def test_scope():
Scope.reset()
dc = DparkContext()
rdd = dc.makeRDD([1, 2, 3]).map(int).map(int).map(int)
dc.scheduler.current_scope = Scope.get("")
for i, r in enumerate([rdd.prev.prev, rdd.prev, rdd]):
assert r.scope.id == i + 1
assert r.scope.api_callsite.startswith("map:{}".format(i))
Scope.reset()
rdd = dc.makeRDD([1, 2, 3]) \
.map(int) \
.map(int) \
.map(int)
for i, r in enumerate([rdd.prev.prev, rdd.prev, rdd]):
assert r.scope.id == i + 1
assert r.scope.api_callsite.startswith("map:0")
def get_rdd(n):
return dc.makeRDD([n, n]).map(int).map(int).map(int)
rdds = [get_rdd(1), get_rdd(2)]
assert rdds[0].scope.id + 4 == rdds[1].scope.id
rdds = [get_rdd(i) for i in range(2)]
assert rdds[0].scope.id == rdds[1].scope.id
def test_scope():
Scope.reset()
dc = DparkContext()
rdd = dc.makeRDD([1, 2, 3]).map(int).map(int).map(int)
dc.scheduler.current_scope = Scope.get("")
for i, r in enumerate([rdd.prev.prev, rdd.prev, rdd]):
assert r.scope.id == i + 1
assert r.scope.api_callsite.startswith("map:{}".format(i))
Scope.reset()
rdd = dc.makeRDD([1, 2, 3]) \
.map(int) \
.map(int) \
.map(int)
for i, r in enumerate([rdd.prev.prev, rdd.prev, rdd]):
assert r.scope.id == i + 1
assert r.scope.api_callsite.startswith("map:0")
def get_rdd(n):
return dc.makeRDD([n, n]).map(int).map(int).map(int)
rdds = [get_rdd(1), get_rdd(2)]
assert rdds[0].scope.id + 4 == rdds[1].scope.id
rdds = [get_rdd(i) for i in range(2)]
assert rdds[0].scope.id == rdds[1].scope.id
def get_rdd(self):
dpark = DparkContext()
return dpark.union(
[dpark.textFile(path, splitSize=64 << 20)
for path in self.paths]
).map(Weblog.from_line)
def test_call_graph_join():
dc = DparkContext()
Scope.reset()
rdd = dc.makeRDD([(1, 1), (1, 2)]).map(lambda x: x)
rdd = rdd.join(rdd)
dc.scheduler.current_scope = Scope.get("")
g = dc.scheduler.get_call_graph(rdd)
pprint(g)
assert g == ([0, 1, 2, 3], {(0, 1): 1, (1, 2): 2, (2, 3): 1})
fg = dc.scheduler.fmt_call_graph(g)
def test_call_graph_join():
dc = DparkContext()
Scope.reset()
rdd = dc.makeRDD([(1, 1), (1, 2)]).map(lambda x: x)
rdd = rdd.join(rdd)
dc.scheduler.current_scope = Scope.get("")
g = dc.scheduler.get_call_graph(rdd)
pprint(g)
assert g == ([0, 1, 2, 3], {(0, 1): 1, (1, 2): 2, (2, 3): 1})
fg = dc.scheduler.fmt_call_graph(g)
def test_call_graph_union():
dc = DparkContext()
Scope.reset()
r1 = dc.union([dc.makeRDD([(1, 2)]) for _ in range(2)])
r2 = dc.union([dc.makeRDD([(3, 4)]) for _ in range(2)])
rdd = r1.union(r2)
dc.scheduler.current_scope = Scope.get("")
g = dc.scheduler.get_call_graph(rdd)
# pprint(g)
fg = dc.scheduler.fmt_call_graph(g)
# pprint(fg)
assert g == ([0, 1, 2, 3, 4, 5], {(0, 1): 2, (1, 4): 1, (2, 3): 2, (3, 4): 1, (4, 5): 1})
def word_count(file_path, word):
# 指定某个Mesos主机进行沟通
dpark = DparkContext()
# 将分布式文件，构造成文件RDD,每块大小为16m
f = dpark.textFile(file_path, splitSize=16 << 20)
# 用map()转变成新的RDD,再用filter过滤出更新的RDD，最后用count()处理返回结果
print(
word, 'count:',
f.map(lambda line: line.strip()).filter(
lambda line: word in line).count())
