{"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","execution":{"iopub.status.busy":"2022-05-03T07:33:54.217085Z","iopub.execute_input":"2022-05-03T07:33:54.217449Z","iopub.status.idle":"2022-05-03T07:33:54.249193Z","shell.execute_reply.started":"2022-05-03T07:33:54.21736Z","shell.execute_reply":"2022-05-03T07:33:54.248469Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import numpy as np \nimport pandas as pd \nfrom tensorflow import keras\nfrom keras import Sequential\nfrom keras.layers import Dense, Conv2D, Flatten, BatchNormalization, Activation\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\nfrom tensorflow.keras.optimizers import SGD","metadata":{"execution":{"iopub.status.busy":"2022-05-03T07:33:54.250845Z","iopub.execute_input":"2022-05-03T07:33:54.251325Z","iopub.status.idle":"2022-05-03T07:34:00.237394Z","shell.execute_reply.started":"2022-05-03T07:33:54.251288Z","shell.execute_reply":"2022-05-03T07:34:00.236619Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"x_train_full=pd.read_csv('/kaggle/input/digit-recognizer/train.csv', header='infer')\nx_test=pd.read_csv('/kaggle/input/digit-recognizer/test.csv', header='infer')","metadata":{"execution":{"iopub.status.busy":"2022-05-03T07:34:00.238858Z","iopub.execute_input":"2022-05-03T07:34:00.239324Z","iopub.status.idle":"2022-05-03T07:34:05.097733Z","shell.execute_reply.started":"2022-05-03T07:34:00.239285Z","shell.execute_reply":"2022-05-03T07:34:05.09699Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"x_train=x_train_full.iloc[:,1:]\ny_train=x_train_full.iloc[:,0]\n\nx_train","metadata":{"execution":{"iopub.status.busy":"2022-05-03T07:34:05.099525Z","iopub.execute_input":"2022-05-03T07:34:05.099771Z","iopub.status.idle":"2022-05-03T07:34:05.131184Z","shell.execute_reply.started":"2022-05-03T07:34:05.099737Z","shell.execute_reply":"2022-05-03T07:34:05.130511Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"x_train=x_train/255.\nx_test=x_test/255.","metadata":{"execution":{"iopub.status.busy":"2022-05-03T07:34:05.132433Z","iopub.execute_input":"2022-05-03T07:34:05.132873Z","iopub.status.idle":"2022-05-03T07:34:05.298078Z","shell.execute_reply.started":"2022-05-03T07:34:05.132836Z","shell.execute_reply":"2022-05-03T07:34:05.297339Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"x_train=x_train.values.reshape(-1,28,28,1)\nx_test=x_test.values.reshape(-1,28,28,1)\n\nx_train.shape","metadata":{"execution":{"iopub.status.busy":"2022-05-03T07:34:05.299436Z","iopub.execute_input":"2022-05-03T07:34:05.299678Z","iopub.status.idle":"2022-05-03T07:34:05.306618Z","shell.execute_reply.started":"2022-05-03T07:34:05.299646Z","shell.execute_reply":"2022-05-03T07:34:05.30585Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_train_vectors=to_categorical(y_train)","metadata":{"execution":{"iopub.status.busy":"2022-05-03T07:34:05.308254Z","iopub.execute_input":"2022-05-03T07:34:05.308851Z","iopub.status.idle":"2022-05-03T07:34:05.315864Z","shell.execute_reply.started":"2022-05-03T07:34:05.3088Z","shell.execute_reply":"2022-05-03T07:34:05.315177Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"x_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":"2022-05-03T07:34:05.317677Z","iopub.execute_input":"2022-05-03T07:34:05.317953Z","iopub.status.idle":"2022-05-03T07:34:05.697356Z","shell.execute_reply.started":"2022-05-03T07:34:05.317914Z","shell.execute_reply":"2022-05-03T07:34:05.696624Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(x_train.shape)\nprint(x_val.shape)\nprint(y_train.shape)\nprint(y_val.shape)","metadata":{"execution":{"iopub.status.busy":"2022-05-03T07:34:05.698734Z","iopub.execute_input":"2022-05-03T07:34:05.699039Z","iopub.status.idle":"2022-05-03T07:34:05.705759Z","shell.execute_reply.started":"2022-05-03T07:34:05.699003Z","shell.execute_reply":"2022-05-03T07:34:05.704882Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model=Sequential()\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'))\n\nmodel.add( Conv2D(filters=48, kernel_size=(3,3), strides=(1,1), padding='valid', activation=None, use_bias=False) )\nmodel.add(BatchNormalization())\nmodel.add(Activation('relu'))\n\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'))\n\nmodel.add( Conv2D(filters=80, kernel_size=(3,3), strides=(1,1), padding='valid', activation=None, use_bias=False) )\nmodel.add(BatchNormalization())\nmodel.add(Activation('relu'))\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'))\n\nmodel.add( Conv2D(filters=112, kernel_size=(3,3), strides=(1,1), padding='valid', activation=None, use_bias=False) )\nmodel.add(BatchNormalization())\nmodel.add(Activation('relu'))\n\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\nmodel.add( Conv2D(filters=144, kernel_size=(3,3), strides=(1,1), padding='valid', activation=None, use_bias=False) )\nmodel.add(BatchNormalization())\nmodel.add(Activation('relu'))\n\nmodel.add( Conv2D(filters=160, kernel_size=(3,3), strides=(1,1), padding='valid', activation=None, use_bias=False) )\nmodel.add(BatchNormalization())\nmodel.add(Activation('relu'))\n\nmodel.add( Conv2D(filters=176, kernel_size=(3,3), strides=(1,1), padding='valid', activation=None, use_bias=False) )\nmodel.add(BatchNormalization())\nmodel.add(Activation('relu'))\n\nmodel.add(Flatten())\n\nmodel.add(Dense(units=10))\nmodel.add(BatchNormalization())\nmodel.add(Activation('softmax'))","metadata":{"execution":{"iopub.status.busy":"2022-05-03T07:34:05.708843Z","iopub.execute_input":"2022-05-03T07:34:05.709381Z","iopub.status.idle":"2022-05-03T07:34:08.425842Z","shell.execute_reply.started":"2022-05-03T07:34:05.709341Z","shell.execute_reply":"2022-05-03T07:34:08.424987Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sgd = SGD(learning_rate=0.05)\n\nmodel.compile(loss=\"categorical_crossentropy\", optimizer=sgd, metrics=[\"accuracy\"])","metadata":{"execution":{"iopub.status.busy":"2022-05-03T07:34:08.427224Z","iopub.execute_input":"2022-05-03T07:34:08.427464Z","iopub.status.idle":"2022-05-03T07:34:08.443864Z","shell.execute_reply.started":"2022-05-03T07:34:08.427433Z","shell.execute_reply":"2022-05-03T07:34:08.442978Z"},"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_generator = train_datagen.flow(x_train, y_train,\n                                     batch_size=120,\n                                     shuffle=True)\n\nval_datagen = ImageDataGenerator()\nval_generator = val_datagen.flow(x_val, y_val,\n                                 batch_size=120,\n                                 shuffle=True)\n","metadata":{"execution":{"iopub.status.busy":"2022-05-03T07:34:08.44578Z","iopub.execute_input":"2022-05-03T07:34:08.446102Z","iopub.status.idle":"2022-05-03T07:34:08.512591Z","shell.execute_reply.started":"2022-05-03T07:34:08.446062Z","shell.execute_reply":"2022-05-03T07:34:08.511845Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"trained_model = model.fit(train_generator,validation_data=(val_generator), epochs=20, batch_size=50)\n","metadata":{"execution":{"iopub.status.busy":"2022-05-03T07:34:08.51371Z","iopub.execute_input":"2022-05-03T07:34:08.51528Z","iopub.status.idle":"2022-05-03T07:38:18.177714Z","shell.execute_reply.started":"2022-05-03T07:34:08.51524Z","shell.execute_reply":"2022-05-03T07:38:18.176982Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"predictions_final = model.predict(x_test)\n\nprint(predictions_final)\n\npredictions_final = np.argmax(predictions_final, axis=1)\n\nprint(predictions_final)","metadata":{"execution":{"iopub.status.busy":"2022-05-03T07:38:18.180811Z","iopub.execute_input":"2022-05-03T07:38:18.181351Z","iopub.status.idle":"2022-05-03T07:38:21.131414Z","shell.execute_reply.started":"2022-05-03T07:38:18.181312Z","shell.execute_reply":"2022-05-03T07:38:21.130637Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub = pd.read_csv('/kaggle/input/digit-recognizer/sample_submission.csv')\n\nsub[\"Label\"] = predictions_final\n\nprint(sub)\n\nsub.to_csv('submission.csv',index=False)","metadata":{"execution":{"iopub.status.busy":"2022-05-03T07:38:21.13286Z","iopub.execute_input":"2022-05-03T07:38:21.133301Z","iopub.status.idle":"2022-05-03T07:38:21.198787Z","shell.execute_reply.started":"2022-05-03T07:38:21.133252Z","shell.execute_reply":"2022-05-03T07:38:21.198074Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}