{"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":"import pandas as pd\nimport numpy as np\nimport warnings\nwarnings.filterwarnings(\"ignore\")\nfrom glob import glob\nfrom tqdm.notebook import tqdm\nfrom ast import literal_eval\nimport os\nimport matplotlib.pyplot as plt\nimport matplotlib\nmatplotlib.rcParams.update({'font.size': 22})\nfrom sklearn.metrics import accuracy_score\nfrom skimage import exposure\nfrom tensorflow.keras import layers\nfrom tensorflow.keras.utils import plot_model\nimport cv2\nfrom matplotlib.patches import Rectangle\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.applications import ResNet50, DenseNet121\nfrom tensorflow.keras.layers import Dense, Flatten, Conv2D, MaxPooling2D, Dropout, GlobalAveragePooling2D\nfrom tensorflow.keras.optimizers import Adam\nfrom tensorflow.keras import models\nfrom tensorflow.keras.callbacks import ReduceLROnPlateau, ModelCheckpoint, EarlyStopping\nimport tensorflow.keras.backend as K\nfrom tensorflow.math import confusion_matrix\n# 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":"2021-05-29T21:46:55.959243Z","iopub.execute_input":"2021-05-29T21:46:55.959661Z","iopub.status.idle":"2021-05-29T21:47:20.655139Z","shell.execute_reply.started":"2021-05-29T21:46:55.959627Z","shell.execute_reply":"2021-05-29T21:47:20.654479Z"},"collapsed":true,"jupyter":{"outputs_hidden":true},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Leemos el csv a nivel de imagen\ndf_image = pd.read_csv('../input/siim-covid19-detection/train_image_level.csv')\ndisplay(df_image.head(5))\nprint(df_image.shape)\n\n# Leemos el csv a nivel de studio con las etiquetas\ndf_study = pd.read_csv('../input/siim-covid19-detection/train_study_level.csv')\ndisplay(df_study.head(5))\nprint(df_study.shape)\n\n# Leemos el csv de sample de submission\ndf_sampleSub = pd.read_csv('../input/siim-covid19-detection/sample_submission.csv')\ndisplay(df_sampleSub.head(5))\nprint(df_sampleSub.shape)\n\n# eliminamos \"_study\" de los id y renombramos la columna\ndf_study['id'] = df_study['id'].str.replace('_study',\"\")\ndf_study.rename({'id': 'StudyInstanceUID'},axis=1, inplace=True)\ndf_study.head(3)\n\n#hacemos merge de las tablas de imagen y studio por el campo StudyInstanceUID \ndf_train = df_image.merge(df_study, on='StudyInstanceUID')\ndf_train.head(3)\n\n# creamos columna target 'study_label' y asignamos el label correspondiente\ndf_train.loc[df_train['Negative for Pneumonia']==1, 'study_label'] = 'negative'\ndf_train.loc[df_train['Typical Appearance']==1, 'study_label'] = 'typical'\ndf_train.loc[df_train['Indeterminate Appearance']==1, 'study_label'] = 'indeterminate'\ndf_train.loc[df_train['Atypical Appearance']==1, 'study_label'] = 'atypical'\n\n#eliminamos las variables de los casos de labels\ndf_train.drop(['Negative for Pneumonia','Typical Appearance', 'Indeterminate Appearance', 'Atypical Appearance'], axis=1, inplace=True)\n\n#remplazamos en el id para dejar el formato de la imagen\ndf_train['id'] = df_train['id'].str.replace('_image', '.jpg')\ndf_train['image_label'] = df_train['label'][0].split()[0]\ndf_train.head(10)","metadata":{"execution":{"iopub.status.busy":"2021-05-29T21:47:51.428102Z","iopub.execute_input":"2021-05-29T21:47:51.428581Z","iopub.status.idle":"2021-05-29T21:47:51.519957Z","shell.execute_reply.started":"2021-05-29T21:47:51.428536Z","shell.execute_reply":"2021-05-29T21:47:51.519341Z"},"collapsed":true,"jupyter":{"outputs_hidden":true},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_dir_jpg = '../input/covid-jpg-512/train'\ntrain_dir_origin ='../input/siim-covid19-detection/train'\npaths_original = []\npaths_jpg = []\nfor _, row in tqdm(df_train.iterrows()):\n    image_id = row['id'].split('_')[0]\n    study_id = row['StudyInstanceUID']\n    image_path_jpg = glob(f'{train_dir_jpg}/{image_id}.jpg')\n    image_path_original = glob(f'{train_dir_origin}/{study_id}/*/{image_id}.dcm')\n    paths_jpg.append(image_path_jpg)\n    paths_original.append(image_path_original)\n    \n\ndf_train['path'] = paths_jpg\ndf_train['origin'] = paths_original\ndf_train.head(3)","metadata":{"execution":{"iopub.status.busy":"2021-05-29T21:48:12.652112Z","iopub.execute_input":"2021-05-29T21:48:12.652559Z","iopub.status.idle":"2021-05-29T21:48:25.568914Z","shell.execute_reply.started":"2021-05-29T21:48:12.652530Z","shell.execute_reply":"2021-05-29T21:48:25.567977Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_size = pd.read_csv('../input/covid-jpg-512/size.csv')\ndf_size.head(3)\n\ndf_train = df_train.merge(df_size, on='id')\ndf_train.head(3)","metadata":{"execution":{"iopub.status.busy":"2021-05-29T21:49:45.728827Z","iopub.execute_input":"2021-05-29T21:49:45.729154Z","iopub.status.idle":"2021-05-29T21:49:45.761728Z","shell.execute_reply.started":"2021-05-29T21:49:45.729124Z","shell.execute_reply":"2021-05-29T21:49:45.760918Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"n = 20\ntrain_dir = '../input/covid-jpg-512/train'\nfig, axs = plt.subplots(4, 5, figsize=(20,20))\nfig.subplots_adjust(hspace=.2, wspace=.2)\naxs = axs.ravel()\nfor i in range(n):\n    img = cv2.imread(os.path.join(train_dir, df_train['id'][i]))\n    axs[i].imshow(img)\n    if type(df_train['boxes'][i])==str:\n        boxes = literal_eval(df_train['boxes'][i])\n        for box in boxes:\n            axs[i].add_patch(Rectangle((box['x']*(512/df_train['dim1'][i]), box['y']*(512/df_train['dim0'][i])), box['width']*(512/df_train['dim1'][i]), box['height']*(512/df_train['dim0'][i]), fill=0, color='y', linewidth=2))\n            axs[i].set_title(df_train['study_label'][i])\n    else:\n        axs[i].set_title(df_train['study_label'][i])","metadata":{"execution":{"iopub.status.busy":"2021-05-29T21:50:24.863700Z","iopub.execute_input":"2021-05-29T21:50:24.864075Z","iopub.status.idle":"2021-05-29T21:50:27.475176Z","shell.execute_reply.started":"2021-05-29T21:50:24.864038Z","shell.execute_reply":"2021-05-29T21:50:27.474508Z"},"trusted":true},"execution_count":null,"outputs":[]}]}