{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":5048,"databundleVersionId":868335,"sourceType":"competition"}],"dockerImageVersionId":30698,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"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        pass\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\n\nimport warnings\nwarnings.filterwarnings('ignore')","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-05-13T20:07:40.107065Z","iopub.execute_input":"2024-05-13T20:07:40.107821Z","iopub.status.idle":"2024-05-13T20:08:21.690737Z","shell.execute_reply.started":"2024-05-13T20:07:40.107785Z","shell.execute_reply":"2024-05-13T20:08:21.689646Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Importações\nimport numpy as np\nimport pandas as pd\nimport os\nimport glob\nfrom PIL import Image\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.preprocessing import LabelEncoder\nfrom keras.preprocessing.image import img_to_array, load_img\nfrom keras.utils import to_categorical\nfrom keras.models import Sequential\nfrom keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout\nfrom keras.optimizers import Adam\nfrom keras.callbacks import EarlyStopping","metadata":{"execution":{"iopub.status.busy":"2024-05-13T20:10:13.025791Z","iopub.execute_input":"2024-05-13T20:10:13.026189Z","iopub.status.idle":"2024-05-13T20:10:13.036538Z","shell.execute_reply.started":"2024-05-13T20:10:13.026162Z","shell.execute_reply":"2024-05-13T20:10:13.035428Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Carregando o conjunto de dados\ntrain_df = pd.read_csv('/kaggle/input/state-farm-distracted-driver-detection/driver_imgs_list.csv')\n\n# Diretório onde as imagens estão armazenadas\nimage_dir = '/kaggle/input/state-farm-distracted-driver-detection/imgs/train/'\n\n# Lista para armazenar todos os nomes de arquivos de imagem\nall_image_files = []\n\n# Percorrer todos os subdiretórios dentro do diretório de imagens\nfor class_dir in os.listdir(image_dir):\n    # Caminho completo para o diretório da classe\n    class_dir_path = os.path.join(image_dir, class_dir)\n    # Adicionar todos os nomes de arquivos de imagem dentro do diretório da classe\n    all_image_files.extend(glob.glob(os.path.join(class_dir_path, '*.jpg')))\n\n# Imprimir o número total de imagens encontradas e exemplos de nomes de arquivos de imagens\nprint(\"Número total de imagens encontradas:\", len(all_image_files))\nprint(\"Exemplos de nomes de arquivos de imagens:\", all_image_files[:5])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Função para carregar e redimensionar imagens\ndef load_images(file_names, image_dir, size=(150, 150)):\n    images = []\n    for file_name in file_names:\n        image = load_img(os.path.join(image_dir, file_name), target_size=size)\n        image = img_to_array(image)\n        images.append(image)\n    return np.array(images)\n\n# Carregar e pré-processar as imagens\nX = load_images(train_df['img'].values, image_dir)\ny = train_df['classname']","metadata":{"execution":{"iopub.status.busy":"2024-05-13T20:09:19.796694Z","iopub.execute_input":"2024-05-13T20:09:19.797504Z","iopub.status.idle":"2024-05-13T20:09:20.346792Z","shell.execute_reply.started":"2024-05-13T20:09:19.797469Z","shell.execute_reply":"2024-05-13T20:09:20.344999Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Codificar rótulos de classe\nlabel_encoder = LabelEncoder()\ny = label_encoder.fit_transform(y)\ny = to_categorical(y)","metadata":{"execution":{"iopub.status.busy":"2024-05-13T20:09:34.905443Z","iopub.execute_input":"2024-05-13T20:09:34.90626Z","iopub.status.idle":"2024-05-13T20:09:34.953426Z","shell.execute_reply.started":"2024-05-13T20:09:34.906223Z","shell.execute_reply":"2024-05-13T20:09:34.951904Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Dividir o conjunto de dados em treinamento e teste\nX_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.2, random_state=42)","metadata":{"execution":{"iopub.status.busy":"2024-05-13T20:09:41.402932Z","iopub.execute_input":"2024-05-13T20:09:41.403318Z","iopub.status.idle":"2024-05-13T20:09:41.451192Z","shell.execute_reply.started":"2024-05-13T20:09:41.40329Z","shell.execute_reply":"2024-05-13T20:09:41.449775Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Construir modelo CNN\nmodel = Sequential([\n    Conv2D(32, (3, 3), activation='relu', input_shape=(150, 150, 3)),\n    MaxPooling2D(pool_size=(2, 2)),\n    Conv2D(64, (3, 3), activation='relu'),\n    MaxPooling2D(pool_size=(2, 2)),\n    Conv2D(128, (3, 3), activation='relu'),\n    MaxPooling2D(pool_size=(2, 2)),\n    Flatten(),\n    Dense(512, activation='relu'),\n    Dropout(0.5),\n    Dense(10, activation='softmax')\n])","metadata":{"execution":{"iopub.status.busy":"2024-05-13T20:09:46.008457Z","iopub.execute_input":"2024-05-13T20:09:46.009599Z","iopub.status.idle":"2024-05-13T20:09:46.286934Z","shell.execute_reply.started":"2024-05-13T20:09:46.009563Z","shell.execute_reply":"2024-05-13T20:09:46.28573Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Compilar modelo\nmodel.compile(optimizer=Adam(lr=0.0001), loss='categorical_crossentropy', metrics=['accuracy'])\n\n# Treinar modelo\nhistory = model.fit(X_train, y_train, epochs=20, batch_size=32, validation_data=(X_val, y_val), \n                    callbacks=[EarlyStopping(monitor='val_loss', patience=3)])","metadata":{"execution":{"iopub.status.busy":"2024-05-13T20:09:50.582461Z","iopub.execute_input":"2024-05-13T20:09:50.582948Z","iopub.status.idle":"2024-05-13T20:09:50.808611Z","shell.execute_reply.started":"2024-05-13T20:09:50.582902Z","shell.execute_reply":"2024-05-13T20:09:50.806823Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Avaliar modelo\nloss, accuracy = model.evaluate(X_val, y_val)\nprint(\"Validation Loss:\", loss)\nprint(\"Validation Accuracy:\", accuracy)","metadata":{"execution":{"iopub.status.busy":"2024-05-13T20:09:54.651677Z","iopub.execute_input":"2024-05-13T20:09:54.652114Z","iopub.status.idle":"2024-05-13T20:09:54.69891Z","shell.execute_reply.started":"2024-05-13T20:09:54.652081Z","shell.execute_reply":"2024-05-13T20:09:54.697447Z"},"trusted":true},"execution_count":null,"outputs":[]}]}