{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"\n","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport matplotlib.pyplot as plt\n\ndf_train = pd.read_csv('../input/osic-pulmonary-fibrosis-progression/train.csv')\n\nn_bins = 20\nfor i in df_train.columns[0:]:\n  print(\"Train Dataset\")\n  fig, axs = plt.subplots(1, 2, figsize = (15,5), sharey=True,)\n  fig.suptitle('{} by Sex'.format(i))\n  axs[0].hist(df_train[i][df_train.Sex == 'Male'], bins=n_bins)\n  axs[0].set_title('Male')\n  axs[1].hist(df_train[i][df_train.Sex == 'Female'], bins=n_bins)\n  axs[1].set_title('Female')\n  plt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Some cheap but might prove useful Conclusions**\n* More Male Values than Female\n* FVC Higher in Males\n* To perform age bucketing, might be useful to consider low female frequency\n* Male Max is Ex-Smoker while Female max is Never-Smoked.\n\n","execution_count":null}],"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}