def run_stage3(params_dict):
input_matrix = params_dict.get('inputmatrix')
#leverage_scores_file = params_dict.get('leveragescores')
#p_score_file = params_dict.get('pscores')
on_rows = stage_3_params.get('on_rows', False)
sc = params_dict.get('sc')
if on_rows: # we do the flip
rows_assigned = sc.textFile(input_matrix).map(lambda x:x.split(',')).map(lambda x:(int(x[1]), int(x[0]), float(x[2])))
leverage_scores_file = params_dict.get('rowleveragescores')
p_score_file = params_dict.get('rowpscores')
else:
rows_assigned = sc.textFile(input_matrix).map(lambda x:x.split(',')).map(lambda x:(int(x[0]), int(x[1]), float(x[2])))
leverage_scores_file = params_dict.get('columnleveragescores')
p_score_file = params_dict.get('columnpscores')
row_shape = rows_assigned.map(lambda x:x[0]).max() + 1
column_shape = rows_assigned.map(lambda x:x[1]).max() + 1
matrix_A = SparseRowMatrix(rows_assigned,'output', row_shape,column_shape, True)
start = time.time()
cx = CX(matrix_A)
k = 5
q = 3
lev, p = cx.get_lev(k,axis=0, q=q)
end = time.time()
np.savetxt(leverage_scores_file, np.array(lev))
np.savetxt(p_score_file, np.array(p))
print 'lev score ', lev, len(lev)
print 'p is ', p, len(p)
print 'time ', end-start
def test_col_lev2(self):
cx = CX(self.matrix_A2)
lev, p = cx.get_lev(10, q=6)
lev_exact, p_exact = compLevExact(A2, 10, axis=1)
print scipy.stats.entropy(p_exact, p)
self.assertEqual(len(lev), 1000)
def test_col_lev2(self):
cx = CX(self.matrix_A2)
lev, p = cx.get_lev(10, q=6)
lev_exact, p_exact = compLevExact(A2, 10, axis=1)
print scipy.stats.entropy(p_exact,p)
self.assertEqual(len(lev), 1000)
def _indexed(grouped_list):
indexed, values = [],[]
for tup in grouped_list:
indexed.append(tup[0])
values.append(tup[1])
return np.array(indexed), np.array(values)
filename = "/global/u2/m/msingh/sc_paper/new_version/sc-2015/cx_spark/data/movielens/ml-10M100K/ratings.dat"
#filename = '/global/u2/m/msingh/sc_paper/new_version/sc-2015/cx_spark/data/ml-100k/u.data'
data = sc.textFile(filename).map(lambda x:parse(x))
row_shape = data.map(lambda x:x[0]).max() +1
column_shape = data.map(lambda x:x[1]).max()+1
drdd = data.map(lambda x:(x[0],(x[1],x[2]))).groupByKey().map(lambda x :(x[0],list(x[1]))).map(lambda x: (x[0],_indexed(x[1])))
print drdd.take(1)
#prep_rdd = prepare_matrix(data)
matrix_A = SparseRowMatrix(drdd,'output', row_shape,column_shape, True)
cx = CX(matrix_A)
k = 2
q = 2
lev, p = cx.get_lev(k,axis=0, q=q)
#end = time.time()
leverage_scores_file='/scratch1/scratchdirs/msingh/sc_paper/experiments/striped_data/movielens_leverage_scores_full1'
p_score_file='/scratch1/scratchdirs/msingh/sc_paper/experiments/striped_data/movielens_p_scores_full1'
np.savetxt(leverage_scores_file, np.array(lev))
np.savetxt(p_score_file, np.array(p))
#825 post street
"""
val = ast.literal_eval(s)
return val[0], (np.array(val[1][0]), np.array(val[1][1]))
data = sc.textFile('/scratch1/scratchdirs/msingh/sc_paper/experiments/striped_data/ncolumns_matrix').map(lambda x:parse(x))
#row_shape = 131048
#column_shape = 8258911
#131047 8258910
row_shape = 8258911
column_shape =131048
#column_shape+=20
print data.take(1)
matrix_A = SparseRowMatrix(data,'output', row_shape,column_shape, False)
cx = CX(matrix_A)
k = 2
q = 2
lev, p = cx.get_lev(k,axis=0, q=q)
#end = time.time()
leverage_scores_file='/scratch1/scratchdirs/msingh/sc_paper/experiments/striped_data/columns_row_leverage_scores_logged'
p_score_file='/scratch1/scratchdirs/msingh/sc_paper/experiments/striped_data/columns_p_scores_logged'
np.savetxt(leverage_scores_file, np.array(lev))
np.savetxt(p_score_file, np.array(p))
"""
def parse_func(x):
stringed = str(x)
chunks = stringed.split(",")
def main(argv):
logging.config.fileConfig('logging.conf',disable_existing_loggers=False)
logger = logging.getLogger('') #using root
parser = argparse.ArgumentParser(description='Getting parameters.',prog='run_cx.sh')
parser.add_argument('dataset', type=str, help='dataset.txt stores the input matrix to run CX on; \
dataset_U.txt stores left-singular vectors of the input matrix (only needed for -t); \
dataset_D.txt stores singular values of the input matrix (only needed for -t)')
parser.add_argument('--dims', metavar=('m','n'), type=int, nargs=2, required=True, help='size of the input matrix')
parser.add_argument('--sparse', dest='sparse', action='store_true', help='whether the data is sparse')
parser.add_argument('--hdfs', dest='file_source', default='local', action='store_const', const='hdfs', help='load dataset from HDFS')
parser.add_argument('-k', '--rank', metavar='targetRank', dest='k', default=5, type=int, help='target rank parameter in the definition of leverage scores, this value shoud not be greater than m or n')
