gpbench 1.0.0__py3-none-any.whl

gpbench/method_reg/DNNGP/DNNGP.py

@@ -0,0 +1,157 @@
+import os
+import time
+import psutil
+import argparse
+import random
+import torch
+import numpy as np
+import pandas as pd
+from sklearn.model_selection import KFold, train_test_split
+from .base_dnngp import DNNGP
+from scipy.stats import pearsonr
+from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score
+from torch.utils.data  import DataLoader, TensorDataset
+from . import DNNGP_Hyperparameters
+
+def parse_args():
+    parser = argparse.ArgumentParser(description="Argument parser")
+    parser.add_argument('--methods', type=str, default='DNNGP/', help='Random seed')
+    parser.add_argument('--species', type=str, default='')
+    parser.add_argument('--phe', type=str, default='', help='Dataset name')
+    parser.add_argument('--data_dir', type=str, default='../../data/')
+    parser.add_argument('--result_dir', type=str, default='result/')
+    
+    parser.add_argument('--epoch', type=int, default=1000, help='Number of training rounds')
+    parser.add_argument('--batch_size', type=int, default=32, help='Batch size')
+    parser.add_argument('--lr', type=float, default=0.01, help='Learning rate')
+    parser.add_argument('--weight_decay', type=float, default=0.001, help='Weight decay')
+    parser.add_argument('--patience', type=int, default=10, help='Patience for early stopping')
+    parser.add_argument('--dropout1', type=float, default=0.5, help='Dropout rate for layer 1')
+    parser.add_argument('--dropout2', type=float, default=0.5, help='Dropout rate for layer 2')
+    args = parser.parse_args()
+    return args
+
+def load_data(args):
+    xData = np.load(os.path.join(args.data_dir, args.species, 'genotype.npz'))["arr_0"]
+    yData = np.load(os.path.join(args.data_dir, args.species, 'phenotype.npz'))["arr_0"]
+    names = np.load(os.path.join(args.data_dir, args.species, 'phenotype.npz'))["arr_1"]
+
+    nsample = xData.shape[0]
+    nsnp = xData.shape[1]
+    print("Number of samples: ", nsample)
+    print("Number of SNPs: ", nsnp)
+    return xData, yData, nsample, nsnp, names
+
+def set_seed(seed=42):
+    random.seed(seed)
+    np.random.seed(seed)
+    torch.manual_seed(seed)
+    torch.cuda.manual_seed_all(seed)
+    torch.backends.cudnn.deterministic = True
+    torch.backends.cudnn.benchmark = False
+
+def run_nested_cv(args, data, label, nsnp, device):
+    result_dir = os.path.join(args.result_dir, args.methods + args.species + args.phe)
+    os.makedirs(result_dir, exist_ok=True)
+    print("Starting 10-fold cross-validation...")
+    kf = KFold(n_splits=10, shuffle=True, random_state=42)
+
+    all_mse, all_mae, all_r2, all_pcc = [], [], [], []
+    time_star = time.time()
+    for fold, (train_index, test_index) in enumerate(kf.split(data)):
+        print(f"Running fold {fold}...")
+        process = psutil.Process(os.getpid())
+        fold_start_time = time.time()
+
+        X_train, X_test = data[train_index], data[test_index]
+        y_train, y_test = label[train_index], label[test_index]
+
+        X_train_sub, X_valid, y_train_sub, y_valid = train_test_split(X_train, y_train, test_size=0.1, random_state=42)
+        
+        x_train_tensor = torch.from_numpy(X_train_sub).float().to(device)
+        y_train_tensor = torch.from_numpy(y_train_sub).float().to(device)
+        x_valid_tensor = torch.from_numpy(X_valid).float().to(device)
+        y_valid_tensor = torch.from_numpy(y_valid).float().to(device)
+        x_test_tensor = torch.from_numpy(X_test).float().to(device)
+        y_test_tensor = torch.from_numpy(y_test).float().to(device)
