{"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_minor":4,"nbformat":4,"cells":[{"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\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 read-only \"../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# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport tensorflow as tf\n\nfrom tensorflow import keras\nfrom keras import Sequential\nfrom keras.layers import Dense, Conv2D, Flatten, BatchNormalization, Activation, MaxPooling2D\nfrom keras.utils.np_utils import to_categorical\nfrom keras.callbacks import ReduceLROnPlateau\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom sklearn.model_selection import train_test_split","metadata":{"execution":{"iopub.status.busy":"2022-02-08T09:33:23.71476Z","iopub.execute_input":"2022-02-08T09:33:23.715074Z","iopub.status.idle":"2022-02-08T09:33:28.618588Z","shell.execute_reply.started":"2022-02-08T09:33:23.714986Z","shell.execute_reply":"2022-02-08T09:33:28.617847Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train = pd.read_csv('../input/digit-recognizer/train.csv').values\ntest = pd.read_csv('../input/digit-recognizer/test.csv').values","metadata":{"execution":{"iopub.status.busy":"2022-02-08T09:33:30.753994Z","iopub.execute_input":"2022-02-08T09:33:30.75425Z","iopub.status.idle":"2022-02-08T09:33:36.011328Z","shell.execute_reply.started":"2022-02-08T09:33:30.754223Z","shell.execute_reply":"2022-02-08T09:33:36.010598Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_train = train[:,1:]\ny_train = train[:,0]\n\nX_train = (X_train.astype(np.float32) - 127.5)/127.5\nX_test = (test.astype(np.float32) - 127.5)/127.5","metadata":{"execution":{"iopub.status.busy":"2022-02-08T09:33:36.012846Z","iopub.execute_input":"2022-02-08T09:33:36.013078Z","iopub.status.idle":"2022-02-08T09:33:36.2114Z","shell.execute_reply.started":"2022-02-08T09:33:36.013045Z","shell.execute_reply":"2022-02-08T09:33:36.21015Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_train=X_train.reshape(-1,28,28,1)\nX_test=X_test.reshape(-1,28,28,1)\n\ny_train_vectors=to_categorical(y_train)\n\nX_train, X_val, y_train, y_val= train_test_split(X_train, y_train_vectors, test_size=0.2, random_state=2)","metadata":{"execution":{"iopub.status.busy":"2022-02-08T09:33:57.445507Z","iopub.execute_input":"2022-02-08T09:33:57.446306Z","iopub.status.idle":"2022-02-08T09:33:57.757889Z","shell.execute_reply.started":"2022-02-08T09:33:57.446269Z","shell.execute_reply":"2022-02-08T09:33:57.757155Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model=Sequential()\n\nmodel.add(Conv2D(filters=32, kernel_size=(3,3), strides=(1,1), padding='valid', activation=None, use_bias=False, input_shape=(X_train.shape[1:])))\nmodel.add(BatchNormalization())\nmodel.add(Activation('relu'))\nmodel.add(Conv2D(filters=64, kernel_size=(3,3), strides=(1,1), padding='valid', activation=None, use_bias=False))\nmodel.add(BatchNormalization())\nmodel.add(Activation('relu'))\nmodel.add(MaxPooling2D(pool_size=(2,2)))\n\nmodel.add(Conv2D(filters=96, kernel_size=(3,3), strides=(1,1), padding='valid', activation=None, use_bias=False))\nmodel.add(BatchNormalization())\nmodel.add(Activation('relu'))\nmodel.add(Conv2D(filters=128, kernel_size=(3,3), strides=(1,1), padding='valid', activation=None, use_bias=False))\nmodel.add(BatchNormalization())\nmodel.add(Activation('relu'))\n\n\nmodel.add(Flatten())\n    \nmodel.add(Dense(units=10))\nmodel.add(BatchNormalization())\nmodel.add(Activation('softmax'))\n\nmodel.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])","metadata":{"execution":{"iopub.status.busy":"2022-02-08T09:33:59.474439Z","iopub.execute_input":"2022-02-08T09:33:59.47496Z","iopub.status.idle":"2022-02-08T09:34:01.6442Z","shell.execute_reply.started":"2022-02-08T09:33:59.474921Z","shell.execute_reply":"2022-02-08T09:34:01.643436Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_datagen = ImageDataGenerator(featurewise_center=False,\n                             samplewise_center=False,\n                             featurewise_std_normalization=False,\n                             samplewise_std_normalization=False,\n                             zca_whitening=False,\n                             rotation_range=10,\n                             zoom_range=0.1,\n                             width_shift_range=0.1,\n                             height_shift_range=0.1,\n                             horizontal_flip=False,\n                             vertical_flip=False\n                            )\n\ntrain_set = train_datagen.flow(X_train, y_train, batch_size=120, shuffle=True)\n\nval_datagen = ImageDataGenerator()\ntest_set = val_datagen.flow(X_val, y_val, batch_size=120, shuffle=True)","metadata":{"execution":{"iopub.status.busy":"2022-02-08T09:34:01.645833Z","iopub.execute_input":"2022-02-08T09:34:01.646255Z","iopub.status.idle":"2022-02-08T09:34:01.956539Z","shell.execute_reply.started":"2022-02-08T09:34:01.646215Z","shell.execute_reply":"2022-02-08T09:34:01.955802Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.fit(train_set, validation_data=test_set, epochs=200)#, callbacks=[reduceLROnPlateau])","metadata":{"execution":{"iopub.status.busy":"2022-02-08T09:34:01.970016Z","iopub.execute_input":"2022-02-08T09:34:01.970223Z","iopub.status.idle":"2022-02-08T10:04:20.036941Z","shell.execute_reply.started":"2022-02-08T09:34:01.970197Z","shell.execute_reply":"2022-02-08T10:04:20.036252Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"prediction_vectors=model.predict(X_test)\n\n#Decide the label from probabilities, so now, prediction_final is 28K x 10\npredictions_final=np.argmax(prediction_vectors, axis=1)\n\nsub = pd.read_csv('../input/digit-recognizer/sample_submission.csv')\n\n#Overwrite labels in dataframe sub\nsub[\"Label\"] = predictions_final\n\n#Write updated dataframes as submission.csv\nsub.to_csv('submission.csv',index=False)","metadata":{"execution":{"iopub.status.busy":"2022-02-08T10:17:25.690094Z","iopub.execute_input":"2022-02-08T10:17:25.690339Z","iopub.status.idle":"2022-02-08T10:17:27.354219Z","shell.execute_reply.started":"2022-02-08T10:17:25.69031Z","shell.execute_reply":"2022-02-08T10:17:27.353411Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}