def linearRegressionDemo(conn): ''' Demonstrate Linear Regression ''' mdl = LinearRegression(conn) #Train Model and Score lreg = LinearRegression(conn) mdl_dict, mdl_params = lreg.train('public.wine_training_set',['1','alcohol','proline','hue','color_intensity','flavanoids'],'quality') #Show model params mdl_params #Now do prediction predictions = lreg.predict('public.wine_test_set','quality') #Show prediction results predictions.head() #Show Scatter Matrix of Actual Vs Predicted smat = scatter_matrix(predictions.get(['quality','prediction']), diagonal='kde') # 1 b) Linear Regression with categorical variables # We'll use the auto_mpg dataset from UCI : http://archive.ics.uci.edu/ml/machine-learning-databases/autos/imports-85.names # make, fuel_type, fuel_system are all categorical variables, rest are real. #Train Linear Regression Model on a mixture of Numeric and Categorical Variables mdl_dict, mdl_params = lreg.train('public.auto_mpg_train',['1','height','width','length','highway_mpg','engine_size','make','fuel_type','fuel_system'],'price') predictions = lreg.predict('public.auto_mpg_test','price') #Show sample predictions predictions.head() #Display Scatter Plot of Actual Vs Predicted Values smat = scatter_matrix(predictions.get(['price','prediction']), diagonal='kde')
def linearRegressionDemo(conn): ''' Demonstrate Linear Regression ''' mdl = LinearRegression(conn) #Train Model and Score lreg = LinearRegression(conn) mdl_dict, mdl_params = lreg.train( 'public.wine_training_set', ['1', 'alcohol', 'proline', 'hue', 'color_intensity', 'flavanoids'], 'quality') #Show model params mdl_params #Now do prediction predictions = lreg.predict('public.wine_test_set', 'quality') #Show prediction results predictions.head() #Show Scatter Matrix of Actual Vs Predicted smat = scatter_matrix(predictions.get(['quality', 'prediction']), diagonal='kde') # 1 b) Linear Regression with categorical variables # We'll use the auto_mpg dataset from UCI : http://archive.ics.uci.edu/ml/machine-learning-databases/autos/imports-85.names # make, fuel_type, fuel_system are all categorical variables, rest are real. #Train Linear Regression Model on a mixture of Numeric and Categorical Variables mdl_dict, mdl_params = lreg.train('public.auto_mpg_train', [ '1', 'height', 'width', 'length', 'highway_mpg', 'engine_size', 'make', 'fuel_type', 'fuel_system' ], 'price') predictions = lreg.predict('public.auto_mpg_test', 'price') #Show sample predictions predictions.head() #Display Scatter Plot of Actual Vs Predicted Values smat = scatter_matrix(predictions.get(['price', 'prediction']), diagonal='kde')
def linearRegressionDemo(conn): ''' Demonstrate Linear Regression ''' lreg = LinearRegression(conn) lreg.train('public.wine_training_set',['1','alcohol','proline','hue','color_intensity','flavanoids'],'quality') cursor = lreg.predict('public.wine_test_set','quality') rowset = conn.printTable(cursor,['id','quality','prediction']) cols = conn.fetchColumns(rowset,['quality','prediction']) actual = cols['quality'] predicted = cols['prediction'] scatterPlot(actual,predicted, 'wine_test_set') # 1 b) Linear Regression with categorical variables # We'll use the auto_mpg dataset from UCI : http://archive.ics.uci.edu/ml/machine-learning-databases/autos/imports-85.names # make, fuel_type, fuel_system are all categorical variables, rest are real. lreg.train('public.auto_mpg_train',['1','height','width','length','highway_mpg','engine_size','make','fuel_type','fuel_system'],'price') cursor = lreg.predict('public.auto_mpg_test','price') rowset = conn.printTable(cursor,['id','price','prediction']) cols = conn.fetchColumns(rowset,['price','prediction']) print '\n\n Linear Regression Predictions (with categorical variables) :' actual = cols['price'] predicted = cols['prediction'] scatterPlot(actual,predicted, 'auto_mpg_test')