+        
+        x_train_tensor = x_train_tensor.unsqueeze(1)
+        x_valid_tensor = x_valid_tensor.unsqueeze(1)
+        x_test_tensor  = x_test_tensor.unsqueeze(1)
+
+        train_data = TensorDataset(x_train_tensor, y_train_tensor)
+        valid_data = TensorDataset(x_valid_tensor, y_valid_tensor)
+        test_data = TensorDataset(x_test_tensor, y_test_tensor)
+
+        train_loader = DataLoader(train_data, args.batch_size, shuffle=True)
+        valid_loader = DataLoader(valid_data, args.batch_size, shuffle=False)
+        test_loader = DataLoader(test_data, args.batch_size, shuffle=False)
+
+        model = DNNGP(nsnp, args.dropout1, args.dropout2)
+        model.train_model(train_loader, valid_loader, args.epoch, args.lr, args.weight_decay, args.patience, device)
+        y_pred = model.predict(test_loader)
+
+        mse = mean_squared_error(y_test, y_pred)
+        r2 = r2_score(y_test, y_pred)
+        mae = mean_absolute_error(y_test, y_pred)
+        pcc, _ = pearsonr(y_test, y_pred)
+
+        all_mse.append(mse)
+        all_r2.append(r2)
+        all_mae.append(mae)
+        all_pcc.append(pcc)
+
+        fold_time = time.time() - fold_start_time
+        fold_gpu_mem = torch.cuda.max_memory_allocated() / 1024**2 if torch.cuda.is_available() else 0
+        fold_cpu_mem = process.memory_info().rss / 1024**2
+        print(f'Fold {fold}:  Corr={pcc:.4f}, MAE={mae:.4f}, MSE={mse:.4f}, R2={r2:.4f}, Time={fold_time:.2f}s, '
+              f'GPU={fold_gpu_mem:.2f}MB, CPU={fold_cpu_mem:.2f}MB')
+
+        torch.cuda.empty_cache()
+        torch.cuda.reset_peak_memory_stats()
+        results_df = pd.DataFrame({'Y_test': y_test, 'Y_pred': y_pred})
+        results_df.to_csv(os.path.join(result_dir, f"fold{fold}.csv"), index=False)
+
+    print("\n===== Cross-validation summary =====")
+    print(f"Average PCC: {np.mean(all_pcc):.4f} ± {np.std(all_pcc):.4f}")
+    print(f"Average MAE: {np.mean(all_mae):.4f} ± {np.std(all_mae):.4f}")
+    print(f"Average MSE: {np.mean(all_mse):.4f} ± {np.std(all_mse):.4f}")
+    print(f"Average R2 : {np.mean(all_r2):.4f} ± {np.std(all_r2):.4f}")
+    print(f"Time: {time.time() - time_star:.2f}s")
+
+
+def DNNGP_reg():
+    set_seed(42)
+    torch.cuda.empty_cache()  
+    args = parse_args()
+    device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
+    all_species =['Cotton/']
+    
+    for i in range(len(all_species)):
+        args.species = all_species[i]
+        args.device = device  
+        X, Y, nsamples, nsnp, names = load_data(args)
+        for j in range(len(names)):
+            args.phe = names[j]
+            print("starting run " + args.methods + args.species + args.phe)
+            label = Y[:, j]
+            label = np.nan_to_num(label, nan=np.nanmean(label))
+            best_params = DNNGP_Hyperparameters.Hyperparameter(X, label, nsnp)
+            args.learning_rate = best_params['learning_rate']
+            args.patience = best_params['patience']
+            args.dropout1 = best_params['dropout1']
+            args.dropout2 = best_params['dropout2']
+            args.weight_decay = best_params['weight_decay']
+            start_time = time.time() 
+            torch.cuda.reset_peak_memory_stats()
+            process = psutil.Process(os.getpid())
+
+            run_nested_cv(args, data=X, label=label, nsnp = nsnp, device = args.device)
+
+            elapsed_time = time.time() - start_time
+            print(f"running time: {elapsed_time:.2f} s")
+            print("successfully")
+
+    
+if __name__ == "__main__":
+    DNNGP_reg()