parser.add_argument('-r', metavar='numRowsToSelect', default=20, type=int, help='number of rows to select in CX')
parser.add_argument('-q', '--niters', metavar='numIters', dest='q', default=2, type=int, help='number of iterations to run in approximation of leverage scores')
parser.add_argument('--deterministic', dest='scheme', default='randomized', action='store_const', const='deterministic', help='use deterministic scheme instead of randomized when selecting rows')
parser.add_argument('-c', '--cache', action='store_true', help='cache the dataset in Spark')
parser.add_argument('-t', '--test', action='store_true', help='compute accuracies of the returned solutions')
parser.add_argument('-s', '--save_logs', action='store_true', help='save Spark logs')
parser.add_argument('--nrepetitions', metavar='numRepetitions', default=1, type=int, help='number of times to stack matrix vertically in order to generate large matrices')
parser.add_argument('--npartitions', metavar='numPartitions', default=280, type=int, help='number of partitions in Spark')
group = parser.add_mutually_exclusive_group()
group.add_argument('--row', dest='axis', default=0, action='store_const', const=0, help='compute row leverage scores')
group.add_argument('--column', dest='axis', default=0, action='store_const', const=1, help='compute column leverage scores')
group = parser.add_mutually_exclusive_group()
group.add_argument('--leverage-scores-only', dest='stage', default='full', action='store_const', const='leverage', help='return approximate leverage scores only')
group.add_argument('--indices-only', dest='stage', default='full', action='store_const', const='indices', help='return approximate leverage scores and selected row indices only')
if len(argv)>0 and argv[0]=='print_help':
parser.print_help()
sys.exit(1)
args = parser.parse_args(argv)
(m,n) = args.dims
# validating
if args.k > m or args.k > n:
raise ValueError('Rank parameter({0}) should not be greater than m({1}) or n({2})'.format(args.k,m,n))
if args.npartitions > m or args.npartitions > n:
args.npartitions = min(m,n)
if args.test and args.nrepetitions>1:
raise OptionError('Do not use the test mode(-t) on replicated data(numRepetitions>1)!')
if args.axis == 0:
raise OptionError('Need to implement transpose first!')
if args.sparse and args.file_source=='hdfs':
raise OptionError('Not yet!')
# print parameters
print_params(args, logger)
# TO-DO: put these to a configuration file
dire = '../data/'
hdfs_dire = 'data/'
logs_dire = 'file:///home/jiyan/cx_logs'
# instantializing a Spark instance
if args.save_logs:
conf = SparkConf().set('spark.eventLog.enabled','true').set('spark.eventLog.dir',logs_dire)
else:
conf = SparkConf()
sc = SparkContext(appName="cx_exp",conf=conf)
# loading data
if args.file_source=='hdfs':
A_rdd = sc.textFile(hdfs_dire+args.dataset+'.txt',args.npartitions) #loading dataset from HDFS
else:
A = np.loadtxt(dire+args.dataset+'.txt') #loading dataset from local disc
if args.sparse:
sA = to_sparse(A)
A_rdd = sc.parallelize(sA,args.npartitions)
else:
A_rdd = sc.parallelize(A.tolist(),args.npartitions)
if args.axis == 0:
pass # get rdd from the transpose of A
t = time.time()
if args.sparse:
matrix_A = SparseRowMatrix(A_rdd,args.dataset,m,n,args.cache) # creating a SparseRowMatrix instance
else:
matrix_A = RowMatrix(A_rdd,args.dataset,m,n,args.cache,repnum=args.nrepetitions) # creating a RowMatrix instance
cx = CX(matrix_A)
lev, p = cx.get_lev(args.k, q=args.q) # getting the approximate row leverage scores. it has the same size as the number of rows
if args.test:
if args.file_source != 'local':
A = np.loadtxt(dire+args.dataset+'.txt')
U, D, V = np.linalg.svd(A,0)
if args.axis == 0:
lev_exact = np.sum(U[:,:args.k]**2,axis=1)
else:
lev_exact = np.sum(V.T[:,:args.k]**2,axis=1)
p_exact = lev_exact/args.k
logger.info('KL divergence between the estimation of leverage scores and the exact one is {0}'.format( scipy.stats.entropy(p_exact,p) ))
logger.info('finished stage 1')
logger.info('----------------------------------------------')
if args.stage=='indices' or args.stage=='full':
idx = cx.comp_idx(args.scheme,args.r) # choosing rows based on the leverage scores
# maybe to store the indices to file
logger.info('finished stage 2')
logger.info('----------------------------------------------')
if args.stage=='full':
rows = cx.get_rows() # getting back the selected rows based on the idx computed above (this might give you different results if you rerun the above)
if args.test:
