{"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":"train_Data = pd.read_csv('../input/Kannada-MNIST/train.csv')\ndig_mnist  =  pd.read_csv('../input/Kannada-MNIST/Dig-MNIST.csv')\ntest_data  = pd.read_csv('../input/Kannada-MNIST/test.csv')\ntrain_Data.head() #validation set :)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import seaborn as sns\n\ng = sns.countplot(train_Data['label'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"g = sns.countplot(dig_mnist['label'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = train_Data[:]\nval   = dig_mnist[:]\ntrain_label = np.float32(train.label)\nval_label = np.float32(val.label)\ntrain_image = np.float32(train[train.columns[1:]])\nval_image = np.float32(val[val.columns[1:]])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.preprocessing.image import ImageDataGenerator\nfrom keras.utils import to_categorical\ndatagen = ImageDataGenerator(\n    rotation_range=10,\n    width_shift_range=0.1,\n    height_shift_range=0.1,\n    shear_range = 10,\n    horizontal_flip = False,\n    zoom_range = 0.15)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(train_label.shape)\nprint(val_label.shape)\ntrain_label = to_categorical(train_label) \nval_label = to_categorical(val_label)\nprint(train_label.shape)\nprint(val_label.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_image = train_image/255.0 \nval_image = val_image/255.0\ntrain_image = train_image.reshape(train_image.shape[0],28,28,1)\nval_image = val_image.reshape(val_image.shape[0],28,28,1)\nprint(train_image.shape)\nprint(val_image.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import keras\nfrom keras.models import Sequential\nfrom keras.layers import Dense, Dropout, Flatten\nfrom keras.layers import Conv2D, MaxPooling2D,Activation\nfrom keras.utils import to_categorical\nfrom keras.preprocessing import image\nfrom keras.layers.normalization import BatchNormalization\nfrom keras.callbacks import ModelCheckpoint,History,EarlyStopping,LearningRateScheduler\nfrom keras.layers import LeakyReLU\nimport numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nfrom sklearn.model_selection import train_test_split\nfrom keras.utils import to_categorical\nfrom tqdm import tqdm\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model=Sequential()\nmodel.add(Conv2D(28,(5,5),padding='same',input_shape=(28,28,1)))\nmodel.add(Conv2D(28,(5,5)))\nmodel.add(Activation('relu'))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(28,(5,5)))\nmodel.add(Activation('relu'))\nmodel.add(MaxPooling2D(pool_size=(2,2)))\nmodel.add(Dropout(0.25))\nmodel.add(Conv2D(32,(5,5),padding='same',input_shape=(28,28,1)))\nmodel.add(Conv2D(32,(5,5)))\nmodel.add(Activation('relu'))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(32,(5,5)))\nmodel.add(Activation('relu'))\nmodel.add(MaxPooling2D(pool_size=(2,2)))\nmodel.add(Dropout(0.45))\nmodel.add(Flatten())\nmodel.add(Dense(512))\nmodel.add(Activation('relu'))\nmodel.add(Dropout(0.25))\nmodel.add(Dense(128))\nmodel.add(Activation('relu'))\nmodel.add(Dropout(0.5))\nmodel.add(Dense(10))\nmodel.add(Activation('softmax'))\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.optimizers import Adam, Adadelta, RMSprop, SGD\nfrom keras import optimizers\nmodel.compile(loss = 'categorical_crossentropy' , optimizer= optimizers.SGD(lr=0.001 , momentum=0.9) , metrics=['accuracy'])\n# training\ncheckpoint = ModelCheckpoint(\"custom.h5\", monitor='val_acc', verbose=1, save_best_only=True, save_weights_only=False, mode='auto', period=1)\nearly = EarlyStopping(monitor='val_loss', min_delta=0, patience=5, verbose=1, mode='auto')\nhistory = model.fit_generator(datagen.flow(train_image,train_label, batch_size=256),\n                              epochs = 20,\n                              shuffle=True,\n                              validation_data = (val_image,val_label),\n                              verbose = 1,\n                              steps_per_epoch=117,callbacks= [checkpoint ,early])\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test = test_data[:]\ntest_id = (test.id)\ntest_image = np.float32(test[test.columns[1:]])\ntest_image = test_image/255.0 \ntest_image = test_image.reshape(test_image.shape[0],28,28,1)\ntest_image.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"prediction = model.predict_classes(test_image)\nsubmission = pd.DataFrame({'id':test_id,'label':prediction})\nprint(submission.head())\nfilename = 'submission.csv'\nsubmission.to_csv(filename,header=True,index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"output = pd.read_csv('submission.csv')\noutput.head()\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!cp /kaggle/working/submission.csv /Kannada-MNIST/","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":4}