def main():
args = parse_args()
seed_everything(args.seed)
app_train = joblib.load('../data/05_onehot/application_train.joblib')
app_test = joblib.load('../data/05_onehot/application_test.joblib')
sequences = read_all('../data/06_onehot_seq/')
dims = joblib.load('../data/07_dims/dims05.joblib')
app_dims = {}
app_dims['application_train'] = dims.pop('application_train')
app_dims['application_test'] = dims.pop('application_test')
app_data = {'application_train': app_train, 'application_test': app_test}
loader_maker = LoaderMaker(app_data, sequences, args, onehot=True)
skf = StratifiedKFold(n_splits=5)
folds = skf.split(app_train['SK_ID_CURR'], app_train['TARGET'])
best_models = []
for train_index, val_index in folds:
encoders = pretrain(app_train, app_test, sequences, dims, train_index,
val_index, args)
train_dataloader = loader_maker.make(train_index)
val_dataloader = loader_maker.make(val_index)
model = LightningModel(
PretrainedR2N(app_dims, args.n_hidden, args.n_main, encoders),
nn.BCEWithLogitsLoss(), train_dataloader, val_dataloader, args)
name = '82_vaelstm_fine'
trainer = HomeCreditTrainer(name, args.n_epochs, args.patience)
trainer.fit(model)
best_model = load_model(model, name, trainer.logger.version)
best_models.append(best_model)
# Predict
test_dataloader = loader_maker.make(index=None, train=False)
df_submission = predict(best_models, test_dataloader)
df_submission.to_csv(f'../submission/{name}.csv', index=False)
def main():
args = parse_args()
seed_everything(args.seed)
if args.onehot:
all_data = read_all(directory='../data/05_onehot')
sequences = read_sequences(directory='../data/06_onehot_seq')
else:
all_data = read_all(directory='../data/03_powertransform')
sequences = read_sequences(directory='../data/04_sequence')
dims = get_dims(all_data)
loader_maker = LoaderMaker(all_data, sequences, args, onehot=args.onehot)
# CV
name = '15_cnn-onehot' if args.onehot else '15_cnn-label'
skf = StratifiedKFold(n_splits=5)
folds = skf.split(all_data['application_train']['SK_ID_CURR'],
all_data['application_train']['TARGET'])
best_models = []
for train_index, val_index in folds:
train_dataloader = loader_maker.make(train_index)
val_dataloader = loader_maker.make(val_index)
model = LightningModel(R2NCNN(dims, args.n_hidden, args.n_main),
nn.BCEWithLogitsLoss(), train_dataloader,
val_dataloader, args)
trainer = HomeCreditTrainer(name, args.n_epochs, args.patience)
trainer.fit(model)
best_model = load_model(model, name, trainer.logger.version)
best_models.append(best_model)
# Predict
test_dataloader = loader_maker.make(index=None, train=False)
df_submission = predict(best_models, test_dataloader)
filename = '../submission/15_r2n-cnn-onehot.csv' if args.onehot else '../submission/15_r2n-cnn-label.csv'
df_submission.to_csv(filename, index=False)
def main():
args = parse_args()
app_train = joblib.load('../data/05_onehot/application_train.joblib')
app_test = joblib.load('../data/05_onehot/application_test.joblib')
sequences = read_all('../data/06_onehot_seq')
dims = joblib.load('../data/07_dims/dims05.joblib')
app_dims = {}
app_dims['application_train'] = dims.pop('application_train')
app_dims['application_test'] = dims.pop('application_test')
encoders = {}
for name, diminfo in dims.items():
model = VAELSTMModule(diminfo, args.n_hidden, None, None, args)
model = load_model(model, name, logdir='../logs/22_vaelstm')
encoder = model.model.encoder
encoders[name] = encoder
run_fine_tuning(args,
app_dims,
app_train,
app_test,
sequences,
encoders,
'42_vaelstm',
onehot=True)
def main():
args = parse_args()
seed_everything(args.seed)
if args.onehot:
app_train = joblib.load('../data/05_onehot/application_train.joblib')
app_test = joblib.load('../data/05_onehot/application_test.joblib')
dims = get_dims({'application_train': app_train})
_, _, cont_dim = dims['application_train']
n_input = cont_dim
else:
app_train = joblib.load(
'../data/03_powertransform/application_train.joblib')
app_test = joblib.load(
'../data/03_powertransform/application_test.joblib')
dims = get_dims({'application_train': app_train})
cat_dims, emb_dims, cont_dim = dims['application_train']
n_input = emb_dims.sum() + cont_dim
n_hidden = args.n_hidden
# CV
skf = StratifiedKFold(n_splits=5)
folds = skf.split(app_train['SK_ID_CURR'], app_train['TARGET'])
best_models = []
for train_index, val_index in folds:
train_dataloader = make_dataloader(app_train,
train_index,
args.batch_size,
onehot=args.onehot)
val_dataloader = make_dataloader(app_train,
val_index,
args.batch_size,
onehot=args.onehot)
if args.onehot:
network = MLPOneHot(n_input, n_hidden)
else:
network = MLP(cat_dims, emb_dims, n_input, n_hidden)
model = LightningModel(network, nn.BCEWithLogitsLoss(),
train_dataloader, val_dataloader, args)
