{"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\n\"\"\"\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":{"trusted":true},"cell_type":"code","source":"import cv2\nimport json \n\nBASE_DIR = \"../input/cassava-leaf-disease-classification/\"\ninput_files = os.listdir(os.path.join(BASE_DIR, \"train_images\"))\ntrain_df = pd.read_csv(os.path.join(BASE_DIR, \"train.csv\"))\n\n# Read class mapping as dict\nwith open(os.path.join(BASE_DIR, \"label_num_to_disease_map.json\")) as file:\n    map_classes = json.loads(file.read())\n\n# Map clas to name\ntrain_df [\"class_name\"] = train_df[\"label\"].astype(str).map(map_classes)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Look at class label distribution\ntrain_df['class_name'].value_counts().plot(kind=\"barh\")\nprint(train_df['class_name'].value_counts())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"## The data is imbalanced and has a high number of CMD class examples","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\n\ndef visualize_batch(image_ids, labels):\n    plt.figure(figsize=(20, 16))\n    \n    for ind, (image_id, label) in enumerate(zip(image_ids, labels)):\n        plt.subplot(4, 4, ind + 1)\n        image = cv2.imread(os.path.join(BASE_DIR, \"train_images\", image_id))\n        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)\n        plt.imshow(image)\n        plt.title(f\"Class: {label}\", fontsize=12)\n        plt.axis(\"off\")\n    \n    plt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Sample df and visualize labels\niters = 3\nnum_samples = 16\nfor i in range(iters):\n    tmp_df = train_df.sample(num_samples)\n    image_ids = tmp_df[\"image_id\"].values\n    labels = tmp_df[\"class_name\"].values\n\n    visualize_batch(image_ids, labels)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Visualize unique classes\nunique_df = train_df.groupby('class_name').aggregate({'image_id': max})\nimage_ids = unique_df[\"image_id\"].values\nlabels = unique_df.index.values\nvisualize_batch(image_ids, labels)","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}