{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":8552606,"sourceType":"datasetVersion","datasetId":4965286}],"dockerImageVersionId":30732,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"### Linear Regression \nLinear regression is a **statistical method** used to model the relationship between a **dependent variable** and one or more **independent variables**. By fitting a linear equation to observed data, linear regression allows us to **predict** the value of the dependent variable based on the values of the independent variables. The simplest form, simple linear regression, involves one independent variable and fits a straight line (y = mx + b) to the data, where \"m\" is the slope and \"b\" is the y-intercept. **Multiple linear regression** extends this to multiple independent variables, allowing for more complex models and predictions. This technique is widely used in fields such as economics, biology, engineering, and social sciences for predictive analysis and **understanding relationships** between variables. \n \n![image.png](attachment:153968ea-23c4-4921-9735-d78a3298147c.png) \n![image.png](attachment:0358930a-79e4-4051-9e64-87f305d690ac.png)","metadata":{},"attachments":{"153968ea-23c4-4921-9735-d78a3298147c.png":{"image/png":"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"},"0358930a-79e4-4051-9e64-87f305d690ac.png":{"image/png":"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"}}},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\n\nX_data = pd.read_csv('/kaggle/input/house-price-ready-to-modeling/X_HousePrice.csv')\nX_data = X_data.set_index(['Unnamed: 0', 'Unnamed: 1'])\nX_data.info()\n\nX_train = X_data.loc['train']\nX_test = X_data.loc['test']\n\ny_data = pd.read_csv('/kaggle/input/house-price-ready-to-modeling/y_HousePrice.csv')\ny_data = y_data.set_index(['Unnamed: 0', 'Id'])\ny_data.info()\n\ny_train = y_data.loc['train']\ny_test = y_data.loc['test']\n\ny_train_log = np.log(y_train.copy())\ny_test_log = np.log(y_test.copy())","metadata":{"execution":{"iopub.status.busy":"2024-06-08T18:23:26.564421Z","iopub.execute_input":"2024-06-08T18:23:26.565229Z","iopub.status.idle":"2024-06-08T18:23:26.653058Z","shell.execute_reply.started":"2024-06-08T18:23:26.565170Z","shell.execute_reply":"2024-06-08T18:23:26.651676Z"},"trusted":true},"execution_count":26,"outputs":[{"name":"stdout","text":"\nMultiIndex: 1439 entries, ('train', 0) to ('test', 437)\nData columns (total 42 columns):\n # Column Non-Null Count Dtype \n--- ------ -------------- ----- \n 0 num__LotFrontage 1439 non-null float64\n 1 num__LotArea 1439 non-null float64\n 2 num__OverallQual 1439 non-null float64\n 3 num__OverallCond 1439 non-null float64\n 4 num__BsmtUnfSF 1439 non-null float64\n 5 num__TotalBsmtSF 1439 non-null float64\n 6 num__1stFlrSF 1439 non-null float64\n 7 num__GrLivArea 1439 non-null float64\n 8 num__BsmtFullBath 1439 non-null float64\n 9 num__HalfBath 1439 non-null float64\n 10 num__TotRmsAbvGrd 1439 non-null float64\n 11 num__Fireplaces 1439 non-null float64\n 12 num__GarageCars 1439 non-null float64\n 13 num__MoSold 1439 non-null float64\n 14 num__AgeBuilt 1439 non-null float64\n 15 num__AgeRemodAdd 1439 non-null float64\n 16 num__AgeGarageBlt 1439 non-null float64\n 17 num__AgeSold 1439 non-null float64\n 18 nom__MSZoning_RM 1439 non-null float64\n 19 nom__LotShape_Reg 1439 non-null float64\n 20 nom__LandContour_Not Lvl 1439 non-null float64\n 21 nom__LandSlope_Not