{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.11.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":3004,"databundleVersionId":861823,"sourceType":"competition"}],"dockerImageVersionId":31234,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2026-01-15T07:14:34.013627Z","iopub.execute_input":"2026-01-15T07:14:34.013965Z","iopub.status.idle":"2026-01-15T07:14:34.020899Z","shell.execute_reply.started":"2026-01-15T07:14:34.013941Z","shell.execute_reply":"2026-01-15T07:14:34.020007Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n\nfrom sklearn.model_selection import train_test_split\n\nimport torch\nimport torch.nn as nn\nfrom torchvision import transforms, models\n\nfrom torch.autograd import Variable\nfrom torch import nn, optim\nimport torch.nn.functional as F\nfrom torch.utils.data import DataLoader, Dataset\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-15T07:14:34.022414Z","iopub.execute_input":"2026-01-15T07:14:34.022702Z","iopub.status.idle":"2026-01-15T07:14:34.045050Z","shell.execute_reply.started":"2026-01-15T07:14:34.022683Z","shell.execute_reply":"2026-01-15T07:14:34.044002Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train = pd.read_csv('/kaggle/input/digit-recognizer/train.csv', dtype=np.float32)\ntest = pd.read_csv('/kaggle/input/digit-recognizer/test.csv', dtype=np.float32)\nsample_hub = pd.read_csv('/kaggle/input/digit-recognizer/sample_submission.csv')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-15T07:14:34.046050Z","iopub.execute_input":"2026-01-15T07:14:34.046496Z","iopub.status.idle":"2026-01-15T07:14:38.559721Z","shell.execute_reply.started":"2026-01-15T07:14:34.046456Z","shell.execute_reply":"2026-01-15T07:14:38.558562Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-15T07:14:38.561073Z","iopub.execute_input":"2026-01-15T07:14:38.561440Z","iopub.status.idle":"2026-01-15T07:14:38.586448Z","shell.execute_reply.started":"2026-01-15T07:14:38.561411Z","shell.execute_reply":"2026-01-15T07:14:38.585569Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train.info()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-15T07:14:38.588556Z","iopub.execute_input":"2026-01-15T07:14:38.588929Z","iopub.status.idle":"2026-01-15T07:14:38.628698Z","shell.execute_reply.started":"2026-01-15T07:14:38.588900Z","shell.execute_reply":"2026-01-15T07:14:38.627539Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#pisahkan Target dan Fitur\ntargets_np = train.label.values\nfeatures_np = train.iloc[:, 1:].values/255\n\n#Split data menjadi Train dan Test set\n\nX_train, X_test, y_train, y_test = train_test_split(features_np, targets_np, test_size=0.2, random_state=42)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-15T07:14:38.629660Z","iopub.execute_input":"2026-01-15T07:14:38.629984Z","iopub.status.idle":"2026-01-15T07:14:39.063591Z","shell.execute_reply.started":"2026-01-15T07:14:38.629956Z","shell.execute_reply":"2026-01-15T07:14:39.062553Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"X_train.shape, X_test.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-15T07:14:39.064724Z","iopub.execute_input":"2026-01-15T07:14:39.064999Z","iopub.status.idle":"2026-01-15T07:14:39.072034Z","shell.execute_reply.started":"2026-01-15T07:14:39.064976Z","shell.execute_reply":"2026-01-15T07:14:39.070912Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Konversi dari Arrays ke Tensors\n\nclass DigitDataset(Dataset):\n    def __init__(self, X, y):\n        self.X = torch.tensor(X, dtype=torch.float32)\n        self.y = torch.tensor(y, dtype=torch.long)\n    def __len__(self):\n        return len(self.y)\n\n    def __getitem__(self, idx):\n        return