{"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\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.linear_model import LinearRegression\nfrom sklearn.ensemble import RandomForestRegressor\n\nimport seaborn as sns\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":"df=pd.read_csv('/kaggle/input/osic-pulmonary-fibrosis-progression/train.csv')\ndf.shape","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Data Analysis","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"df.isna().sum()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df['SmokingStatus'].unique()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.countplot(df['SmokingStatus'],hue=df['Sex'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df['Weeks']=np.where(df['Weeks']<0,-(df['Weeks']),df['Weeks'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.distplot(df['FVC'])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Removing Outliers","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.boxplot(df.Percent)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.distplot(df.Percent)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(df.Percent.describe())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"value=df['Percent'].mean()+df['Percent'].std()*3\nvalue","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df['Percent'].median()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df['Percent']=np.where(df['Percent']>=120,df['Percent'].median(),df['Percent'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.distplot(df['Percent'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.boxplot(df['Percent'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"dummies=pd.get_dummies(df['SmokingStatus'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df=pd.concat([df,dummies],axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X=df.drop(['Patient','SmokingStatus','Sex'],axis=1)\ny=df['FVC']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model=LinearRegression()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.fit(X,y)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.score(X,y)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df1=pd.read_csv('/kaggle/input/osic-pulmonary-fibrosis-progression/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_test=df.drop(['Patient','SmokingStatus','Sex'],axis=1)\ny_test=df['FVC']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_pred=model.predict(X)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.metrics import r2_score","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"r2_score(y,y_pred)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import statsmodels.api as sm","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"regressor_ols=sm.OLS(endog=y,exog=X).fit()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"regressor_ols.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model1=RandomForestRegressor()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model1.fit(X,y)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_pred1=model1.predict(X_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model1.score(X,y)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","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}