def train(self, table_name, indep, dep, numIter=100, optimizer='irls',precision=0.001):
'''
Given train a logistic regression model on the specified table
for the given set of independent and dependent variables
Inputs :
========
table_name : (String) input table name
indep : (String) column containing independent variables as an array, to be used to build the model on
OR
(list) a list of strings, where each element of the list is a column name of table_name or is a constant number
dep : (string) the class label.
Output :
========
The Model coefficients, r2, p_values and t_stats
The function also returns the model object.
'''
self.model = {}
#If indep is a list, then the input is specified as a list of columns in a table.
#1) First, we will transform any categorical columns in this list.
#2) We will marshal the values from the columns into an array, that can be passed on to MADlib's logistic regression algorithm.
if(isinstance(indep,[].__class__)):
self.model['indep_org'] = indep
table_name, indep, dep, _ = pivotCategoricalColumns(self.dbconn,table_name, indep, dep)
#Convert transformed independent columns into an array
table_name, indep = convertsColsToArray(self.dbconn, table_name, indep, dep)
else:
self.model['indep_org'] = indep
self.model['indep'] = indep
self.model['dep'] = dep
stmt = '''
select *
from madlib.logregr('{table_name}','{dep}','{indep}',{numIter}, '{optimizer}', {precision})
'''
stmt = stmt.format(dep=dep,
indep=self.model['indep'],
table_name=table_name,
numIter=numIter,
optimizer=optimizer,
precision=precision
)
print '\nstatement :',stmt
print '\n'
cursor = self.dbconn.getCursor()
cursor.execute(stmt)
row_set = self.dbconn.fetchRowsFromCursor(cursor)
mdl_params = self.dbconn.fetchModelParams(row_set)
self.dbconn.printModel(row_set)
for param in mdl_params:
self.model[param] = mdl_params[param]
return self.model
def predict(self, predict_table_name,actual_label_col='',threshold=0.5):
'''
Return predicted values using the trained model. Also return precision, recall & f-measure
Input:
======
predict_table_name : (String) the name of the table to be used for prediction
actual_label_col : (String) the name of the actual label column (will be ignored if empty).
threshold : (float), the probability beyond which the predicted values will be considered +ve (default: 0.5)
Output:
=======
A cursor to the row set of the results, including the predicted value as column 'prediction'
'''
#If the independent columns specified in the training method were a list (instead of a column name of type array)
#We should transform the independent columns in the predict table as well
if(isinstance(self.model['indep_org'],[].__class__)):
predict_table_name, indep, dep, _ = pivotCategoricalColumns(self.dbconn,predict_table_name, self.model['indep_org'], actual_label_col)
#Convert transformed independent columns into an array
predict_table_name, indep = convertsColsToArray(self.dbconn, predict_table_name, indep, dep)
stmt = ''' '''
if(threshold):
stmt = '''
select *,
case when (1.0/(1.0 + exp(-1.0*madlib.array_dot({indep}, array{coef}::real[])))) > {threshold}
THEN 1 ELSE 0
end as prediction
from {table_name}
'''.format(coef=self.model['coef'],
indep=self.model['indep'],
table_name=predict_table_name,
threshold=threshold
)
else:
#If threshold is not specified, we will return actual predictions
stmt = '''
select *,
(1.0/(1.0 + exp(-1.0*madlib.array_dot({indep}, array{coef}::real[])))) as prediction
from {table_name}
'''.format(coef=self.model['coef'],
indep=self.model['indep'],
table_name=predict_table_name
)
print '\nstatement:',stmt
print '\n'
cursor = self.dbconn.getCursor()
cursor.execute(stmt)
return cursor
def train(self, table_name, indep, dep, numIter=100, optimizer='irls',precision=0.001):
'''
Given train a logistic regression model on the specified table
for the given set of independent and dependent variables
Inputs :
========
table_name : (String) input table name
indep : (String) column containing independent variables as an array, to be used to build the model on
OR
(list) a list of strings, where each element of the list is a column name of table_name or is a constant number
dep : (string) the class label.
Output :
========
The Model coefficients, r2, p_values and t_stats
The function also returns the model object.
'''
self.model = {}
#If indep is a list, then the input is specified as a list of columns in a table.
#1) First, we will transform any categorical columns in this list.
#2) We will marshal the values from the columns into an array, that can be passed on to MADlib's logistic regression algorithm.
if(isinstance(indep,[].__class__)):
self.model['indep_org'] = indep
table_name, indep, dep, _ = pivotCategoricalColumns(self.dbconn,table_name, indep, dep)
#Convert transformed independent columns into an array
table_name, indep = convertsColsToArray(self.dbconn, table_name, indep, dep)
else:
self.model['indep_org'] = indep
self.model['indep'] = indep
self.model['dep'] = dep
stmt = '''
select *
from {madlib_schema}.logregr('{table_name}','{dep}','{indep}',{numIter}, '{optimizer}', {precision})
'''.format(dep=dep,
indep=self.model['indep'],
table_name=table_name,
numIter=numIter,
optimizer=optimizer,
precision=precision,
madlib_schema=self.dbconn.madlib_schema
)
logging.info('statement :{0}'.format(stmt))
mdl_params = psql.read_frame(stmt, self.dbconn.getConnection())
for param in mdl_params.columns:
self.model[param] = mdl_params.get(param)[0]
return self.model, mdl_params
def predict(self, predict_table_name,actual_label_col='',threshold=0.5):
'''
Return predicted values using the trained model. Also return precision, recall & f-measure
Input:
======
predict_table_name : (String) the name of the table to be used for prediction
actual_label_col : (String) the name of the actual label column (will be ignored if empty).
threshold : (float), the probability beyond which the predicted values will be considered +ve (default: 0.5)
Output:
=======
A cursor to the row set of the results, including the predicted value as column 'prediction'
'''
#If the independent columns specified in the training method were a list (instead of a column name of type array)
#We should transform the independent columns in the predict table as well
if(isinstance(self.model['indep_org'],[].__class__)):
predict_table_name, indep, dep, _ = pivotCategoricalColumns(self.dbconn,predict_table_name, self.model['indep_org'], actual_label_col)
#Convert transformed independent columns into an array
predict_table_name, indep = convertsColsToArray(self.dbconn, predict_table_name, indep, dep)
stmt = ''' '''
if(threshold):
stmt = '''
select *,
case when (1.0/(1.0 + exp(-1.0*{madlib_schema}.array_dot({indep}, array{coef}::real[])))) > {threshold}
THEN 1 ELSE 0
end as prediction
from {table_name}
'''.format(coef=self.model['coef'],
indep=self.model['indep'],
table_name=predict_table_name,
threshold=threshold,
madlib_schema=self.dbconn.getMADlibSchema()
)
else:
#If threshold is not specified, we will return actual predictions
stmt = '''
select *,
(1.0/(1.0 + exp(-1.0*{madlib_schema}.array_dot({indep}, array{coef}::real[])))) as prediction
from {table_name}
'''.format(coef=self.model['coef'],
indep=self.model['indep'],
table_name=predict_table_name,
madlib_schema=self.dbconn.getMADlibSchema()
)
logging.info('statement:{0}'.format(stmt))
prediction_results = psql.read_frame(stmt,self.dbconn.getConnection())
return prediction_results
