{"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":"none","dataSources":[{"sourceType":"competition","sourceId":3004,"databundleVersionId":861823,"isSourceIdPinned":false}],"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","execution":{"iopub.status.busy":"2026-03-27T10:33:24.289666Z","iopub.execute_input":"2026-03-27T10:33:24.290071Z","iopub.status.idle":"2026-03-27T10:33:24.298474Z","shell.execute_reply.started":"2026-03-27T10:33:24.290033Z","shell.execute_reply":"2026-03-27T10:33:24.296896Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"mnist_train = pd.read_csv(\"../input/digit-recognizer/train.csv\")\nmnist_test = pd.read_csv(\"../input/digit-recognizer/test.csv\")","metadata":{"execution":{"iopub.status.busy":"2026-03-27T10:33:24.30033Z","iopub.execute_input":"2026-03-27T10:33:24.300987Z","iopub.status.idle":"2026-03-27T10:33:28.649818Z","shell.execute_reply.started":"2026-03-27T10:33:24.300956Z","shell.execute_reply":"2026-03-27T10:33:28.648817Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"y_train1 = pd.get_dummies(mnist_train.label)\nprint(y_train1.shape)","metadata":{"execution":{"iopub.status.busy":"2026-03-27T10:33:28.651102Z","iopub.execute_input":"2026-03-27T10:33:28.651463Z","iopub.status.idle":"2026-03-27T10:33:28.670839Z","shell.execute_reply.started":"2026-03-27T10:33:28.651431Z","shell.execute_reply":"2026-03-27T10:33:28.669695Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"npx = mnist_train.drop(['label'], axis=1)\nx_train1 = np.array(npx).reshape(42000,28,28,1)/255\nprint(x_train1.shape)","metadata":{"execution":{"iopub.status.busy":"2026-03-27T10:33:28.672245Z","iopub.execute_input":"2026-03-27T10:33:28.672671Z","iopub.status.idle":"2026-03-27T10:33:29.05392Z","shell.execute_reply.started":"2026-03-27T10:33:28.672628Z","shell.execute_reply":"2026-03-27T10:33:29.052847Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split #to split our dataset\nx_train, x_val, y_train, y_val = train_test_split(x_train1, y_train1, test_size=0.1, random_state=101)","metadata":{"execution":{"iopub.status.busy":"2026-03-27T10:33:29.057277Z","iopub.execute_input":"2026-03-27T10:33:29.05798Z","iopub.status.idle":"2026-03-27T10:33:29.977497Z","shell.execute_reply.started":"2026-03-27T10:33:29.057945Z","shell.execute_reply":"2026-03-27T10:33:29.976546Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"npx = mnist_test\nx_test = np.array(npx).reshape(28000,28,28,1)/255\nprint(x_test.shape)","metadata":{"execution":{"iopub.status.busy":"2026-03-27T10:33:29.979306Z","iopub.execute_input":"2026-03-27T10:33:29.979843Z","iopub.status.idle":"2026-03-27T10:33:30.130313Z","shell.execute_reply.started":"2026-03-27T10:33:29.979809Z","shell.execute_reply":"2026-03-27T10:33:30.129192Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import keras\nfrom keras.models import Sequential\nfrom keras.optimizers import adam_v2\nfrom keras.utils.np_utils import to_categorical\nfrom keras.layers import Dense, Dropout, Flatten, BatchNormalization\nfrom keras.layers.convolutional import Conv2D, MaxPooling2D\nfrom keras.preprocessing import image\nfrom keras.callbacks import ReduceLROnPlateau\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport cv2 \nfrom PIL import Image \n\nnp.random.seed(99)","metadata":{"execution":{"iopub.status.busy":"2026-03-27T10:33:30.131794Z","iopub.execute_input":"2026-03-27T10:33:30.132136Z","iopub.status.idle":"2026-03-27T10:33:36.302517Z","shell.execute_reply.started":"2026-03-27T10:33:30.132105Z","shell.execute_reply":"2026-03-27T10:33:36.301605Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def display(img):\n  plt.figure(figsize=(5,5))\n  plt.axis(\"off\")\n  