{"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        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":"import seaborn as sns \nimport matplotlib\nimport matplotlib.pyplot as plt\n%matplotlib inline \nnp.warnings.filterwarnings('ignore')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!ls ../input/rsna-pneumonia-detection-challenge/","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df = pd.read_csv('../input/rsna-pneumonia-detection-challenge/stage_2_train_labels.csv')\nprint(df.iloc[0])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(df.iloc[10])\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import pydicom\npatientId = df['patientId'][10]\ndcm_file = '../input/rsna-pneumonia-detection-challenge/stage_2_train_images/%s.dcm' % patientId\ndcm_data = pydicom.read_file(dcm_file)\n\nprint(dcm_data)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data_class = pd.read_csv('../input/rsna-pneumonia-detection-challenge/stage_2_detailed_class_info.csv')\ndata_tlables = pd.read_csv('../input/rsna-pneumonia-detection-challenge/stage_2_train_labels.csv')\n\nprint(data_class.iloc[20])\nprint(data_tlables.iloc[20])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def get_feature_distribution(data, feature):\n    # Get the count for each label\n    label_counts = data[feature].value_counts()\n\n    # Get total number of samples\n    total_samples = len(data)\n\n    # Count the number of items in each class\n    print(\"Feature: {}\".format(feature))\n    for i in range(len(label_counts)):\n        label = label_counts.index[i]\n        count = label_counts.values[i]\n        percent = int((count / total_samples) * 10000) / 100\n        print(\"{:<30s}:   {} or {}%\".format(label, count, percent))\n\nget_feature_distribution(data_class, 'class')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_class_dataf = data_tlables.merge(data_class, left_on='patientId', right_on='patientId', how='inner')\ntrain_class_dataf.sample(10)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_class_dataf.describe()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"get_feature_distribution(train_class_dataf, 'class')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def missing_data(data):\n    total = data.isnull().sum().sort_values(ascending = False)\n    percent = (data.isnull().sum()/data.isnull().count()*100).sort_values(ascending = False)\n    return np.transpose(pd.concat([total, percent], axis=1, keys=['Total', 'Percent']))\nmissing_data(train_class_dataf)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.countplot(data_class['class'],order = data_class['class'].value_counts().index, palette='Set3')\n","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}