{"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        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":{"trusted":true},"cell_type":"code","source":"from pathlib import Path\nfrom tqdm import tqdm\n\nimport plotly.graph_objects as go\nimport plotly_express as px\nimport plotly.figure_factory as ff\nfrom plotly.subplots import make_subplots\n\nimport matplotlib.pyplot as plt\nimport cv2\n\nfrom plotly.offline import init_notebook_mode\ninit_notebook_mode()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"path = Path('../input/cassava-leaf-disease-classification')\n\ntrain_images = os.listdir(path/'train_images/')   #train_images = path /'train_images'\ntest_images = os.listdir(path/'test_images/')     #test_images = path /'test_images'","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data = pd.read_csv(path/'train.csv')\ndiseaseMapping = pd.read_json(path/'label_num_to_disease_map.json', typ='series')\ndiseaseMapping","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"mappingDict = diseaseMapping.to_dict()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data = train_data.replace(mappingDict)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"healthyImages = train_data[train_data['label'] == 'Healthy']['image_id'].count()\ncbbImages = train_data[train_data['label'] == 'Cassava Bacterial Blight (CBB)']['image_id'].count()\ncbsdImages = train_data[train_data['label'] == 'Cassava Brown Streak Disease (CBSD)']['image_id'].count()\ncgmImages = train_data[train_data['label'] == 'Cassava Green Mottle (CGM)']['image_id'].count()\ncmdImages = train_data[train_data['label'] == 'Cassava Mosaic Disease (CMD)']['image_id'].count()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"healthyImages.sum(), cbbImages.sum(), cbsdImages.sum(), cgmImages.sum(), cmdImages.sum()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import seaborn as sn \nplt.figure(figsize=(16, 8))\nsn.countplot(x = \"label\",data=train_data);","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"uniqueIds = train_data['image_id'].nunique()\nif(uniqueIds == len(train_data)):\n    print('There are no repeating Image IDs in the dataset')\nelse:\n    print(f'There are {len(train_data) - uniqueIds} repeating Image IDs')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from PIL import Image\nimport glob\nimage_list = []\nfor filename in glob.glob('../input/cassava-leaf-disease-classification/train_images/*.jpg'): \n    image=Image.open(filename)\n    image_list.append(image)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for i in range(10):\n    plt.figure(figsize = (5,5))\n    plt.imshow(image_list[i])\n    plt.title(\"Random Image\");","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_sub = pd.read_csv(\"../input/cassava-leaf-disease-classification/sample_submission.csv\", index_col=0)\ndf_sub","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"os.listdir(os.path.join(path, \"test_images\"))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_sub[\"label\"] = 3","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_sub.to_csv(\"submission.csv\")","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}