gpbench/method_reg/DNNGP/DNNGP_Hyperparameters.py

@@ -0,0 +1,118 @@
+import os
+import time
+import psutil
+import random
+import torch
+import numpy as np
+import optuna
+from sklearn.model_selection import KFold, train_test_split
+from .base_dnngp import DNNGP
+from scipy.stats import pearsonr
+from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score
+from torch.utils.data  import DataLoader, TensorDataset
+from optuna.exceptions import TrialPruned 
+
+def run_nested_cv_with_early_stopping(data, label, nsnp, learning_rate, 
+                                      dropout1, dropout2, weight_decay, patience, batch_size=64, epoch=1000):
+    device = torch.device("cuda:0")
+    print("Starting 10-fold cross-validation...")
+    kf = KFold(n_splits=10, shuffle=True, random_state=42)
+    all_mse, all_mae, all_r2, all_pcc = [], [], [], []
+
+    for fold, (train_index, test_index) in enumerate(kf.split(data)):
+        print(f"Running fold {fold}...")
+        process = psutil.Process(os.getpid())
+        fold_start_time = time.time()
+
+        X_train, X_test = data[train_index], data[test_index]
+        y_train, y_test = label[train_index], label[test_index]
+
+        X_train_sub, X_valid, y_train_sub, y_valid = train_test_split(X_train, y_train, test_size=0.1, random_state=42)
+
+        x_train_tensor = torch.from_numpy(X_train_sub).float().to(device)
+        y_train_tensor = torch.from_numpy(y_train_sub).float().to(device)
+        x_valid_tensor = torch.from_numpy(X_valid).float().to(device)
+        y_valid_tensor = torch.from_numpy(y_valid).float().to(device)
+        x_test_tensor = torch.from_numpy(X_test).float().to(device)
+        y_test_tensor = torch.from_numpy(y_test).float().to(device)
+        
+        x_train_tensor = x_train_tensor.unsqueeze(1)
+        x_valid_tensor = x_valid_tensor.unsqueeze(1)
+        x_test_tensor  = x_test_tensor.unsqueeze(1)
+
+        train_data = TensorDataset(x_train_tensor, y_train_tensor)
+        valid_data = TensorDataset(x_valid_tensor, y_valid_tensor)
+        test_data = TensorDataset(x_test_tensor, y_test_tensor)
+
+        train_loader = DataLoader(train_data, batch_size, shuffle=True)
+        valid_loader = DataLoader(valid_data, batch_size, shuffle=False)
+        test_loader = DataLoader(test_data, batch_size, shuffle=False)
+
+        model = DNNGP(nsnp, dropout1, dropout2)
+        model.train_model(train_loader, valid_loader, epoch, learning_rate, weight_decay, patience, device)
+        y_pred = model.predict(test_loader)
+
+        mse = mean_squared_error(y_test, y_pred)
+        r2 = r2_score(y_test, y_pred)
+        mae = mean_absolute_error(y_test, y_pred)
+        pcc, _ = pearsonr(y_test, y_pred)
+
+        if np.isnan(pcc):
+            print(f"Fold {fold} resulted in NaN PCC, pruning the trial...")
+            raise TrialPruned()
+
+        all_mse.append(mse)
+        all_r2.append(r2)
+        all_mae.append(mae)
+        all_pcc.append(pcc)
+
+        fold_time = time.time() - fold_start_time
+        fold_gpu_mem = torch.cuda.max_memory_allocated() / 1024**2 if torch.cuda.is_available() else 0
+        fold_cpu_mem = process.memory_info().rss / 1024**2
+        print(f'Fold {fold}:  Corr={pcc:.4f}, MAE={mae:.4f}, MSE={mse:.4f}, R2={r2:.4f}, Time={fold_time:.2f}s, '
+                f'GPU={fold_gpu_mem:.2f}MB, CPU={fold_cpu_mem:.2f}MB')
+        
+    return np.mean(all_pcc) if all_pcc else 0.0
+
+def set_seed(seed=42):
+    random.seed(seed)
+    np.random.seed(seed)
+    torch.manual_seed(seed)
+    if torch.cuda.is_available():
+        torch.cuda.manual_seed_all(seed)
+    torch.backends.cudnn.deterministic = True
+    torch.backends.cudnn.benchmark = False
+
+def Hyperparameter(data, label, nsnp):
+    set_seed(42)
+    
+    def objective(trial):
+        lr = trial.suggest_float("learning_rate", 1e-4, 0.1)
+        patience = trial.suggest_int("patience", 10, 100, step=10)
+        batch_size = trial.suggest_categorical("batch_size",[64])
+        dropout1 = trial.suggest_float("dropout1", 0.0, 0.9, step=0.1)
+        dropout2 = trial.suggest_float("dropout2", 0.0, 0.9, step=0.1)
+        weight_decay = trial.suggest_categorical("weight_decay", [1e-5, 1e-4, 1e-3])
+
+        try:
+            corr_score = run_nested_cv_with_early_stopping(
+                data=data,
+                label=label,
+                nsnp=nsnp,
+                learning_rate=lr,
+                patience=patience,
+                dropout1=dropout1,
+                dropout2=dropout2,
+                weight_decay=weight_decay
+            )
+
+        except TrialPruned:
+            return float("-inf")
+        return corr_score
+    
+    study = optuna.create_study(direction="maximize")
+    study.optimize(objective, n_trials=20)
+
+    print("best params:", study.best_params)
+    print("successfully")
+    return study.best_params

