{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np \nimport pandas as pd \nimport cv2\nimport matplotlib as plt\nimport random\nimport seaborn as sns\n%matplotlib inline","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"df = pd.read_csv('/kaggle/input/vinbigdata-chest-xray-abnormalities-detection/train.csv')\nprint(df.count())\ndf.head(3)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(df['image_id'][df['class_id']==14].count())\ndf.isna().sum()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"There is no missing values.\n\n(14 is the class ID for no finding, and this provides a one-pixel bounding box with a confidence of 1.0)"},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.countplot(x='class_id',data=df)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"del df['image_id'],df['rad_id']\nsns.pairplot(df, hue='class_id')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df['x_diff'] = df['x_max'] - df['x_min']\ndf['y_diff'] = df['y_max'] - df['y_min']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df.groupby('class_id').agg(['min', 'max', 'mean'])","execution_count":null,"outputs":[]}],"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":4,"nbformat_minor":4}