY', 'index_pt'),
self.cv_tag,
self.cv_num,
fold_id,
self.config.get('MODEL',
'offline_rawset_name'))
offline_test_indexs = DataUtil.load_vector(offline_test_indexs_fp, 'int')
offline_test_features, offline_test_labels, offline_test_balanced_indexs = \
CrossValidation.__generate_data(offline_test_indexs,
offline_labels,
offline_features,
offline_test_pos_rate)
LogUtil.log('INFO', 'offline test data generation done')
model = Model.new(self.config.get('MODEL', 'model_name'), self.config)
model_fp = self.config.get('DIRECTORY', 'model_pt') + '/cv_n%d_f%d.%s.model' % \
(self.cv_num,
fold_id,
self.config.get('MODEL', 'model_name'))
model.save(model_fp)
offline_train_preds, offline_valid_preds, offline_test_preds = model.fit(offline_train_features,
offline_train_labels,
offline_valid_features,
offline_valid_labels,
offline_test_features,
offline_test_labels)
offline_train_score = Evaluator.evaluate(self.config.get('MODEL', 'evaluator_name'),
offline_train_labels,
offline_train_preds)
offline_valid_score = Evaluator.evaluate(self.config.get('MODEL', 'evaluator_name'),
offline_valid_labels,
offline_valid_preds)
offline_test_score = Evaluator.evaluate(self.config.get('MODEL', 'evaluator_name'),
offline_test_labels,
offline_test_preds)
score_fp = '%s/%s.score' % (self.config.get('DIRECTORY', 'score_pt'), 'cv')
score_file = open(score_fp, 'a')
score_file.write('fold:%d\ttrain:%s\tvalid:%s\ttest:%s\n' % (fold_id,
offline_train_score,
offline_valid_score,
offline_test_score))
score_file.close()
# merge prediction results
for index in range(len(offline_valid_balanced_indexs)):
offline_valid_preds_all[offline_valid_balanced_indexs[index]] = offline_valid_preds[index]
for index in range(len(offline_test_balanced_indexs)):
offline_test_preds_all[offline_test_balanced_indexs[index]] = offline_test_preds[index]
LogUtil.log('INFO', 'cross test fold_id(%d) done' % fold_id)
# save prediction results
offline_valid_preds_all_fp = '%s/cv_n%d_valid.%s.pred' % (self.config.get('DIRECTORY', 'pred_pt'),
self.cv_num,
self.config.get('MODEL', 'offline_rawset_name'))
DataUtil.save_vector(offline_valid_preds_all_fp, offline_valid_preds_all, 'w')
offline_test_preds_all_fp = '%s/cv_n%d_test.%s.pred' % (self.config.get('DIRECTORY', 'pred_pt'),
self.cv_num,
self.config.get('MODEL', 'offline_rawset_name'))
DataUtil.save_vector(offline_test_preds_all_fp, offline_test_preds_all, 'w')
# evaluate
offline_valid_score = Evaluator.evaluate(self.config.get('MODEL', 'evaluator_name'),
offline_labels,
offline_valid_preds_all)
offline_test_score = Evaluator.evaluate(self.config.get('MODEL', 'evaluator_name'),
offline_labels,
offline_test_preds_all)
score_fp = '%s/%s.score' % (self.config.get('DIRECTORY', 'score_pt'), 'cv')
score_file = open(score_fp, 'a')
score_file.write('cross_validation\tvalid:%s\ttest:%s\n' % (offline_valid_score, offline_test_score))
score_file.close()
def run_offline(self):
# load feature matrix
offline_features = Feature.load_all(self.config.get('DIRECTORY', 'feature_pt'),
self.config.get('FEATURE', 'feature_selected').split(),
self.config.get('MODEL', 'offline_rawset_name'),
self.config.get('FEATURE', 'will_save'))
# load labels
offline_labels = DataUtil.load_vector('%s/%s.label' % (self.config.get('DIRECTORY', 'label_pt'),
self.config.get('MODEL', 'offline_rawset_name')),
True)