self.X[idx], self.y[idx]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-15T07:14:39.073095Z","iopub.execute_input":"2026-01-15T07:14:39.073514Z","iopub.status.idle":"2026-01-15T07:14:39.093313Z","shell.execute_reply.started":"2026-01-15T07:14:39.073491Z","shell.execute_reply":"2026-01-15T07:14:39.092043Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"torch.manual_seed(1111)\ntrain_dataset = DigitDataset(X_train, y_train)\ntest_dataset = DigitDataset(X_test, y_test)\nlen(train_dataset)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-15T07:14:39.094436Z","iopub.execute_input":"2026-01-15T07:14:39.094779Z","iopub.status.idle":"2026-01-15T07:14:39.188524Z","shell.execute_reply.started":"2026-01-15T07:14:39.094747Z","shell.execute_reply":"2026-01-15T07:14:39.187720Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_dataset.X.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-15T07:14:39.189573Z","iopub.execute_input":"2026-01-15T07:14:39.189907Z","iopub.status.idle":"2026-01-15T07:14:39.195669Z","shell.execute_reply.started":"2026-01-15T07:14:39.189877Z","shell.execute_reply":"2026-01-15T07:14:39.194767Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"batch_size = 64\ng = torch.Generator()\ng.manual_seed(1111)\ntrain_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True, generator=g)\ntest_loader = DataLoader(test_dataset, batch_size=batch_size, shuffle=True, generator=g)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-15T07:14:39.196677Z","iopub.execute_input":"2026-01-15T07:14:39.196912Z","iopub.status.idle":"2026-01-15T07:14:39.219357Z","shell.execute_reply.started":"2026-01-15T07:14:39.196892Z","shell.execute_reply":"2026-01-15T07:14:39.218065Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"len(train_loader) #batch size","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-15T07:14:39.220520Z","iopub.execute_input":"2026-01-15T07:14:39.220842Z","iopub.status.idle":"2026-01-15T07:14:39.242578Z","shell.execute_reply.started":"2026-01-15T07:14:39.220813Z","shell.execute_reply":"2026-01-15T07:14:39.241562Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_loader.dataset.X.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-15T07:14:39.243957Z","iopub.execute_input":"2026-01-15T07:14:39.244746Z","iopub.status.idle":"2026-01-15T07:14:39.266627Z","shell.execute_reply.started":"2026-01-15T07:14:39.244710Z","shell.execute_reply":"2026-01-15T07:14:39.265717Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"VISUALISASI DATA","metadata":{}},{"cell_type":"code","source":"def plot_images(images):\n    n_images = len(images)\n    rows = int(np.sqrt(n_images))\n    cols = int(np.sqrt(n_images))\n\n    fig = plt.figure()\n    for i in range(rows*cols):\n        ax = fig.add_subplot(rows, cols, i+1)\n        ax.imshow(images[i].view(28,28), cmap='bone')\n        ax.axis('off')\n    #plt.title('handwritten digit')\n    plt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-15T07:14:39.269862Z","iopub.execute_input":"2026-01-15T07:14:39.270310Z","iopub.status.idle":"2026-01-15T07:14:39.287918Z","shell.execute_reply.started":"2026-01-15T07:14:39.270282Z","shell.execute_reply":"2026-01-15T07:14:39.286732Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"N_IMAGES = 25\n\nimages = [image for image, label in [train_dataset[i] for i in range(N_IMAGES)]]\n\nplot_images(images)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-15T07:14:39.289659Z","iopub.execute_input":"2026-01-15T07:14:39.290120Z","iopub.status.idle":"2026-01-15T07:14:39.873998Z","shell.execute_reply.started":"2026-01-15T07:14:39.290085Z","shell.execute_reply":"2026-01-15T07:14:39.873147Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"MLP ARCHITECTURE","metadata":{}},{"cell_type":"code","source":"class MLPdigit(nn.Module):\n    def __init__(self, input_dim, output_dim):\n        super().