def print_metrics(model, train_dataset, test_dataset, train_result):
model.train(False)
test_preds = train_utils.get_preds(test_dataset.data[:, 1:], model)
test_AUC = train_utils.compute_AUC(test_dataset.data[:, :1], test_preds)
test_PRAUC = train_utils.compute_PRAUC(test_dataset.data[:, :1], test_preds)
test_accuracy = train_utils.compute_accuracy(test_dataset.data[:, :1], test_preds)
test_TP, test_TN, test_FN, test_FP = train_utils.compute_confusion(test_dataset.data[:, :1], test_preds)
train_preds = train_utils.get_preds(train_dataset.data[:1000, 1:], model)
train_AUC = train_utils.compute_AUC(train_dataset.data[:1000, :1], train_preds)
train_PRAUC = train_utils.compute_PRAUC(train_dataset.data[:1000, :1], train_preds)
train_accuracy = train_utils.compute_accuracy(train_dataset.data[:1000, :1], train_preds)
train_result.test_AUC_list.append("%.04f" % test_AUC)
train_result.test_PRAUC_list.append("%.04f" % test_PRAUC)
train_result.test_accuracy_list.append("%.04f" % test_accuracy)
train_result.test_TP_list.append("%.04f" %test_TP)
train_result.test_TP_list.append("%.04f" %test_TN)
train_result.test_TP_list.append("%.04f" %test_FN)
train_result.test_TP_list.append("%.04f" %test_FP)
return train_AUC, test_AUC, test_PRAUC, train_accuracy, test_accuracy, test_preds, test_TP, test_TN, test_FN, test_FP
def train_RandomForestClassifier(info: TrainInformation, split, fold):
"""주어진 split에 대한 학습과 테스트를 진행한다."""
bs = info.BS
init_lr = info.INIT_LR
lr_decay = info.LR_DECAY
momentum = info.MOMENTUM
weight_decay = info.WEIGHT_DECAY
optimizer_method = info.OPTIMIZER_METHOD
epoch = info.EPOCH
nchs = info.NCHS
filename = info.FILENAME
model_name = info.MODEL_NAME
exp_name = info.NAME
print("Using File {}".format(filename))
train_dataset = Dataset(split=split, fold=fold, phase="train", filename=filename, use_data_dropout=info.USE_DATA_DROPOUT)
#val_dataset = Dataset(split=split, fold=fold, phase="val", filename=filename)
test_dataset = Dataset(split=split, fold=fold, phase="test", filename=filename, use_data_dropout=False)
import sklearn.linear_model
regressor = sklearn.linear_model.LogisticRegression()
regressor.fit(train_dataset.train_data[:, 1:], test_dataset.train_data[:, :1])
preds_regressor = regressor.predict_proba(test_dataset.data[:, 1:])[:, 1]
auc_regressor = train_utils.compute_AUC(test_dataset.data[:, :1], preds_regressor)
print(f'auc_regressor is {auc_regressor}')
from sklearn.ensemble import RandomForestClassifier
from sklearn.datasets import make_classification
forest = RandomForestClassifier()
forest.fit(train_dataset.train_data[:, 1:], test_dataset.train_data[:, :1])
preds_forest = forest.predict_proba(test_dataset.data[:, 1:])[:, 1]
auc_forest = train_utils.compute_AUC(test_dataset.data[:, :1], preds_forest)
print(f'auc_forest is {auc_forest}')
savepath = "/content/drive/My Drive/research/frontiers/checkpoints/random_forest/split_%02d.png" % split
os.makedirs(os.path.dirname(savepath), exist_ok=True)
#train_utils.plot_AUC_v2(preds, test_dataset.data[:, :1], savepath=savepath)
model = get_classifier_model(model_name, train_dataset.feature_size, nchs, info.ACTIVATION)
savedir = "/content/drive/My Drive/research/frontiers/checkpoints/%s" % exp_name
best_test_epoch = 25
loadpath = "%s/epoch_%04d_fold_%02d.pt" % (savedir, best_test_epoch, train_dataset.split)
#model.load_state_dict(torch.load(savepath))
model = torch.load(loadpath)
model.eval()
test_preds = train_utils.get_preds(test_dataset.data[:, 1:], model)