Gtl 1439 non-null float64\n 22 nom__Neighborhood_CollgCr 1439 non-null float64\n 23 nom__Neighborhood_Sawyer 1439 non-null float64\n 24 nom__RoofStyle_Not Gable 1439 non-null float64\n 25 nom__Exterior2nd_Stucco 1439 non-null float64\n 26 nom__GarageType_Attchd 1439 non-null float64\n 27 nom__GarageType_Basment 1439 non-null float64\n 28 nom__Fence_non-existent 1439 non-null float64\n 29 nom__SaleCondition_Not Normal 1439 non-null float64\n 30 ord__MSSubClass 1439 non-null float64\n 31 ord__ExterQual 1439 non-null float64\n 32 ord__BsmtQual 1439 non-null float64\n 33 ord__BsmtExposure 1439 non-null float64\n 34 ord__BsmtFinType1 1439 non-null float64\n 35 ord__BsmtFinSF1 1439 non-null float64\n 36 ord__BsmtFinType2 1439 non-null float64\n 37 ord__KitchenQual 1439 non-null float64\n 38 ord__FireplaceQu 1439 non-null float64\n 39 ord__GarageArea 1439 non-null float64\n 40 ord__GarageCond 1439 non-null float64\n 41 ord__OpenPorchSF 1439 non-null float64\ndtypes: float64(42)\nmemory usage: 516.7+ KB\n\nMultiIndex: 1439 entries, ('train', 708) to ('test', 1121)\nData columns (total 1 columns):\n # Column Non-Null Count Dtype\n--- ------ -------------- -----\n 0 SalePrice 1439 non-null int64\ndtypes: int64(1)\nmemory usage: 59.2+ KB\n","output_type":"stream"}]},{"cell_type":"code","source":"!pip install --upgrade scikit-learn","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.linear_model import LinearRegression\nfrom sklearn.metrics import r2_score, root_mean_squared_error\n\nmodel = LinearRegression(fit_intercept=True)\nmodel.fit(X_train, y_train_log)\n\ny_pred_train = model.predict(X_train)\ny_pred_test = model.predict(X_test)\n\n\n# R-squared (R2) score for training set\nr2_train = r2_score(y_train_log, y_pred_train)\n\n# Root Mean Squared Error (RMSE) for training set\nrmse_train = root_mean_squared_error(y_train_log, y_pred_train)\n\n# Mean Absolute Percentage Error (MAPE) for training set\n# Avoiding division by zero\ny_train_values = y_train_log.to_numpy()\ny_train_values = y_train_values.reshape(y_train_values.shape[0])\nmape_train = np.mean(np.abs((y_train_values - y_pred_train) / np.where(y_train_values == 0, 1, y_train_values))) * 100\n\n# Correlation between predicted and real values for training set\ncorr_train = np.corrcoef(y_train_values, y_pred_train.ravel())[0, 1]\n\nprint(\"R-squared (R2) score for Training Set:\", r2_train)\nprint(\"Root Mean Squared Error (RMSE) for Training Set:\", rmse_train)\nprint(\"Mean Absolute Percentage Error (MAPE) for Training Set:\", mape_train)\nprint(\"Correlation between predicted and real values for Training Set:\", corr_train)\n\nprint(\"#\"*100)\n#------------------------------------------------------------------------\n\n# R-squared (R2) score\nr2 = r2_score(y_test_log, y_pred_test)\n\n# Root Mean Squared Error (RMSE)\nrmse = root_mean_squared_error(y_test_log, y_pred_test)\n\n# Mean Absolute Percentage Error (MAPE)\n# Avoiding division by zero\ny_test_values = y_test_log.to_numpy()\ny_test_values = y_test_values.reshape(y_test_values.shape[0])\nmape = np.mean(np.abs((y_test_values - y_pred_test) / np.where(y_test_values == 0, 1, y_test_values))) * 100\n\n# Correlation between predicted and real values\ncorr = np.corrcoef(y_test_values, y_pred_test.ravel())[0, 1]\n\nprint(\"R-squared (R2) score for Test Set:\", r2)\nprint(\"Root Mean Squared Error (RMSE) for Test Set:\", rmse)\nprint(\"Mean Absolute Percentage Error (MAPE) for Test