__init__()\n        self.fc1 = nn.Linear(input_dim, 512)\n        self.fc2 = nn.Linear(512, 256)\n        self.fc3 = nn.Linear(256, 128)\n        self.fc4 = nn.Linear(128, 64)\n        self.fc5 = nn.Linear(64, output_dim)\n\n        self.dropout = nn.Dropout(p=0.2)\n        #self.sftmax = F.softmax\n\n    def forward(self, x):\n        x = self.dropout(F.relu(self.fc1(x)))\n        x = self.dropout(F.relu(self.fc2(x)))\n        x = self.dropout(F.relu(self.fc3(x)))\n        x = self.dropout(F.relu(self.fc4(x)))\n        x = self.fc5(x)\n\n        return x","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-15T07:14:39.874781Z","iopub.execute_input":"2026-01-15T07:14:39.875037Z","iopub.status.idle":"2026-01-15T07:14:39.882628Z","shell.execute_reply.started":"2026-01-15T07:14:39.875016Z","shell.execute_reply":"2026-01-15T07:14:39.881493Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"TRAINING DAN VALIDATION","metadata":{}},{"cell_type":"code","source":"input_dim = 28 * 28\noutput_dim = 10\nlr=0.001\n\ndevice = torch.device('cuda' if torch.cuda.is_available() else 'cpu')\n\nmodel = MLPdigit(input_dim, output_dim)\ncriterion = nn.CrossEntropyLoss()\noptimizer = optim.Adam(model.parameters(), lr=lr)\n\nprint(f'This model uses {device}')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-15T07:14:39.883634Z","iopub.execute_input":"2026-01-15T07:14:39.884013Z","iopub.status.idle":"2026-01-15T07:14:39.912253Z","shell.execute_reply.started":"2026-01-15T07:14:39.883988Z","shell.execute_reply":"2026-01-15T07:14:39.911051Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def cal_accuracy(y_pred, y):\n    predicted = torch.argmax(y_pred, dim=-1)\n    correct = (predicted == y).sum()\n    acc = correct.float() / y.shape[0]\n    return acc","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-15T07:14:39.913385Z","iopub.execute_input":"2026-01-15T07:14:39.913690Z","iopub.status.idle":"2026-01-15T07:14:39.936645Z","shell.execute_reply.started":"2026-01-15T07:14:39.913666Z","shell.execute_reply":"2026-01-15T07:14:39.934914Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def train(model, train_loader, optimizer, criterion, device):\n    epoch_loss = 0.0\n    epoch_acc = 0.0\n\n    model.train()\n\n    for X, y in train_loader:\n        y_pred = model(X).to(device)        \n        \n        loss = criterion(y_pred, y)\n\n        acc = cal_accuracy(y_pred, y)\n\n        optimizer.zero_grad()\n        loss.backward()\n        optimizer.step()\n\n        epoch_loss += loss.item()\n        epoch_acc += acc.item()\n\n    return epoch_loss/len(train_loader), epoch_acc/len(train_loader)  ","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-15T07:14:39.937558Z","iopub.execute_input":"2026-01-15T07:14:39.937807Z","iopub.status.idle":"2026-01-15T07:14:39.964106Z","shell.execute_reply.started":"2026-01-15T07:14:39.937786Z","shell.execute_reply":"2026-01-15T07:14:39.962970Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def evaluate(model, test_loader, criterion, device):\n    epoch_loss = 0\n    epoch_acc = 0\n\n    model.eval()\n\n    with torch.no_grad():\n        for X, y in test_loader:\n            y_pred = model(X).to(device)\n            loss = criterion(y_pred, y)\n            acc = cal_accuracy(y_pred, y)\n\n            epoch_loss += loss.item()\n            epoch_acc += acc.item()\n\n    return