def main(data_path="data/split/", feature_path="data/features/", out_path="data/pca/"):
X_train, X_test, y_train, y_test = read_data(data_path)
params = read_params("params.yaml", "pca")
pca = PCA(**params).fit(X_train)
train_feature = pd.DataFrame(pca.transform(X_train))
test_feature = pd.DataFrame(pca.transform(X_test))
train_feature["class"] = y_train
test_feature["class"] = y_test
if not os.path.isdir(feature_path):
os.mkdir(feature_path)
train_feature.to_csv(f"{feature_path}train.csv", index=False)
test_feature.to_csv(f"{feature_path}test.csv", index=False)
save_results(out_path, pca, None)
print(f"Finished Feature Engineering:\nStats:")
print(f"\tExplained Variance: {pca.explained_variance_}")
print(f"\tExplained Variance Ratio: {pca.explained_variance_ratio_}")
log_experiment(
out_path,
metrics=dict(
explained_variance_=pca.explained_variance_,
explained_variance_ratio_=pca.explained_variance_ratio_,
),
)
def main(data_path='data/split/',
feature_path='data/features/',
out_path='data/pca/'):
X_train, X_test, y_train, y_test = read_data(data_path)
params = read_params('params.yaml', 'pca')
pca = PCA(**params).fit(X_train)
train_feature = pd.DataFrame(pca.transform(X_train))
test_feature = pd.DataFrame(pca.transform(X_test))
train_feature['class'] = y_train
test_feature['class'] = y_test
if not os.path.isdir(feature_path):
os.mkdir(feature_path)
train_feature.to_csv(f'{feature_path}train.csv', index=False)
test_feature.to_csv(f'{feature_path}test.csv', index=False)
save_results(out_path, pca, None)
print(f'Finished Feature Engineering:\nStats:')
print(f'\tExplained Variance: {pca.explained_variance_}')
print(f'\tExplained Variance Ratio: {pca.explained_variance_ratio_}')
log_experiment(
out_path,
params=params,
metrics=dict(explained_variance_=pca.explained_variance_,
explained_variance_ratio_=pca.explained_variance_ratio_))
def main(config):
experiment_name, current_time = setup_experiment(config.title, config)
# normalization (creating t1_landmarks.npy file)
create_normalization_file(
use_controls=config.use_controls,
use_nofcd=config.use_ae,
mods=config.nb_of_modalities,
)
print('Normalization is finished')
# patch extraction
get_patch_list(use_controls=config.use_controls,
use_fcd=config.use_ae,
use_coronal=config.use_coronal,
use_sagital=config.use_sagital,
augment=config.augment,
h=config.height,
w=config.width,
hard_labeling=config.hard_labeling,
mods=config.nb_of_modalities,
batch_size=config.batch_size)
print('Patch extraction is finished')
# cnn model
top_k_scores = train_model(mods=config.nb_of_modalities,
use_ae=config.use_ae,
h=config.height,
w=config.width,
use_coronal=config.use_coronal,
use_sagital=config.use_sagital,
use_controls=config.use_controls,
latent_dim=config.latent_size,
batch_size=config.batch_size,
lr=config.lr,
weight_decay=config.weight_decay,
weight_of_class=config.weight_of_class,
n_epochs=config.nb_epochs,
n_epochs_ae=config.nb_epochs_ae,
p=config.dropout_rate,
save_masks=config.save_masks,
parallel=config.parallel,
experiment_name=experiment_name,
temporal_division=config.temporal_division,
seed=config.seed)
print(top_k_scores)
print('LOO mean top-k score:', top_k_scores.mean())
# logging
log_experiment(config, current_time, (top_k_scores > 0).mean())
def main(data_path="data/features/", out_path="data/models/svc/"):
X_train, X_test, y_train, y_test = read_data(data_path)
name = "LinearSVC"
params = read_params("params.yaml", "svc")
model = LinearSVC(**params)
model.fit(X_train, y_train)
accuracy, c_matrix, fig = evaluate_model(model, X_test, y_test)
print_results(accuracy, c_matrix, name)
save_results(out_path, model, fig)
log_experiment(out_path,
metrics=dict(accuracy=accuracy, confusion_matrics=c_matrix))
def main(data_path='data/features/', out_path='data/models/logistic/'):
X_train, X_test, y_train, y_test = read_data(data_path)
name = 'LogisticRegression'
params = read_params('params.yaml', 'logistic')
model = LogisticRegression(**params)
model.fit(X_train, y_train)
accuracy, c_matrix, fig = evaluate_model(model, X_test, y_test)
print_results(accuracy, c_matrix, name)
save_results(out_path, model, fig)
log_experiment(out_path,
params=params,
metrics=dict(accuracy=accuracy, confusion_matrics=c_matrix))
def main(data_path='data/features/',
out_path='data/models/r_forrest/',
n_estimators=10,
max_samples=30):
X_train, X_test, y_train, y_test = read_data(data_path)
name = 'RandomForrest'
params = read_params('params.yaml', 'forrest')
model = RandomForestClassifier(**params)
model.fit(X_train, y_train)
accuracy, c_matrix, fig = evaluate_model(model, X_test, y_test)
print_results(accuracy, c_matrix, name)
save_results(out_path, model, fig)
log_experiment(out_path,
params=params,
metrics=dict(accuracy=accuracy, confusion_matrics=c_matrix))
def main(data_path='data/features/',
model_path='data/models/',
out_path='data/models/ensemble/'):
X_train, X_test, y_train, y_test = read_data(data_path)
name = 'Ensemble'
params = read_params('params.yaml', 'ensemble')
cl1 = load_model(f'{model_path}/logistic/')
cl2 = load_model(f'{model_path}/svc/')
cl3 = load_model(f'{model_path}/r_forrest/')
estimators = [('l_regression', cl1), ('l_svc', cl2), ('r_forrest', cl3)]
model = VotingClassifier(estimators, **params)
model.fit(X_train, y_train)
accuracy, c_matrix, fig = evaluate_model(model, X_test, y_test)
print_results(accuracy, c_matrix, name)
save_results(out_path, model, fig)
log_experiment(out_path,
metrics=dict(accuracy=accuracy, confusion_matrics=c_matrix))
def __call__(
self,
read_old_model=True,
model='TransE',
num_epochs=2,
train_batch_size=512,
evaluation_batch_size=128,
model_location=MODEL_SAVE_DIR
):
# this fits the data from the old model - if model is present.
if read_old_model:
if os.path.exists(os.path.join(model_location, 'trained_model.pkl')):
# use an old saved model
self.__model = torch.load(os.path.join(model_location, 'trained_model.pkl'))
else:
# if no model found - just train the model
raise FileNotFoundError(
f"Old model not found at {model_location}. "
f"Please check the path provided"
)
else:
self.__fit(
model_text=model,
num_epochs=num_epochs,
train_batch_size=train_batch_size,
eval_batch_size=evaluation_batch_size,
model_location=model_location
)
# if versioning has been set to true, the details are logged in mlflow
if len(self.__exp_tags):
log_experiment(
params={
"num_epochs":num_epochs,
"train_batch_size":train_batch_size,
"eval_batch_size":evaluation_batch_size
},
tags=self.__exp_tags,
)
