{"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":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nfrom keras.utils import np_utils\nfrom keras.models import Sequential\nfrom keras.layers import Dense,Dropout,Conv2D,MaxPool2D,Flatten,BatchNormalization\nfrom keras.optimizers import Adam,Nadam\nfrom sklearn.model_selection import train_test_split\nfrom keras import regularizers\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom sklearn.utils import shuffle\nimport matplotlib.pyplot as plt ","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Load Data"},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv('/kaggle/input/Kannada-MNIST/train.csv')\ntest = pd.read_csv('/kaggle/input/Kannada-MNIST/test.csv')\nsubmission = pd.read_csv('/kaggle/input/Kannada-MNIST/sample_submission.csv')\ndisplay(train.shape,test.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Id = test['id']","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Data preprocessing"},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train, x_test, y_train, y_test = train_test_split(train.iloc[:, 1:], train.iloc[:, 0], test_size=0.05)\ndisplay(x_train.shape,y_train.shape,x_test.shape,y_test.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train, y_train = shuffle(x_train, y_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# (60000,784)->(60000,28,28,1)\nx_train = x_train.values.reshape(-1,28,28,1)/255.0\nx_test = x_test.values.reshape(-1,28,28,1)/255.0\n\ny_train = np_utils.to_categorical(y_train,num_classes=10)\ny_test = np_utils.to_categorical(y_test,num_classes=10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"imagegen = ImageDataGenerator(\n            rotation_range = 10,     \n            width_shift_range = 0.2, \n            height_shift_range = 0.2,         \n            shear_range = 20,       \n            zoom_range = 0.2  \n             )\nimagegen.fit(x_train)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"model"},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Sequential()\n\nmodel.add(Conv2D(input_shape=(28, 28, 1),filters=64, kernel_size=(3, 3), padding='SAME', activation='relu'))\nmodel.add(Conv2D(64, kernel_size=(3, 3), padding='SAME', activation='relu'))\nmodel.add(BatchNormalization(momentum=0.5))\nmodel.add(MaxPool2D(pool_size=(2, 2)))\nmodel.add(Dropout(0.2))\n\nmodel.add(Conv2D(filters=128, kernel_size=(3, 3), padding='SAME', activation='relu'))\nmodel.add(Conv2D(filters=128, kernel_size=(3, 3), padding='SAME', activation='relu'))\nmodel.add(BatchNormalization(momentum=0.5))\nmodel.add(MaxPool2D(pool_size=(2, 2)))\nmodel.add(Dropout(0.2))\n\nmodel.add(Conv2D(filters=256, kernel_size=(3, 3), padding='SAME', activation='relu'))\nmodel.add(Conv2D(filters=256, kernel_size=(3, 3), padding='SAME', activation='relu'))\nmodel.add(BatchNormalization(momentum=0.5))\nmodel.add(MaxPool2D(pool_size=(2, 2)))\nmodel.add(Dropout(0.2))\n\nmodel.add(Flatten())\nmodel.add(Dense(256, activation = \"relu\"))\nmodel.add(BatchNormalization())\nmodel.add(Dense(10, activation = \"softmax\"))\n\n\nmodel.compile(optimizer=Nadam(),loss='categorical_crossentropy',metrics=['accuracy'])\n\nfit = model.fit_generator(imagegen.flow(x_train,y_train,batch_size=128),epochs=80,validation_data=(x_test,y_test),verbose = 1,steps_per_epoch=100)\n\nloss,accuracy = model.evaluate(x_test,y_test)\n\nprint('test loss',loss)\nprint('test accuracy',accuracy)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.figure(figsize=(12,6))\nplt.plot(fit.history['loss'])\nplt.plot(fit.history['val_loss'])\nplt.title('model train vs validation loss')\nplt.ylabel('loss')\nplt.xlabel('epoch')\nplt.legend(['train', 'validation'], loc='upper right')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test = test.drop(['id'],axis=1)\ntest = test.values.reshape(test.shape[0],28,28,1)/255.0\nFINAL_PREDS = model.predict_classes(test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.DataFrame({ 'id': Id,\n                            'label': FINAL_PREDS })\nsubmission.to_csv(path_or_buf =\"submission.csv\", index=False)\nsubmission.head()","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}