{"cells":[{"metadata":{"_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","_kg_hide-input":false,"_kg_hide-output":false,"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","collapsed":true,"trusted":true},"cell_type":"code","source":"import numpy as np # linear algebra\nimport matplotlib.pyplot as plt\n%matplotlib inline\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import confusion_matrix","execution_count":29,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_kg_hide-input":true,"_kg_hide-output":true,"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true,"collapsed":true},"cell_type":"code","source":"from keras.utils.np_utils import to_categorical # convert to one-hot-encoding\nfrom keras.models import Sequential\nfrom keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPool2D, BatchNormalization\nfrom keras.optimizers import Adam\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.callbacks import LearningRateScheduler","execution_count":30,"outputs":[]},{"metadata":{"collapsed":true,"trusted":true,"_uuid":"a30396d04122eb176683d469eb314e32d9f1e0cf"},"cell_type":"code","source":"train_file = \"../input/train.csv\"\ntest_file = \"../input/test.csv\"\noutput_file = \"submission.csv\"","execution_count":31,"outputs":[]},{"metadata":{"collapsed":true,"trusted":true,"_uuid":"a784be5c7d59d2af0afad123c4e5739eed1daca1"},"cell_type":"code","source":"raw_data = np.loadtxt(train_file, skiprows=1, dtype='int', delimiter=',')\nx_train, x_val, y_train, y_val = train_test_split(raw_data[:,1:], raw_data[:,0], test_size=0.1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"1ea9520a6d4ccdd52f59d7a4ae2153aaada14416"},"cell_type":"code","source":"fig, ax = plt.subplots(2, 1, figsize=(12,6))\nax[0].plot(x_train[0])\nax[0].set_title('784x1 data')\nax[1].imshow(x_train[0].reshape(28,28), cmap='gray')\nax[1].set_title('28x28 data')","execution_count":12,"outputs":[]},{"metadata":{"collapsed":true,"trusted":true,"_uuid":"2ec1c731e1707726e751432da080b22bf2c6006b"},"cell_type":"code","source":"x_train = x_train.reshape(-1, 28, 28, 1)\nx_val = x_val.reshape(-1, 28, 28, 1)","execution_count":13,"outputs":[]},{"metadata":{"collapsed":true,"trusted":true,"_uuid":"26a9fb277668adc0035c3bca9b54c86b5745e5b0"},"cell_type":"code","source":"x_train = x_train.astype(\"float32\")/255.\nx_val = x_val.astype(\"float32\")/255.","execution_count":14,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"f090032cdf42aebf4c016ad23b5898dcb425a1ff"},"cell_type":"code","source":"y_train = to_categorical(y_train)\ny_val = to_categorical(y_val)\n#example:\nprint(y_train[0])","execution_count":15,"outputs":[]},{"metadata":{"collapsed":true,"trusted":true,"_uuid":"ed2450bafad4d675be1ca393e101908516d7402f"},"cell_type":"code","source":"model = Sequential()\n\nmodel.add(Conv2D(filters = 16, kernel_size = (3, 3), activation='relu',\n                 input_shape = (28, 28, 1)))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(filters = 16, kernel_size = (3, 3), activation='relu'))\nmodel.add(BatchNormalization())\n#model.add(Conv2D(filters = 16, kernel_size = (3, 3), activation='relu'))\n#model.add(BatchNormalization())\nmodel.add(MaxPool2D(strides=(2,2)))\nmodel.add(Dropout(0.25))\n\nmodel.add(Conv2D(filters = 32, kernel_size = (3, 3), activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(filters = 32, kernel_size = (3, 3), activation='relu'))\nmodel.add(BatchNormalization())\n#model.add(Conv2D(filters = 32, kernel_size = (3, 