plt.imshow(img,cmap=\"gray\")\n\ndisplay(x_train[1191])","metadata":{"execution":{"iopub.status.busy":"2026-03-27T10:33:36.303915Z","iopub.execute_input":"2026-03-27T10:33:36.305203Z","iopub.status.idle":"2026-03-27T10:33:36.423501Z","shell.execute_reply.started":"2026-03-27T10:33:36.305157Z","shell.execute_reply":"2026-03-27T10:33:36.422478Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from keras.preprocessing.image import ImageDataGenerator\n\ndatagen = ImageDataGenerator(rotation_range = 10, width_shift_range = 0.1, shear_range = 0.1,\n                             height_shift_range = 0.1, zoom_range = [0.9,1.1], fill_mode = 'nearest', \n                             horizontal_flip = False, vertical_flip = False)\ndatagen.fit(x_train)","metadata":{"execution":{"iopub.status.busy":"2026-03-27T10:33:36.42488Z","iopub.execute_input":"2026-03-27T10:33:36.425301Z","iopub.status.idle":"2026-03-27T10:33:36.561188Z","shell.execute_reply.started":"2026-03-27T10:33:36.425261Z","shell.execute_reply":"2026-03-27T10:33:36.560032Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def Conv_Net_model():\n  model = Sequential()\n  \n  # Layer Conv 1 & 2 (Pattern: Double Conv untuk menangkap fitur lebih detail)\n  model.add(Conv2D(32,(3,3), input_shape=(28,28,1), padding=\"same\", activation=\"relu\"))\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))\n\n  # Layer Conv 3 & 4\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  # Layer Conv 5 & 6\n  model.add(Conv2D(128,(3,3), activation=\"relu\", padding=\"same\"))\n  model.add(BatchNormalization())\n  model.add(Flatten())\n  \n  # Fully Connected Layer\n  model.add(Dense(256, activation=\"relu\"))\n  model.add(BatchNormalization())\n  model.add(Dropout(rate=0.4))\n  model.add(Dense(10, activation=\"softmax\"))\n  return model\n\nmodel = Conv_Net_model()\nprint(model.summary())","metadata":{"execution":{"iopub.status.busy":"2026-03-27T10:33:36.562472Z","iopub.execute_input":"2026-03-27T10:33:36.562797Z","iopub.status.idle":"2026-03-27T10:33:36.803342Z","shell.execute_reply.started":"2026-03-27T10:33:36.562768Z","shell.execute_reply":"2026-03-27T10:33:36.802293Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"reduce_lr = ReduceLROnPlateau(monitor = 'val_accuracy', \n                              min_lr = 0.00001, verbose = 1,  patience = 2, factor = 0.8, mode = 'auto', cooldown = 0)","metadata":{"execution":{"iopub.status.busy":"2026-03-27T10:33:36.804684Z","iopub.execute_input":"2026-03-27T10:33:36.805002Z","iopub.status.idle":"2026-03-27T10:33:36.810219Z","shell.execute_reply.started":"2026-03-27T10:33:36.804973Z","shell.execute_reply":"2026-03-27T10:33:36.80914Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"opt = adam_v2.Adam(learning_rate=0.001, beta_1=0.9, beta_2=0.999, amsgrad=True)\n\nmodel.compile(optimizer=opt, loss = \"categorical_crossentropy\", metrics = [\"accuracy\"])\n\n# Optimalisasi Training: Menambah epoch ke 40 agar model mencapai potensi maksimal\nh = model.fit(datagen.flow(x_train,y_train, batch_size=64), epochs=40, \n              validation_data=(x_val,y_val), shuffle=1, verbose=1, callbacks=[reduce_lr])","metadata":{"execution":{"iopub.status.busy":"2026-03-27T10:33:36.811778Z","iopub.execute_input":"2026-03-27T10:33:36.812284Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"y_pred=model.predict(x_test)\ny_test = np.argmax(y_pred,axis=1)\nprint(y_test.shape)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"sample = pd.read_csv(\"../input/digit-recognizer/sample_submission.csv\")\ni = sample.ImageId\n\noutput = pd.DataFrame({'ImageId' : i,'Label': y_test})\noutput.head(20)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"display(x_test[18])","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"output.to_csv('submission.csv', index=False)","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}