{"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# for 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 5GB 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":{},"cell_type":"markdown","source":"**Some of the content are reffered from different notebooks**","execution_count":null},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"\nimport os\nimport json\nfrom pathlib import Path\n\nimport matplotlib.pyplot as plt\n%matplotlib inline","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"path = Path(\"kaggle/input/siim-isic-melanoma-classification/\")\ntrain_path = path / 'train'\ntest_path = path / 'test'\n\nprint(train_path)\nprint(test_path)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!ls /kaggle/input/siim-isic-melanoma-classification/","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"img_train_path = path / 'jpeg' / 'train'\nimg_test_path = path / 'jpeg' / 'test'\n\nprint(img_train_path)\nprint(img_test_path)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow.python.keras.preprocessing.image import load_img, img_to_array\n\nfrom keras import models, regularizers, layers, optimizers, losses, metrics\nfrom keras.models import Sequential\nfrom keras.layers import Dense, Conv2D, Conv3D\nfrom keras.utils import np_utils, to_categorical\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.preprocessing import image","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def image_show(img_num, img_folder, img_size):\n    \n    img_ind = 'ISIC'\n    img_name = '{}_{}'.format(img_ind, img_num)\n    \n    if img_folder == 'train':\n        img_dir = img_train_path\n    elif img_folder == 'test':\n        img_dir = img_test_path\n        \n    img_path = str(img_dir)+'/'+str(img_name)+'.jpg'\n    \n    print(\"Image Path\", img_path)\n    \n    img = image.load_img(img_path, target_size = (img_size, img_size))\n    imgplot = plt.imshow(img)\n    print(img_ind, \"Image Number\", img_num)\n    plt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"image_show('0074542', 'train', 224)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#importing CSV Dataset\ntrain_path = path / 'train.csv'\ntest_path = path / 'test.csv'\ntrain = pd.read_csv(train_path)\ntest  = pd.read_csv(test_path)\n\ntrain.shape, test.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.isna().sum()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train['sex'] = train['sex'].fillna('na')\ntrain['anatom_site_general_challenge'] = train['anatom_site_general_challenge'].fillna('na')\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Replacing Null age values with the mean age of the training_set\n\ntrain['age_approx'] = train['age_approx'].fillna(int(train['age_approx'].mean()))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test.isna().sum()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test['anatom_site_general_challenge'] = test['anatom_site_general_challenge'].fillna('na')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head()","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}