gpbench/method_reg/DNNGP/__init__.py

@@ -0,0 +1,5 @@
+from .DNNGP import DNNGP_reg
+
+DNNGP = DNNGP_reg
+
+__all__ = ["DNNGP","DNNGP_reg"]

gpbench/method_reg/DNNGP/base_dnngp.py

@@ -0,0 +1,101 @@
+import torch
+import torch.nn as nn
+import numpy as np
+
+
+class DNNGP(nn.Module):
+    def __init__(self, input_size, dropout1, dropout2):
+        super().__init__()
+        self.CNN1 = nn.Conv1d(in_channels = 1, out_channels=64, kernel_size=4)
+        self.Relu1 = nn.ReLU()
+        self.Drop1 = nn.Dropout(dropout1)
+
+        self.Batchnorm = nn.BatchNorm1d(num_features=64)
+
+        self.CNN2 = nn.Conv1d(in_channels = 64, out_channels=64, kernel_size=4)
+        self.Relu2 = nn.ReLU()
+        self.Drop2 = nn.Dropout(dropout2)
+
+        self.CNN3 = nn.Conv1d(in_channels = 64, out_channels=64, kernel_size=4)
+        self.Relu3 = nn.ReLU()
+
+        self.Flatten = nn.Flatten()
+        self.Dense = nn.Linear(in_features=64*(input_size-9), out_features=3)
+        self.Output = nn.Linear(in_features=3, out_features=1)
+
+    def forward(self, x):
+        x = self.CNN1(x)
+        x = self.Relu1(x)
+        x = self.Drop1(x)
+        x = self.Batchnorm(x)
+        x = self.CNN2(x)
+        x = self.Relu2(x)
+        x = self.Drop2(x)
+        x = self.CNN3(x)
+        x = self.Relu3(x)
+        x = self.Flatten(x)
+        x = self.Dense(x)
+        x = self.Output(x)
+        return x
+
+
+    def train_model(self, train_loader, valid_loader, num_epochs, learning_rate, weight_decay, patience, device):
+        optimizer = torch.optim.Adam(self.parameters(), lr=learning_rate, weight_decay=weight_decay)
+        criterion = nn.MSELoss()
+        self.to(device)
+
+        best_loss = float('inf')
+        best_state = None
+        trigger_times = 0
+
+        for epoch in range(num_epochs):
+            self.train()
+            train_loss = 0.0
+            for inputs, labels in train_loader:
+                inputs, labels = inputs.to(device), labels.to(device)
+                optimizer.zero_grad()
+                outputs = self(inputs)
+                labels = labels.unsqueeze(1)
+                loss = criterion(outputs, labels)
+                loss.backward()
+                optimizer.step()
+                train_loss += loss.item() * inputs.size(0)
+
+            self.eval()
+            valid_loss = 0.0
+            with torch.no_grad():
+                for inputs, labels in valid_loader:
+                    inputs, labels = inputs.to(device), labels.to(device)
+                    outputs = self(inputs)
+                    labels = labels.unsqueeze(1)
+                    loss = criterion(outputs, labels)
+                    valid_loss += loss.item() * inputs.size(0)
+
+            train_loss /= len(train_loader.dataset)
+            valid_loss /= len(valid_loader.dataset)
+
+            # ---------- Early stopping ----------
+            if valid_loss < best_loss:
+                best_loss = valid_loss
+                best_state = self.state_dict()
+                trigger_times = 0
+            else:
+                trigger_times += 1
+                if trigger_times >= patience:
+                    print(f"Early stopping at epoch {epoch+1}")
+                    break
+
+        if best_state is not None:
+            self.load_state_dict(best_state)
+        return best_loss
+        
+    def predict(self, test_loader):
+        self.eval()
+        y_pred = []
+        with torch.no_grad():
+            for inputs, _ in test_loader:
+                outputs = self(inputs)  
+                y_pred.append(outputs.cpu().numpy())
+        y_pred = np.concatenate(y_pred, axis=0)
+        y_pred = np.squeeze(y_pred)
+        return y_pred