train_utils.plot_AUC_v2([('Deep Neural Network', test_preds), ('Logistic Regression', preds_regressor), ('Random Forest', preds_forest)], test_dataset.data[:, :1], savepath=savepath)
def compute_contributing_variables(model, test_dataset):
print("Evaluating contributing variables")
model.train(False)
variable_by_column = np.load("../datasets/sleep1_no_space_columnnames.npy")
#variable_by_column = np.array([v.replace("HE_ast", "HE_alt") for v in variable_by_column])
assert variable_by_column.shape[0] == test_dataset.data.shape[1] - 1
variables = np.unique(variable_by_column)
AUCs = []
print("Computing variable contributions")
print(variables)
for variable in variables:
corresponding_indices = (variable_by_column == variable)
#print("zeroing %s" % str(np.where(corresponding_indices)))
val_data = test_dataset.data[:, 1:].copy()
val_data[:, corresponding_indices] = 0.0
#print((val_data[:, :17] ** 2).mean())
#val_data = val_data * len(variables) / (len(variables) - 1)
preds = train_utils.get_preds(val_data, model)
target = test_dataset.data[:, :1]
test_AUC = train_utils.compute_AUC(target, preds)
print("%s %f" % (variable, test_AUC))
AUCs.append(test_AUC)
sorting_indices = np.argsort(AUCs)
sorted_variables = [variables[i] for i in sorting_indices]
sorted_AUCs = [AUCs[i] for i in sorting_indices]
sorted_pairs = [(v, auc) for (v, auc) in zip(sorted_variables, sorted_AUCs)]
for i, (v, auc) in enumerate(sorted_pairs[:20]):
print("%03d: %s %f" % (i, v, auc))
return [(v, auc) for (v, auc) in zip(variables, AUCs)]
def train_supportvectormachine(info: TrainInformation, split, fold):
"""주어진 split에 대한 학습과 테스트를 진행한다."""
bs = info.BS
init_lr = info.INIT_LR
lr_decay = info.LR_DECAY
momentum = info.MOMENTUM
weight_decay = info.WEIGHT_DECAY
optimizer_method = info.OPTIMIZER_METHOD
epoch = info.EPOCH
nchs = info.NCHS
filename = info.FILENAME
model_name = info.MODEL_NAME
exp_name = info.NAME
print("Using File {}".format(filename))
train_dataset = Dataset(split=split,
fold=fold,
phase="train",
filename=filename,
use_data_dropout=info.USE_DATA_DROPOUT)
#val_dataset = Dataset(split=split, fold=fold, phase="val", filename=filename)
test_dataset = Dataset(split=split,
fold=fold,
phase="test",
filename=filename,
use_data_dropout=False)
from sklearn.svm import LinearSVC
regressor = LinearSVC()
regressor.fit(train_dataset.train_data[:, 1:],
test_dataset.train_data[:, :1])
Y = regressor.decision_function(test_dataset.data[:, 1:])
preds = (Y - Y.min()) / (Y.max() - Y.min())
auc = train_utils.compute_AUC(test_dataset.data[:, :1], preds)
print(auc)
savepath = "/content/drive/My Drive/research/frontiers/checkpoints/logistic_regression/split_%02d.png" % split
os.makedirs(os.path.dirname(savepath), exist_ok=True)
#train_utils.plot_AUC_v2(preds, test_dataset.data[:, :1], savepath=savepath)
model = get_classifier_model(model_name, train_dataset.feature_size, nchs,
info.ACTIVATION)
savedir = "/content/drive/My Drive/research/frontiers/checkpoints/%s" % exp_name
best_test_epoch = 25
loadpath = "%s/epoch_%04d_fold_%02d.pt" % (savedir, best_test_epoch,
train_dataset.split)
#model.load_state_dict(torch.load(savepath))
model = torch.load(loadpath)
model.eval()
test_preds = train_utils.get_preds(test_dataset.data[:, 1:], model)
train_utils.plot_AUC_v2([('Deep Neural Network', test_preds),
('support vector machine', preds)],
test_dataset.data[:, :1],
savepath=savepath)
def train(info: TrainInformation, split, fold):
"""주어진 split에 대한 학습과 테스트를 진행한다."""