def main(infile, outfile): ctx = DparkContext() rdd = ctx.textFile(infile) rdd = rdd.map(map_unit_type_priority) rdd = rdd.reduceByKey(reduce_by_key) rdd = rdd.map(map_to_string) rdd.saveAsTextFile(outfile)
def test_lineage():
Scope.reset()
dc = DparkContext()
rdd1 = dc.union([dc.makeRDD([(1, 2)]) for _ in range(5)])
assert len(rdd1.dep_lineage_counts) == 1
rdd2 = dc.union([dc.makeRDD([(1, 2)]) for _ in range(3)])
rdd3 = rdd1.union(rdd2)
assert len(rdd3.dep_lineage_counts) == 2
rdd4 = dc.union([dc.union([dc.makeRDD([(1, 2)]) for _ in range(2)]) for _ in range(4)])
assert len(rdd4.dep_lineage_counts) == 1
assert len(list(rdd4.dependencies)[0].rdd.dep_lineage_counts) == 1
rdd5 = rdd3.groupWith(rdd4)
print("rdd1", rdd1.id, rdd1.dep_lineage_counts)
stage = dc.scheduler.newStage(rdd1, None)
pprint(stage.pipelines)
pprint(stage.pipeline_edges)
assert list(stage.pipelines.keys()) == [rdd1.id]
assert stage.pipeline_edges == {}
stage = dc.scheduler.newStage(rdd3, None)
pprint(stage.pipelines)
pprint(stage.pipeline_edges)
assert sorted(list(stage.pipelines.keys())) == [rdd1.id, rdd2.id, rdd3.id]
assert stage.pipeline_edges == {((-1, rdd1.id), (-1, rdd3.id)):1,
((-1, rdd2.id), (-1, rdd3.id)):1}
stage = dc.scheduler.newStage(rdd4, None)
pprint(stage.pipelines)
pprint(stage.pipeline_edges)
assert list(stage.pipelines.keys()) == [rdd4.id]
assert stage.pipeline_edges == {}
print("rdd5", rdd5.id, rdd3.id, rdd4.id)
stage = dc.scheduler.newStage(rdd5, None)
pprint(stage.pipelines)
pprint(stage.pipeline_edges)
assert sorted(list(stage.pipelines.keys())) == [rdd5.id]
assert sorted(stage.pipeline_edges) == sorted([((s.id, s.rdd.id), (-1, rdd5.id)) for s in stage.parents])
print('-' * 100)
pprint(stage.get_pipeline_graph())
for s in stage.parents:
if s.rdd.id == rdd4.id:
assert list(s.pipelines.keys()) == [rdd4.id]
assert s.pipeline_edges == {}
elif s.rdd.id == rdd3.id:
assert sorted(list(s.pipelines.keys())) == [rdd1.id, rdd2.id, rdd3.id]
assert s.pipeline_edges == {((-1, rdd1.id), (-1, rdd3.id)): 1,
((-1, rdd2.id), (-1, rdd3.id)): 1}
else:
assert False
pprint(s.get_pipeline_graph())
def test_call_graph_union():
dc = DparkContext()
Scope.reset()
r1 = dc.union([dc.makeRDD([(1, 2)]) for _ in range(2)])
r2 = dc.union([dc.makeRDD([(3, 4)]) for _ in range(2)])
rdd = r1.union(r2)
dc.scheduler.current_scope = Scope.get("")
g = dc.scheduler.get_call_graph(rdd)
# pprint(g)
fg = dc.scheduler.fmt_call_graph(g)
# pprint(fg)
assert g == ([0, 1, 2, 3, 4, 5], {
(0, 1): 2,
(1, 4): 1,
(2, 3): 2,
(3, 4): 1,
(4, 5): 1
})
def main():
current_path = os.path.dirname(os.path.abspath(__file__))
for i in cmp_list:
assert os.path.isdir('cmp'+str(i+1))
dpark_ctx = DparkContext('process')
# Dpark thread
def map_iter(i):
dir_name = 'cmp' + str(i+1)
logger = os.path.join(dir_name, 'log')
if os.path.isdir(logger) and os.listdir(logger):
return
print "Start running: ", i+1
os.chdir(os.path.join(current_path, 'cmp') + str(i+1))
os.system('python ./cmp.py')
dpark_ctx.makeRDD(cmp_list).foreach(map_iter)
print 'Done.'
