{"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)\nimport matplotlib.pyplot as plt\n%matplotlib inline\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 5GB 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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import pandas as pd\nimport numpy as np\n\nimport matplotlib.pyplot as plt\n\nfrom sklearn.model_selection import train_test_split\n\nfrom keras.models import Sequential\nfrom keras.utils.np_utils import to_categorical\nfrom keras.callbacks import LearningRateScheduler\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPool2D, AvgPool2D, BatchNormalization, Reshape\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv(\"/kaggle/input/digit-recognizer/train.csv\")\ntest = pd.read_csv(\"/kaggle/input/digit-recognizer/test.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Y_train = train[\"label\"]\nX_train = train.drop(labels = [\"label\"], axis = 1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = X_train / 255.0\nX_test = test / 255.0","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = X_train.values.reshape(-1, 28, 28, 1)\nX_test = X_test.values.reshape(-1, 28, 28, 1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Y_train = to_categorical(Y_train, num_classes = 10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"datagen = ImageDataGenerator(\n        rotation_range = 5,  \n        zoom_range = 0.05,  \n        width_shift_range = 0.05, \n        height_shift_range = 0.05)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Sequential()\n\n# 2D convolutional layer\nmodel.add(Conv2D(64,kernel_size=3, activation='relu', input_shape=(28,28,1)))\n# batch normalization layer\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(64,kernel_size=3, activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(64,kernel_size=5, strides=2, padding='same', activation='relu'))\nmodel.add(BatchNormalization())\n# dropout layer\nmodel.add(Dropout(0.45))\n\nmodel.add(Conv2D(128, kernel_size=3, activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(128, kernel_size=3, activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(128, kernel_size=5, strides=2, padding='same' ,activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Dropout(0.45))\n\n# Flattens input\nmodel.add(Flatten())\n# fully connected layer\nmodel.add(Dense(256, activation ='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Dropout(0.45))\nmodel.add(Dense(10, activation='softmax'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(optimizer=\"adam\", loss=\"categorical_crossentropy\", metrics=[\"accuracy\"])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train, X_val, Y_train, Y_val = train_test_split(X_train, Y_train, test_size = 0.2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history = model.fit_generator(datagen.flow(X_train, Y_train, batch_size=64), \n    epochs = 45, validation_data = (X_val, Y_val), verbose=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predictions = model.predict(X_test)\n\npredictions = np.argmax(predictions, axis = 1)\n\npredictions = pd.Series(predictions, name = \"Label\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.concat([pd.Series(range(1, 28001), name = \"ImageId\"), predictions], axis = 1)\n\nsubmission.to_csv(\"MNIST_top_CNN_submission.csv\", index = False)","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}