{"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":"train_data = pd.read_csv('/kaggle/input/Kannada-MNIST/train.csv')\ntest_data = pd.read_csv(\"/kaggle/input/Kannada-MNIST/test.csv\")\nDig_MNIST = pd.read_csv(\"/kaggle/input/Kannada-MNIST/Dig-MNIST.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(train_data.shape)\nprint(test_data.shape)\nprint(Dig_MNIST.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#训练集数据\ntrain=train_data.iloc[:,1:].values\ntrain_label=train_data.iloc[:,0].values\nprint(\"训练数据shape：\",train.shape)\nprint(\"标签数据shape\",train_label.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#对训练数据进行预处理\ntrain=train.reshape(train.shape[0],28,28,1)\nprint(\"训练数据shape:\",train.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import tensorflow as tf\nfrom sklearn.model_selection import train_test_split\nimport keras\ntrain_label=keras.utils.to_categorical(train_label,10)\nprint(\"标签shape:\",train_label.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#测试数据\ntest=test_data.drop('id',axis=1).iloc[:,:].values\ntest=test.reshape(test.shape[0],28,28,1)\nprint(\"测试数据shape:\",test.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#验证数据\nvalid=Dig_MNIST.drop('label',axis=1).iloc[:,:].values\nprint(\"验证数据shape\",valid.shape)\nvalid = valid.reshape(valid.shape[0], 28, 28,1)\nprint(\"reshape后的shape:\",valid.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#valid标签\nvalid_label=Dig_MNIST.label\nprint(\"标签数据shape:\",valid_label.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train,X_valid,y_train,y_valid=train_test_split(train,train_label,test_size=0.1,random_state=42)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(X_train.shape)\nprint(X_valid.shape)\nprint(y_train.shape)\nprint(y_valid.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\nplt.imshow(X_train[5][:,:,0])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.models import Sequential\nfrom keras.layers import Dense,Conv2D,Flatten,MaxPool2D,Dropout,BatchNormalization","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#模型的构建\nmodel = Sequential()\nmodel.add(Conv2D(filters = 32, kernel_size = (5,5),padding = 'Same', \n                 activation ='relu', input_shape = (28,28,1)))\nmodel.add(Conv2D(filters = 32, kernel_size = (5,5),padding = 'Same', \n                 activation ='relu'))\nmodel.add(BatchNormalization(momentum=.15))\nmodel.add(MaxPool2D(pool_size=(2,2)))\nmodel.add(Dropout(0.25))\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(BatchNormalization(momentum=0.15))\nmodel.add(MaxPool2D(pool_size=(2,2), strides=(2,2)))\nmodel.add(Dropout(0.25))\n\n\nmodel.add(Conv2D(filters = 32, kernel_size = (5,5),padding = 'Same', \n                 activation ='relu', input_shape = (28,28,1)))\nmodel.add(Conv2D(filters = 32, kernel_size = (5,5),padding = 'Same', \n                 activation ='relu'))\nmodel.add(BatchNormalization(momentum=.15))\nmodel.add(MaxPool2D(pool_size=(2,2)))\nmodel.add(Dropout(0.25))\nmodel.add(Flatten())\nmodel.add(Dense(256, activation = \"relu\"))\nmodel.add(Dropout(0.4))\nmodel.add(Dense(10, activation = \"softmax\"))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.optimizers import RMSprop\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.callbacks import ReduceLROnPlateau\n\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},"cell_type":"code","source":"optimizer=RMSprop(lr=0.001,rho=0.9,decay=0.0)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(optimizer=optimizer,loss=['categorical_crossentropy'],metrics=['accuracy'])","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)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"epochs=30\nbatch_size=64","execution_count":null,"outputs":[]},{"metadata":{"trusted":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_valid,y_valid),\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":"model.evaluate(X_train,y_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"my_predicted=model.predict(test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"my_predicted","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_pre=my_predicted.astype(int)\ny_pre=np.argmax(y_pre,axis=-1)\ny_pre","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"sub=pd.read_csv('../input/Kannada-MNIST/sample_submission.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub['label']=y_pre","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub.to_csv('submission.csv',index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub.head(20)","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}