Set:\", mape)\nprint(\"Correlation between predicted and real values for Test Set:\", corr)","metadata":{"execution":{"iopub.status.busy":"2024-06-08T18:25:33.763383Z","iopub.execute_input":"2024-06-08T18:25:33.763936Z","iopub.status.idle":"2024-06-08T18:25:33.895499Z","shell.execute_reply.started":"2024-06-08T18:25:33.763895Z","shell.execute_reply":"2024-06-08T18:25:33.893426Z"},"trusted":true},"execution_count":27,"outputs":[{"name":"stdout","text":"R-squared (R2) score for Training Set: 0.9120896462653965\nRoot Mean Squared Error (RMSE) for Training Set: 0.11608348587873038\nMean Absolute Percentage Error (MAPE) for Training Set: 3.5800026443536317\nCorrelation between predicted and real values for Training Set: 0.9550338456124973\n####################################################################################################\nR-squared (R2) score for Test Set: 0.8709783052657468\nRoot Mean Squared Error (RMSE) for Test Set: 0.14114253503861884\nMean Absolute Percentage Error (MAPE) for Test Set: 3.599525629236643\nCorrelation between predicted and real values for Test Set: 0.9489769733781047\n","output_type":"stream"}]},{"cell_type":"code","source":"model.coef_\nmodel.intercept_\nmodel.n_features_in_","metadata":{"trusted":true},"execution_count":30,"outputs":[{"execution_count":30,"output_type":"execute_result","data":{"text/plain":"42"},"metadata":{}}]},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n\nplt.figure(figsize=(6, 4))\nplt.scatter(y_test_log, y_pred_test, color='blue', alpha=0.5)\nplt.plot([y_test_log.min(), y_test_log.max()], [y_test_log.min(), y_test_log.max()], 'k--', lw=2) # Plot the diagonal line\nplt.xlabel('True Values')\nplt.ylabel('Predicted Values')\nplt.title('Predicted Values vs True Values')\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2024-06-08T18:28:05.903758Z","iopub.execute_input":"2024-06-08T18:28:05.904184Z","iopub.status.idle":"2024-06-08T18:28:06.166111Z","shell.execute_reply.started":"2024-06-08T18:28:05.904149Z","shell.execute_reply":"2024-06-08T18:28:06.164739Z"},"trusted":true},"execution_count":31,"outputs":[{"output_type":"display_data","data":{"text/plain":"
","image/png":"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"},"metadata":{}}]},{"cell_type":"markdown","source":"### Ridge Regression \nRidge regression is a type of linear regression that addresses **multicollinearity** (when independent variables are **highly correlated)** by **adding a regularization term to the loss function**. This regularization term, also known as the **penalty term**, is the sum of the squares of the coefficients multiplied by a tuning parameter (alpha). The ridge regression equation minimizes the sum of the squared residuals plus lambda times the sum of the squared coefficients, which helps to **shrink the coefficients towards zero**, thereby reducing their variance and improving model **stability**. This method is particularly useful when dealing with datasets with a **large number of predictors**, providing a balance between bias and variance, and often leading to more **reliable** predictions. \n \n![image.png](attachment:def1545b-2eaa-420b-af81-d90dfc1faccf.png)","metadata":{},"attachments":{"def1545b-2eaa-420b-af81-d90dfc1faccf.png":{"image/png":"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"}}},{"cell_type":"code","source":"from sklearn.linear_model import RidgeCV\nfrom sklearn.metrics import r2_score, root_mean_squared_error\n\nridge_model = RidgeCV(alphas=(0.1, 1.0, 10.0), fit_intercept=True, cv=5, scoring='neg_root_mean_squared_error')\nridge_model.fit(X_train, y_train_log)\n\ny_pred_train = ridge_model.predict(X_train)\ny_pred_test = ridge_model.predict(X_test)\n\n# R-squared (R2) score for training set\nr2_train = r2_score(y_train_log, y_pred_train)\n\n# Root Mean Squared Error (RMSE) for training set\nrmse_train = root_mean_squared_error(y_train_log, y_pred_train)\n\n# Mean Absolute Percentage Error (MAPE) for training set\n# Avoiding division by zero\ny_train_values = y_train_log.to_numpy()\ny_train_values = y_train_values.reshape(y_train_values.shape[0])\nmape_train = np.mean(np.abs((y_train_values - y_pred_train) / np.where(y_train_values == 0, 1, y_train_values))) * 100\n\n# Correlation between predicted and real values for training set\ncorr_train = np.corrcoef(y_train_values, y_pred_train.ravel())[0, 1]\n\nprint(\"R-squared (R2) score for Training Set:\", r2_train)\nprint(\"Root Mean Squared Error (RMSE) for Training Set:\", rmse_train)\nprint(\"Mean Absolute Percentage Error (MAPE) for Training Set:\", mape_train)\nprint(\"Correlation between predicted and real values for Training Set:\", corr_train)\n\nprint(\"#\"*100)\n#------------------------------------------------------------------------\n\n# R-squared (R2) score\nr2 = r2_score(y_test_log, y_pred_test)\n\n# Root Mean Squared Error (RMSE)\nrmse = root_mean_squared_error(y_test_log, y_pred_test)\n\n# Mean Absolute Percentage Error (MAPE)\n# Avoiding division by zero\ny_test_values = y_test_log.to_numpy()\ny_test_values = y_test_values.reshape(y_test_values.shape[0])\nmape = np.mean(np.abs((y_test_values - y_pred_test) / np.where(y_test_values == 0, 1, y_test_values))) * 100\n\n# Correlation between predicted and real values\ncorr = np.corrcoef(y_test_values, y_pred_test.ravel())[0, 1]\n\nprint(\"R-squared (R2) score for Test Set:\", r2)\nprint(\"Root Mean Squared Error (RMSE) for Test Set:\", rmse)\nprint(\"Mean Absolute Percentage Error (MAPE) for Test Set:\", mape)\nprint(\"Correlation between predicted and real values for Test Set:\", corr)","metadata":{"execution":{"iopub.status.busy":"2024-06-08T18:37:13.734350Z","iopub.execute_input":"2024-06-08T18:37:13.735534Z","iopub.status.idle":"2024-06-08T18:37:14.066911Z","shell.execute_reply.started":"2024-06-08T18:37:13.735489Z","shell.execute_reply":"2024-06-08T18:37:14.064684Z"},"trusted":true},"execution_count":32,"outputs":[{"name":"stdout","text":"R-squared (R2) score for Training Set: 0.9119304315514501\nRoot Mean Squared Error (RMSE) for Training Set: 0.11618855790660114\nMean Absolute Percentage Error (MAPE) for Training Set: 3.574659989833252\nCorrelation between predicted and real values for Training Set: 0.9549561751667812\n####################################################################################################\nR-squared (R2) score for Test Set: 0.8606718263592288\nRoot Mean Squared Error (RMSE) for Test Set: 0.1466715949027221\nMean Absolute Percentage Error (MAPE) for Test Set: 3.612553866724936\nCorrelation between predicted and real values for Test Set: 0.9496859680967532\n","output_type":"stream"}]},{"cell_type":"code","source":"ridge_model.coef_\nridge_model.intercept_\nridge_model.alpha_\nridge_model.best_score_","metadata":{"trusted":true},"execution_count":36,"outputs":[{"execution_count":36,"output_type":"execute_result","data":{"text/plain":"-0.12164768968627689"},"metadata":{}}]},{"cell_type":"markdown","source":"### Lasso