def main():
stub = sys.argv[1]
cxn = SQLCxn(timeout=None, username='******', db='ubuntu')
if not cxn.table_exists('adclick_clean_vectors_split'):
shape = cxn.get_shape('adclick_clean{}_dense'.format(stub))
stmt = """
CREATE TABLE adclick_clean_vectors_split AS (
SELECT row_num, val[1]::INTEGER y, val[2:{}]::NUMERIC[] indep_vars
FROM adclick_clean{}_dense
) DISTRIBUTED BY (row_num)
""".format(shape[1], stub)
cxn.execute(stmt)
if not cxn.table_exists('adclick_clean_indepvars_long'):
stmt = """
CREATE TABLE adclick_clean_indepvars_long AS (
SELECT row_num, ix AS col_num, indep_vars[ix] AS val
FROM (
SELECT *, GENERATE_SUBSCRIPTS(indep_vars, 1) AS ix
FROM adclick_clean_vectors_split
) tmp
) DISTRIBUTED BY (row_num, col_num)
"""
cxn.execute(stmt)
if not cxn.table_exists('adclick_clean_y'):
stmt = """
CREATE TABLE adclick_clean_y AS (
SELECT row_num, 1 AS col_num, y AS val
FROM adclick_clean_vectors_split
) DISTRIBUTED BY (row_num)
"""
cxn.execute(stmt)
def main(kwargs):
opType = kwargs.get('opType')
savestub = kwargs.get('savestub')
nodes = kwargs.get('nodes')
x_table_name = kwargs.get('xTableName')
y_table_name = kwargs.get('yTableName')
savestub = '' if (savestub is None) else savestub
print 'Evaluating: {}'.format(opType)
cxn = SQLCxn(username='******', db='ubuntu', timeout=10000)
colnames = [
'nodes', 'rows', 'cols', 'time1', 'time2', 'time3', 'time4', 'time5'
]
runTimes = pd.DataFrame(np.zeros((1, len(colnames))))
runTimes.columns = colnames
shape = cxn.get_shape(x_table_name)
env = {
'x_table_name': x_table_name,
'y_table_name': y_table_name,
'do_logit': do_logit,
'do_reg': do_reg,
'do_gnmf': do_gnmf,
'do_robust': do_robust,
'shape': shape,
'cxn': cxn
}
cleanup = None
if opType == 'logit':
call = 'do_logit(x_table_name, y_table_name, shape, cxn)'
elif opType == 'gnmf':
call = 'do_gnmf(x_table_name, shape, 10, cxn)'
elif opType == 'reg':
call = 'do_reg(x_table_name, y_table_name, cxn)'
cleanup = ("map(lambda x: cxn.execute("
"'DROP TABLE {}'.format(x)), ['XTX','XTY','XTX_INV','B'])")
elif opType == 'robust':
cxn.execute('DROP TABLE IF EXISTS R2 CASCADE')
cxn.execute(
"SELECT MADLIB.matrix_random({},1,NULL,'uniform','R2',NULL)".
