{"cells":[{"metadata":{"trusted":true,"_kg_hide-output":true},"cell_type":"code","source":"# pandas version should be >= 0.24.1\n!pip install --upgrade pandas","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nfrom sklearn.model_selection import train_test_split\nfrom keras.utils.np_utils import to_categorical\nfrom keras import models, layers, optimizers\nfrom keras.models import Sequential\nfrom keras.layers import Dense, Activation, Conv2D, Flatten, MaxPool2D, Dropout\nfrom keras.optimizers import Adam\nfrom keras import backend as K\n\nprint('Pandas version: ' + pd.__version__)\nprint(K.tensorflow_backend._get_available_gpus())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv('../input/train.csv')\ntest = pd.read_csv('../input/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y = train['label'].to_numpy().reshape((train.shape[0], 1))\ny = to_categorical(y, num_classes=10)\n\ndel train['label']\nX = train.to_numpy()\n\npred = test.to_numpy().reshape((-1, 28, 28, 1)) / 255.0","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.15)\n\nX_train = X_train / 255.0\nX_test = X_test / 255.0\n\nX_train = X_train.reshape((-1, 28, 28, 1))\nX_test = X_test.reshape((-1, 28, 28, 1))","execution_count":null,"outputs":[]},{"metadata":{"scrolled":false,"trusted":true},"cell_type":"code","source":"model = Sequential()\n\nmodel.add(Conv2D(32, kernel_size=(5, 5), input_shape=(X_train.shape[1:]), activation='tanh'))\nmodel.add(Conv2D(32, kernel_size=(5, 5), activation='tanh'))\nmodel.add(Dropout(0.2))\n# model.add(MaxPool2D(pool_size=(2, 2)))\n\nmodel.add(Conv2D(64, kernel_size=(3, 3), activation='tanh'))\nmodel.add(Conv2D(64, kernel_size=(3, 3), activation='tanh'))\nmodel.add(Dropout(0.2))\n# model.add(MaxPool2D(pool_size=(2, 2)))\n\nmodel.add(Flatten())\nmodel.add(Dense(512, activation='tanh'))\nmodel.add(Dense(128, activation='tanh'))\n# model.add(Dense(64, activation='tanh'))\nmodel.add(Dense(10, activation='softmax'))\n\nadam = Adam(lr=0.001)\nmodel.compile(optimizer='rmsprop', loss='categorical_crossentropy', metrics=['accuracy'])\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"scrolled":true,"trusted":true},"cell_type":"code","source":"model.fit(X_train, y_train, epochs=50)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.evaluate(X_test, y_test, verbose=0)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predictions = np.argmax(model.predict(pred), axis=-1)\npredictions = predictions.reshape((predictions.shape[0], 1))\nsubmission = pd.DataFrame({'ImageId':[i for i in range(1, predictions.shape[0] +1)], 'Label':predictions[:,0]})\nsubmission.to_csv('submission.csv', index=False)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"<a href=\"./submission.csv\">Download submission.csv</a>"},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.6.8"}},"nbformat":4,"nbformat_minor":1}