{"cells":[{"metadata":{"trusted":true,"collapsed":true,"_uuid":"d90504f8bd07fad707ccb3565e82f0982ea0b596"},"cell_type":"code","source":"# -*- coding: utf-8 -*-\nimport numpy as np\nimport pandas as pd\nfrom keras.models import Sequential  # https://keras.io/ja/getting-started/sequential-model-guide/\nfrom keras.layers import Dense,  Dropout, Lambda, Flatten\nfrom keras.optimizers import Adam, RMSprop\nfrom keras.optimizers import RMSprop, Adam, Adamax, Nadam\nfrom keras.utils.np_utils import to_categorical\nfrom keras.models import Sequential\nfrom keras.layers import Dense, Dropout, Conv2D, MaxPooling2D, Flatten, MaxPool2D\nfrom keras.callbacks import ReduceLROnPlateau\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom sklearn.model_selection import train_test_split\nimport seaborn as sns\nimport matplotlib\nimport matplotlib.pyplot as plt\nimport matplotlib.image as mpimg\n\n%matplotlib inline \nsns.set(style='white', context='notebook', palette='deep')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"62daf92af855bf5098db6e00c4a5b3e29faa059e","collapsed":true},"cell_type":"code","source":"# データ読み込み\ntrain = pd.read_csv(\"../input/train.csv\")\ntest = pd.read_csv(\"../input/test.csv\")\n\nY_train = train[\"label\"]  # ラベルだけ\nX_train = train.drop(labels = [\"label\"], axis = 1)  # ラベルを削除\n\ng = sns.countplot(Y_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"340188e57a45cd29a2e23a913c32bbba33561cbb","scrolled":true,"collapsed":true},"cell_type":"code","source":"# [0...255]の値を[0.0...1.0]にする\nX_train = X_train / 255.0\ntest = test / 255.0","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"7ed1727391226de47d48df25e1ac9542fddb2e52","collapsed":true},"cell_type":"code","source":"# 28x28x1の3Dマトリックスにする\nX_train = X_train.values.reshape(-1,28,28,1)\ntest = test.values.reshape(-1,28,28,1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"collapsed":true,"_uuid":"bd9fba99882376a2fc35f7b34bf00375cee11195"},"cell_type":"code","source":"# 0〜9までのラベルをバイナリのクラス行列に変換\n# 例: 2 -> [0,0,1,0,0,0,0,0,0,0]\n# https://keras.io/ja/utils/np_utils/\nY_train = to_categorical(Y_train, num_classes = 10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"06bb6e3e18242f0798f3cbcb07139dbf52c6c1aa","collapsed":true},"cell_type":"code","source":"# 訓練用データと検証用データに分割\nrandom_seed = 2\nX_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,"_uuid":"477719bba483b75e15e7bed8a82ca66501177abb","collapsed":true},"cell_type":"code","source":"# CNNモデル\nmodel = Sequential()\nmodel.add(Conv2D(filters = 32, kernel_size = (5,5),padding = 'Same',  activation ='relu', input_shape = (28,28,1)))\nmodel.add(Conv2D(filters = 32, kernel_size = (5,5),padding = 'Same', activation ='relu'))\nmodel.add(MaxPool2D(pool_size=(2,2)))\nmodel.add(Dropout(0.25))\nmodel.add(Conv2D(filters = 64, kernel_size = (3,3),padding = 'Same', activation ='relu'))\nmodel.add(Conv2D(filters = 64, kernel_size = (3,3),padding = 'Same',  activation ='relu'))\nmodel.add(MaxPool2D(pool_size=(2,2), strides=(2,2)))\nmodel.add(Dropout(0.25))\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,"collapsed":true,"_uuid":"3dfbb5718124362d74f412ff42640d8a491a7c9d"},"cell_type":"code","source":"# オプティマイザ定義\n# https://keras.io/ja/optimizers/#rmsprop\noptimizer = RMSprop(lr=0.001, rho=0.9, epsilon=1e-08, decay=0.0)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"collapsed":true,"_uuid":"74a69be7cfb6e3928789529dc4ea0c06a47949e3"},"cell_type":"code","source":"# モデルのコンパイル\n# 損失関数 https://keras.io/ja/losses/#categorical_crossentropy\nmodel.compile(optimizer = optimizer , loss = \"categorical_crossentropy\", metrics=[\"accuracy\"])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"collapsed":true,"_uuid":"70ddad9ed26e8122c21f2002ff8d57c7127f0f4d"},"cell_type":"code","source":"# https://keras.io/ja/callbacks/#reducelronplateau\n# 評価値の改善が止まったときに学習率をへらす\n# monitor: 監視する値\n# patienceで指定したエポック数の間改善がなければ学習率をfactor下げる\n# verbose=1 学習率を下げたときにメッセージ表示\n# min_lr: 学習率の下限\nlearning_rate_reduction = ReduceLROnPlateau(monitor='val_acc', \n                                            patience=3, \n                                            verbose=1, \n                                            factor=0.5, \n                                            min_lr=0.00001)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"collapsed":true,"_uuid":"914093ca4d9c20a1b37591473bf7d6ecd9a6ec64"},"cell_type":"code","source":"epochs = 10\nbatch_size = 86","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"560e6ce2329c9a7f5572004b73b64474cbbe400f","collapsed":true},"cell_type":"code","source":"# https://keras.io/ja/preprocessing/image/#imagedatagenerator\ndatagen = ImageDataGenerator(\n        featurewise_center=False,  # set input mean to 0 over the dataset\n        samplewise_center=False,  # set each sample mean to 0\n        featurewise_std_normalization=False,  # divide inputs by std of the dataset\n        samplewise_std_normalization=False,  # divide each input by its std\n        zca_whitening=False,  # apply ZCA whitening\n        rotation_range=10,  # randomly rotate images in the range (degrees, 0 to 180)\n        zoom_range = 0.1, # Randomly zoom image \n        width_shift_range=0.1,  # randomly shift images horizontally (fraction of total width)\n        height_shift_range=0.1,  # randomly shift images vertically (fraction of total height)\n        horizontal_flip=False,  # randomly flip images\n        vertical_flip=False)  # randomly flip images\n\n\ndatagen.fit(X_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"245f20f2bcd114aa327a583d8ff9cd9722db86b3","collapsed":true},"cell_type":"code","source":"history = model.fit_generator(datagen.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,"_uuid":"d33e5256133850fe0a39685f69382b1e439af674","collapsed":true},"cell_type":"code","source":"# predict results\nresults = model.predict(test)\n\n# select the indix with the maximum probability\nresults = np.argmax(results,axis = 1)\n\nresults = pd.Series(results,name=\"Label\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"collapsed":true,"_uuid":"3354e76a9fe8367fb12d03ba079f03c09a2a0274"},"cell_type":"code","source":"submission = pd.concat([pd.Series(range(1,28001),name = \"ImageId\"),results],axis = 1)\n\nsubmission.to_csv(\"cnn_mnist_datagen.csv\",index=False)","execution_count":null,"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}