{"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":31089,"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":"2026-01-16T16:03:56.559209Z","iopub.execute_input":"2026-01-16T16:03:56.559645Z","iopub.status.idle":"2026-01-16T16:03:59.194506Z","shell.execute_reply.started":"2026-01-16T16:03:56.559475Z","shell.execute_reply":"2026-01-16T16:03:59.193339Z"}},"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","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-16T16:03:59.196291Z","iopub.execute_input":"2026-01-16T16:03:59.196741Z","iopub.status.idle":"2026-01-16T16:04:11.516402Z","shell.execute_reply.started":"2026-01-16T16:03:59.196714Z","shell.execute_reply":"2026-01-16T16:04:11.515293Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### Load data","metadata":{}},{"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":"2026-01-16T16:04:11.517278Z","iopub.execute_input":"2026-01-16T16:04:11.517843Z","iopub.status.idle":"2026-01-16T16:04:16.550630Z","shell.execute_reply.started":"2026-01-16T16:04:11.517809Z","shell.execute_reply":"2026-01-16T16:04:16.549597Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-16T16:04:16.551767Z","iopub.execute_input":"2026-01-16T16:04:16.552076Z","iopub.status.idle":"2026-01-16T16:04:16.596382Z","shell.execute_reply.started":"2026-01-16T16:04:16.552052Z","shell.execute_reply":"2026-01-16T16:04:16.595440Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train.info()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-16T16:04:16.598813Z","iopub.execute_input":"2026-01-16T16:04:16.599106Z","iopub.status.idle":"2026-01-16T16:04:16.647850Z","shell.execute_reply.started":"2026-01-16T16:04:16.599083Z","shell.execute_reply":"2026-01-16T16:04:16.646731Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### Olah DATAset\n* Pisahkan data menjadi Target dan Fitur. Lakukan normalisasi dengan membagi tiap Kolum atau Pixel dengan 255, sehingga skala pixel menjadi 0-1\n* Konversi data dari Numpy arrays menjadi Pytorch Tensors.","metadata":{}},{"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)\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-16T16:04:16.648743Z","iopub.execute_input":"2026-01-16T16:04:16.649073Z","iopub.status.idle":"2026-01-16T16:04:17.098571Z","shell.execute_reply.started":"2026-01-16T16:04:16.649043Z","shell.execute_reply":"2026-01-16T16:04:17.097419Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"X_train.shape, X_test.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-16T16:04:17.100038Z","iopub.execute_input":"2026-01-16T16:04:17.100536Z","iopub.status.idle":"2026-01-16T16:04:17.106987Z","shell.execute_reply.started":"2026-01-16T16:04:17.100503Z","shell.execute_reply":"2026-01-16T16:04:17.106070Z"}},"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":"2026-01-16T16:04:17.107907Z","iopub.execute_input":"2026-01-16T16:04:17.108194Z","iopub.status.idle":"2026-01-16T16:04:17.124992Z","shell.execute_reply.started":"2026-01-16T16:04:17.108167Z","shell.execute_reply":"2026-01-16T16:04:17.124020Z"}},"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":"2026-01-16T16:04:17.125963Z","iopub.execute_input":"2026-01-16T16:04:17.126232Z","iopub.status.idle":"2026-01-16T16:04:17.224627Z","shell.execute_reply.started":"2026-01-16T16:04:17.126212Z","shell.execute_reply":"2026-01-16T16:04:17.223775Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_dataset.X.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-16T16:04:17.225510Z","iopub.execute_input":"2026-01-16T16:04:17.225812Z","iopub.status.idle":"2026-01-16T16:04:17.231952Z","shell.execute_reply.started":"2026-01-16T16:04:17.225789Z","shell.execute_reply":"2026-01-16T16:04:17.230976Z"}},"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":"2026-01-16T16:04:17.232951Z","iopub.execute_input":"2026-01-16T16:04:17.233271Z","iopub.status.idle":"2026-01-16T16:04:17.251844Z","shell.execute_reply.started":"2026-01-16T16:04:17.233240Z","shell.execute_reply":"2026-01-16T16:04:17.250445Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"len(train_loader) #batch size","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-16T16:04:17.252828Z","iopub.execute_input":"2026-01-16T16:04:17.253140Z","iopub.status.idle":"2026-01-16T16:04:17.274818Z","shell.execute_reply.started":"2026-01-16T16:04:17.253112Z","shell.execute_reply":"2026-01-16T16:04:17.273757Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_loader.dataset.X.