{"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)\nfrom tensorflow.python import keras \nimport csv\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\n#sub=pd.read_csv()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train_df = pd.read_csv('/kaggle/input/Kannada-MNIST/train.csv')\ntest_df = pd.read_csv('/kaggle/input/Kannada-MNIST/Dig-MNIST.csv')\npred_df = pd.read_csv('/kaggle/input/Kannada-MNIST/test.csv')\ntrain_df = train_df.append(test_df)\n\nX_train = train_df.drop(['label'], axis = 1)\nY_train = train_df['label']\nX_pred = pred_df.drop(['id'], axis = 1)\nfrom sklearn.model_selection import train_test_split\nX_train, X_test, Y_train, Y_test = train_test_split(X_train, Y_train, test_size=0.20)\nX_train, X_test, X_pred = X_train.apply(lambda x: x/255), X_test.apply(lambda x: x/255), X_pred.apply(lambda x: x/255)\n\nX_train = X_train.values.reshape(-1, 28, 28, 1)\nX_test = X_test.values.reshape(-1, 28, 28, 1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = keras.Sequential([keras.layers.Conv2D(32, 5, 1, input_shape=(28, 28, 1), padding=\"same\", activation=\"relu\"),\n\t\t\t\t\t\t\t  keras.layers.MaxPooling2D(),\n\t\t\t\t\t\t\t  keras.layers.Dropout(0.5),\n\t\t\t\t\t\t\t  keras.layers.Conv2D(64, 5, 1, padding=\"same\", activation=\"relu\"),\n\t\t\t\t\t\t\t  keras.layers.MaxPooling2D(),\n\t\t\t\t\t\t\t  keras.layers.Dropout(0.5),\n\t\t\t\t\t\t\t  keras.layers.Flatten(),\n\t\t\t\t\t\t\t  keras.layers.Dense(1024, activation=\"relu\"),\n\t\t\t\t\t\t\t  keras.layers.Dropout(0.5),\n\t\t\t\t\t\t\t  keras.layers.Dense(10, activation=\"softmax\")])\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(optimizer=keras.optimizers.Adam(), loss=\"sparse_categorical_crossentropy\", metrics=['accuracy'])\nmodel.fit(X_train, Y_train, batch_size=32, epochs=20,\n\t\t\t\t\t\tvalidation_data=(X_test,Y_test))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def save_result(filename, results):\n\twith open(filename, 'w', newline='') as f:\n\t\tmyWriter = csv.writer(f)\n\t\tmyWriter.writerow(['id', 'label'])\n\t\tfor i, result in enumerate(results):\n\t\t\tmyWriter.writerow([i , result])\nX_pred = X_pred.values.reshape(-1, 28, 28, 1)\nresult1 = model.predict(X_pred, batch_size=64)\nresult1 = np.argmax(result1, axis=-1)\nsave_result(\"nnResult.csv\", result1)","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}