gpbench/method_reg/DeepCCR/DeepCCR.py

@@ -0,0 +1,149 @@
+import os
+import time
+import psutil
+import argparse
+import random
+import torch
+import numpy as np
+import pandas as pd
+from sklearn.model_selection import KFold, train_test_split
+from .base_DeepCCR import DeepCCR
+from scipy.stats import pearsonr
+from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score
+from torch.utils.data  import DataLoader, TensorDataset
+from . import DeepCCR_Hyperparameters
+
+def parse_args():
+    parser = argparse.ArgumentParser(description="Argument parser")
+    parser.add_argument('--methods', type=str, default='DeepCCR/', help='Random seed')
+    parser.add_argument('--species', type=str, default='')
+    parser.add_argument('--phe', type=str, default='', help='Dataset name')
+    parser.add_argument('--data_dir', type=str, default='../../data/')
+    parser.add_argument('--result_dir', type=str, default='result/')
+
+    parser.add_argument('--epoch', type=int, default=1000, help='Number of training rounds')
+    parser.add_argument('--batch_size', type=int, default=64, help='Batch size')
+    parser.add_argument('--lr', type=float, default=0.001, help='Learning rate')
+    parser.add_argument('--patience', type=int, default=10, help='Patience for early stopping')
+    args = parser.parse_args()
+    return args
+
+def load_data(args):
+    xData = np.load(os.path.join(args.data_dir, args.species, 'genotype.npz'))["arr_0"]
+    yData = np.load(os.path.join(args.data_dir, args.species, 'phenotype.npz'))["arr_0"]
+    names = np.load(os.path.join(args.data_dir, args.species, 'phenotype.npz'))["arr_1"]
+
+    nsample = xData.shape[0]
+    nsnp = xData.shape[1]
+    print("Number of samples: ", nsample)
+    print("Number of SNPs: ", nsnp)
+    return xData, yData, nsample, nsnp, names
+
+def set_seed(seed=42):
+    random.seed(seed)
+    np.random.seed(seed)
+    torch.manual_seed(seed)
+    torch.cuda.manual_seed_all(seed)
+    torch.backends.cudnn.deterministic = True
+    torch.backends.cudnn.benchmark = False
+
+def run_nested_cv(args, data, label, nsnp, device):
+    result_dir = os.path.join(args.result_dir, args.methods + args.species + args.phe)
+    os.makedirs(result_dir, exist_ok=True)
+    print("Starting 10-fold cross-validation...")
+    kf = KFold(n_splits=10, shuffle=True, random_state=42)
+
+    all_mse, all_mae, all_r2, all_pcc = [], [], [], []
+    time_star = time.time()
+    for fold, (train_index, test_index) in enumerate(kf.split(data)):
+        print(f"Running fold {fold}...")
+        process = psutil.Process(os.getpid())
+        fold_start_time = time.time()
+
+        X_train, X_test = data[train_index], data[test_index]
+        y_train, y_test = label[train_index], label[test_index]
+
+        X_train_sub, X_valid, y_train_sub, y_valid = train_test_split(X_train, y_train, test_size=0.1, random_state=42)
+        
+        x_train_tensor = torch.from_numpy(X_train_sub).float()
+        y_train_tensor = torch.from_numpy(y_train_sub).float()
+        x_valid_tensor = torch.from_numpy(X_valid).float()
+        y_valid_tensor = torch.from_numpy(y_valid).float()
+        x_test_tensor = torch.from_numpy(X_test).float()
+        y_test_tensor = torch.from_numpy(y_test).float()
+        x_train_tensor = x_train_tensor.unsqueeze(1)
+        x_valid_tensor = x_valid_tensor.unsqueeze(1)