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-16T16:04:17.275769Z","iopub.execute_input":"2026-01-16T16:04:17.276098Z","iopub.status.idle":"2026-01-16T16:04:17.295696Z","shell.execute_reply.started":"2026-01-16T16:04:17.276076Z","shell.execute_reply":"2026-01-16T16:04:17.294762Z"}},"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":"2026-01-16T16:04:17.299573Z","iopub.execute_input":"2026-01-16T16:04:17.299904Z","iopub.status.idle":"2026-01-16T16:04:17.313742Z","shell.execute_reply.started":"2026-01-16T16:04:17.299881Z","shell.execute_reply":"2026-01-16T16:04:17.312441Z"}},"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":"2026-01-16T16:04:17.314783Z","iopub.execute_input":"2026-01-16T16:04:17.315107Z","iopub.status.idle":"2026-01-16T16:04:17.973790Z","shell.execute_reply.started":"2026-01-16T16:04:17.315080Z","shell.execute_reply":"2026-01-16T16:04:17.972749Z"}},"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\n        ","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-16T16:04:17.974878Z","iopub.execute_input":"2026-01-16T16:04:17.975388Z","iopub.status.idle":"2026-01-16T16:04:17.982692Z","shell.execute_reply.started":"2026-01-16T16:04:17.975362Z","shell.execute_reply":"2026-01-16T16:04:17.981669Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### Training & 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":"2026-01-16T16:04:17.983461Z","iopub.execute_input":"2026-01-16T16:04:17.983899Z","iopub.status.idle":"2026-01-16T16:04:18.024051Z","shell.execute_reply.started":"2026-01-16T16:04:17.983870Z","shell.execute_reply":"2026-01-16T16:04:18.022852Z"}},"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":"2026-01-16T16:04:18.025191Z","iopub.execute_input":"2026-01-16T16:04:18.025670Z","iopub.status.idle":"2026-01-16T16:04:18.032836Z","shell.execute_reply.started":"2026-01-16T16:04:18.025630Z","shell.execute_reply":"2026-01-16T16:04:18.031729Z"}},"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":"2026-01-16T16:04:18.033908Z","iopub.execute_input":"2026-01-16T16:04:18.034187Z","iopub.status.idle":"2026-01-16T16:04:18.054794Z","shell.execute_reply.started":"2026-01-16T16:04:18.034165Z","shell.execute_reply":"2026-01-16T16:04:18.053897Z"}},"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":"2026-01-16T16:04:18.055869Z","iopub.execute_input":"2026-01-16T16:04:18.056199Z","iopub.status.idle":"2026-01-16T16:04:18.074695Z","shell.execute_reply.started":"2026-01-16T16:04:18.056172Z","shell.execute_reply":"2026-01-16T16:04:18.073465Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"best_valid_loss = 0\nEPOCHS = 50\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}')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-16T16:04:18.076071Z","iopub.execute_input":"2026-01-16T16:04:18.076334Z","iopub.status.idle":"2026-01-16T16:08:22.646672Z","shell.execute_reply.started":"2026-01-16T16:04:18.076315Z","shell.execute_reply":"2026-01-16T16:08:22.645312Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Learning Curve","metadata":{}},{"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# --- 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":"2026-01-16T16:08:22.647726Z","iopub.execute_input":"2026-01-16T16:08:22.647993Z","iopub.status.idle":"2026-01-16T16:08:23.160632Z","shell.execute_reply.started":"2026-01-16T16:08:22.647972Z","shell.execute_reply":"2026-01-16T16:08:23.159400Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Dari grafik terlihat bahwa loss training terus menurun secara signifikan, sedangkan loss validasi sempat menurun lalu cenderung stagnan dan sedikit meningkat setelah beberapa epoch. Akurasi training terus meningkat hingga mendekati 99%, sementara akurasi validasi berhenti di kisaran 97–98%. Hal ini menunjukkan bahwa model mulai mengalami overfitting, karena performa pada data latih terus membaik tetapi tidak diikuti peningkatan yang sebanding pada data validasi.","metadata":{}}]}