def dt_model():
tr_x, tr_y, va_x, va_y, te_x, te_y = load_data()
param_grid = {
"min_samples_split": range(1, 10000, 1000),
"min_samples_leaf": range(1, 10000, 1000),
# 'max_leaf_nodes': [0, 100, 1000, 10000],
"max_depth": [None, 100, 1000, 10000],
}
param_grid = grid_generator(param_grid)
# Dpark
dpark_ctx = DparkContext()
def map_iter(param):
idx = param[0][0] * 2 + param[0][1]
param = param[1]
m = tree.DecisionTreeClassifier(criterion="entropy", **param)
print "%d, Start traininig Decision Tree model." % idx
m = m.fit(tr_x, tr_y)
print "%d, Training done." % idx
proba = m.predict_proba(va_x)
fpr, tpr, thresh = roc_curve(va_y, proba[:, 1])
auc_ = auc(fpr, tpr)
print "%d, AUC is %f" % (idx, auc_)
return idx, param, auc_
print "It will train %d models" % len(param_grid)
result_record = dpark_ctx.makeRDD(param_grid, 50).enumerate().map(map_iter).collect()
file_record = open("dt_result.pkl", "w")
pickle.dump(result_record, file_record)
file_record.close()
# testing
opt = reduce(lambda x, y: x if x[2] > y[2] else y, result_record)
m = tree.DecisionTreeClassifier(criterion="entropy", **opt[1])
m = m.fit(tr_x, tr_y)
proba = m.predict_proba(te_x)
fpr, tpr, thresh = roc_curve(te_y, proba[:, 1])
auc_ = auc(fpr, tpr)
print "Testing AUC is %f" % auc_
def main(txt, infile, outfile):
ctx = DparkContext()
csvfilename = infile
txtfilename = txt
txt_rdd = ctx.textFile(txtfilename)
txt_rdd = txt_rdd.map(divide_txt)
#('5988', ['2', 'CPM'])
csv_rdd = ctx.textFile(csvfilename, splitSize=64<<20)
#print csv_rdd.take(100)
csv_rdd = csv_rdd.filter(remove_some_bid_unitid)
csv_rdd = csv_rdd.map(divide_csv)
#('6379', ['-1', '1236054964187470000', '6379', '77', '1', '1', '0'])
record_rdd = txt_rdd.join(csv_rdd)
#('6370', (['2', 'COMPLEMENT'], ['-1', '8183016859528920000', '6370', '86', '3', '1', '0']))
record_rdd = record_rdd.mapValue(join_element)
#('6370', ['2', 'COMPLEMENT', '-1', '8183016859528920000', '6370', '86', '3', '1', '0'])
record_rdd = record_rdd.groupBy(lambda line : str(line[1]).split()[5] + str(line[1]).split()[1])
#print record_rdd.take(1)
record_rdd = record_rdd.map(map_unit_type)
#print record_rdd.take(1)
record_rdd = record_rdd.flatMap(flat_map_unit_type_priority)
#print record_rdd.take(5)
record_rdd = record_rdd.groupByKey()
#print "*" * 50
#print record_rdd.take(5)
record_rdd = record_rdd.mapValue(map_value_unit_type_priority)
#print "#" * 50
#print record_rdd.take(5)
record_rdd = record_rdd.map(map_unit_type_priority)
#print "$" * 50
#print record_rdd.take(5)
# unit type prioritt cluster n_ad n_imp n_click ctr
record_rdd.saveAsTextFile(outfile)
import time
from dpark import DparkContext, optParser
from dpark.file_manager import file_manager
dc = DparkContext()
optParser.set_usage("%prog [options] path")
options, args = optParser.parse_args()
path = args[0]
def run(split_size=1):
t = time.time()
dc.textFile(path).mergeSplit(
splitSize=split_size).filter(lambda x: "yangxiufeng" in x).count()
return time.time() - t
run() # file cache
print("{}s with locality".format(run()))
file_manager.fs_list = file_manager.fs_list[1:]
print("{}s merge & without locality".format(run(10)))
print("{}s without locality, ".format(run()))
#coding:utf-8
from random import shuffle, random, sample
import traceback