+        x_test_tensor  = x_test_tensor.unsqueeze(1)
+
+        train_data = TensorDataset(x_train_tensor, y_train_tensor)
+        valid_data = TensorDataset(x_valid_tensor, y_valid_tensor)
+        test_data = TensorDataset(x_test_tensor, y_test_tensor)
+
+        train_loader = DataLoader(train_data, args.batch_size, shuffle=True)
+        valid_loader = DataLoader(valid_data, args.batch_size, shuffle=False)
+        test_loader = DataLoader(test_data, args.batch_size, shuffle=False)
+
+        model = DeepCCR(input_seq_len = nsnp)
+        model.train_model(train_loader, valid_loader, args.epoch, args.lr, args.patience, device)
+        y_pred = model.predict(test_loader, device)
+
+        mse = mean_squared_error(y_test, y_pred)
+        r2 = r2_score(y_test, y_pred)
+        mae = mean_absolute_error(y_test, y_pred)
+        pcc, _ = pearsonr(y_test, y_pred)
+
+        all_mse.append(mse)
+        all_r2.append(r2)
+        all_mae.append(mae)
+        all_pcc.append(pcc)
+
+        fold_time = time.time() - fold_start_time
+        fold_gpu_mem = torch.cuda.max_memory_allocated() / 1024**2 if torch.cuda.is_available() else 0
+        fold_cpu_mem = process.memory_info().rss / 1024**2
+        print(f'Fold {fold}:  Corr={pcc:.4f}, MAE={mae:.4f}, MSE={mse:.4f}, R2={r2:.4f}, Time={fold_time:.2f}s, '
+              f'GPU={fold_gpu_mem:.2f}MB, CPU={fold_cpu_mem:.2f}MB')
+
+        torch.cuda.empty_cache()
+        torch.cuda.reset_peak_memory_stats()
+        results_df = pd.DataFrame({'Y_test': y_test, 'Y_pred': y_pred})
+        results_df.to_csv(os.path.join(result_dir, f"fold{fold}.csv"), index=False)
+
+    print("\n===== Cross-validation summary =====")
+    print(f"Average PCC: {np.mean(all_pcc):.4f} ± {np.std(all_pcc):.4f}")
+    print(f"Average MAE: {np.mean(all_mae):.4f} ± {np.std(all_mae):.4f}")
+    print(f"Average MSE: {np.mean(all_mse):.4f} ± {np.std(all_mse):.4f}")
+    print(f"Average R2 : {np.mean(all_r2):.4f} ± {np.std(all_r2):.4f}")
+    print(f"Time: {time.time() - time_star:.2f}s")
+
+
+def DeepCCR_reg():
+    set_seed(42)
+    torch.cuda.empty_cache()  
+    args = parse_args()
+    device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
+    all_species =['Cotton/']
+    for i in range(len(all_species)):
+        args.species = all_species[i]
+        args.device = device  
+        X, Y, nsamples, nsnp, names = load_data(args)
+        for j in range(len(names)):
+            args.phe = names[j]
+            print("starting run " + args.methods + args.species + args.phe)
+            label = Y[:, j]
+            label = np.nan_to_num(label, nan=np.nanmean(label))
+            best_params = DeepCCR_Hyperparameters.Hyperparameter(X, label, nsnp)
+            args.lr = best_params['learning_rate']
+            args.patience = best_params['patience']
+            args.batch_size = best_params['batch_size']
+            start_time = time.time() 
+            torch.cuda.reset_peak_memory_stats()
+            process = psutil.Process(os.getpid())
+            run_nested_cv(args, data=X, label=label, nsnp = nsnp, device = args.device)
+
+            elapsed_time = time.time() - start_time
+            print(f"running time: {elapsed_time:.2f} s")
+            print("successfully")
+
+
+if __name__ == "__main__":
+    DeepCCR_reg()

