def doMatrixOp(kwargs):
opType = kwargs.get('opType')
mattype = kwargs.get('mattype')
tableStub = kwargs.get('tableStub')
savestub = kwargs.get('savestub')
nodes = kwargs.get('nodes')
outdir = kwargs.get('outdir')
savestub = '' if (savestub is None) else savestub
try:
tableStub = int(tableStub)
except ValueError:
pass
Mname = 'M{}'.format(tableStub)
Nname = 'N{}'.format(tableStub)
wname = 'w{}'.format(tableStub)
print 'Evaluating: {}'.format(opType)
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=2000)
shape = cxn.get_shape_dense('M{}'.format(tableStub))
cleanup = []
if (opType == 'SVD'):
call = "svd('{}','svd','row_num',10, 10,'svd_summary')".format(
Mname, shape[1])
cleanup.append('svd_s')
cleanup.append('svd_u')
cleanup.append('svd_v')
cleanup.append('svd_summary')
else:
raise NotImplementedError('Invalid Operation')
for obj in cleanup:
cxn.execute('DROP TABLE IF EXISTS {}'.format(obj))
sql_call = 'SELECT madlib.{}'.format(call)
rows = shape[0]
cols = shape[1]
path = '../output/{}/madlib_{}_{}{}.txt'.format(outdir, mattype, opType,
int(nodes))
runTimes.ix[:, ['nodes', 'rows', 'cols']] = (nodes, rows, cols)
madlib_timeout = ('../temp/madlib_punked_out.json', opType)
res = cxn.time(sql_call, cleanup, madlib_timeout)
if (res is None):
print 'Timed Out'
return
runTimes.ix[:, 3:] = res
writeHeader = False if (os.path.exists(path)) else True
runTimes.to_csv(path, index=False, header=writeHeader, mode='a')
def doMatrixOp(kwargs):
opType = kwargs.get('opType')
mattype = kwargs.get('mattype')
tableStub = kwargs.get('tableStub')
savestub = kwargs.get('savestub')
nodes = kwargs.get('nodes')
outdir = kwargs.get('outdir')
sr = kwargs.get('sr')
try:
tableStub = int(tableStub)
except ValueError:
pass
Mname = 'M{}'.format(tableStub)
Nname = 'M{}'.format(tableStub)
wname = 'w{}'.format(tableStub)
if opType == 'GMM':
Nname = Mname.replace('wide','tall')
print 'Evaluating: {}'.format(opType)
colnames = ['nodes','sr','time1','time2','time3','time4','time5']
runTimes = pd.DataFrame(np.zeros((1,len(colnames))))
runTimes.columns = colnames
runTimes['nodes'] = runTimes['nodes'].astype('O')
runTimes['sr'] = runTimes['sr'].astype('O')
cxn = SQLCxn(username='******', db='ubuntu', timeout=10000)
cleanup = []
if (opType == 'TRANS'):
call = "matrix_trans('{}',NULL,'Mt',NULL)".format(Mname)
cleanup.append('Mt')
elif (opType == 'NORM'):
call = "matrix_norm('{}',NULL,'fro')".format(Mname)
elif (opType == 'GMM'):
call = "matrix_mult('{}',NULL,'{}',NULL,'MN',NULL)".format(Mname,Nname)
cleanup.append('MN')
elif (opType == 'MVM'):
array_call = 'SELECT array_agg(random()) FROM generate_series(1,100)'
call = "matrix_vec_mult('{}',NULL,({}))".format(Mname,array_call)
cleanup.append('Mw')
elif (opType == 'TSM'):
call = "matrix_mult('{0}','trans=True','{0}',NULL,'MtM',NULL)".format(Mname)
cleanup.append('MtM')
elif (opType == 'ADD'):
call = "matrix_add('{}',NULL,'{}',NULL,'M_N',NULL)".format(Mname, Nname)
cleanup.append('M_N')
else:
raise NotImplementedError('Invalid Operation')
for obj in cleanup:
cxn.execute('DROP TABLE IF EXISTS {}'.format(obj))
sql_call = 'SELECT madlib.{}'.format(call)
fmt = (outdir, mattype, opType, nodes)
path = '../output/{}/madlib_{}_{}{}.txt'.format(*fmt)
res = cxn.time(sql_call, cleanup)
if (res is None):
print 'Timed Out'
return
runTimes.ix[:,'nodes'] = nodes
runTimes.ix[:,'sr'] = sr
runTimes.ix[:,2:] = res
writeHeader = False if (os.path.exists(path)) else True
runTimes.to_csv(path, index=False, header = writeHeader, mode = 'a')
def doMatrixOp(kwargs):
opType = kwargs.get('opType')
mattype = kwargs.get('mattype')
