def logisticRegDemo(conn):
'''
Demonstrate Logistic Regression
'''
#1) Logistic Regression with Numeric Variables Alone
log_reg = LogisticRegression(conn)
#Train Model
mdl_dict, mdl_params = log_reg.train('public.wine_bool_training_set','indep','quality_label')
#Show Model Parameters
mdl_params.head()
#2) Logistic Regression Prediction
predictions = log_reg.predict('wine_bool_test_set','',None)
predictions.head()
#Display ROC Curve
actual = predictions.get('quality_label')
predicted = predictions.get('prediction')
ROCPlot('ROC curve Logistic Reg. on Continuous Features ',['Logistic Regression'],actual,predicted)
# 2) Logistic Regression with mixture of numeric and categorical columns
mdl_dict, mdl_params = log_reg.train('public.auto_mpg_bool_train',['1','height','width','length','highway_mpg',
'engine_size','make','fuel_type','fuel_system'],
'is_expensive'
)
predictions = log_reg.predict('auto_mpg_bool_test','is_expensive',None)
cols = conn.fetchColumns(cursor,['is_expensive','prediction'])
actual = predictions.get('is_expensive')
predicted = predictions.get('prediction')
ROCPlot('ROC curve Logistic Reg. including categorical data',['Logistic Regression'],actual,predicted)
def logisticRegDemo(conn):
'''
Demonstrate Logistic Regression
'''
# a) Logistic Regression with numeric attributes
log_reg = LogisticRegression(conn)
log_reg.train('public.wine_bool_training_set','indep','quality_label')
cursor = log_reg.predict('public.wine_bool_test_set','',0.5)
conn.printTable(cursor,['id','quality_label','prediction'])
# b) ROC curve for Logistic Regression using numeric features alone,
# Note: Here threshold is set to None, to be able to plot ROC curve
cursor = log_reg.predict('wine_bool_test_set','',None)
cols = conn.fetchColumns(cursor,['quality_label','prediction'])
actual = cols['quality_label']
predicted = cols['prediction']
#show ROC curve
ROCPlot('ROC curve Logistic Reg. on Continuous Features ',['Logistic Regression'],actual,predicted)
# c) Logistic Regression with mixture of numeric and categorical columns
log_reg.train('public.auto_mpg_bool_train',['1','height','width','length','highway_mpg','engine_size','make','fuel_type','fuel_system'],'is_expensive')
cursor = log_reg.predict('auto_mpg_bool_test','is_expensive',None)
cols = conn.fetchColumns(cursor,['is_expensive','prediction'])
actual = cols['is_expensive']
predicted = cols['prediction']
ROCPlot('ROC curve Logistic Reg. including categorical data',['Logistic Regression'],actual,predicted)
def logisticRegDemo(conn):
'''
Demonstrate Logistic Regression
'''
#1) Logistic Regression with Numeric Variables Alone
log_reg = LogisticRegression(conn)
#Train Model
mdl_dict, mdl_params = log_reg.train('public.wine_bool_training_set',
'indep', 'quality_label')
#Show Model Parameters
mdl_params.head()
#2) Logistic Regression Prediction
predictions = log_reg.predict('wine_bool_test_set', '', None)
predictions.head()
#Display ROC Curve
actual = predictions.get('quality_label')
predicted = predictions.get('prediction')
ROCPlot('ROC curve Logistic Reg. on Continuous Features ',
['Logistic Regression'], actual, predicted)
# 2) Logistic Regression with mixture of numeric and categorical columns
mdl_dict, mdl_params = log_reg.train('public.auto_mpg_bool_train', [
'1', 'height', 'width', 'length', 'highway_mpg', 'engine_size', 'make',
'fuel_type', 'fuel_system'
], 'is_expensive')
predictions = log_reg.predict('auto_mpg_bool_test', 'is_expensive', None)
cols = conn.fetchColumns(cursor, ['is_expensive', 'prediction'])
actual = predictions.get('is_expensive')
predicted = predictions.get('prediction')
ROCPlot('ROC curve Logistic Reg. including categorical data',
['Logistic Regression'], actual, predicted)