from dpark import DparkContext
dp = DparkContext('mesos')
'''shuffle不返回数据值'''
rdd1 = dp.parallelize([[(1, 2), (3, 4), (5, 6)]]).map(lambda x: shuffle(x))
print 'rdd1:'
print rdd1.take(1)
rdd2 = dp.parallelize([((1, 2), (3, 4), (5, 6))]).map(lambda x: shuffle(x))
print 'rdd2:'
try:
print rdd2.take(1)
except Exception, e:
print traceback.print_exc()
'''O(NlogN)'''
rdd3 = dp.parallelize([[(1, 2), (3, 4), (5, 6)]
]).map(lambda x: sorted(x, key=lambda k: random()))
print 'rdd3:'
print rdd3.take(1)
'''O(N)'''
rdd4 = dp.parallelize([[(1, 2), (3, 4),
(5, 6)]]).map(lambda x: sample(x, len(x)))
print 'rdd4:'
print rdd4.take(1)
rdd5 = dp.parallelize([((1, 2), (3, 4), (5, 6))
]).map(lambda x: sample(x, len(x)))
from dpark import DparkContext
def m(x):
return x
def r(x, y):
return x + y
def src():
return dc.makeRDD([(1,1)],2)
dc = DparkContext("mesos")
rdd1 = src()
rdd2 = src().reduceByKey(r)
to_union_1_a = [src() for _ in range(2)]
to_union_1_b = [src()]
to_union_2_a = [dc.union(to_union_1_a + to_union_1_b) for _ in range(2)]
to_union_2_b = [rdd2, rdd1]
to_union_3_a = [dc.union(to_union_2_a + to_union_2_b).map(m).reduceByKey(r)]
to_union_3_b = [rdd2]
rdd3 = dc.union(to_union_3_a + to_union_3_b)
rdd4 = rdd2.join(rdd2)
rdd1.collect()
rdd2.collect()
# generate new training data
# uid,iid,r - mu - bi
# iid,1.|pi...
import glob
from dpark import DparkContext
MU_PATH='/nfs/wuhong/offline_use/global_params_0'
IBIAS_PATH='/nfs/wuhong/offline_use/ibias_0/'
RATING_PATH='/nfs/wuhong/fm_data/user_music_factor_model/user_track_rating_for_training/'
ITEM_FACTOR_PATH='/nfs/wuhong/offline_use/H_0/'
NEW_RATING_PATH='/nfs/wuhong/offline_use/rating_new/'
NEW_ITEM_FACTOR_PATH='/nfs/wuhong/offline_use/H_new/'
dpark = DparkContext()
f_global = file(MU_PATH)
line = ''
for l in f_global:
line = l
mu = float(line.strip().split('\t')[1])
f_global.close()
mu = dpark.broadcast(mu)
def local_mapper(line):
iid, v, _ = line.strip().split('\t')
return (iid, float(v))
ibias = {}
ibias = dpark.textFile(glob.glob(IBIAS_PATH)).map(
from dpark import DparkContext, optParser
dc = DparkContext()
options, args = optParser.parse_args()
infile = args[0]
outfile = args[1]
print("from {} to {}".format(infile, outfile))
def fm(x):
for w in x.strip().split():
yield (w, 1)
(dc.textFile(infile)
.flatMap(fm)
.reduceByKey(lambda x, y: x + y, numSplits=6)
.map(lambda x: " ".join(list(map(str, x))))
.saveAsTextFile(outfile, overwrite=False))
def to_vertex((id, lines)):
outEdges = [SPEdge(tid, int(v))
for _, tid, v in lines]
return (id, SPVertex(id, sys.maxint, outEdges, True))
def compute(self, vs, agg, superstep):
newValue = min(self.value, vs[0]) if vs else self.value
if newValue != self.value:
outbox = [SPMessage(edge.target_id, newValue + edge.value)
for edge in self.outEdges]
else:
outbox = []
return SPVertex(self.id, newValue, self.outEdges, False), outbox
if __name__ == '__main__':
ctx = DparkContext()
lines = ctx.textFile('graph.txt').map(lambda line:line.split(' '))
vertices = lines.filter(lambda x:len(x)==3).groupBy(
lambda line:line[0]).map(to_vertex)
messages = lines.filter(lambda x:len(x)==2).map(
lambda (vid, v): (vid, SPMessage(vid, int(v)))
)
print 'read', vertices.count(), 'vertices and ', messages.count(), 'messages.'
