{"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 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.","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train = pd.read_csv('/kaggle/input/state-farm-distracted-driver-detection/driver_imgs_list.csv')","metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train['img'] = train['classname']+'/'+train['img']","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train['img'] ='/kaggle/input/state-farm-distracted-driver-detection/imgs/train/'+train['img']","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train['classname'].value_counts()","metadata":{"collapsed":true,"jupyter":{"outputs_hidden":true},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nx_train, x_valid = train_test_split(train, test_size=0.15, random_state=1,\n                                    stratify=train['classname'])\nx_valid['classname'].value_counts()","metadata":{"collapsed":true,"jupyter":{"outputs_hidden":true},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from keras.preprocessing.image import ImageDataGenerator\ngen = ImageDataGenerator(rescale=1/255, horizontal_flip=True)\ntrain_generator = gen.flow_from_dataframe(x_train, x_col='img', y_col='classname',\n                                         batch_size=64, target_size=(200,200))\n\nvalid_generator = gen.flow_from_dataframe(x_valid, x_col='img', y_col='classname',\n                                         batch_size=64, target_size=(200,200))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!pip install git+https://github.com/qubvel/efficientnet","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import efficientnet.keras as efn\nfrom keras import Sequential\nfrom keras.layers import Dense\n\nmodel = Sequential()\nmodel.add(efn.EfficientNetB2(weights='imagenet', include_top=False, pooling='avg'))\nmodel.add(Dense(10, activation='softmax'))\nmodel.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['acc'])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from keras.callbacks import EarlyStopping, ModelCheckpoint, ReduceLROnPlateau\nes = EarlyStopping(patience=3, verbose=1)\nmc = ModelCheckpoint('best.h5',save_best_only=True)\nrl = ReduceLROnPlateau(patience=2, factor=0.1, verbose=1)\nmodel.fit_generator(train_generator, validation_data=valid_generator, epochs=10, \n                   callbacks=[es, mc, rl])\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"path = os.listdir('/kaggle/input/state-farm-distracted-driver-detection/imgs/test')\ntest = pd.DataFrame({'path' : path})\ntest['path'] = '/kaggle/input/state-farm-distracted-driver-detection/imgs/test/'+test['path']\ngen2 = ImageDataGenerator(rescale=1/255)\ntest_generator = gen2.flow_from_dataframe(test, x_col='path', y_col=None,\n                                         batch_size=64, target_size=(200,200),\n                                         shuffle=False, class_mode=None)\nmodel.load_weights('best.h5')\nresult = model.predict_generator(test_generator, verbose=1, workers=4)\n\n\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub = pd.read_csv(\"/kaggle/input/state-farm-distracted-driver-detection/sample_submission.csv\")\nsub['img'] = test_generator.filenames\nsub['img'] = sub['img'].apply(lambda x: x.split('/')[-1])\nsub.iloc[:,1:] = result","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub.to_csv(\"/kaggle/working/submission.csv\", index=False)","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}