{"cells":[{"cell_type":"code","execution_count":2,"metadata":{"id":"l-o4NKrapnp-","executionInfo":{"status":"ok","timestamp":1690600675509,"user_tz":-480,"elapsed":1113,"user":{"displayName":"tc Lin","userId":"05338448855796845949"}}},"outputs":[],"source":["import numpy as np\n","import pandas as pd\n","\n","#from sklearn.datasets import load_boston\n","from sklearn.model_selection import train_test_split\n","from sklearn import metrics\n","from sklearn import preprocessing\n","from sklearn.neighbors import KNeighborsRegressor"]},{"cell_type":"code","execution_count":3,"metadata":{"id":"OpXxDIwUpnqB","executionInfo":{"status":"ok","timestamp":1690600678826,"user_tz":-480,"elapsed":301,"user":{"displayName":"tc Lin","userId":"05338448855796845949"}}},"outputs":[],"source":["# load digits data\n","data_url = \"http://lib.stat.cmu.edu/datasets/boston\"\n","raw_df = pd.read_csv(data_url, sep=\"\\s+\", skiprows=22, header=None)\n","data = np.hstack([raw_df.values[::2, :], raw_df.values[1::2, :2]])\n","target = raw_df.values[1::2, 2]\n","\n","boston_X = data\n","boston_y = target"]},{"cell_type":"code","execution_count":4,"metadata":{"id":"9IVy_NEtpnqB","executionInfo":{"status":"ok","timestamp":1690600682452,"user_tz":-480,"elapsed":272,"user":{"displayName":"tc Lin","userId":"05338448855796845949"}}},"outputs":[],"source":["boston_X = preprocessing.scale(boston_X, axis=0)"]},{"cell_type":"code","execution_count":5,"metadata":{"id":"a3T5Tn0TpnqC","executionInfo":{"status":"ok","timestamp":1690600685285,"user_tz":-480,"elapsed":288,"user":{"displayName":"tc Lin","userId":"05338448855796845949"}}},"outputs":[],"source":["# split training data\n","train_X, val_X, train_y, val_y = train_test_split(boston_X,\n","                                                  boston_y,\n","                                                  test_size=0.2,\n","                                                  random_state=5566)"]},{"cell_type":"code","execution_count":6,"metadata":{"id":"V8eHWrPSpnqC","executionInfo":{"status":"ok","timestamp":1690600689052,"user_tz":-480,"elapsed":4,"user":{"displayName":"tc Lin","userId":"05338448855796845949"}}},"outputs":[],"source":["# create KNN model\n","model = KNeighborsRegressor(n_neighbors=3)\n","\n","# Train the model using the training sets\n","model.fit(train_X, train_y)\n","\n","# Predict Output\n","predicted = model.predict(val_X)"]},{"cell_type":"code","execution_count":7,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"BkzHw8P1pnqD","executionInfo":{"status":"ok","timestamp":1690600692285,"user_tz":-480,"elapsed":302,"user":{"displayName":"tc Lin","userId":"05338448855796845949"}},"outputId":"e81b8a03-e331-4a9b-e4a8-5d6883d1b3c4"},"outputs":[{"output_type":"stream","name":"stdout","text":["r2 score:  0.7845053625839071\n"]}],"source":["# r2 score\n","r2 = metrics.r2_score(y_true=val_y, y_pred=predicted)\n","print('r2 score: ', r2)"]},{"cell_type":"code","execution_count":8,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"BX7IPOU8pnqD","executionInfo":{"status":"ok","timestamp":1690600694366,"user_tz":-480,"elapsed":306,"user":{"displayName":"tc Lin","userId":"05338448855796845949"}},"outputId":"df516116-e659-4bd8-ad53-fc8972c916cc"},"outputs":[{"output_type":"stream","name":"stdout","text":["mse score:  17.71159041394336\n"]}],"source":["# mse\n","mse = metrics.mean_squared_error(y_true=val_y, y_pred=predicted)\n","print('mse score: ', mse)"]}],"metadata":{"kernelspec":{"display_name":"Python 3 (ipykernel)","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.10.2"},"toc":{"base_numbering":1,"nav_menu":{},"number_sections":true,"sideBar":true,"skip_h1_title":false,"title_cell":"Table of Contents","title_sidebar":"Contents","toc_cell":false,"toc_position":{},"toc_section_display":true,"toc_window_display":false},"colab":{"provenance":[]}},"nbformat":4,"nbformat_minor":0}