Regression\nLasso regression, or Least Absolute Shrinkage and Selection Operator, is a type of linear regression that enhances **prediction accuracy** and **interpretability** by performing both **variable selection and regularization**. It introduces a penalty equal to the absolute value of the magnitude of the coefficients, controlled by a tuning parameter (alpha). This penalty can **shrink some coefficients to zero**, effectively selecting a **simpler model** by excluding less significant predictors. Lasso regression is particularly useful when dealing with **high-dimensional data**, as it helps **prevent overfitting** and enhances model interpretability by identifying and retaining only the most relevant features. \n \n![image.png](attachment:6c1a4a6d-ec3d-4e51-a6ad-eaf98b00a8cd.png)\n","metadata":{},"attachments":{"6c1a4a6d-ec3d-4e51-a6ad-eaf98b00a8cd.png":{"image/png":"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"}}},{"cell_type":"code","source":"from sklearn.linear_model import LassoCV\nfrom sklearn.metrics import r2_score, root_mean_squared_error\n\nlasso_model = LassoCV(alphas=None, fit_intercept=True, cv=None)\nlasso_model.fit(X_train, y_train_log)\n\ny_pred_train = lasso_model.predict(X_train)\ny_pred_test = lasso_model.predict(X_test)\n\n\n# R-squared (R2) score for training set\nr2_train = r2_score(y_train_log, y_pred_train)\n\n# Root Mean Squared Error (RMSE) for training set\nrmse_train = root_mean_squared_error(y_train_log, y_pred_train)\n\n# Mean Absolute Percentage Error (MAPE) for training set\n# Avoiding division by zero\ny_train_values = y_train_log.to_numpy()\ny_train_values = y_train_values.reshape(y_train_values.shape[0])\nmape_train = np.mean(np.abs((y_train_values - y_pred_train) / np.where(y_train_values == 0, 1, y_train_values))) * 100\n\n# Correlation between predicted and real values for training set\ncorr_train = np.corrcoef(y_train_values, y_pred_train.ravel())[0, 1]\n\nprint(\"R-squared (R2) score for Training Set:\", r2_train)\nprint(\"Root Mean Squared Error (RMSE) for Training Set:\", rmse_train)\nprint(\"Mean Absolute Percentage Error (MAPE) for Training Set:\", mape_train)\nprint(\"Correlation between predicted and real values for Training Set:\", corr_train)\n\nprint(\"#\"*100)\n#------------------------------------------------------------------------\n\n# R-squared (R2) score\nr2 = r2_score(y_test_log, y_pred_test)\n\n# Root Mean Squared Error (RMSE)\nrmse = root_mean_squared_error(y_test_log, y_pred_test)\n\n# Mean Absolute Percentage Error (MAPE)\n# Avoiding division by zero\ny_test_values = y_test_log.to_numpy()\ny_test_values = y_test_values.reshape(y_test_values.shape[0])\nmape = np.mean(np.abs((y_test_values - y_pred_test) / np.where(y_test_values == 0, 1, y_test_values))) * 100\n\n# Correlation between predicted and real values\ncorr = np.corrcoef(y_test_values, y_pred_test.ravel())[0, 1]\n\nprint(\"R-squared (R2) score for Test Set:\", r2)\nprint(\"Root Mean Squared Error (RMSE) for Test Set:\", rmse)\nprint(\"Mean Absolute Percentage Error (MAPE) for Test Set:\", mape)\nprint(\"Correlation between predicted and real values for Test