# generate index file
if '' == self.se_tag:
self.se_tag = self.out_tag
self.__generate_index(offline_features.shape[0])
index_pt = self.config.get('DIRECTORY', 'index_pt')
# generate training data set
offline_train_pos_rate = float(self.config.get('MODEL', 'train_pos_rate'))
offline_train_indexs_fp = '%s/se_tag%s_train.%s.index' % (index_pt,
self.se_tag,
self.config.get('MODEL', 'offline_rawset_name'))
offline_train_indexs = DataUtil.load_vector(offline_train_indexs_fp, 'int')
offline_train_features, offline_train_labels, offline_train_balanced_indexs = \
SingleExec.__generate_data(offline_train_indexs,
offline_labels,
offline_features,
offline_train_pos_rate)
LogUtil.log('INFO', 'offline train data generation done')
# generate validation data set
offline_valid_pos_rate = float(self.config.get('MODEL', 'valid_pos_rate'))
offline_valid_indexs_fp = '%s/se_tag%s_valid.%s.index' % (index_pt,
self.se_tag,
self.config.get('MODEL', 'offline_rawset_name'))
offline_valid_indexs = DataUtil.load_vector(offline_valid_indexs_fp, 'int')
offline_valid_features, offline_valid_labels, offline_valid_balanced_indexs = \
SingleExec.__generate_data(offline_valid_indexs,
offline_labels,
offline_features,
offline_valid_pos_rate)
LogUtil.log('INFO', 'offline valid data generation done')
# generate test data set
offline_test_pos_rate = float(self.config.get('MODEL', 'test_pos_rate'))
offline_test_indexs_fp = '%s/se_tag%s_test.%s.index' % (index_pt,
self.se_tag,
self.config.get('MODEL', 'offline_rawset_name'))
offline_test_indexs = DataUtil.load_vector(offline_test_indexs_fp, 'int')
offline_test_features, offline_test_labels, offline_test_balanced_indexs = \
SingleExec.__generate_data(offline_test_indexs,
offline_labels,
offline_features,
offline_test_pos_rate)
LogUtil.log('INFO', 'offline test data generation done')
model = Model.new(self.config.get('MODEL', 'model_name'), self.config)
model_fp = self.config.get('DIRECTORY', 'model_pt') + '/se.%s.model' % self.config.get('MODEL', 'model_name')
model.save(model_fp)
offline_train_preds, offline_valid_preds, offline_test_preds = model.fit(offline_train_features,
offline_train_labels,
offline_valid_features,
offline_valid_labels,
offline_test_features,
offline_test_labels)
offline_train_score = Evaluator.evaluate(self.config.get('MODEL', 'evaluator_name'),
offline_train_labels,
offline_train_preds)
offline_valid_score = Evaluator.evaluate(self.config.get('MODEL', 'evaluator_name'),
offline_valid_labels,
offline_valid_preds)
offline_test_score = Evaluator.evaluate(self.config.get('MODEL', 'evaluator_name'),
offline_test_labels,
offline_test_preds)
score_fp = '%s/%s.score' % (self.config.get('DIRECTORY', 'score_pt'), 'cv')
score_file = open(score_fp, 'a')
score_file.write('single_exec\ttrain:%s\tvalid:%s\ttest:%s\n' % (offline_train_score,
offline_valid_score,
offline_test_score))
score_file.close()
# save prediction results
offline_valid_preds_fp = '%s/se_valid.%s.pred' % (self.config.get('DIRECTORY', 'pred_pt'),
self.config.get('MODEL', 'offline_rawset_name'))
DataUtil.save_vector(offline_valid_preds_fp, offline_valid_preds, 'w')
offline_test_preds_fp = '%s/se_test.%s.pred' % (self.config.get('DIRECTORY', 'pred_pt'),
self.config.get('MODEL', 'offline_rawset_name'))
DataUtil.save_vector(offline_test_preds_fp, offline_test_preds, 'w')