result = Bagel.run(ctx, vertices, messages, compute, MinCombiner())
startVertex = 0
print 'Shortest path from %s to all vertices:' % startVertex
for v in result.collect():
if v.value == sys.maxint:
v.value = 'inf'
print v.id, v.value
def compute(self, vs, agg, superstep):
newValue = min(self.value, vs[0]) if vs else self.value
if newValue != self.value:
outbox = [
SPMessage(edge.target_id, newValue + edge.value)
for edge in self.outEdges
]
else:
outbox = []
return SPVertex(self.id, newValue, self.outEdges, False), outbox
if __name__ == '__main__':
ctx = DparkContext()
lines = ctx.textFile('graph.txt').map(lambda line: line.split(' '))
vertices = lines.filter(lambda x: len(x) == 3).groupBy(
lambda line: line[0]).map(to_vertex)
messages = lines.filter(lambda x: len(x) == 2).map(
lambda (vid, v): (vid, SPMessage(vid, int(v))))
print 'read', vertices.count(), 'vertices and ', messages.count(
), 'messages.'
result = Bagel.run(ctx, vertices, messages, compute, MinCombiner())
startVertex = 0
print 'Shortest path from %s to all vertices:' % startVertex
for v in result.collect():
if v.value == sys.maxint:
v.value = 'inf'
print v.id, v.value
import time
from dpark import DparkContext
def m(x):
if x[0] == 0:
time.sleep(100)
return x
def r(x, y):
return x + y
dc = DparkContext("mesos")
rdd = dc.makeRDD([(i, i) for i in range(2)], 2)
rdd.collect()
rdd.reduceByKey(r).map(m).reduceByKey(r).collect()
import math
import random
import os, sys
from pprint import pprint
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from dpark import DparkContext
ctx = DparkContext()
# range
nums = ctx.parallelize(range(100), 4)
print nums.count()
print nums.reduce(lambda x, y: x + y)
# text search
f = ctx.textFile("./", ext="py").map(lambda x: x.strip())
log = f.filter(lambda line: "logging" in line).cache()
print "logging", log.count()
print "error", log.filter(lambda line: "error" in line).count()
for line in log.filter(lambda line: "error" in line).collect():
print line
# word count
counts = f.flatMap(lambda x: x.split()).map(lambda x: (x, 1)).reduceByKey(lambda x, y: x + y).cache()
pprint(counts.filter(lambda (_, v): v > 50).collectAsMap())
pprint(sorted(counts.filter(lambda (_, v): v > 20).map(lambda (x, y): (y, x)).groupByKey().collect()))
pprint(counts.map(lambda v: "%s:%s" % v).saveAsTextFile("wc/"))
# Pi
import random
def get_rdd(self):
dpark = DparkContext()
return dpark.union([
dpark.textFile(path, splitSize=64 << 20) for path in self.paths
]).map(Weblog.from_line)
# -*- coding: utf-8 -*-
from __future__ import absolute_import
from __future__ import print_function
from dpark import DparkContext
from dpark.mutable_dict import MutableDict
from random import shuffle
import six.moves.cPickle
import numpy
from six.moves import range
from six.moves import zip
dpark = DparkContext()
with open('ab.mat') as f:
ori = six.moves.cPickle.loads(f.read())
k = 50
d = 20
M = len(ori)
V = len(ori[0])
assert M % d == 0
assert V % d == 0
m = M / d
v = V / d
GAMMA = 0.02
LAMBDA = 0.1
STEP = 0.9
W = MutableDict(d)
def DownLoad(file_path):