format(shape[0]))
cxn.execute('ALTER TABLE R2 RENAME COLUMN ROW TO ROW_NUM')
call = 'do_robust(x_table_name, cxn)'
rows = shape[0]
cols = shape[1]
path = '../output/madlib_adclick_{}{}.txt'.format(opType, int(nodes))
runTimes.ix[:, ['nodes', 'rows', 'cols']] = (nodes, rows, cols)
res = utils.timeOp(call, env, cleanup)
print res
runTimes.ix[:, 3:] = res
writeHeader = False if (os.path.exists(path)) else True
runTimes.to_csv(path, index=False, header=writeHeader, mode='a')
def main(kwargs):
opType = kwargs.get('opType')
savestub = kwargs.get('savestub')
nodes = kwargs.get('nodes')
x_table_name = kwargs.get('xTableName')
y_table_name = kwargs.get('yTableName')
savestub = '' if (savestub is None) else savestub
print 'Evaluating: {}'.format(opType)
cxn = SQLCxn(username='******', db='ubuntu', timeout=10000)
colnames = ['nodes','rows','cols','time1','time2','time3','time4','time5']
runTimes = pd.DataFrame(np.zeros((1,len(colnames))))
runTimes.columns = colnames
shape = cxn.get_shape(x_table_name)
env = {'x_table_name': x_table_name,
'y_table_name': y_table_name,
'do_logit': do_logit,
'do_gnmf': do_gnmf,
'do_reg': do_reg,
'do_robust': do_robust,
'shape': shape,
'cxn': cxn}
cleanup = None
if opType == 'logit':
call = 'do_logit(x_table_name, y_table_name, shape, cxn)'
elif opType == 'gnmf':
call = 'do_gnmf(x_table_name, shape, 10, cxn)'
elif opType == 'reg':
call = 'do_reg(x_table_name, y_table_name, cxn)'
cleanup = ("map(lambda x: cxn.execute("
"'DROP TABLE {}'.format(x)), ['XTX','XTY','XTX_INV','B'])")
elif opType == 'robust':
#do_reg(x_table_name, y_table_name, cxn)
#preproc = """
# DROP TABLE IF EXISTS Y_HAT;
# SELECT madlib.matrix_mult('{X}',NULL,'B',NULL,'Y_HAT');
# CREATE TABLE R2 AS (
# SELECT {y}.row_num, ARRAY[POW({y}.val[1]-y_hat.val[1],2)] val
# FROM {y}
# INNER JOIN y_hat ON {y}.row_num = y_hat.row_num
# ) DISTRIBUTED BY (row_num)
#""".format(X=x_table_name, y=y_table_name)
# We can just generate a vector of residuals on the fly
# rather than computing them explicitly.
cxn.execute('DROP TABLE IF EXISTS R2')
cxn.randomMatrix(shape[0], 1, 'R2')
call = 'do_robust(x_table_name, cxn)'
rows = shape[0]
cols = shape[1]
path = '../output/madlib_tall_{}{}.txt'.format(opType, int(nodes))
runTimes.ix[:,['nodes','rows','cols']] = (nodes, rows, cols)
res = utils.timeOp(call, env, cleanup)
res
runTimes.ix[:,3:] = res
writeHeader = False if (os.path.exists(path)) else True
runTimes.to_csv(path, index=False, header = writeHeader, mode = 'a')
def main(kwargs):
opType = kwargs.get('opType')
savestub = kwargs.get('savestub')
nodes = kwargs.get('nodes')
x_table_name = kwargs.get('xTableName')
y_table_name = kwargs.get('yTableName')
savestub = '' if (savestub is None) else savestub
print 'Evaluating: {}'.format(opType)
cxn = SQLCxn(username='******', db='ubuntu', timeout=2000)
colnames = [
'nodes', 'rows', 'cols', 'time1', 'time2', 'time3', 'time4', 'time5'
]
runTimes = pd.DataFrame(np.zeros((1, len(colnames))))
runTimes.columns = colnames
shape = cxn.get_shape(x_table_name)
env = {
'x_table_name': x_table_name,
'y_table_name': y_table_name,
'do_logit': do_logit,
'do_reg': do_reg,
'shape': shape,
'cxn': cxn
}
cleanup = None
if opType == 'logit':
call = 'do_logit(x_table_name, y_table_name, shape, cxn)'
elif opType == 'gnmf':
call = 'do_gnmf(x_table_name, shape, 10, cxn)'
elif opType == 'reg':
