tagsLoader = TagsLoader(directory_tags_path, classification_DIP_result)
tagsLoader.Load()
#
#
gnx = result[0]
map_fetures = result[1]
number_of_learning_for_mean = 1.0
save_clf_file_name = result_path + r'clf/'
load_clf_file_name = None
random_state = 1
deep = False
if (deep):
mm.deepLearning(
gnx,
map_fetures,
number_of_learning_for_mean=number_of_learning_for_mean,
classifications=classification_DIP_result,
tags_loader=tagsLoader,
result_path=result_path,
random_state=random_state)
else:
mm.machineLearning(
gnx,
map_fetures,
number_of_learning_for_mean=number_of_learning_for_mean,
classifications=classification_DIP_result,
ml_algos=ml_algos,
tags_loader=tagsLoader,
result_path=result_path)
map_fetures = result[1]
number_of_learning_for_mean = 1.0
deep = True
if (deep):
mm.deepLearning(gnx,
map_fetures,
number_of_learning_for_mean=3.0,
classifications=classification_wiki_result,
tags_loader=tagsLoader,
result_path=result_path,
edges=True,
save_clf_file_name=result_path + r'clf/',
load_clf_file_name=None,
random_state=1)
else:
mm.machineLearning(
gnx,
map_fetures,
number_of_learning_for_mean=number_of_learning_for_mean,
classifications=classification_wiki_result,
ml_algos=ml_algos,
tags_loader=tagsLoader,
result_path=result_path,
edges=True,
save_clf_file_name=None,
load_clf_file_name=result_path + r'clf/',
random_state=1)
#step 3: vizualization