From 11d1f6d753dcce079e6720cb575667f41ab0e8e4 Mon Sep 17 00:00:00 2001 From: Omair Aasim Date: Thu, 13 Aug 2020 09:54:54 +0530 Subject: [PATCH] Update multiple_linear_regression.py --- .../multiple_linear_regression.py | 38 +++---------------- 1 file changed, 5 insertions(+), 33 deletions(-) diff --git a/project_2_multiple_linear_regression/multiple_linear_regression.py b/project_2_multiple_linear_regression/multiple_linear_regression.py index 8840033..ca1126c 100644 --- a/project_2_multiple_linear_regression/multiple_linear_regression.py +++ b/project_2_multiple_linear_regression/multiple_linear_regression.py @@ -13,12 +13,11 @@ y = dataset.iloc[:,4].values # Step 2 - Encode Categorical Data -from sklearn.preprocessing import LabelEncoder, OneHotEncoder -labelEncoder_X = LabelEncoder() -X[:,3] = labelEncoder_X.fit_transform(X[:,3]) - -oneHotEncoder = OneHotEncoder(categorical_features=[3]) -X = oneHotEncoder.fit_transform(X).toarray() +from sklearn.preprocessing import OneHotEncoder +from sklearn.compose import ColumnTransformer +import numpy as np +ct = ColumnTransformer(transformers=[('encoder',OneHotEncoder(),[3])], remainder='passthrough') +X = np.array(ct.fit_transform(X)) # Step 3 - Dummy Trap X = X[:,1:] @@ -34,30 +33,3 @@ # Step 6 - Predict y_pred = regressor.predict(X_test) - -# Add ones -import numpy as np -ones = np.ones(shape = (50,1), dtype=int) -X = np.append(arr = ones, values= X, axis=1) - -# Backward Elimination -import statsmodels.formula.api as sm -X_opt = X[:,[0,1,2,3,4,5]] -regressor_OLS = sm.OLS(endog = y, exog=X_opt).fit() -regressor_OLS.summary() - -X_opt = X[:,[0,1,3,4,5]] -regressor_OLS = sm.OLS(endog = y, exog=X_opt).fit() -regressor_OLS.summary() - -X_opt = X[:,[0,3,4,5]] -regressor_OLS = sm.OLS(endog = y, exog=X_opt).fit() -regressor_OLS.summary() - -X_opt = X[:,[0,3,5]] -regressor_OLS = sm.OLS(endog = y, exog=X_opt).fit() -regressor_OLS.summary() - -X_opt = X[:,[0,3]] -regressor_OLS = sm.OLS(endog = y, exog=X_opt).fit() -regressor_OLS.summary()