fixedAxis = int(kwargs.get('fixedAxis'))
nrow_scale = map(lambda x: int(x), kwargs['nrows'].split(' '))
nproc = kwargs.get('nproc')
port = GPDB_PORT_MAP[nproc] if nproc is not None else None
if nproc is not None:
cxn = start_gpdb(port, nproc)
cxn.execute('DROP TABLE IF EXISTS M16_tall')
atexit.register(stop_gpdb, nproc, cxn)
else:
cxn = SQLCxn(username='******', db='ubuntu', timeout=10000)
colnames = ['rows', 'time1', 'time2', 'time3', 'time4', 'time5']
runTimes = pd.DataFrame(np.zeros((1, len(colnames))))
runTimes.columns = colnames
if nproc is None:
path = os.path.join('..', 'output',
'madlib_{}_{}.txt'.format(mattype, opType))
else:
path = os.path.join('..', 'output',
'madlib_cpu_{}_scale.txt'.format(opType))
for nr in nrow_scale:
nrow = fixedAxis if opType == 'GMM' else nr
ncol = nr if opType == 'GMM' else fixedAxis
print nrow
print ncol
Mname = 'M{}{}'.format(nrow, ncol)
if not cxn.table_exists('M{}{}'.format(nrow, ncol)):
cxn.randomMatrix(nrow, ncol, 'M{}{}'.format(nrow, ncol))
if (opType == 'GMM'):
if not cxn.table_exists('N{}{}'.format(ncol, nrow)):
cxn.randomMatrix(ncol, nrow, 'N{}{}'.format(ncol, nrow))
Nname = 'N{}{}'.format(ncol, nrow)
elif (opType == 'ADD'):
if not cxn.table_exists('N{}{}'.format(nrow, ncol)):
cxn.randomMatrix(nrow, ncol, 'N{}{}'.format(nrow, ncol))
Nname = 'N{}{}'.format(nrow, ncol)
cleanup = []
if (opType == 'TRANS'):
call = "matrix_trans('{}',NULL,'Mt',NULL)".format(Mname)
cleanup.append('Mt')
elif (opType == 'NORM'):
call = "matrix_norm('{}',NULL,'fro')".format(Mname)
elif (opType == 'GMM'):
call = "matrix_mult('{}',NULL,'{}',NULL,'MN',NULL)".format(
Mname, Nname)
cleanup.append('MN')
elif (opType == 'MVM'):
array_call = 'SELECT array_agg(random()) FROM generate_series(1,{})'.format(
ncol)
call = "matrix_vec_mult('{}',NULL,({}))".format(Mname, array_call)
elif (opType == 'TSM'):
call = "matrix_mult('{0}','trans=True','{0}',NULL,'MtM',NULL)".format(
Mname)
cleanup.append('MtM')
elif (opType == 'ADD'):
call = "matrix_add('{}',NULL,'{}',NULL,'M_N',NULL)".format(
Mname, Nname)
cleanup.append('M_N')
else:
raise NotImplementedError('Invalid Operation')
sql_call = 'SELECT madlib.{}'.format(call)
runTimes.ix[:, 'rows'] = nr if nproc is None else nproc
runTimes.ix[:, 1:] = cxn.time(sql_call, cleanup)
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')
shape = cxn.get_shape_dense('adclick_clean{}_dense'.format(stub))
if not cxn.table_exists('adclick_clean_vectors_split'):
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)
# need to do a bit of preprocessing
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_vectors_split',
'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_vectors_split',
'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')
stmt = """
CREATE TABLE adclick_clean_depvars AS (
SELECT row_num, val[2:{}]::NUMERIC[] val
FROM adclick_clean{}_dense
) DISTRIBUTED BY (row_num)
""".format(shape[1], stub)
if not cxn.table_exists('adclick_clean_depvars'):
cxn.execute(stmt)
call = """
SELECT madlib.pca_train('adclick_clean_depvars',
'result_table',
'row_num',
5);
SELECT madlib.pca_project('adclick_clean_depvars',
'result_table',
'adclick_prj',
'row_num',
'residual_table',
'result_summary_table')
"""
cleanup = [
'result_table', 'result_table_mean', 'residual_table',
'result_summary_table', 'adclick_prj'
]
#shape = cxn.get_shape_dense('adclick_clean{}_dense'.format(stub))
runTimes.ix[:, ['rows', 'cols']] = shape
path = '../output/madlib_{}{}_dense.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)
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)