def main():
"""Summary
Args:
study_info_ (StudyInfo): Description
"""
study_info = StudyInfo("2019 study")
# plot_all_csv(study_info_)
#
initial_test(study_info)
test_models(study_info)
test_features(study_info)
pass
def output_all_polyseme_info():
"""Summary
:param study_info_:
Args:
study_info_ (TYPE): Description
"""
print("outputting all polyseme info")
study_info_ = StudyInfo("2019 study")
all_scenes = study_info_.scene_name_list
generated_polyseme_models = GeneratePolysemeModels(all_scenes, all_scenes,
study_info_)
generated_polyseme_models.distinct_supervised_model.output_polyseme_info()
def output_typicality():
"""Summary
:param study_info_:
Args:
study_info_ (TYPE): Description
"""
print("outputting typicalities")
s_info = StudyInfo("2019 study")
all_scenes = s_info.scene_name_list
generated_polyseme_models = GeneratePolysemeModels(all_scenes, all_scenes,
s_info)
p_models = generated_polyseme_models.models
for model in p_models:
for preposition in PREPOSITION_LIST:
model.output_typicalities(preposition)
def get_standard_preposition_parameters(train_scenes):
model_study_info = StudyInfo("2019 study")
# scene_list = model_study_info.scene_name_list
preposition_models_dict = dict()
features_to_remove = Configuration.object_specific_features.copy()
# Get parameters for each preposition
for p in PREPOSITION_LIST:
M = GeneratePrepositionModelParameters(
model_study_info,
p,
train_scenes,
features_to_remove=features_to_remove)
M.work_out_models()
preposition_models_dict[p] = M
return preposition_models_dict
Args:
scene (TYPE): Description
f (TYPE): Description
g (TYPE): Description
Returns:
TYPE: Description
"""
for i in self.instance_list:
if i.configuration_match([scene, f, g]):
return i
if __name__ == '__main__':
study_info = StudyInfo("2019 study")
# First preprocess features
preprocess_features.process_all_features(study_info)
### Semantic Annotations
### Collect annotation instances and attach values to them
svcollection = SemanticCollection(study_info)
svcollection.write_preposition_stats_csvs()
svcollection.write_config_ratios()
#### Comparative Annotations
compcollection = ComparativeCollection(study_info)
"""Summary
Contains Features class which, for a given study, reads file of extracted features, removes some features,
gets average location control, standardises values and outputs
"""
from data_import import StudyInfo
def process_all_features(study):
"""Summary
"""
f = study.feature_processor
nd = f.standardise_values()
f.write_new(nd)
f.write_mean_std()
if __name__ == '__main__':
process_all_features(StudyInfo("2019 study"))
process_all_features(StudyInfo("2020 study"))