Merge branch 'main' into feat-#12/CV

DKT/.gitignore

@@ -106,6 +106,7 @@ input/
 saved/
 datasets/
 submission/
+output/
 
 # editor, os cache directory
 .vscode/
@@ -119,6 +120,9 @@ asset/
 
 # model
 save_pic/
-*.txt
 *.png
-*.pickle
+*.pickle
+*.png
+*.pickle
+*.pkl
+lgbm_model.txt

DKT/args_LQ.py

@@ -0,0 +1,95 @@
+import argparse
+
+
+def parse_args(mode="train"):
+    parser = argparse.ArgumentParser()
+
+    parser.add_argument("--seed", default=42, type=int, help="seed")
+    parser.add_argument("--device", default="cpu", type=str, help="cpu or gpu")
+
+    # -- 데이터 경로 및 파일 이름 설정
+    parser.add_argument(
+        "--data_dir",
+        default="/opt/ml/input/data/",
+        type=str,
+        help="data directory",
+    )
+    parser.add_argument(
+        "--asset_dir", default="asset/", type=str, help="data directory"
+    )
+    parser.add_argument(
+        "--file_name", default="train_data.csv", type=str, help="train file name"
+    )
+
+    # -- 모델의 경로 및 이름, 결과 저장
+    parser.add_argument(
+        "--model_dir", default="models/", type=str, help="model directory"
+    )
+    parser.add_argument(
+        "--model_name", default="model.pt", type=str, help="model file name"
+    )
+    parser.add_argument(
+        "--output_dir", default="output/", type=str, help="output directory"
+    )
+    parser.add_argument(
+        "--test_file_name", default="test_data.csv", type=str, help="test file name"
+    )
+
+    parser.add_argument(
+        "--max_seq_len", default=30, type=int, help="max sequence length"
+    )
+    parser.add_argument("--num_workers", default=4, type=int, help="number of workers")
+
+    # 모델
+    parser.add_argument(
+        "--hidden_dim", default=300, type=int, help="hidden dimension size"
+    )
+    parser.add_argument("--n_layers", default=2, type=int, help="number of layers")
+    parser.add_argument("--n_heads", default=4, type=int, help="number of heads")
+    parser.add_argument("--drop_out", default=0.2, type=float, help="drop out rate")
+
+    # 훈련
+    parser.add_argument("--n_epochs", default=30, type=int, help="number of epochs")
+    parser.add_argument("--batch_size", default=64, type=int, help="batch size")
+    parser.add_argument("--lr", default=0.009668, type=float, help="learning rate")
+    parser.add_argument("--clip_grad", default=10, type=int, help="clip grad")
+    parser.add_argument("--patience", default=10, type=int, help="for early stopping")
+
+    parser.add_argument(
+        "--log_steps", default=50, type=int, help="print log per n steps"
+    )
+
+    ### 중요 ###
+    parser.add_argument("--model", default="LastQuery", type=str, help="model type")
+    parser.add_argument("--optimizer", default="adam", type=str, help="optimizer type")
+    parser.add_argument(
+        "--scheduler", default="plateau", type=str, help="scheduler type"
+    )
+
+    # -- Data split methods : default(user), k-fold, ...
+    parser.add_argument(
+        "--split_method", default="k-fold", type=str, help="data split strategy"
+    )
+    parser.add_argument(
+        "--n_splits", default=5, type=str, help="number of k-fold splits"
+    )
+
+    ### Argumentation 관련 ###
+
+    parser.add_argument(
+        "--window", default=True, type=bool, help="Arumentation with stridde window"
+    )
+    parser.add_argument(
+        "--shuffle", default=False, type=bool, help="data shuffle option"
+    )
+    parser.add_argument("--stride", default=80, type=int)
+    parser.add_argument("--shuffle_n", default=2, type=int)
+
+    ### Tfixup 관련 ###
+    parser.add_argument("--Tfixup", default=False, type=bool, help="Tfixup")
+
+    args = parser.parse_args()
+
+    # args.stride = args.max_seq_len
+
+    return args

DKT/base/base_data_loader.py

@@ -2,15 +2,17 @@
 from torch.utils.data import DataLoader
 from torch.utils.data.dataloader import default_collate
 from torch.utils.data.sampler import SubsetRandomSampler
+from sklearn.model_selection import KFold
 
 
 class BaseDataLoader(DataLoader):
     """
     Base class for all data loaders
     """
-    def __init__(self, dataset, batch_size, shuffle, validation_split, num_workers, collate_fn=default_collate):
+    def __init__(self, dataset, batch_size, shuffle, validation_split, num_workers, fold, collate_fn=default_collate):
         self.validation_split = validation_split
         self.shuffle = shuffle
+        self.fold = fold
 
         self.batch_idx = 0
         self.n_samples = len(dataset)
@@ -42,8 +44,21 @@ def _split_sampler(self, split):
         else:
             len_valid = int(self.n_samples * split)
 
-        valid_idx = idx_full[0:len_valid]
-        train_idx = np.delete(idx_full, np.arange(0, len_valid))
+        if self.fold == 0:
+            valid_idx = idx_full[0:len_valid]
+            train_idx = np.delete(idx_full, np.arange(0, len_valid))
+        elif self.fold == 1:
+            valid_idx = idx_full[len_valid:2*len_valid]
+            train_idx = np.delete(idx_full, np.arange(0, len_valid))
+        elif self.fold == 2:
+            valid_idx = idx_full[2*len_valid:3*len_valid]
+            train_idx = np.delete(idx_full, np.arange(0, len_valid))
+        elif self.fold == 3:
+            valid_idx = idx_full[3*len_valid:4*len_valid]
+            train_idx = np.delete(idx_full, np.arange(0, len_valid))
+        else:
+            valid_idx = idx_full[4*len_valid:]
+            train_idx = np.delete(idx_full, np.arange(0, len_valid))
 
         train_sampler = SubsetRandomSampler(train_idx)
         valid_sampler = SubsetRandomSampler(valid_idx)

