{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"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","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport os\nimport shutil \nimport json\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nsns.set()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"base_dir = '/kaggle/input/cassava-leaf-disease-classification/'\nworking_dir = \"/kaggle/working/\"\ndata_dir = working_dir+'ordered_images/'","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"os.listdir(base_dir)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Viewing the classes and their corresponding labels"},{"metadata":{"trusted":true},"cell_type":"code","source":"with open(base_dir+'label_num_to_disease_map.json') as f:\n    labels = json.load(f)\nlabels","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df = pd.read_csv(base_dir+'train.csv')\ndf.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.countplot(data = df,x=\"label\",hue=\"label\");","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Setting up the Directory structure"},{"metadata":{"trusted":true},"cell_type":"code","source":"try:\n    shutil.rmtree(data_dir)\nexcept:\n    pass","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"os.mkdir(data_dir)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for key,value in labels.items():\n    os.mkdir(data_dir+value)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"os.listdir(data_dir)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Arranging the images according to their classes"},{"metadata":{"trusted":true},"cell_type":"code","source":"for file_name, key in df.values:\n    shutil.copy2(base_dir+'train_images/'+file_name,data_dir+labels[str(key)])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Cross check xD"},{"metadata":{"trusted":true},"cell_type":"code","source":"len(df[df.label==1])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"len(os.listdir(data_dir+labels[str(1)]))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","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}