plot_decision_function(X, y, clf, ax[0], '(a)')
clf = make_pipeline(SMOTE(random_state=0), LinearSVC(random_state=0))
clf.fit(X, y)
plot_decision_function(X, y, clf, ax[1], '(b)')
fig.tight_layout()
plt.savefig(
join(analysis_path, 'resampling_decision_function.pdf'),
bbox_inches='tight',
pad_inches = 0
)
if __name__=='__main__':
data_path, results_path, analysis_path = generate_paths()
# load datasets
datasets = load_datasets(data_dir=data_path)
# load results
results = []
for name in RESULTS_NAMES:
file_path = join(results_path, f'{name}.pkl')
results.append(pd.read_pickle(file_path))
# combine and select results
results = combine_results(*results)
results = select_results(results, oversamplers_names=OVRS_NAMES, classifiers_names=CLFS_NAMES)
# datasets description
('KNN', KNeighborsClassifier(), {'n_neighbors': [3, 5, 8]}),
('RF', RandomForestClassifier(), {'max_depth':
[None, 3, 6], 'n_estimators': [50, 100, 200]})
],
'scoring': ['accuracy', 'f1_macro', 'geometric_mean_score_macro'],
'n_splits': 5,
'n_runs': 3,
'rnd_seed': 0,
'n_jobs': -1
}
if __name__ == '__main__':
# Extract paths
data_dir, results_dir, _ = generate_paths()
# Load datasets
datasets = load_datasets(data_dir=data_dir)
# Extract oversamplers
oversamplers = CONFIG['oversamplers']
# Generate oversamplers
for oversampler in oversamplers:
# Define and fit experiment
experiment = ImbalancedExperiment(
oversamplers=[oversampler],
classifiers=CONFIG['classifiers'],
scoring=CONFIG['scoring'],
],
'scoring': ['accuracy', 'f1_macro', 'geometric_mean_score_macro'],
'n_splits':
5,
'n_runs':
3,
'rnd_seed':
0,
'n_jobs':
-1
}
if __name__ == '__main__':
# Extract paths
data_path, results_path, _ = generate_paths()
# Load lucas dataset
datasets = load_datasets(data_path=data_path, data_type='csv')
# Extract oversamplers
oversamplers = CONFIG['oversamplers']
# Generate oversamplers
for oversampler in oversamplers:
# Define and fit experiment
experiment = ImbalancedExperiment(
oversamplers=[oversampler],
classifiers=CONFIG['classifiers'],
scoring=CONFIG['scoring'],
def createGens(input_example=INPUT_EXAMPLE,
output_example=OUTPUT_EXAMPLE,
shape=(256, 256),
batch_size=32,
split=0.2):
'''
Denotes and returns Train and Validation genrators ...
'''
input_root, input_suffix, output_root, output_suffix, output_separator = generate_paths(
input_example, output_example)
print("Input: ", input_root)
print("Output root: ", output_root)
image_paths = glob(os.path.join(input_root, "*" + input_suffix))
print("-- #Image_paths: ", len(image_paths))
mask_paths = glob(os.path.join(output_root, "*" + output_suffix))
print("-- #Mask_paths: ", len(mask_paths))
if MASK_PATHS != "": # update mask paths to the dedicated ones if it is denoted ...
with open(MASK_PATHS, 'r') as f:
dedicated_mask_paths = json.load(f)
attribute = OUTPUT_EXAMPLE.split(output_separator)[-1].split('.')[0]
mask_paths = dedicated_mask_paths[attribute]
print(" -- However we gonna consume only ", len(mask_paths))
if PREPROPROCESSING_MASK_EXAMPLE:
# TODO: we care only about preprocessing_output and suffix
_, _, preprocessing_root, preprocessing_suffix, _ = generate_paths \
(INPUT_EXAMPLE, PREPROPROCESSING_MASK_EXAMPLE)
preprocessing_paths = glob(os.path.join(preprocessing_root, "*"+\
preprocessing_suffix))
preprocessing_ids = list(map(lambda path: path.split('/')[-1]\
.split(preprocessing_suffix)[0], \
preprocessing_paths))
else:
preprocessing_paths = []
# apparently not all images have a corresponding mask so we need the intersection of those
image_ids = list(map(lambda x: x.split('/')[-1].split(input_suffix)[0], \
image_paths))
mask_ids = list(map(lambda x: x.split('/')[-1].split(output_suffix)[0], \
mask_paths))
if preprocessing_paths:
intersection = list(set(image_ids) & set(mask_ids) & \
set(preprocessing_ids))
preprocessing_paths = list(map(lambda x: os.path.join( \
preprocessing_root, x+preprocessing_suffix), \
intersection))
else:
intersection = list(set(image_ids) & set(mask_ids))
image_paths = list(map(lambda x: os.path.join( \
input_root, x + input_suffix), \
intersection))
mask_paths = list(map(lambda x: os.path.join( \
output_root, x + output_suffix), \
intersection)) # output_suffix is whatever is placed after the id ...
dataset_len = len(image_paths)
train_image_paths = image_paths[:floor(dataset_len * (1 - split))]
train_mask_paths = mask_paths[:floor(dataset_len * (1 - split))]
if preprocessing_paths:
train_preprocessing_paths = preprocessing_paths[:floor(dataset_len *
(1 - split))]
else:
train_preprocessing_paths = []
validation_image_paths = image_paths[ceil(dataset_len * (1 - split)):]
validation_mask_paths = mask_paths[ceil(dataset_len * (1 - split)):]
if preprocessing_paths:
validation_preprocessing_paths = preprocessing_paths[ceil(dataset_len *
(1 -
split)):]
else:
validation_preprocessing_paths = []
return Generator(train_image_paths, train_mask_paths, shape, batch_size,
train_preprocessing_paths), Generator(
validation_image_paths, validation_mask_paths, shape,
batch_size, validation_preprocessing_paths)
