{"cells":[{"metadata":{},"cell_type":"markdown","source":"# The dataset includes another csv, called train_annotations.cvs that has segmentation (well, more like tracing) of the catheter lines with their labels. In this notebook I will show how to read and display these"},{"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\nimport cv2\nimport re\nfrom matplotlib import pyplot as plt\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":"#read and merge the segmentation csv with the training csv. There are only 17999 annotated images\nseg_df = pd.read_csv(\"../input/ranzcr-clip-catheter-line-classification/train_annotations.csv\")                                                                                                                    \ntrain_df = pd.read_csv(\"../input/ranzcr-clip-catheter-line-classification/train.csv\")                                                                                                                              \nseg_df = seg_df.set_index('StudyInstanceUID').join(train_df.set_index('StudyInstanceUID'), how = 'inner').reset_index()                                                  \n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"images_seg = seg_df.groupby('StudyInstanceUID')\n\ncount = 5 # show only 5 images\n                                                                                                                                                                         \nfor name, group in images_seg:                                                                                                                                           \n    img = cv2.imread(\"../input/ranzcr-clip-catheter-line-classification/train/{}.jpg\".format(name))                                                                                                    \n    print(img.shape)                                                                                                                                                     \n    for d, l in zip(group['data'], group['label']):   \n        print(l)\n        pts = re.sub(\"[\\[\\],]\", \"\", d)                                                                                                                                   \n        pts = np.fromstring(pts, dtype=int, sep=' ')                                                                                                                     \n        pts = pts.reshape(-1, 2)                                                                                                                                         \n        cv2.polylines(img, [pts], False, (255, 255, 0), thickness=4)                                                                                                     \n    plt.imshow(cv2.resize(img, (0,0), fx=0.25, fy=0.25))\n    plt.show()\n    count -= 1\n    if count == 0:\n        break\n","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}