{"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":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import pandas as pd\n\ndf_train = pd.read_csv(\"/kaggle/input/digit-recognizer/train.csv\")\ndf_test = pd.read_csv(\"/kaggle/input/digit-recognizer/test.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.models import Sequential\nfrom keras.layers.normalization import BatchNormalization\nfrom keras.layers.convolutional import Conv2D\nfrom keras.layers.convolutional import MaxPooling2D\nfrom keras.layers.core import Activation,Flatten,Dropout,Dense\nfrom keras import backend as K\nfrom keras.models import Sequential\nfrom keras.optimizers import SGD","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Sequential()\nmodel.add(Conv2D(32, (5, 5), input_shape=( 28, 28,1), activation='relu'))\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\nmodel.add(Conv2D(32, (3, 3), input_shape=( 28, 28,1), activation='relu'))\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\nmodel.add(Dropout(0.2))\nmodel.add(Flatten())\nmodel.add(Dense(128, activation='relu'))\nmodel.add(Dropout(0.5))\nmodel.add(Dense(10, activation='softmax', name='predict'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.utils.np_utils import to_categorical\nimport tensorflow as tf\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.optimizers import Adam\nfrom sklearn.model_selection import train_test_split\nfrom keras.preprocessing.image import img_to_array\nfrom keras.utils import to_categorical\nfrom sklearn.metrics import classification_report\nfrom sklearn.metrics import confusion_matrix\n\nimport matplotlib.pyplot as plt\nimport numpy as np\nimport argparse\nimport random\nimport cv2\nimport os\n\ntrainY = df_train[\"label\"]\ntrainX = df_train.drop(labels = [\"label\"],axis = 1) \ntrainX = trainX / 255.0\ndf_test = df_test / 255.0\ntrainX = trainX.values.reshape(-1,28,28,1)\ntrainY = to_categorical(trainY, num_classes = 10)\nrandom_seed = 42\n\ntrainX, X_val, trainY, Y_val = train_test_split(trainX, trainY, test_size = 0.2, random_state=random_seed)\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.optimizers import RMSprop\noptimizer = RMSprop(lr=0.001)\n# Compile the model\nmodel.compile(optimizer = optimizer , loss = \"categorical_crossentropy\", metrics=[\"accuracy\"])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"epochs = 10 \nbatch_size = 32\n\ndatagen = ImageDataGenerator(rotation_range=10, zoom_range = 0.1, width_shift_range=0.1, height_shift_range=0.1,horizontal_flip=False,   vertical_flip=False)  \ndatagen.fit(trainX)\nhistory = model.fit_generator(datagen.flow(trainX,trainY, batch_size=batch_size),\nepochs = epochs, validation_data = (X_val,Y_val), verbose = 2, steps_per_epoch=trainX.shape[0] // batch_size)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_test.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_test = df_test.values.reshape(-1,28,28,1)\nresults = model.predict(df_test)\n\nresults = np.argmax(results,axis = 1)\n\nresults = pd.Series(results,name=\"Label\")\n\nsubmission = pd.concat([pd.Series(range(1,28001),name = \"ImageId\"),results],axis = 1)\n\nsubmission.to_csv(\"cnn_mnist_datagen.csv\",index=False)\n\n","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}