{"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":{"trusted":true},"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport matplotlib.image as mpimg\nimport seaborn as sns\n%matplotlib inline\n\n\n\nnp.random.seed(2)   #the random block of the validation set data to be always the same\n\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import confusion_matrix\nimport itertools\n\nfrom keras.utils.np_utils import to_categorical\nfrom keras.models import Sequential\nfrom keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPool2D\nfrom keras.optimizers import RMSprop\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.callbacks import ReduceLROnPlateau\n\nimport warnings\nwarnings.filterwarnings(\"ignore\")","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","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\"]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = train.drop(labels = [\"label\"],axis = 1) ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Y_train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train.isnull().any().describe()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = X_train.values.reshape(-1,28,28,1)\ntest = test.values.reshape(-1,28,28,1)\nY_train = to_categorical(Y_train, num_classes = 10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"random_seed = 4","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 = 0.1, random_state=random_seed)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Sequential()\n\nmodel.add(Conv2D(filters = 32, kernel_size = (5,5),padding = 'Same', \n                 activation ='relu', input_shape = (28,28,1)))\n\nmodel.add(Conv2D(filters = 64, kernel_size = (5,5),padding = 'Same', \n                 activation ='relu'))\nmodel.add(Conv2D(filters = 128, kernel_size = (5,5),padding = 'Same', \n                 activation ='relu'))\n\nmodel.add(Conv2D(filters = 64, kernel_size = (5,5),padding = 'Same', \n                 activation ='relu'))\n\nmodel.add(Conv2D(filters = 32, kernel_size = (5,5),padding = 'Same', \n                 activation ='relu'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.add(MaxPool2D(pool_size=(2,2)))\nmodel.add(Dropout(0.25))\n\n\nmodel.add(Conv2D(filters = 64, kernel_size = (3,3),padding = 'Same', \n                 activation ='relu'))\nmodel.add(Conv2D(filters = 64, kernel_size = (3,3),padding = 'Same', \n                 activation ='relu'))\nmodel.add(MaxPool2D(pool_size=(2,2), strides=(2,2)))\nmodel.add(Dropout(0.25))\n\n\nmodel.add(Flatten())\nmodel.add(Dense(256, activation = \"relu\"))\nmodel.add(Dropout(0.5))\nmodel.add(Dense(10, activation = \"softmax\"))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"g1 = plt.imshow(X_train[0][:,:,0])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"g2 = plt.imshow(X_train[1][:,:,0])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"g3 = plt.imshow(X_train[3][:,:,0])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"g4 = plt.imshow(X_train[4][:,:,0])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"optimizer = RMSprop(lr=0.001, rho=0.9, epsilon=1e-08, decay=0.0)\n\nmodel.compile(optimizer = optimizer , loss = \"categorical_crossentropy\", metrics=[\"accuracy\"])\n\nmodel.compile","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learning_rate_reduction = ReduceLROnPlateau(monitor='val_acc', \n                                            patience=3, \n                                            verbose=1, \n                                            factor=0.5, \n                                            min_lr=0.00001)\n\nepochs = 1 \nbatch_size = 86","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data_overfitting = ImageDataGenerator(\n        featurewise_center=False,  \n        samplewise_center=False,  \n        featurewise_std_normalization=False,  \n        samplewise_std_normalization=False,  \n        zca_whitening=False, \n        rotation_range=10,  \n        zoom_range = 0.1, \n        width_shift_range=0.1, \n        height_shift_range=0.1, \n        horizontal_flip=False, \n        vertical_flip=False)\n\ndata_overfitting.fit(X_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fitmodel = model.fit_generator(data_overfitting.flow(X_train,Y_train, batch_size=batch_size),\n                              epochs = epochs, validation_data = (X_val,Y_val),\n                              verbose = 2, steps_per_epoch=X_train.shape[0] // batch_size\n                              , callbacks=[learning_rate_reduction])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"results = model.predict(test)\nresults = np.argmax(results,axis = 1)\nresults = pd.Series(results,name=\"Label\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"results","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"result = pd.concat([pd.Series(range(1,len(test)+1),name = \"ImageId\"),results],axis = 1)\n\nresult.to_csv(\"predicted_digit_recognizer.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":4}