{"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\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\n\nimport tensorflow as tf\nfrom tensorflow import keras\nDNN_callback = keras.callbacks.TensorBoard(log_dir=\"logs\\\\DNN\")\nCNN_callback = keras.callbacks.TensorBoard(log_dir=\"logs\\\\DNN\")","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train = pd.read_csv(\"../input/digit-recognizer/train.csv\")\ntest = pd.read_csv(\"../input/digit-recognizer/test.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"val = train[-9000:]\ntrain = train[:-9000]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train = train.drop(columns=\"label\")\ny_train = train.label\nx_val = val.drop(columns=\"label\")\ny_val = val.label\ny_train = keras.utils.to_categorical(y_train)\ny_val = keras.utils.to_categorical(y_val)\nx_val = x_val.values\nx_train = x_train.values","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def logical_regression(x_train, x_valid, y_train, y_valid, callback):\n    model = tf.keras.models.Sequential()\n    model.add(tf.keras.layers.Dense(10, activation=\"softmax\", input_shape=(784,)))\n    model.compile(loss=\"categorical_crossentropy\", optimizer=\"SGD\", metrics=[\"accuracy\"])\n    model.fit(x_train, y_train, epochs=10, verbose=1, validation_data=(x_valid, y_valid), callbacks=[callback])\n    return model\n\n\ndef dense_neural_network(x_train, x_valid, y_train, y_valid, callback):\n    model = tf.keras.models.Sequential()\n    model.add(tf.keras.layers.Dense(256, activation=\"relu\", input_shape=(784,)))\n    model.add(tf.keras.layers.Dense(10, activation=\"softmax\"))\n    model.compile(loss=\"categorical_crossentropy\", optimizer=\"Adam\", metrics=[\"accuracy\"])\n    model.summary()\n    model.fit(x_train, y_train, epochs=10, verbose=1, validation_data=(x_valid, y_valid), callbacks=[callback])\n    return model\n\n\ndef convolutional_neural_network(x_train, x_valid, y_train, y_valid, callback, batch_normalization=False):\n\n    # Reshaping data\n    x_train = x_train.reshape(33000, 28, 28, 1)\n    x_valid = x_valid.reshape(9000, 28, 28, 1)\n\n    model = tf.keras.models.Sequential()\n    model.add(tf.keras.layers.Convolution2D(filters=32, kernel_size=3, activation=\"relu\", input_shape=(28, 28, 1)))\n    if batch_normalization:\n        model.add(tf.keras.layers.BatchNormalization())\n    model.add(tf.keras.layers.MaxPooling2D(pool_size=2))\n    model.add(tf.keras.layers.Convolution2D(filters=64, kernel_size=3, activation=\"relu\"))\n    if batch_normalization:\n        model.add(tf.keras.layers.BatchNormalization())\n    model.add(tf.keras.layers.MaxPooling2D(pool_size=2))\n    model.add(tf.keras.layers.Flatten())\n    model.add(tf.keras.layers.Dense(64, activation=\"relu\"))\n    model.add(tf.keras.layers.Dense(10, activation=\"softmax\"))\n    model.compile(loss=\"categorical_crossentropy\", optimizer=\"Adam\", metrics=[\"accuracy\"])\n    model.summary()\n    model.fit(x_train, y_train, epochs=10, verbose=1, validation_data=(x_valid, y_valid), callbacks=[callback])\n    return model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"dense_nn = dense_neural_network(x_train=x_train, x_valid=x_val, y_train=y_train, y_valid=y_val, callback=DNN_callback)\nconv_nn = convolutional_neural_network(x_train=x_train, x_valid=x_val, y_train=y_train, y_valid=y_val, callback=CNN_callback)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predictions = conv_nn.predict(test.values.reshape(28000, 28, 28, 1))\npredictions = [np.argmax(p) for p in predictions]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test[\"ImageId\"] = test.index + 1\ntest[\"Label\"] = predictions","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test.to_csv(\"result.csv\", columns = [\"ImageId\", \"Label\"], index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test","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":4}