{"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=pd.read_csv(\"/kaggle/input/Kannada-MNIST/train.csv\")\ntest=pd.read_csv(\"/kaggle/input/Kannada-MNIST/test.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X=train.iloc[:,1:].values\ny=train.iloc[:,1].values","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#reshape data\nX = X.reshape(X.shape[0], 28, 28)/255.0\nX = X.reshape(X.shape[0], 28,28,1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test=test.iloc[:,1:].values","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test = test.reshape(test.shape[0], 28, 28)/255.0\ntest = test.reshape(test.shape[0], 28,28,1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#import keras libraries\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Convolution2D\nfrom tensorflow.keras.layers import MaxPooling2D\nfrom tensorflow.keras.layers import Flatten\nfrom tensorflow.keras.layers import Dense,Dropout","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#initialize\nclassifier=Sequential()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#layer1\nclassifier.add(Convolution2D(28,3,3,input_shape=(28,28,1),activation='relu'))\nclassifier.add(MaxPooling2D(pool_size=(2,2)))\nclassifier.add(Dropout(0.25))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#layer2\nclassifier.add(Convolution2D(32,padding='same',kernel_size=3,activation='relu'))\nclassifier.add(MaxPooling2D(pool_size=(2,2)))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#layer3\nclassifier.add(Convolution2D(64,padding='same',kernel_size=3,activation='relu'))\nclassifier.add(MaxPooling2D(pool_size=(2,2)))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#flattening\nclassifier.add(Flatten())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"classifier.add(Dense(units=128,activation='relu'))\nclassifier.add(Dropout(0.5))\nclassifier.add(Dense(units=10,activation='softmax'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#compile\nclassifier.compile(optimizer='adam',loss='sparse_categorical_crossentropy',metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#fit model\nclassifier.fit(X, y, batch_size = 12, epochs = 20)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#predict\ny_pred = classifier.predict(test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import numpy as np\nresults = np.argmax(y_pred,axis = 1)\ndata_out = pd.DataFrame({'id': range(len(test)), 'label': results})\ndata_out.to_csv('try.csv', index = None)","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}