name = '13_mlp-onehot' if args.onehot else '13_mlp-label'
trainer = HomeCreditTrainer(name, args.n_epochs, args.patience)
trainer.fit(model)
best_model = load_model(model, name, trainer.logger.version)
best_models.append(best_model)
# Predict
test_dataloader = make_dataloader(app_test,
None,
args.batch_size,
train=False,
onehot=args.onehot)
df_submission = predict(best_models, test_dataloader)
filename = '../submission/13_mlp-onehot.csv' if args.onehot else '../submission/13_mlp-label.csv'
df_submission.to_csv(filename, index=False)
def pretrain(app_train, app_test, sequences, dims, train_index, val_index,
args):
encoders = {}
for name, diminfo in dims.items():
cat = sequences[f'{name}_cat']
cont = sequences[f'{name}_cont']
train_loader = torch.utils.data.DataLoader(
SequenceDataset(app_train,
cat,
cont,
index=train_index,
app_test=app_test),
batch_size=args.batch_size,
shuffle=True,
num_workers=6,
worker_init_fn=worker_init_fn)
val_loader = torch.utils.data.DataLoader(SequenceDataset(
app_train, cat, cont, index=val_index),
batch_size=args.batch_size,
shuffle=False,
num_workers=6,
worker_init_fn=worker_init_fn)
model = DIMLSTMModule(diminfo, args.n_hidden, train_loader, val_loader,
args)
logdir = '../logs/81_dimlstm'
path = pathlib.Path(logdir) / name
if not path.exists():
path.mkdir(parents=True)
logger = TensorBoardLogger(logdir, name=name)
early_stopping = EarlyStopping(patience=args.patience,
monitor='val_loss_main',
mode='min')
filepath = pathlib.Path(
logdir) / name / f'version_{logger.version}' / 'checkpoints'
model_checkpoint = ModelCheckpoint(str(filepath),
monitor='val_loss_main',
mode='min')
trainer = pl.Trainer(default_save_path=logdir,
gpus=-1,
max_epochs=args.n_epochs,
early_stop_callback=early_stopping,
logger=logger,
row_log_interval=100,
checkpoint_callback=model_checkpoint)
trainer.fit(model)
best_model = load_model(model,
name,
trainer.logger.version,
logdir=logdir)
encoders[name] = best_model.encoder
return encoders
def main():
args = parse_args()
app_train = joblib.load('../data/03_powertransform/application_train.joblib')
app_test = joblib.load('../data/03_powertransform/application_test.joblib')
sequences = read_all('../data/04_sequence')
dims = joblib.load('../data/07_dims/dims03.joblib')
app_dims = {}
app_dims['application_train'] = dims.pop('application_train')
app_dims['application_test'] = dims.pop('application_test')
encoders = {}
for name, diminfo in dims.items():
model = DIMLSTMModule(diminfo, args.n_hidden, None, None, args)
model = load_model(model, name, logdir='../logs/21_dimlstm')
encoder = model.encoder
encoders[name] = encoder
run_fine_tuning(args, app_dims, app_train, app_test, sequences, encoders, '41_dimlstm')
def main():
args = parse_args()
seed_everything(args.seed)
app_train = joblib.load(
'../data/03_powertransform/application_train.joblib')
app_test = joblib.load('../data/03_powertransform/application_test.joblib')
sequences = read_sequences('../data/04_sequence/')
dims = joblib.load('../data/07_dims/dims03.joblib')
dims.pop('application_train')
dims.pop('application_test')
for name, diminfo in dims.items():
cat = sequences[f'{name}_cat']
cont = sequences[f'{name}_cont']
train_loader = torch.utils.data.DataLoader(
SequenceDataset(app_train, cat, cont),
batch_size=args.batch_size,
shuffle=True,
num_workers=6,
worker_init_fn=worker_init_fn)
test_loader = torch.utils.data.DataLoader(
SequenceDataset(app_test, cat, cont),
batch_size=args.batch_size,
shuffle=False,
num_workers=6,
worker_init_fn=worker_init_fn)
model = DIMLSTMModule(diminfo, args.n_hidden, train_loader,
test_loader, args)
logdir = '../logs/21_dimlstm'
path = pathlib.Path(logdir) / name
if not path.exists():
path.mkdir(parents=True)
logger = TensorBoardLogger(logdir, name=name)
early_stopping = EarlyStopping(patience=args.patience,
monitor='val_loss_main',
mode='min')
filepath = pathlib.Path(
logdir) / name / f'version_{logger.version}' / 'checkpoints'
model_checkpoint = ModelCheckpoint(str(filepath),
monitor='val_loss_main',
mode='min')
trainer = pl.Trainer(default_save_path=logdir,
gpus=-1,
max_epochs=args.n_epochs,
early_stop_callback=early_stopping,
logger=logger,
row_log_interval=100,
checkpoint_callback=model_checkpoint)
trainer.fit(model)
best_model = load_model(model,
name,
trainer.logger.version,
logdir=logdir)
train_loader_no_shuffle = torch.utils.data.DataLoader(
SequenceDataset(app_train, cat, cont),
batch_size=args.batch_size,
shuffle=False,
num_workers=6,
worker_init_fn=worker_init_fn)
df_train = predict(name, best_model, train_loader_no_shuffle)
df_test = predict(name, best_model, test_loader)
df_encoding = pd.concat([df_train, df_test])
dump(df_encoding, f'../data/21_dimlstm/{name}.joblib')