diff = cx.comp_err() # computing the relative error
logger.info('relative error ||A-CX||/||A|| is {0}'.format( diff/np.linalg.norm(A,'fro') ))
logger.info('raltive error of the best rank-{0} approximation is {1}'.format( args.k, np.sqrt(np.sum(D[args.k:]**2))/np.sqrt(np.sum(D**2)) ))
logger.info('finished stage 3')
rtime = time.time() - t
logger.info('time elapsed: {0} second'.format( rtime ))
def test_col_lev2(self):
cx = CX(self.matrix_A2)
lev, p = cx.get_lev(5, q=10)
self.assertEqual(len(lev), 1000)
from utils import prepare_matrix
import os
import logging.config
logging.config.fileConfig('logging.conf', disable_existing_loggers=False)
logger = logging.getLogger(__name__)
sc = SparkContext()
logger.info("job_cx starting with appId=" + sc._jsc.sc().applicationId())
prefix = 'hdfs:///sc-2015/'
name = 'Lewis_Dalisay_Peltatum_20131115_hexandrum_1_1-masked'
logger.info("job_cx loading RDD from %s" % name)
#dataset = MSIDataset.load(sc, 'meta/' + name, prefix + name).cache()
#msimat = MSIMatrix.from_dataset(sc, dataset)
#msimat.save(prefix, 'meta', name)
msimat = MSIMatrix.load(sc, prefix, 'meta', name)
logger.info("shape: %s" % (msimat.shape, ))
mat = prepare_matrix(msimat.nonzeros).cache()
mat = SparseRowMatrix(mat,
"msimat",
msimat.shape[0],
msimat.shape[1],
cache=False)
cx = CX(mat)
k = 32
q = 5
lev, p = cx.get_lev(k, axis=0, q=q)
with open('dump.pkl', 'w') as outf:
import cPickle as pickle
data = {'lev': lev, 'p': p}
pickle.dump(data, outf)
def test_col_lev2(self):
cx = CX(self.matrix_A2)
lev, p = cx.get_lev(5, q=10)
self.assertEqual(len(lev), 1000)
def main(argv):
logging.config.fileConfig('logging.conf', disable_existing_loggers=False)
logger = logging.getLogger('') #using root
parser = argparse.ArgumentParser(description='Getting parameters.',
prog='run_cx.sh')
parser.add_argument(
'dataset',
type=str,
help='dataset.txt stores the input matrix to run CX on; \
dataset_U.txt stores left-singular vectors of the input matrix (only needed for -t); \
dataset_D.txt stores singular values of the input matrix (only needed for -t)'
)
parser.add_argument('--dims',
metavar=('m', 'n'),
type=int,
nargs=2,
required=True,
help='size of the input matrix')
parser.add_argument('--sparse',
dest='sparse',
action='store_true',
help='whether the data is sparse')
parser.add_argument('--hdfs',
dest='file_source',
default='local',
action='store_const',
const='hdfs',
help='load dataset from HDFS')
parser.add_argument(
'-k',
'--rank',
metavar='targetRank',
dest='k',
default=5,
type=int,
help=
'target rank parameter in the definition of leverage scores, this value shoud not be greater than m or n'
)
parser.add_argument('-r',
metavar='numRowsToSelect',
default=20,
type=int,
help='number of rows to select in CX')
parser.add_argument(
'-q',
'--niters',
metavar='numIters',
dest='q',
default=2,
type=int,
help='number of iterations to run in approximation of leverage scores')
parser.add_argument(
'--deterministic',
dest='scheme',
default='randomized',
action='store_const',
const='deterministic',
help=
'use deterministic scheme instead of randomized when selecting rows')
parser.add_argument('-c',
'--cache',
action='store_true',
help='cache the dataset in Spark')
parser.add_argument('-t',
'--test',
action='store_true',
help='compute accuracies of the returned solutions')
parser.add_argument('-s',
'--save_logs',
action='store_true',
help='save Spark logs')
parser.add_argument(
'--nrepetitions',
metavar='numRepetitions',
default=1,
type=int,
help=
'number of times to stack matrix vertically in order to generate large matrices'
)
parser.add_argument('--npartitions',
metavar='numPartitions',
default=280,
type=int,
help='number of partitions in Spark')
group = parser.add_mutually_exclusive_group()
group.add_argument('--row',
dest='axis',
default=0,
action='store_const',
const=0,
help='compute row leverage scores')
group.add_argument('--column',
dest='axis',
default=0,
action='store_const',
const=1,
help='compute column leverage scores')
group = parser.add_mutually_exclusive_group()
group.add_argument('--leverage-scores-only',
dest='stage',
default='full',
action='store_const',
const='leverage',
help='return approximate leverage scores only')
group.add_argument(
'--indices-only',
dest='stage',
default='full',
action='store_const',
const='indices',
help='return approximate leverage scores and selected row indices only'
)
if len(argv) > 0 and argv[0] == 'print_help':
parser.print_help()
sys.exit(1)
args = parser.parse_args(argv)
(m, n) = args.dims
# validating
if args.k > m or args.k > n:
raise ValueError(
'Rank parameter({0}) should not be greater than m({1}) or n({2})'.
