{"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)\nimport seaborn as sns\nimport matplotlib.pyplot as plt\n%matplotlib inline\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":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train_df = pd.read_csv(\"/kaggle/input/siim-isic-melanoma-classification/train.csv\")\ntest_df = pd.read_csv(\"/kaggle/input/siim-isic-melanoma-classification/test.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(\"Class count for training dataset \\n\",pd.Index(train_df['benign_malignant']).value_counts())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df.isna().sum()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df.patient_id.nunique()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df['target'].value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df['anatom_site_general_challenge'].value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df['diagnosis'].value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import random\nIMAGE_PATH = \"../input/siim-isic-melanoma-classification/\"\nimages = train_df['image_name'].values\nrandom_images = [np.random.choice(images+'.jpg') for i in range(6)]\nimg_dir = IMAGE_PATH+'/jpeg/train'\nplt.figure(figsize=(10,8))\nfor i in range(6):\n    plt.subplot(2, 3, i + 1)\n    img = plt.imread(os.path.join(img_dir, random_images[i]))\n    plt.imshow(img, cmap='gray')\n    plt.axis('off')\nplt.tight_layout()  ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import pydicom\ndef show_dcm_info(dataset):\n    print(\"Filename.........:\", file_path)\n    print(\"Storage type.....:\", dataset.SOPClassUID)\n    print()\n\n    pat_name = dataset.PatientName\n    display_name = pat_name.family_name + \", \" + pat_name.given_name\n    print(\"Patient's name......:\", display_name)\n    print(\"Patient id..........:\", dataset.PatientID)\n    print(\"Patient's Age.......:\", dataset.PatientAge)\n    print(\"Patient's Sex.......:\", dataset.PatientSex)\n    print(\"Modality............:\", dataset.Modality)\n    print(\"Body Part Examined..:\", dataset.BodyPartExamined)\n    \n    if 'PixelData' in dataset:\n        rows = int(dataset.Rows)\n        cols = int(dataset.Columns)\n        print(\"Image size.......: {rows:d} x {cols:d}, {size:d} bytes\".format(\n            rows=rows, cols=cols, size=len(dataset.PixelData)))\n        if 'PixelSpacing' in dataset:\n            print(\"Pixel spacing....:\", dataset.PixelSpacing)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def plot_pixel_array(dataset, figsize=(10,10)):\n    plt.figure(figsize=figsize)\n    plt.imshow(dataset.pixel_array, cmap=plt.cm.bone)\n    plt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"i = 1\nnum_to_plot = 2\nfor file_name in os.listdir('../input/siim-isic-melanoma-classification/train/'):\n    file_path = os.path.join('../input/siim-isic-melanoma-classification/train/', file_name)\n    dataset = pydicom.dcmread(file_path)\n    show_dcm_info(dataset)\n    plot_pixel_array(dataset)\n    \n    if i >= num_to_plot:\n        break\n    \n    i += 1","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}