{"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 in \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 \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n\nimport os\nprint(os.listdir(\"../input\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"# Read the data\ntrain = pd.read_csv('../input/train.csv')\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"150c26476ccfe251d615ce27f78000e2cb14a66c"},"cell_type":"code","source":"\n# pull data into target (y) and predictors (X)\ntrain_y = train.SalePrice\npredictor_cols = ['LotArea', 'OverallQual', 'YearBuilt', 'TotRmsAbvGrd']\n\n# Create training predictors data\ntrain_X = train[predictor_cols]\n\nfrom sklearn.ensemble import RandomForestRegressor\nmy_model = RandomForestRegressor()\nmy_model.fit(train_X, train_y)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"33e1d8e1ea45c6dc8b064bc531cbdadff0007a26"},"cell_type":"code","source":"# Read the test data\ntest = pd.read_csv('../input/test.csv')\n# Treat the test data in the same way as training data. In this case, pull same columns.\ntest_X = test[predictor_cols]\n# Use the model to make predictions\npredicted_prices = my_model.predict(test_X)\n# We will look at the predicted prices to ensure we have something sensible.\nprint(predicted_prices)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"073544821e3f98b0d3a0c479e36f549186cc9d62"},"cell_type":"code","source":"my_submission = pd.DataFrame({'Id': test.Id, 'SalePrice': predicted_prices})\n# you could use any filename. We choose submission here\nmy_submission.to_csv('submission.csv', index=False)","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}