clf = commons.best_model
# Run deep vs light unconsciousness
print(f"Bootstrap: Graph {graph} at eml5_vs_emf5_step_{s}")
bootstrap_filename = commons.OUTPUT_DIR + f"bootstrap/bootstrap_10000_Final_model_{graph}_eml5_vs_emf5_step_{s}.csv"
boot_data = pd.DataFrame(np.zeros((1, 6)))
names = ['epoch', 'graph', 'Acc_Dist Mean', 'Acc_Dist Std', 'acc_interval_low', 'acc_interval_high']
boot_data.columns = names
c = 0
if graph != "both":
print(f"MODE {graph}")
print(f"FINAL Model Graph {graph} at emf5 vs eml5")
X, y, group = filter_dataframe(graph, 'emf5', 'eml5', s)
if graph == "both":
print(f"MODE {graph}")
print(f"FINAL Model Graph {graph} at emf5 vs eml5")
X_pli, y_pli, group_pli = filter_dataframe('pli', 'emf5', 'eml5', s)
X_aec, y_aec, group_aec = filter_dataframe('aec', 'emf5', 'eml5', s)
X = np.hstack((X_aec, X_pli))
if np.array_equal(y_aec, y_pli):
print("Y-values equal")
y = y_aec
if np.array_equal(group_aec, group_pli):
print("group-values equal")
group = group_aec
#build pipeline with best model
# This will be given by the srun in the bash file
# Get the argument
EPOCHS = {"ind","emf5","eml5","ec8"} # to compare against baseline
GRAPHS = ["aec", "pli", "both"]
Steps = ['01', '10']
clf = commons.best_model
for s in Steps:
for graph in GRAPHS:
for epoch in EPOCHS:
final_acc_filename = commons.OUTPUT_DIR + f"final_models/FINAL_MODEL_{graph}_ec1_vs_{epoch}_step_{s}.pickle"
if graph != "both":
print(f"MODE {graph}")
print(f"FINAL Model Graph {graph} at ec1 vs {epoch}")
X, y, group = filter_dataframe(graph, 'ec1', epoch, s)
if graph == "both":
print(f"MODE {graph}")
print(f"FINAL Model Graph {graph} at ec1 vs {epoch}")
X_pli, y_pli, group_pli = filter_dataframe('pli', 'ec1', epoch, s)
X_aec, y_aec, group_aec = filter_dataframe('aec', 'ec1', epoch, s)
X = np.hstack((X_aec, X_pli))
if np.array_equal(y_aec, y_pli):
print("Y-values equal")
y = y_aec
if np.array_equal(group_aec, group_pli):
print("group-values equal")
group = group_aec
#build pipeline with best model
import commons
from commons import load_pickle, find_best_model
from commons import classify_loso_model_selection
from commons import DummyEstimator, print_summary, filter_dataframe, search_space
# Get the argument
analysis_param = sys.argv[1]
best_clf_filename = commons.OUTPUT_DIR + f'best_clf_{analysis_param}.pickle'
# Parse the parameters
(graph, epoch, feature_group) = analysis_param.split("_")
print(f"Graph {graph} at ec1 vs {epoch} with feature {feature_group}")
X, y, group = filter_dataframe(graph, epoch, feature_group)
# Create a pipeline
pipe = Pipeline([('imputer',
SimpleImputer(missing_values=np.nan, strategy='mean')),
('scaler', StandardScaler()),
('clf', DummyEstimator())]) # Placeholder Estimator
# We will use as many processor as possible for the gridsearch
gs = GridSearchCV(pipe, search_space, cv=LeaveOneGroupOut(), n_jobs=-1)
accuracies, f1s, cms, best_params = classify_loso_model_selection(
X, y, group, gs)
# Saving the performance metrics
clf_data = {