bs = info.BS
init_lr = info.INIT_LR
lr_decay = info.LR_DECAY
momentum = info.MOMENTUM
weight_decay = info.WEIGHT_DECAY
optimizer_method = info.OPTIMIZER_METHOD
epoch = info.EPOCH
nchs = info.NCHS
filename = info.FILENAME
model_name = info.MODEL_NAME
exp_name = info.NAME
print("Using File {}".format(filename))
train_dataset = Dataset(split=split, fold=fold, phase="train", filename=filename, use_data_dropout=info.USE_DATA_DROPOUT)
#val_dataset = Dataset(split=split, fold=fold, phase="val", filename=filename)
test_dataset = Dataset(split=split, fold=fold, phase="test", filename=filename, use_data_dropout=False)
model = get_classifier_model(model_name, train_dataset.feature_size, nchs, info.ACTIVATION)
print(model)
# Optimizer 설정
optimizer = set_optimizer(
optimizer_method, model, init_lr, weight_decay, momentum=momentum
)
data_loader = torch.utils.data.DataLoader(
train_dataset, batch_size=bs, shuffle=True, num_workers=0, drop_last=True
)
bce_loss = torch.nn.BCEWithLogitsLoss().cuda()
train_result = TrainResult()
train_result.set_sizes(
len(train_dataset.data), 0, len(test_dataset.data)
)
for ep in range(epoch):
global prev_plot
prev_plot = 0
train_step(
exp_name,
ep,
model,
train_dataset,
test_dataset,
optimizer,
init_lr,
lr_decay,
data_loader,
bce_loss,
train_result,
)
savedir = "/content/drive/My Drive/research/frontiers/checkpoints/%s" % exp_name
best_test_epoch = train_result.best_test_epoch #25
savepath = "%s/epoch_%04d_fold_%02d.pt" % (savedir, best_test_epoch, train_dataset.split)
#model.load_state_dict(torch.load(savepath))
model = torch.load(savepath)
model.eval()
test_preds = train_utils.get_preds(test_dataset.data[:, 1:], model)
test_AUC = train_utils.compute_AUC(test_dataset.data[:, :1], test_preds)
test_PRAUC = train_utils.compute_PRAUC(test_dataset.data[:, :1], test_preds)
train_utils.plot_AUC(test_dataset, test_preds, test_AUC, savepath=savepath.replace(".pt", "_AUC.tiff"))
contributing_variables = compute_contributing_variables(model, test_dataset)
with open(os.path.join(savedir, "contributing_variables_epoch_%04d_fold_%02d.txt" % (best_test_epoch, train_dataset.split)), "w") as f:
for (v, auc) in contributing_variables:
f.write("%s %f\n" % (v, auc))
info.split_index = split
info.result_dict = train_result
info.save_result()
return train_result
def train_ml_compare(info: TrainInformation, split, fold):
"""주어진 split에 대한 학습과 테스트를 진행한다."""