dpark = DparkContext()
file_block = dpark.textFile(file_path,splitSize=16<<20)
file_block.foreach(write_to_wav)
import glob
from dpark import DparkContext
RATING_PATH = '/nfs/wuhong/offline_use/rating_new/'
TRAINING_PATH = '/nfs/wuhong/paracel/data/als_fm/train'
TEST_PATH = '/nfs/wuhong/paracel/data/als_fm/test'
dpark = DparkContext()
def local_filter1(line):
tmp = line.strip().split(',')[1]
if tmp.endswith('0') or tmp.endswith('1') or tmp.endswith('2'):
return False
return True
def local_filter2(line):
tmp = line.strip().split(',')[1]
if tmp.endswith('0') or tmp.endswith('1') or tmp.endswith('2'):
return True
return False
dpark.textFile(
glob.glob(RATING_PATH)).filter(local_filter1).saveAsTextFile(TRAINING_PATH)
dpark.textFile(
glob.glob(RATING_PATH)).filter(local_filter2).saveAsTextFile(TEST_PATH)
outEdges = [Edge(ref) for ref in refs]
return (title, Vertex(title, 1.0/numV, outEdges, True))
def gen_compute(num, epsilon):
def compute(self, messageSum, agg, superstep):
if messageSum and messageSum[0]:
newValue = 0.15 / num + 0.85 * messageSum[0]
else:
newValue = self.value
terminate = (superstep >= 10 and abs(newValue-self.value) < epsilon) or superstep > 30
outbox = [Message(edge.target_id, newValue / len(self.outEdges))
for edge in self.outEdges] if not terminate else []
return Vertex(self.id, newValue, self.outEdges, not terminate), outbox
return compute
if __name__ == '__main__':
inputFile = 'wikipedia.txt'
threshold = 0.01
dpark = DparkContext()
input = dpark.textFile(inputFile)
numVertex = input.count()
vertices = input.map(lambda line: parse_vertex(line, numVertex)).cache()
epsilon = 0.01 / numVertex
messages = dpark.parallelize([])
result = Bagel.run(dpark, vertices, messages,
gen_compute(numVertex, epsilon))
for v in result.filter(lambda x:x.value > threshold).collect():
print v.id, v.value
#!/usr/bin/env python
import sys, os, os.path
import random
from dpark import DparkContext
dpark = DparkContext()
from vector import Vector
def parseVector(line):
num = map(int, line.strip().split('\t')[2:])
num = [n-num[0] for n in num]
return Vector(num[20:])
return Vector(map(int, line.strip().split('\t')[2:]))
def closestCenter(p, centers):
bestDist = p.squaredDist(centers[0])
bestIndex = 0
for i in range(1, len(centers)):
d = p.squaredDist(centers[i])
if d < bestDist:
bestDist = d
bestIndex = i
return bestIndex
def minDist(p, centers):
bestDist = p.squaredDist(centers[0])
for i in range(1, len(centers)):
d = p.squaredDist(centers[i])
if d < bestDist:
bestDist = d
return bestDist
def test_lineage():
Scope.reset()
dc = DparkContext()
rdd1 = dc.union([dc.makeRDD([(1, 2)]) for _ in range(5)])
assert len(rdd1.dep_lineage_counts) == 1
rdd2 = dc.union([dc.makeRDD([(1, 2)]) for _ in range(3)])
rdd3 = rdd1.union(rdd2)
assert len(rdd3.dep_lineage_counts) == 2
rdd4 = dc.union(
[dc.union([dc.makeRDD([(1, 2)]) for _ in range(2)]) for _ in range(4)])
assert len(rdd4.dep_lineage_counts) == 1
assert len(list(rdd4.dependencies)[0].rdd.dep_lineage_counts) == 1
rdd5 = rdd3.groupWith(rdd4)
