{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.7.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceType":"competition","sourceId":3004,"databundleVersionId":861823}],"dockerImageVersionId":30260,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"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","execution":{"iopub.status.busy":"2026-03-27T12:42:29.534886Z","iopub.execute_input":"2026-03-27T12:42:29.535634Z","iopub.status.idle":"2026-03-27T12:42:29.591423Z","shell.execute_reply.started":"2026-03-27T12:42:29.535549Z","shell.execute_reply":"2026-03-27T12:42:29.590385Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport os\nimport matplotlib.pyplot as plt\nfrom sklearn.model_selection import train_test_split\n\n# Import TensorFlow Keras terbaru\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Dense, Dropout, Flatten, BatchNormalization, Conv2D, MaxPooling2D\nfrom tensorflow.keras.optimizers import Adam\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.callbacks import ReduceLROnPlateau\n\nprint(\"Mempersiapkan data...\")\n# 1. Memuat Data\nmnist_train = pd.read_csv(\"../input/digit-recognizer/train.csv\")\nmnist_test = pd.read_csv(\"../input/digit-recognizer/test.csv\")\n\n# 2. Pemrosesan Data\n# Mengubah label menjadi kategori (One-Hot Encoding)\ny_train_full = pd.get_dummies(mnist_train['label']).values \n\n# Memisahkan fitur dan mengubah dimensi (Reshape) serta Normalisasi (/255)\nx_train_full = mnist_train.drop(['label'], axis=1).values.reshape(-1, 28, 28, 1) / 255.0\nx_test = mnist_test.values.reshape(-1, 28, 28, 1) / 255.0\n\n# Membagi data menjadi Training (90%) dan Validation (10%)\nx_train, x_val, y_train, y_val = train_test_split(x_train_full, y_train_full, test_size=0.1, random_state=101)\n\n# 3. Membuat Model CNN yang Dioptimalkan\ndef build_optimized_model():\n    model = Sequential()\n    \n    # Blok Konvolusi 1\n    model.add(Conv2D(32, (3,3), activation='relu', padding='same', input_shape=(28,28,1)))\n    model.add(BatchNormalization())\n    model.add(Conv2D(32, (3,3), activation='relu', padding='same'))\n    model.add(BatchNormalization())\n    model.add(MaxPooling2D(pool_size=(2,2)))\n    model.add(Dropout(0.25)) # Mencegah overfitting\n\n    # Blok Konvolusi 2\n    model.add(Conv2D(64, (3,3), activation='relu', padding='same'))\n    model.add(BatchNormalization())\n    model.add(Conv2D(64, (3,3), activation='relu', padding='same'))\n    model.add(BatchNormalization())\n    model.add(MaxPooling2D(pool_size=(2,2)))\n    model.add(Dropout(0.25))\n\n    # Fully Connected Layer (Classifier)\n    model.add(Flatten())\n    model.add(Dense(256, activation='relu'))\n    model.add(BatchNormalization())\n    model.add(Dropout(0.5))\n    model.add(Dense(10, activation='softmax')) # 10 output untuk digit 0-9\n    \n    return model\n\nmodel = build_optimized_model()\nprint(model.summary())\n\n# 4. Augmentasi Data (Modifikasi gambar untuk memperbanyak variasi data)\ndatagen = ImageDataGenerator(\n    rotation_range=10,\n    zoom_range=0.1,\n    width_shift_range=0.1,\n    height_shift_range=0.1\n)\ndatagen.fit(x_train)\n\n# 5. Konfigurasi Pelatihan (Compile & Callbacks)\n# Callback: Mengurangi kecepatan belajar (learning rate) jika akurasi mandek\nreduce_lr = ReduceLROnPlateau(monitor='val_accuracy', patience=3, verbose=1, factor=0.5, min_lr=0.00001)\n\noptimizer = Adam(learning_rate=0.001)\nmodel.compile(optimizer=optimizer, loss=\"categorical_crossentropy\", metrics=[\"accuracy\"])\n\n# 6. Memulai Pelatihan\nprint(\"Memulai proses pelatihan model...\")\nepochs = 30 \nbatch_size = 64\n\nhistory = model.fit(\n    datagen.flow(x_train, y_train, batch_size=batch_size),\n    epochs=epochs,\n    validation_data=(x_val, y_val),\n    verbose=1,\n    callbacks=[reduce_lr]\n)\n\n# 7. Melakukan Prediksi dan Membuat File Submission\nprint(\"Membuat prediksi untuk data test...\")\ny_pred = model.predict(x_test)\ny_classes = np.argmax(y_pred, axis=1) # Mengambil indeks prediksi tertinggi\n\nsample = pd.read_csv(\"../input/digit-recognizer/sample_submission.csv\")\noutput = pd.DataFrame({'ImageId': sample.ImageId, 'Label': y_classes})\noutput.to_csv('submission_optimized.csv', index=False)\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-27T12:42:29.593098Z","iopub.execute_input":"2026-03-27T12:42:29.593418Z","iopub.status.idle":"2026-03-27T12:48:38.162503Z","shell.execute_reply.started":"2026-03-27T12:42:29.593391Z","shell.execute_reply":"2026-03-27T12:48:38.161744Z"}},"outputs":[],"execution_count":null}]}