{"cells":[{"metadata":{"trusted":true},"cell_type":"code","source":"import pandas as pd\ntrain_df = pd.read_csv(\"../input/osic-pulmonary-fibrosis-progression/train.csv\")\ntrain_df","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.pyplot as plt\nsns.regplot(x=train_df[\"Age\"], y=train_df[\"FVC\"])\nsns.scatterplot(x=train_df[\"Age\"], y=train_df[\"FVC\"], hue=train_df['SmokingStatus'])\n\nax = plt.axes()\nax.set_title('Distribution of Age and FVC for unique patients')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.lmplot(x=\"Age\", y=\"FVC\", hue=\"SmokingStatus\", data=train_df)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.lmplot(x=\"Age\", y=\"FVC\", hue=\"Sex\", data=train_df)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\nsns.swarmplot(x=train_df['Sex'],\n              y=train_df['FVC'],hue=train_df['SmokingStatus'])\nplt.figure(figsize=(10,10))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\nsns.swarmplot(x=train_df['SmokingStatus'],\n              y=train_df['FVC'],hue=train_df['Sex'])\nplt.figure(figsize=(10,10))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"new_df = train_df.groupby([train_df.Patient,train_df.Age,train_df.Sex, train_df.SmokingStatus])['Patient'].count() \nnew_df.index = new_df.index.set_names(['id','Age','Sex','SmokingStatus'])\nnew_df = new_df.reset_index()\nnew_df.rename(columns = {'Patient': 'freq'},inplace = True) \nnew_df","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\nfor Patient in new_df['id']:\n    train2=train_df.loc[train_df.Patient == Patient]\n    graph = plt.plot(train2[\"Weeks\"], train2[\"FVC\"] )\n    plt.xlabel(\"Weeks\")\n    plt.ylabel(\"FVC\")\n    plt.title(\"{}\".format(Patient))\n    plt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Reference**\n\n・https://www.kaggle.com/twinkle0705/your-starter-notebook-for-osic","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}