bs = info.BS
init_lr = info.INIT_LR
lr_decay = info.LR_DECAY
momentum = info.MOMENTUM
weight_decay = info.WEIGHT_DECAY
optimizer_method = info.OPTIMIZER_METHOD
epoch = info.EPOCH
nchs = info.NCHS
filename = info.FILENAME
model_name = info.MODEL_NAME
exp_name = info.NAME
print("Using File {}".format(filename))
train_dataset = Dataset(split=split, fold=fold, phase="train", filename=filename, use_data_dropout=info.USE_DATA_DROPOUT)
#val_dataset = Dataset(split=split, fold=fold, phase="val", filename=filename)
test_dataset = Dataset(split=split, fold=fold, phase="test", filename=filename, use_data_dropout=False)
train_input = train_dataset.train_data[:, 1:]
train_label = test_dataset.train_data[:, :1]
# logisticregressoin ######################
import sklearn.linear_model
regressor = sklearn.linear_model.LogisticRegression()
regressor.fit(train_input, train_label)
preds_regressor = regressor.predict_proba(test_dataset.data[:, 1:])[:, 1]
auc_regressor = train_utils.compute_AUC(test_dataset.data[:, :1], preds_regressor)
TP, TN, FN, FP = confusion_matrix(test_dataset.data[:, :1], regressor.predict(test_dataset.data[:, 1:])).ravel()
print(f'auc_regressor is {auc_regressor}')
print("logistic regression TP, TN, FN, FP : {}, {}, {}, {}".format( TP, TN, FN, FP))
###########################################
# randomforest ############################
from sklearn.ensemble import RandomForestClassifier
from sklearn.datasets import make_classification
forest = RandomForestClassifier()
forest.fit(train_input, train_label)
preds_forest = forest.predict_proba(test_dataset.data[:, 1:])[:, 1]
auc_forest = train_utils.compute_AUC(test_dataset.data[:, :1], preds_forest)
TP, TN, FN, FP = confusion_matrix(test_dataset.data[:, :1], forest.predict(test_dataset.data[:, 1:])).ravel()
print(f'auc_forest is {auc_forest}')
print("random forest TP, TN, FN, FP : {}, {}, {}, {}".format(TP, TN, FN, FP))
###########################################
# svc #####################################
from sklearn.svm import LinearSVC
svc = LinearSVC()
svc.fit(train_input, train_label)
Y = svc.decision_function(test_dataset.data[:, 1:])
preds_svc = (Y - Y.min()) / (Y.max() - Y.min())
TP, TN, FN, FP = confusion_matrix(test_dataset.data[:, :1], svc.predict(test_dataset.data[:, 1:])).ravel()
auc_svc = train_utils.compute_AUC(test_dataset.data[:, :1], preds_svc)
print(f'auc_svc is {auc_svc}')
print("svc TP, TN, FN, FP : {}, {}, {}, {}".format(TP, TN, FN, FP))
###########################################
# kneighbors ############################
from sklearn.neighbors import KNeighborsClassifier
kneighbors = KNeighborsClassifier()
kneighbors.fit(train_input, train_label)
preds_kneighbors = kneighbors.predict_proba(test_dataset.data[:, 1:])[:, 1]
auc_kneighbors = train_utils.compute_AUC(test_dataset.data[:, :1], preds_kneighbors)
TP, TN, FN, FP = confusion_matrix(test_dataset.data[:, :1], kneighbors.predict(test_dataset.data[:, 1:])).ravel()
print(f'auc_kneighbors is {auc_kneighbors}')
print("kneighbors TP, TN, FN, FP : {}, {}, {}, {}".format(TP, TN, FN, FP))
###########################################
savepath = "/content/drive/My Drive/research/frontiers/checkpoints/ml_compare/split_%02d.tiff" % split
os.makedirs(os.path.dirname(savepath), exist_ok=True)
model = get_classifier_model(model_name, train_dataset.feature_size, nchs, info.ACTIVATION)
savedir = "/content/drive/My Drive/research/frontiers/checkpoints/%s" % exp_name
best_test_epoch = 25 # train_result.best_test_epoch
loadpath = "%s/epoch_%04d_fold_%02d.pt" % (savedir, best_test_epoch, train_dataset.split)
#model.load_state_dict(torch.load(savepath))
model = torch.load(loadpath)
model.eval()
test_preds = train_utils.get_preds(test_dataset.data[:, 1:], model)
train_utils.plot_AUC_v2([('Deep learning (AUC 0.870)', test_preds), ('Logistic regression (AUC 0.858)', preds_regressor), ('Linear SVM (AUC 0.849)', preds_svc), ('Random forest classifier (AUC 0.810)', preds_forest), ('K-nearest neighbors (AUC 0.740)', preds_kneighbors)], test_dataset.data[:, :1], savepath=savepath)