call = 'do_reg(x_table_name, y_table_name, cxn)'
cleanup = ("map(lambda x: cxn.execute("
"'DROP TABLE {}'.format(x)), ['XTX','XTY','XTX_INV','B'])")
elif opType == 'robust':
do_reg(x_table_name, y_table_name, cxn)
preproc = """
DROP TABLE IF EXISTS Y_HAT;
SELECT madlib.matrix_mult('{X}',NULL,'B',NULL,'Y_HAT');
CREATE TABLE R2 AS (
SELECT {y}.row_num, ARRAY[POW({y}.val[1]-y_hat.val[1],2)] val
FROM {y}
INNER JOIN y_hat ON {y}.row_num = y_hat.row_num
) DISTRIBUTED BY (row_num)
""".format(X=x_table_name, y=y_table_name)
cxn.execute(preproc)
call = 'do_robust(x_table_name, cxn)'
elif opType == 'pca':
print 'Not Implemented'
return
rows = shape[0]
cols = shape[1]
path = '../output/madlib_adclick_{}{}.txt'.format(opType, int(nodes))
runTimes.ix[:, ['nodes', 'rows', 'cols']] = (nodes, rows, cols)
res = utils.timeOp(call, env, cleanup)
print res
runTimes.ix[:, 3:] = res
writeHeader = False if (os.path.exists(path)) else True
runTimes.to_csv(path, index=False, header=writeHeader, mode='a')
def main(kwargs):
op_type = kwargs['opType']
nodes = kwargs['nodes']
stub = kwargs['stub']
colnames = [
'nodes', 'rows', 'cols', 'time1', 'time2', 'time3', 'time4', 'time5'
]
runTimes = pd.DataFrame(np.zeros((1, len(colnames))))
runTimes.columns = colnames
cxn = SQLCxn(username='******', db='ubuntu', timeout=10000)
shape = cxn.get_shape('adclick_clean_1_sparse')
if not cxn.table_exists('adclick_clean_1_vectors_sparse'):
stmt = """
CREATE TABLE adclick_clean_1_vectors_sparse AS (
SELECT x.row_num, madlib.svec_cast_positions_float8arr(
ARRAY_AGG(x.col_num), ARRAY_AGG(x.val), {}, 0.0
) AS indep_vars, y.val AS y
FROM adclick_clean_1_sparse x
INNER JOIN adclick_clean_y y ON x.row_num = y.row_num
GROUP BY x.row_num, y.val
) DISTRIBUTED BY (row_num)
""".format(shape[1])
cxn.execute(stmt)
if op_type == 'logit':
cxn.execute('DROP TABLE IF EXISTS adclick_logit_summary')
cxn.execute('DROP TABLE IF EXISTS adclick_logit')
call = """
SELECT madlib.logregr_train('adclick_clean_1_vectors_sparse',
'adclick_logit',
'y', 'indep_vars', NULL,
3, 'igd', .000001)
"""
cleanup = ['adclick_logit_summary', 'adclick_logit']
elif op_type == 'reg':
cxn.execute('DROP TABLE IF EXISTS adclick_reg_summary')
cxn.execute('DROP TABLE IF EXISTS adclick_reg')
call = """
SELECT madlib.linregr_train('adclick_clean_1_vectors_sparse',
'adclick_reg', 'y', 'indep_vars')
"""
cleanup = ['adclick_reg_summary', 'adclick_reg']
elif op_type == 'pca':
cxn.execute('DROP TABLE IF EXISTS result_table')
cxn.execute('DROP TABLE IF EXISTS result_table_mean')
cxn.execute('DROP TABLE IF EXISTS residual_table')
cxn.execute('DROP TABLE IF EXISTS result_summary_table')
cxn.execute('DROP TABLE IF EXISTS adlick_prj')
call = """
SELECT madlib.pca_sparse_train('adclick_clean_1_sparse',
'result_table',
'row_num',
'col_num',
'val',
'{0}',
'{1}',
5);
SELECT madlib.pca_sparse_project('adclick_clean_1_sparse',
'result_table',
'adclick_prj',
'row_num',
'col_num',
'val',
'{0}',
'{1}',
'residual_table',
'result_summary_table')
""".format(*shape)
cleanup = [
'result_table', 'result_table_mean', 'residual_table',
'result_summary_table', 'adclick_prj'
]
runTimes.ix[:, ['rows', 'cols']] = shape
path = '../output/madlib_{}{}_sparse.txt'.format(op_type, int(nodes))
runTimes.ix[:, 'nodes'] = nodes
res = cxn.time(call, cleanup)
runTimes.ix[:, 3:] = res
runTimes.to_csv(path, index=False)