epoch_loss/len(test_loader), epoch_acc/len(test_loader)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-15T07:14:39.965294Z","iopub.execute_input":"2026-01-15T07:14:39.965550Z","iopub.status.idle":"2026-01-15T07:14:39.990630Z","shell.execute_reply.started":"2026-01-15T07:14:39.965529Z","shell.execute_reply":"2026-01-15T07:14:39.989269Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"best_valid_loss = 0\nEPOCHS = 15\ntrain_losses, test_losses, train_accs, valid_accs = [], [], [], []\n\nfor epoch in range(EPOCHS):\n    train_loss, train_acc = train(model, train_loader, optimizer, criterion, device)\n    valid_loss, valid_acc = evaluate(model, test_loader, criterion, device)\n    train_losses.append(train_loss)\n    test_losses.append(valid_loss)\n    train_accs.append(train_acc)\n    valid_accs.append(valid_acc)\n\n    if valid_loss < best_valid_loss:\n        best_valid_loss = valid_loss\n        torch.save(model.state_dict(), 'digit-model.pt')\n\n    print(f'Epoch: {epoch}')\n    print(f'\\t Train loss: {train_loss:.3f} | Train acc: {train_acc:.3f}')\n    print(f'\\t  Val  loss: {valid_loss:.3f} |   Val acc: {valid_acc:.3f}')\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-15T07:14:39.991873Z","iopub.execute_input":"2026-01-15T07:14:39.992255Z","iopub.status.idle":"2026-01-15T07:15:55.652597Z","shell.execute_reply.started":"2026-01-15T07:14:39.992192Z","shell.execute_reply":"2026-01-15T07:15:55.651472Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(15, 5))\n\n# --- Plot 1: Losses ---\nax1.plot(train_losses, label='Training Loss')\nax1.plot(test_losses, label='Validation Loss')\nax1.set_title('Loss vs. Epochs')\nax1.set_xlabel('Epoch')\nax1.set_ylabel('Loss')\nax1.legend()\nax1.grid(True)\n\n\n# --- Plot 2: Accuracies ---\nax2.plot(train_accs, label='Training Accuracy', color='green')\nax2.plot(valid_accs, label='Validation Accuracy', color='orange')\nax2.set_title('Accuracy vs. Epochs')\nax2.set_xlabel('Epoch')\nax2.set_ylabel('Accuracy')\nax2.legend()\nax2.grid(True)\n\nplt.tight_layout()\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-15T07:15:55.653781Z","iopub.execute_input":"2026-01-15T07:15:55.654146Z","iopub.status.idle":"2026-01-15T07:15:56.161034Z","shell.execute_reply.started":"2026-01-15T07:15:55.654115Z","shell.execute_reply":"2026-01-15T07:15:56.160089Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Kesimpulan: \nPada grafik loss vs epoch menunjukan bahwa nilai training loss terus menurun pada setiap epoch, itu menunjukan bahwa model yang digunakan semakin dalam mengenali pola pada data latih. Namun, validation loss hanya menurun di awal lalu cenderung berhenti dan sedikit meningkat. Itu menandakan bahwa model mulai kesulitan saat di lakukan pengujian dengan data baru. Sedangkan pada data grafik accuracy vs epoch, training eccuracy terus meningkat hingga hampir maksimal, sedangkan validation accuracy hanya naik di awal lalu cenderung stabil tanpa peningkatan yang signifikan. Perbedaan hasil antara data latih dan data validasi menunjukan bahwa model mulai overfiting pada epoch-epoch yang terakhir.","metadata":{}},{"cell_type":"markdown","source":"Kesimpulan: \nPada grafik loss vs epoch menunjukan bahwa nilai training loss terus menurun pada setiap epoch, itu menunjukan bahwa model yang digunakan semakin dalam mengenali pola pada data latih. Namun, validation loss hanya menurun di awal lalu cenderung berhenti dan sedikit meningkat. Itu menandakan bahwa model mulai kesulitan saat di lakukan pengujian dengan data baru. Sedangkan pada data grafik accuracy vs epoch, training eccuracy terus meningkat hingga hampir maksimal, sedangkan validation accuracy hanya naik di awal lalu cenderung stabil tanpa peningkatan yang signifikan. Perbedaan hasil antara data latih dan data validasi menunjukan bahwa model mulai overfiting pada epoch-epoch yang terakhir.","metadata":{}}]}