{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":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":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\n%matplotlib inline","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"raw_data = pd.read_csv('/kaggle/input/osic-pulmonary-fibrosis-progression/train.csv')\ntest = pd.read_csv('/kaggle/input/osic-pulmonary-fibrosis-progression/test.csv')\nraw_data.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import seaborn as sns\nsns.distplot(raw_data['FVC'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y  = raw_data['FVC']\nx =  raw_data[['Patient','Weeks','Percent','Age','Sex','SmokingStatus']]\ny_test  = test['FVC']\nx_test =  test[['Patient','Weeks','Percent','Age','Sex','SmokingStatus']]\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.preprocessing import OneHotEncoder\noe = OneHotEncoder()\nX = oe.fit_transform(x)\nX_test = oe.transform(x_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X.shape,X_test.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.decomposition import TruncatedSVD\ntv = TruncatedSVD(n_components = 10)\nX_transformed = tv.fit_transform(X)\nX_test_transformed = tv.transform(X_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_transformed.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_test_transformed.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.cluster import KMeans\nkmeans = KMeans(n_clusters =2)\nkmeans.fit(X_transformed,y)\nX_transformed= pd.DataFrame(X_transformed)\nX_test_transformed1 = pd.DataFrame(X_test_transformed)\nX_transformed['labels'] = kmeans.labels_\ny_pred_dummy = kmeans.predict(X_test_transformed1)\nX_test_transformed1['labels'] =y_pred_dummy","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_transformed","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_test_transformed1","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from xgboost import XGBRegressor\nxgb = XGBRegressor(reg_lambda = 0.5 ,learning_rate = 1.5)\nxgb.fit(X_transformed,y)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"xgb.score(X_test_transformed1,y_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_pred = xgb.predict(X_test_transformed1)\ny_pred = pd.DataFrame(y_pred)\ny_test = pd.DataFrame(y_test)\ny_pred","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"list1 = []\nfor i in test.index:\n    list1.append(test.Patient[i]+str('_-')+str(test.Weeks[i]))\n    \nlist1\nsub = pd.DataFrame(columns = ['ID','FVC','Confidence'])\nsub['ID'] = list1\nsub['FVC'] = y_pred[0]\nsub['Confidence'] = 100\nsub.to_csv('submission.csv', index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub","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}