{"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 the files in the input directory\n\nimport os\nprint(os.listdir(\"../input\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"from keras.models import Sequential, load_model\nfrom keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPool2D\nfrom keras.optimizers import Adam, RMSprop\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.callbacks import ReduceLROnPlateau\n\n\ndef model_cnn():\n\n    ###  Model Definition\n    model = Sequential()\n    model.add(Conv2D(filters=32, kernel_size=(5, 5), padding='Valid', activation='relu', input_shape=(28, 28, 1)))\n    model.add(Conv2D(filters=32, kernel_size=(3, 3), padding='Same', activation='relu'))\n    model.add(MaxPool2D(pool_size=(2, 2)))\n    model.add(Dropout(0.2))\n\n    model.add(Conv2D(filters=64, kernel_size=(5, 5), padding='Valid', activation='relu'))\n    model.add(Conv2D(filters=64, kernel_size=(3, 3), padding='Same', activation='relu'))\n    model.add(MaxPool2D(pool_size=(2, 2), strides=(2, 2)))\n    model.add(Dropout(0.2))\n\n    model.add(Flatten())\n    model.add(Dense(519, activation=\"relu\"))  \n    model.add(Dropout(0.5))\n    model.add(Dense(10, activation=\"softmax\"))\n\n    model.compile(loss='categorical_crossentropy', optimizer=Adam(lr=1e-3), metrics=[\"accuracy\"])\n\n    annealer = ReduceLROnPlateau(monitor='val_acc', patience=1, verbose=2, factor=0.5, min_lr=0.0000001) #patience=2\n\n    datagen = 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\n    return model, annealer, datagen","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\nfrom sklearn.model_selection import ShuffleSplit\nfrom sklearn.metrics import accuracy_score, confusion_matrix\nfrom keras.utils.np_utils import to_categorical\n\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv(\"../input/train.csv\")\nprint(train.shape)\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y = train[\"label\"]\nX = train.drop(\"label\", axis = 1)\nprint(y.value_counts().to_dict())\ny = to_categorical(y, num_classes = 10)\ndel train\n\nX = X / 255.0\nX = X.values.reshape(-1,28,28,1)\n\n# Shuffle Split Train and Test from original dataset\nseed=2\ntrain_index, valid_index = ShuffleSplit(n_splits=1,\n                                        train_size=0.9,\n                                        test_size=None,\n                                        random_state=seed).split(X).__next__()\nx_train = X[train_index]\nY_train = y[train_index]\nx_test = X[valid_index]\nY_test = y[valid_index]\n\n# Parameters\nepochs = 30\nbatch_size = 64\nvalidation_steps = 10000\n\n# initialize Model, Annealer and Datagen\nmodel, annealer, datagen = model_cnn()\n\n# Start training\ntrain_generator = datagen.flow(x_train, Y_train, batch_size=batch_size)\ntest_generator = datagen.flow(x_test, Y_test, batch_size=batch_size)\n\nhistory = model.fit_generator(train_generator,\n                    steps_per_epoch=x_train.shape[0]//batch_size,\n                    epochs=epochs,\n                    validation_data=test_generator,\n                    validation_steps=validation_steps//batch_size,\n                    callbacks=[annealer])\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Saving Model for future API\nmodel.save('keras_cnn.h5')\n\nplt.plot(history.history['acc'])\nplt.plot(history.history['val_acc'])\nplt.title('model accuracy')\nplt.ylabel('accuracy')\nplt.xlabel('epoch')\nplt.legend(['train', 'test'], loc='lower right')\nplt.show()\n\nplt.plot(history.history['loss'])\nplt.plot(history.history['val_loss'])\nplt.title('model loss')\nplt.ylabel('loss')\nplt.xlabel('epoch')\nplt.legend(['train', 'test'], loc='upper right')\nplt.show()\n\n\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"## Model predict\ntest = pd.read_csv(\"../input/test.csv\")\nprint(test.shape)\ntest = test / 255\ntest = test.values.reshape(-1, 28, 28, 1)\np = np.argmax(model.predict(test), axis=1)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"valid_loss, valid_acc = model.evaluate(x_test, Y_test, verbose=0)\nvalid_p = np.argmax(model.predict(x_test), axis=1)\ntarget = np.argmax(Y_test, axis=1)\ncm = confusion_matrix(target, valid_p)\nprint(cm)\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.DataFrame(pd.Series(range(1, p.shape[0] + 1), name='ImageId'))\nsubmission['Label'] = p\nfilename=\"keras-cnn.csv\"\nsubmission.to_csv(filename, index=False)","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}