gpbench/method_reg/DeepCCR/DeepCCR_Hyperparameters.py

@@ -0,0 +1,110 @@
+import os
+import time
+import psutil
+import random
+import torch
+import numpy as np
+import optuna
+from sklearn.model_selection import KFold, train_test_split
+from .base_DeepCCR import DeepCCR
+from scipy.stats import pearsonr
+from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score
+from torch.utils.data  import DataLoader, TensorDataset
+from optuna.exceptions import TrialPruned 
+
+def run_nested_cv_with_early_stopping(data, label, nsnp, learning_rate, batch_size, patience, epoch=1000):
+    device = torch.device("cuda:0")
+    print("Starting 10-fold cross-validation...")
+    kf = KFold(n_splits=10, shuffle=True, random_state=42)
+    all_mse, all_mae, all_r2, all_pcc = [], [], [], []
+
+    for fold, (train_index, test_index) in enumerate(kf.split(data)):
+        print(f"Running fold {fold}...")
+        process = psutil.Process(os.getpid())
+        fold_start_time = time.time()
+
+        X_train, X_test = data[train_index], data[test_index]
+        y_train, y_test = label[train_index], label[test_index]
+
+        X_train_sub, X_valid, y_train_sub, y_valid = train_test_split(X_train, y_train, test_size=0.1, random_state=42)
+
+        x_train_tensor = torch.from_numpy(X_train_sub).float()
+        y_train_tensor = torch.from_numpy(y_train_sub).float()
+        x_valid_tensor = torch.from_numpy(X_valid).float()
+        y_valid_tensor = torch.from_numpy(y_valid).float()
+        x_test_tensor = torch.from_numpy(X_test).float()
+        y_test_tensor = torch.from_numpy(y_test).float()
+        x_train_tensor = x_train_tensor.unsqueeze(1)
+        x_valid_tensor = x_valid_tensor.unsqueeze(1)
+        x_test_tensor  = x_test_tensor.unsqueeze(1)
+
+        train_data = TensorDataset(x_train_tensor, y_train_tensor)
+        valid_data = TensorDataset(x_valid_tensor, y_valid_tensor)
+        test_data = TensorDataset(x_test_tensor, y_test_tensor)
+
+        train_loader = DataLoader(train_data, batch_size, shuffle=True)
+        valid_loader = DataLoader(valid_data, batch_size, shuffle=False)
+        test_loader = DataLoader(test_data, batch_size, shuffle=False)
+
+        model = DeepCCR(input_seq_len = nsnp)
+        model.train_model(train_loader, valid_loader, epoch, learning_rate, patience, device)
+        y_pred = model.predict(test_loader, device)
+
+        mse = mean_squared_error(y_test, y_pred)
+        r2 = r2_score(y_test, y_pred)
+        mae = mean_absolute_error(y_test, y_pred)
+        pcc, _ = pearsonr(y_test, y_pred)
+
+        if np.isnan(pcc):
+            print(f"Fold {fold} resulted in NaN PCC, pruning the trial...")
+            raise TrialPruned()
+
+        all_mse.append(mse)
+        all_r2.append(r2)
+        all_mae.append(mae)
+        all_pcc.append(pcc)
+
+        fold_time = time.time() - fold_start_time
+        fold_gpu_mem = torch.cuda.max_memory_allocated() / 1024**2 if torch.cuda.is_available() else 0
+        fold_cpu_mem = process.memory_info().rss / 1024**2
+        print(f'Fold {fold}:  Corr={pcc:.4f}, MAE={mae:.4f}, MSE={mse:.4f}, R2={r2:.4f}, Time={fold_time:.2f}s, '
+                f'GPU={fold_gpu_mem:.2f}MB, CPU={fold_cpu_mem:.2f}MB')
+        
+    return np.mean(all_pcc) if all_pcc else 0.0
+
+def set_seed(seed=42):
+    random.seed(seed)
+    np.random.seed(seed)
+    torch.manual_seed(seed)
+    if torch.cuda.is_available():
+        torch.cuda.manual_seed_all(seed)
+    torch.backends.cudnn.deterministic = True
+    torch.backends.cudnn.benchmark = False
+
+def Hyperparameter(data, label, nsnp):
+    set_seed(42)
+    
+    def objective(trial):
+        lr = trial.suggest_float("learning_rate", 1e-4, 0.1)
+        batch_size = trial.suggest_categorical("batch_size", [32, 64, 128])
+        patience = trial.suggest_int("patience", 1, 10)
+        try:
+            corr_score = run_nested_cv_with_early_stopping(
+                data=data,
+                label=label,
+                nsnp=nsnp,
+                learning_rate=lr,
+                batch_size=batch_size,
+                patience=patience
+            )
+
+        except TrialPruned:
+            return float("-inf")
+        return corr_score
+    
+    study = optuna.create_study(direction="maximize")
+    study.optimize(objective, n_trials=20)
+
+    print("best params:", study.best_params)
+    print("successfully")
+    return study.best_params

gpbench/method_reg/DeepCCR/__init__.py

@@ -0,0 +1,5 @@
+from .DeepCCR import DeepCCR_reg
+
+DeepCCR = DeepCCR_reg
+
+__all__ = ["DeepCCR","DeepCCR_reg"]