Set:\", corr)\n","metadata":{"execution":{"iopub.status.busy":"2024-06-08T18:44:38.728927Z","iopub.execute_input":"2024-06-08T18:44:38.729404Z","iopub.status.idle":"2024-06-08T18:44:39.120489Z","shell.execute_reply.started":"2024-06-08T18:44:38.729370Z","shell.execute_reply":"2024-06-08T18:44:39.119059Z"},"trusted":true},"execution_count":37,"outputs":[{"name":"stderr","text":"/opt/conda/lib/python3.10/site-packages/sklearn/linear_model/_coordinate_descent.py:1653: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n y = column_or_1d(y, warn=True)\n","output_type":"stream"},{"name":"stdout","text":"R-squared (R2) score for Training Set: 0.9113534959920047\nRoot Mean Squared Error (RMSE) for Training Set: 0.11656850689300889\nMean Absolute Percentage Error (MAPE) for Training Set: 0.7074634886518049\nCorrelation between predicted and real values for Training Set: 0.9546758256352217\n####################################################################################################\nR-squared (R2) score for Test Set: 0.8710392078411361\nRoot Mean Squared Error (RMSE) for Test Set: 0.14110921909694096\nMean Absolute Percentage Error (MAPE) for Test Set: 0.9095417394305836\nCorrelation between predicted and real values for Test Set: 0.950678412981423\n","output_type":"stream"}]},{"cell_type":"code","source":"lasso_model.alpha_\nlasso_model.coef_\nnumber_nonzero_coef = len(lasso_model.coef_[lasso_model.coef_ != 0])\nlasso_model.feature_names_in_[lasso_model.coef_ != 0]\nlasso_model.intercept_\nlasso_model.mse_path_\nlasso_model.alphas_ ","metadata":{"trusted":true},"execution_count":45,"outputs":[{"execution_count":45,"output_type":"execute_result","data":{"text/plain":"array([0.32110482, 0.29946343, 0.27928059, 0.26045802, 0.24290402,\n 0.2265331 , 0.21126553, 0.19702694, 0.18374798, 0.17136398,\n 0.15981462, 0.14904365, 0.13899861, 0.12963057, 0.1208939 ,\n 0.11274606, 0.10514735, 0.09806077, 0.0914518 , 0.08528826,\n 0.07954012, 0.07417938, 0.06917994, 0.06451744, 0.06016918,\n 0.05611398, 0.05233208, 0.04880508, 0.04551578, 0.04244817,\n 0.0395873 , 0.03691925, 0.03443102, 0.03211048, 0.02994634,\n 0.02792806, 0.0260458 , 0.0242904 , 0.02265331, 0.02112655,\n 0.01970269, 0.0183748 , 0.0171364 , 0.01598146, 0.01490437,\n 0.01389986, 0.01296306, 0.01208939, 0.01127461, 0.01051474,\n 0.00980608, 0.00914518, 0.00852883, 0.00795401, 0.00741794,\n 0.00691799, 0.00645174, 0.00601692, 0.0056114 , 0.00523321,\n 0.00488051, 0.00455158, 0.00424482, 0.00395873, 0.00369193,\n 0.0034431 , 0.00321105, 0.00299463, 0.00279281, 0.00260458,\n 0.00242904, 0.00226533, 0.00211266, 0.00197027, 0.00183748,\n 0.00171364, 0.00159815, 0.00149044, 0.00138999, 0.00129631,\n 0.00120894, 0.00112746, 0.00105147, 0.00098061, 0.00091452,\n 0.00085288, 0.0007954 , 0.00074179, 0.0006918 , 0.00064517,\n 0.00060169, 0.00056114, 0.00052332, 0.00048805, 0.00045516,\n 0.00042448, 0.00039587, 0.00036919, 0.00034431, 0.0003211 ])"},"metadata":{}}]},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n\nplt.figure(figsize=(6, 4))\nplt.plot(lasso_model.alphas_ , lasso_model.mse_path_, marker='o')\nplt.xlabel('Alphas')\nplt.ylabel('MSE')\nplt.title('MSEs at Different Alphas in CV')\nplt.grid(True)\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2024-06-08T18:48:43.563130Z","iopub.execute_input":"2024-06-08T18:48:43.563577Z","iopub.status.idle":"2024-06-08T18:48:43.898445Z","shell.execute_reply.started":"2024-06-08T18:48:43.563544Z","shell.execute_reply":"2024-06-08T18:48:43.897051Z"},"trusted":true},"execution_count":46,"outputs":[{"output_type":"display_data","data":{"text/plain":"
","image/png":"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"},"metadata":{}}]}]}