print("rdd1", rdd1.id, rdd1.dep_lineage_counts)
stage = dc.scheduler.newStage(rdd1, None)
pprint(stage.pipelines)
pprint(stage.pipeline_edges)
assert list(stage.pipelines.keys()) == [rdd1.id]
assert stage.pipeline_edges == {}
stage = dc.scheduler.newStage(rdd3, None)
pprint(stage.pipelines)
pprint(stage.pipeline_edges)
assert sorted(list(stage.pipelines.keys())) == [rdd1.id, rdd2.id, rdd3.id]
assert stage.pipeline_edges == {
((-1, rdd1.id), (-1, rdd3.id)): 1,
((-1, rdd2.id), (-1, rdd3.id)): 1
}
stage = dc.scheduler.newStage(rdd4, None)
pprint(stage.pipelines)
pprint(stage.pipeline_edges)
assert list(stage.pipelines.keys()) == [rdd4.id]
assert stage.pipeline_edges == {}
print("rdd5", rdd5.id, rdd3.id, rdd4.id)
stage = dc.scheduler.newStage(rdd5, None)
pprint(stage.pipelines)
pprint(stage.pipeline_edges)
assert sorted(list(stage.pipelines.keys())) == [rdd5.id]
assert sorted(stage.pipeline_edges) == sorted([
((s.id, s.rdd.id), (-1, rdd5.id)) for s in stage.parents
])
print('-' * 100)
pprint(stage.get_pipeline_graph())
for s in stage.parents:
if s.rdd.id == rdd4.id:
assert list(s.pipelines.keys()) == [rdd4.id]
assert s.pipeline_edges == {}
elif s.rdd.id == rdd3.id:
assert sorted(list(
s.pipelines.keys())) == [rdd1.id, rdd2.id, rdd3.id]
assert s.pipeline_edges == {
((-1, rdd1.id), (-1, rdd3.id)): 1,
((-1, rdd2.id), (-1, rdd3.id)): 1
}
else:
assert False
pprint(s.get_pipeline_graph())
def main():
# Loading data
print "Loading..."
data_train = sample_image()
# Initialize networks
visible_size = 64 # number of input units
hidden_size = [25, 16, 9] # number of hidden units of each layer
lamb = 0.0001 # weight decay parameter
beta = 3 # weight of sparsity penalty dataset
# dpark initialize
dpark_ctx = DparkContext()
# Start training, and L-BFGS is adopted
# We apply a stack-wise greedy training process
layer_ind = range(len(hidden_size) + 1)
layer_ind.remove(0)
layer_size = [visible_size] + hidden_size
# desired average activation
sparsity_param = dict()
for ind in layer_ind:
# standard: 64 units -> sparsity parameter 0.01
sparsity_param[ind] = layer_size[ind - 1] * 0.01 / 64
data = data_train
opttheta = dict() # parameter vector of stack AE
img = dict() # visualization mode
for ind in layer_ind:
print "start training layer No.%d" % ind
# Obtain random parameters of considered layer
theta = initial_parameter(layer_size[ind], layer_size[ind - 1])
# Training begins
options = (data, layer_size[ind - 1], layer_size[ind], lamb,
sparsity_param[ind], beta, dpark_ctx)
opt = optimize.fmin_l_bfgs_b(compute_cost, theta, compute_grad,
options)
opttheta[ind] = opt[0]
W = opttheta.get(ind)[:layer_size[ind]*layer_size[ind-1]].\
reshape(layer_size[ind], layer_size[ind-1])
data = np.dot(W, data)
# visulization shows
img[ind] = display_effect(W)
plt.axis('off')
plt.savefig(str(ind) + '.jpg')
# Trained parameters of stack AE
para_stack = vecstack2stack(opttheta, hidden_size, visible_size)
# Save trained weights and bias
out = open("weights_bias.pkl", "wb")
pickle.dump(para_stack, out)
out.close()
print "Mission complete!"