3), activation='relu'))\n#model.add(BatchNormalization())\nmodel.add(MaxPool2D(strides=(2,2)))\nmodel.add(Dropout(0.25))\n\nmodel.add(Flatten())\nmodel.add(Dense(512, activation='relu'))\nmodel.add(Dropout(0.25))\nmodel.add(Dense(1024, activation='relu'))\nmodel.add(Dropout(0.5))\nmodel.add(Dense(10, activation='softmax'))","execution_count":16,"outputs":[]},{"metadata":{"collapsed":true,"trusted":true,"_uuid":"cb246b9e3861428572329012933db6486e25af08"},"cell_type":"code","source":"datagen = ImageDataGenerator(zoom_range = 0.1,\n                            height_shift_range = 0.1,\n                            width_shift_range = 0.1,\n                            rotation_range = 10)","execution_count":17,"outputs":[]},{"metadata":{"collapsed":true,"trusted":true,"_uuid":"457216b91f458203b3f35e002ea4764123c7942d"},"cell_type":"code","source":"model.compile(loss='categorical_crossentropy', optimizer = Adam(lr=1e-4), metrics=[\"accuracy\"])","execution_count":18,"outputs":[]},{"metadata":{"collapsed":true,"trusted":true,"_uuid":"b34ed20134d3abe9a02b987bba50bd789ee6ed74"},"cell_type":"code","source":"annealer = LearningRateScheduler(lambda x: 1e-3 * 0.9 ** x)","execution_count":19,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"912435f28ad38fe0937fff1e79e18ff989ee4ea2"},"cell_type":"code","source":"hist = model.fit_generator(datagen.flow(x_train, y_train, batch_size=16),\n                           steps_per_epoch=500,\n                           epochs=20, #Increase this when not on Kaggle kernel\n                           verbose=2,  #1 for ETA, 0 for silent\n                           validation_data=(x_val[:400,:], y_val[:400,:]), #For speed\n                           callbacks=[annealer])","execution_count":20,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"06f1acba759da13c3027d85a07e94f649d339ac9"},"cell_type":"code","source":"final_loss, final_acc = model.evaluate(x_val, y_val, verbose=0)\nprint(\"Final loss: {0:.4f}, final accuracy: {1:.4f}\".format(final_loss, final_acc))","execution_count":21,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"0ffd9aeceeae2403575415e7d7a15d06b8c85bb4"},"cell_type":"code","source":"plt.plot(hist.history['loss'], color='b')\nplt.plot(hist.history['val_loss'], color='r')\nplt.show()\nplt.plot(hist.history['acc'], color='b')\nplt.plot(hist.history['val_acc'], color='r')\nplt.show()","execution_count":22,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"ba09fc243501b203fa9085e91bb90c69a32fd458"},"cell_type":"code","source":"y_hat = model.predict(x_val)\ny_pred = np.argmax(y_hat, axis=1)\ny_true = np.argmax(y_val, axis=1)\ncm = confusion_matrix(y_true, y_pred)\nprint(cm)","execution_count":23,"outputs":[]},{"metadata":{"collapsed":true,"trusted":true,"_uuid":"b333b3e28aa4a361d29df29d6940bd670f3e884a"},"cell_type":"code","source":"mnist_testset = np.loadtxt(test_file, skiprows=1, dtype='int', delimiter=',')\nx_test = mnist_testset.astype(\"float32\")\nx_test = x_test.reshape(-1, 28, 28, 1)/255.","execution_count":24,"outputs":[]},{"metadata":{"collapsed":true,"trusted":true,"_uuid":"f49e921411c5f8ea13087c84acd9e2537c17222b"},"cell_type":"code","source":"y_hat = model.predict(x_test, batch_size=64)","execution_count":26,"outputs":[]},{"metadata":{"collapsed":true,"trusted":true,"_uuid":"1cc9cd6d8eb1fa67cbb010d2d890cb857179f13c"},"cell_type":"code","source":"y_pred = np.argmax(y_hat,axis=1)","execution_count":27,"outputs":[]},{"metadata":{"collapsed":true,"trusted":true,"_uuid":"61399b79ba3cf04fa6c00b63bce1194e5890fcaf"},"cell_type":"code","source":"with open(output_file, 'w') as f :\n    f.write('ImageId,Label\\n')\n    for i in range(len(y_pred)) :\n        f.write(\"\".join([str(i+1),',',str(y_pred[i]),'\\n']))","execution_count":28,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.5","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}