{"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_minor":4,"nbformat":4,"cells":[{"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 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","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2021-09-30T09:59:58.017531Z","iopub.execute_input":"2021-09-30T09:59:58.017926Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train = pd.read_csv(\"../input/rsna-miccai-brain-tumor-radiogenomic-classification/train_labels.csv\")\nprint(\"df_train['MGMT_value'].mean(): {:.6f}\".format(df_train['MGMT_value'].mean()))\ndf_train.head()","metadata":{"execution":{"iopub.status.busy":"2021-09-30T10:01:16.444276Z","iopub.execute_input":"2021-09-30T10:01:16.444576Z","iopub.status.idle":"2021-09-30T10:01:16.463448Z","shell.execute_reply.started":"2021-09-30T10:01:16.444548Z","shell.execute_reply":"2021-09-30T10:01:16.462570Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_test = pd.read_csv(\"../input/rsna-miccai-brain-tumor-radiogenomic-classification/sample_submission.csv\")\nprint('len(df_test): {}'.format(len(df_test)))\ndf_test.head()","metadata":{"execution":{"iopub.status.busy":"2021-09-30T10:01:37.895009Z","iopub.execute_input":"2021-09-30T10:01:37.895309Z","iopub.status.idle":"2021-09-30T10:01:37.914424Z","shell.execute_reply.started":"2021-09-30T10:01:37.895277Z","shell.execute_reply":"2021-09-30T10:01:37.913516Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train.info()","metadata":{"execution":{"iopub.status.busy":"2021-09-30T10:03:34.535160Z","iopub.execute_input":"2021-09-30T10:03:34.535477Z","iopub.status.idle":"2021-09-30T10:03:34.561555Z","shell.execute_reply.started":"2021-09-30T10:03:34.535446Z","shell.execute_reply":"2021-09-30T10:03:34.559803Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train.hist()","metadata":{"execution":{"iopub.status.busy":"2021-09-30T10:03:48.372662Z","iopub.execute_input":"2021-09-30T10:03:48.373077Z","iopub.status.idle":"2021-09-30T10:03:48.828897Z","shell.execute_reply.started":"2021-09-30T10:03:48.373046Z","shell.execute_reply":"2021-09-30T10:03:48.827775Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import matplotlib.pyplot as plt\ndf_train.head(5).value_counts().plot(kind=\"bar\")","metadata":{"execution":{"iopub.status.busy":"2021-09-30T10:06:46.858482Z","iopub.execute_input":"2021-09-30T10:06:46.858762Z","iopub.status.idle":"2021-09-30T10:06:47.065830Z","shell.execute_reply.started":"2021-09-30T10:06:46.858734Z","shell.execute_reply":"2021-09-30T10:06:47.064671Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train.head(10).value_counts().plot(kind=\"pie\")\nplt.title(\"unique values count in train dataset\")","metadata":{"execution":{"iopub.status.busy":"2021-09-30T10:07:43.261869Z","iopub.execute_input":"2021-09-30T10:07:43.262143Z","iopub.status.idle":"2021-09-30T10:07:43.421837Z","shell.execute_reply.started":"2021-09-30T10:07:43.262117Z","shell.execute_reply":"2021-09-30T10:07:43.420514Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_test.head(10).value_counts().plot(kind=\"pie\")\nplt.title(\"values count in 'test data set'\")","metadata":{"execution":{"iopub.status.busy":"2021-09-30T10:09:13.729558Z","iopub.execute_input":"2021-09-30T10:09:13.729896Z","iopub.status.idle":"2021-09-30T10:09:13.898480Z","shell.execute_reply.started":"2021-09-30T10:09:13.729864Z","shell.execute_reply":"2021-09-30T10:09:13.897606Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_test.head(5).plot(kind=\"line\")\nplt.title(\"line chart for the test dataset\")","metadata":{"execution":{"iopub.status.busy":"2021-09-30T10:10:51.818505Z","iopub.execute_input":"2021-09-30T10:10:51.818794Z","iopub.status.idle":"2021-09-30T10:10:52.109642Z","shell.execute_reply.started":"2021-09-30T10:10:51.818765Z","shell.execute_reply":"2021-09-30T10:10:52.108544Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train.head(5).plot(kind=\"line\")\nplt.title(\"line chart for the test dataset\")","metadata":{"execution":{"iopub.status.busy":"2021-09-30T10:11:04.282701Z","iopub.execute_input":"2021-09-30T10:11:04.282995Z","iopub.status.idle":"2021-09-30T10:11:04.580796Z","shell.execute_reply.started":"2021-09-30T10:11:04.282967Z","shell.execute_reply":"2021-09-30T10:11:04.579911Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}