{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"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 in \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 \"../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# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Load train data"},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train_data = pd.read_csv(\"../input/Kannada-MNIST/train.csv\")\ntrain_data.shape","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Visualise train data"},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\n\nshow_exmpl = train_data.values[:8, :-1]\nplt.figure(1, figsize=(14, 7))\nfor i in range(8):\n    plt.subplot(2, 4, i + 1)\n    plt.imshow(show_exmpl[i].reshape((28, 28)), cmap='gray')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Divide to train and validate data"},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train_test = train_data.values[:, 1:]\ny_train_test = train_data.label.values\n\nind = np.random.permutation(X_train_test.shape[0])\nX_train_test = X_train_test[ind]\ny_train_test = y_train_test[ind]\n\nvalidate_size = int(0.2 * X_train_test.shape[0])\nX_train, X_test = X_train_test[validate_size:], X_train_test[:validate_size]\ny_train, y_test = y_train_test[validate_size:], y_train_test[:validate_size]\n\nprint('Train shapes: ', X_train.shape, y_train.shape)\nprint('Test shapes: ', X_test.shape, y_test.shape)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Data normalization"},{"metadata":{"trusted":true},"cell_type":"code","source":"print(np.min(X_train), np.max(X_train))\nX_train_max = np.max(X_train)\nX_train = X_train / (0.5 * X_train_max) - 1\nprint(np.min(X_train), np.max(X_train))\n\nprint(np.min(X_test), np.max(X_test))\nX_test = X_test / (0.5 * X_train_max) - 1 \nprint(np.min(X_test), np.max(X_test))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Simple CNN with SGD Optimizer"},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.layers import *\nfrom keras.models import Sequential","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Sequential()\n\nmodel.add(Conv2D(64, kernel_size=3, activation='relu', input_shape=(28, 28, 1),padding='same'))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(64, kernel_size=3, activation='relu',padding='same'))\nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\nmodel.add(Dropout(0.7))\n\nmodel.add(Conv2D(128, kernel_size=3, activation='relu',padding='same'))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(128, kernel_size=3, activation='relu',padding='same'))\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\nmodel.add(Dropout(0.7))\n\nmodel.add(Flatten())\nmodel.add(Dense(128))\nmodel.add(BatchNormalization())\nmodel.add(Dropout(0.7))\nmodel.add(Dense(10, activation='softmax'))\n\nmodel.compile(optimizer ='sgd',\n              loss = 'sparse_categorical_crossentropy',\n              metrics=['accuracy'])\n\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.callbacks import CSVLogger, ModelCheckpoint","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = X_train.reshape(X_train.shape[0],28,28,1)\nX_test = X_test.reshape(X_test.shape[0],28,28,1)\n\nmodel.fit(X_train, y_train,\n          epochs=25,\n          verbose=1,\n          validation_data=(X_test, y_test),\n          callbacks=[\n              ModelCheckpoint('/kaggle/working/best_kannada_model.h5', save_best_only=True),\n              CSVLogger('/kaggle/working/learning_log.csv'),\n          ])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Submission"},{"metadata":{"trusted":true},"cell_type":"code","source":"test_csv = pd.read_csv(\"../input/Kannada-MNIST/test.csv\")\nX_val = np.array(test_csv.drop(\"id\",axis=1), dtype=np.float32)\nX_val.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_val_max = np.max(X_val)\nX_val = X_val / (0.5 * X_val_max) - 1\nX_val = np.reshape(X_val, (-1,28,28,1))\n\nprint(X_val.shape, np.min(X_val), np.max(X_val))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.models import load_model\n\nbest_model = load_model('/kaggle/working/best_kannada_model.h5')\nY_val = best_model.predict(X_val)\nY_val = np.argmax(Y_val, axis = 1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.read_csv(\"../input/Kannada-MNIST/sample_submission.csv\")\nsubmission['label'] = Y_val\nsubmission.to_csv(\"submission.csv\",index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":1}