def train_logisticregressoin(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.predict_proba(test_dataset.data[:, 1:])[:, 1]
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),
('Logistic Regression', preds)],
test_dataset.data[:, :1],
savepath=savepath)
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)