DKT/base/base_trainer.py

@@ -8,14 +8,15 @@ class BaseTrainer:
     """
     Base class for all trainers
     """
-    def __init__(self, model, criterion, metric_ftns, optimizer, config):
+    def __init__(self, model, criterion, metric_ftns, optimizer, config, fold):
         self.config = config
         self.logger = config.get_logger('trainer', config['trainer']['verbosity'])
 
         self.model = model
         self.criterion = criterion
         self.metric_ftns = metric_ftns
         self.optimizer = optimizer
+        self.fold = fold
 
         cfg_trainer = config['trainer']
         self.epochs = cfg_trainer['epochs']
@@ -119,9 +120,9 @@ def _save_checkpoint(self, epoch, save_best=False):
         torch.save(state, filename)
         self.logger.info("Saving checkpoint: {} ...".format(filename))
         if save_best:
-            best_path = str(self.checkpoint_dir / 'model_best.pth')
+            best_path = str(self.checkpoint_dir / 'model_best{}.pth'.format(self.fold))
             torch.save(state, best_path)
-            self.logger.info("Saving current best: model_best.pth ...")
+            self.logger.info("Saving current best: model_best{}.pth ...".format(self.fold))
 
     def _resume_checkpoint(self, resume_path):
         """

DKT/config/config_HM.json

@@ -0,0 +1,79 @@
+{
+    "name": "HybridModel",
+    "n_gpu": 1,
+
+    "arch": {
+        "type": "HMModel_lstm",
+        "args": {
+            "n_test": 1537,
+            "n_tag": 912,
+            "gamma": 1e-4,
+            "lambda": 0.8,
+            "hidden_dim": 256,
+            "n_layers": 3,
+            "n_heads": 4,
+            "drop_out": 0.4,
+            "model_dir": "/opt/ml/level2_dkt-recsys-09/DKT/saved/models/UltraGCN/0524_043901/model_best.pth",
+            "ultragcn": {
+                "user_num": 7442,
+                "item_num": 9454,
+                "embedding_dim": 64,
+                "gamma": 1e-4,
+                "lambda": 0.8
+            }
+        }
+    },
+    "data_loader": {
+        "type": "HMDataLoader",
+        "args":{
+            "data_dir": "/opt/ml/input/data",
+            "asset_dir": "./asset",
+            "batch_size": 512,
+            "shuffle": true,
+            "num_workers": 2,
+            "max_seq_len": 200,
+            "validation_split": 0.2,
+            "stride": 10,
+            "shuffle_n": 2,
+            "shuffle_aug": false
+        }
+    },
+    "optimizer": {
+        "type": "Adam",
+        "args":{
+            "lr": 0.001,
+            "weight_decay": 0,
+            "amsgrad": true
+        }
+    },
+    "loss": "BCE_loss",
+    "metrics": [
+        "accuracy", "auc"
+    ],
+    "lr_scheduler": {
+        "type": "StepLR",
+        "args": {
+            "step_size": 50,
+            "gamma": 0.1
+        }
+    },
+    "trainer": {
+        "epochs": 100,
+
+        "save_dir": "saved/",
+        "save_period": 1,
+        "verbosity": 2,
+
+        "monitor": "min val_loss",
+        "early_stop": 10,
+
+        "tensorboard": true
+    },
+    "test": {
+        "data_dir": "~/input/data/test_data_modify.csv",
+        "model_dir": "/opt/ml/level2_dkt-recsys-09/DKT/saved/models/HybridModel/0524_162035/model_best.pth",
+        "submission_dir": "~/level2_dkt-recsys-09/DKT/submission/UltraGCN_HM_aug_lstm.csv",
+        "sample_submission_dir": "~/input/data/sample_submission.csv",
+        "batch_size": 128
+    }
+}

DKT/config/config_LGBM.json

@@ -0,0 +1,55 @@
+{
+    "name": "LGBM",
+    "n_gpu": 1,
+    "seed":42,
+    "pic_dir": "save_pic/",
+    "output_dir": "output/",
+
+    "arch": {
+        "type": "",
+        "args": {}
+    },
+    "data_loader": {
+        "data_dir": "/opt/ml/input/data/",
+        "df_train": "train_data.csv",
+        "df_test": "test_data.csv",
+        "feature_engineering": false,
+        "fe_train": "train_featured.csv",
+        "fe_test": "test_featured.csv",
+        "asset_dir": "asset/",
+        "batch_size": 128,
+        "shuffle": true,
+        "split_ratio": 0.8,
+        "num_workers": 2
+    },
+    "optimizer": {
+        "type": "Adam",
+        "args":{
+            "lr": 0.001,
+            "weight_decay": 0,
+            "amsgrad": true
+        }
+    },
+    "loss": "nll_loss",
+    "metrics": [
+        "accuracy", "top_k_acc"
+    ],
+    "lr_scheduler": {
+        "type": "StepLR",
+        "args": {
+            "step_size": 50,
+            "gamma": 0.1
+        }
+    },
+    "trainer": {
+        "num_boost_round": 2500,
+
+        "model_dir": "model/",
+        "verbos_eval": 100,
+        "threshold": 0.5,
+
+        "early_stopping_rounds": 100,
+
+        "tuning": false
+    }
+}