{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nfrom sklearn.preprocessing import LabelEncoder\nimport matplotlib.pyplot as plt\nimport os\nfrom pathlib import Path\nfrom sklearn.model_selection import KFold\nfrom sklearn.metrics import mean_absolute_error\n\nle = LabelEncoder()\nROOT = Path(\"../input/osic-pulmonary-fibrosis-progression\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv(ROOT / 'train.csv')\ntest = pd.read_csv(ROOT / 'test.csv')\nsub = pd.read_csv(ROOT / 'sample_submission.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# create training data\n\ntrainData = []\nfor p in train['Patient'].unique():\n    patientData = train[train['Patient'] == p]\n    firstMeasure = list(patientData.iloc[0, :].values)\n    for i, week in enumerate(patientData['Weeks'].iloc[1:]):\n        fvc = patientData.iloc[i, 2]\n        trainDataPoint = firstMeasure + [week, fvc]\n        trainData.append(trainDataPoint)\ntrainData = pd.DataFrame(trainData)\n\ntrainData.columns = ['PatientID', 'first_week', 'first_FVC', 'first_Percent', 'Age', 'Sex', 'SmokingStatus'] + ['target_week', 'target_FVC']\ntrainData['delta_week'] = trainData['target_week'] - trainData['first_week']\ntrainData.drop(columns = ['first_Percent', 'target_week', 'first_week'], inplace = True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# create testing data\nsubSplit = np.array(list(sub['Patient_Week'].apply(lambda x: x.split('_')).values))\ntestData = []\nfor p in np.unique(subSplit[:, 0]):\n    patientData = test[test['Patient'] == p]\n    firstMeasure = list(patientData.iloc[0, :].values)\n    for week in subSplit[subSplit[:, 0] == p, 1]:\n        testDataPoint = firstMeasure + [week]\n        testData.append(testDataPoint)\ntestData = pd.DataFrame(testData)\ntestData.columns = ['PatientID', 'first_week', 'first_FVC', 'first_Percent', 'Age', 'Sex', 'SmokingStatus'] + ['target_week']\n\ntestData['delta_week'] = testData['target_week'].map(int) - testData['first_week']\ntestData.drop(columns = ['first_Percent', 'first_week'], inplace = True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# fe engineering\n# trainData.drop(columns = ['PatientID'], inplace = True)\n# testData.drop(columns = ['PatientID'], inplace = True)\n\ntrainData['Sex'] = le.fit_transform(trainData['Sex'])\ntestData['Sex'] = le.transform(testData['Sex'])\n\ntrainData['SmokingStatus'] = le.fit_transform(trainData['SmokingStatus'])\ntestData['SmokingStatus'] = le.transform(testData['SmokingStatus'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.linear_model import LinearRegression\nfrom sklearn.neighbors import KNeighborsRegressor\n\nmodel = LinearRegression()\nmodel.fit(trainData.drop(columns = ['PatientID', 'target_FVC']), trainData['target_FVC'])\nprediction = model.predict(testData.drop(columns = ['PatientID', 'target_week']))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub = []\nfor i in range(testData.shape[0]):\n    patient, week, pred = testData.loc[i, 'PatientID'], testData.loc[i, 'target_week'], prediction[i]\n    confidence = 225\n    sub.append([patient + '_' + str(week), pred, confidence])\nsub = pd.DataFrame(sub)\nsub.columns = ['Patient_Week', 'FVC', 'Confidence']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub.to_csv('submission.csv', index=False)","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}