{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"collapsed":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":{},"cell_type":"markdown","source":"# **Data Analysis**","execution_count":null},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"df_train = pd.read_csv('/kaggle/input/osic-pulmonary-fibrosis-progression/train.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train.head(5)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train.hist()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train.describe()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train['Sex'].value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train['SmokingStatus'].value_counts()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# **Simple Linear Model**\nThe correlation between the input features (Age, Sex, SmokingStatus) and the predicted variable(FVC)","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.linear_model import LinearRegression\nfrom sklearn.ensemble import RandomForestRegressor\nfrom sklearn.model_selection import train_test_split\nfrom sklearn import preprocessing\nmin_max_scaler = preprocessing.MinMaxScaler()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train['Sex'] = df_train['Sex'].replace({'Male':0,'Female':1})\ndf_train['SmokingStatus'] = df_train['SmokingStatus'].replace({'Ex-smoker':0,'Never smoked':1,'Currently smokes':2})\ndf_train = df_train.sort_values(['Patient','Weeks'])\ndf = df_train.drop_duplicates(subset = ['Patient'],keep='first')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X = df_train[['Age','Sex','SmokingStatus']]\ny = df_train[['FVC']]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.8, random_state = 42)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"reg = LinearRegression().fit(X_train, y_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"reg.score(X_test,y_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"forest = RandomForestRegressor(max_depth=2, random_state=0)\nforest.fit(X_train,y_train['FVC'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"forest.score(X_test,y_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"collapsed":true},"cell_type":"code","source":"!pip install rfpimp","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.metrics import r2_score\nfrom rfpimp import permutation_importances\n\ndef r2(rf, X_train, y_train):\n    return r2_score(y_train, rf.predict(X_train))\n\nperm_imp_rfpimp = permutation_importances(forest, X_train, y_train, r2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"perm_imp_rfpimp","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train[df_train['Sex']==0]['FVC'].hist()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train[df_train['Sex']==1]['FVC'].hist()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train.plot.scatter(x='Age',y='FVC')","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}