format(args.k, m, n))
if args.npartitions > m or args.npartitions > n:
args.npartitions = min(m, n)
if args.test and args.nrepetitions > 1:
raise OptionError(
'Do not use the test mode(-t) on replicated data(numRepetitions>1)!'
)
if args.axis == 0:
raise OptionError('Need to implement transpose first!')
if args.sparse and args.file_source == 'hdfs':
raise OptionError('Not yet!')
# print parameters
print_params(args, logger)
# TO-DO: put these to a configuration file
dire = '../data/'
hdfs_dire = 'data/'
logs_dire = 'file:///home/jiyan/cx_logs'
# instantializing a Spark instance
if args.save_logs:
conf = SparkConf().set('spark.eventLog.enabled',
'true').set('spark.eventLog.dir', logs_dire)
else:
conf = SparkConf()
sc = SparkContext(appName="cx_exp", conf=conf)
# loading data
if args.file_source == 'hdfs':
A_rdd = sc.textFile(hdfs_dire + args.dataset + '.txt',
args.npartitions) #loading dataset from HDFS
else:
A = np.loadtxt(dire + args.dataset +
'.txt') #loading dataset from local disc
if args.sparse:
sA = to_sparse(A)
A_rdd = sc.parallelize(sA, args.npartitions)
else:
A_rdd = sc.parallelize(A.tolist(), args.npartitions)
if args.axis == 0:
pass # get rdd from the transpose of A
t = time.time()
if args.sparse:
matrix_A = SparseRowMatrix(
A_rdd, args.dataset, m, n,
args.cache) # creating a SparseRowMatrix instance
else:
matrix_A = RowMatrix(
A_rdd, args.dataset, m, n, args.cache,
repnum=args.nrepetitions) # creating a RowMatrix instance
cx = CX(matrix_A)
lev, p = cx.get_lev(
args.k, q=args.q
) # getting the approximate row leverage scores. it has the same size as the number of rows
if args.test:
if args.file_source != 'local':
A = np.loadtxt(dire + args.dataset + '.txt')
U, D, V = np.linalg.svd(A, 0)
if args.axis == 0:
lev_exact = np.sum(U[:, :args.k]**2, axis=1)
else:
lev_exact = np.sum(V.T[:, :args.k]**2, axis=1)
p_exact = lev_exact / args.k
logger.info(
'KL divergence between the estimation of leverage scores and the exact one is {0}'
.format(scipy.stats.entropy(p_exact, p)))
logger.info('finished stage 1')
logger.info('----------------------------------------------')
if args.stage == 'indices' or args.stage == 'full':
idx = cx.comp_idx(args.scheme,
args.r) # choosing rows based on the leverage scores
# maybe to store the indices to file
logger.info('finished stage 2')
logger.info('----------------------------------------------')
if args.stage == 'full':
rows = cx.get_rows(
) # getting back the selected rows based on the idx computed above (this might give you different results if you rerun the above)
if args.test:
diff = cx.comp_err() # computing the relative error
logger.info('relative error ||A-CX||/||A|| is {0}'.format(
diff / np.linalg.norm(A, 'fro')))
logger.info(
'raltive error of the best rank-{0} approximation is {1}'.
format(args.k,
np.sqrt(np.sum(D[args.k:]**2)) / np.sqrt(np.sum(D**2))))
logger.info('finished stage 3')
rtime = time.time() - t
logger.info('time elapsed: {0} second'.format(rtime))