#!/usr/bin/env python
import sys, os, os.path
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import random
from dpark import DparkContext
dpark = DparkContext()
from vector import Vector
def parseVector(line):
return Vector(map(float, line.strip().split(' ')))
def closestCenter(p, centers):
bestDist = p.squaredDist(centers[0])
bestIndex = 0
for i in range(1, len(centers)):
d = p.squaredDist(centers[i])
if d < bestDist:
bestDist = d
bestIndex = i
return bestIndex
if __name__ == '__main__':
D = 4
K = 3
IT = 10
MIN_DIST = 0.01
centers = [Vector([random.random() for j in range(D)]) for i in range(K)]
points = dpark.textFile('kmeans_data.txt').map(parseVector).cache()
for it in range(IT):
def main():
# Loading data
print "Loading..."
data = sample_image()
# Initialize networks
visible_size = 64 # number of input units
hidden_size = [25, 16, 9] # number of hidden units of each layer
#lamb = 0.0001 # weight decay parameter
'''
lamb = 0 # No weight decay!
beta = 0.01
'''
# sigmoid DEBUG
lamb = 0.0001
beta = 3
# dpark initialize
dpark_ctx = DparkContext()
# Start training, and L-BFGS is adopted
# We apply a stack-wise greedy training process
layer_ind = range(len(hidden_size) + 1)
layer_ind.remove(0)
layer_size = [visible_size] + hidden_size
opttheta = dict() # parameter vector of stack AE
img = dict() # visualization mode
sparsity_param = dict()
for ind in layer_ind:
# standard: 64 units -> sparsity parameter 0.01
sparsity_param[ind] = layer_size[ind - 1] * 0.01 / 64
for ind in layer_ind:
print "start training layer No.%d" % ind
# Obtain random parameters of considered layer
theta = initial_parameter(layer_size[ind], layer_size[ind - 1])
# SGD with mini-batch
options = (data, layer_size[ind - 1], layer_size[ind], lamb,
sparsity_param[ind], beta, dpark_ctx)
opttheta[ind] = stocha_grad_desc_agagrad(compute_cost,
compute_grad,
theta,
options,
step_size_init=0.2,
max_iter=25,
tol=1e-7)
# Preparing next layer!
W = opttheta.get(ind)[:layer_size[ind]*layer_size[ind-1]].\
reshape(layer_size[ind], layer_size[ind-1])
b = opttheta.get(ind)[2*layer_size[ind]*layer_size[ind-1]:\
2*layer_size[ind]*layer_size[ind-1]+layer_size[ind]].\
reshape(layer_size[ind], 1)
data = ReLU(np.dot(W, data) + b)
# visulization shows
img[ind] = display_effect(W)
plt.axis('off')
plt.savefig(str(ind) + '.jpg')
# DEBUG
fin = open("theta_DEBUG.pkl", "wb")
pickle.dump((W, b), fin)
fin.close()
sys.exit()
# Trained parameters of stack AE
para_stack = vecstack2stack(opttheta, hidden_size, visible_size)
# Save trained weights and bias
out = open("weights_bias.pkl", "wb")
pickle.dump(para_stack, out)
out.close()
print "Mission complete!"
import sys
sys.path.append('../')
from dpark import DparkContext
dpark = DparkContext()
name = '/mfs/tmp/weblog-pre-20111019.csv'
name = '/mfs/tmp/weblog-20111019.csv'
name = '/tmp/weblog-20111019.csv.small'
# name = '/tmp/weblog-20111019.csv.medium'
name = 'resume_text_seg_data-2014-06-01.txt'
pv = dpark.textFile(name)
pv = pv.map(lambda x:x.split(',')).map(lambda l:(l[3], l[7]))
pv = pv.flatMap(lambda (i, u):(u.startswith('/movie') and [(i, 2)]
or u.startswith('/group') and [(i, 3)]
or []))
# print pv.take(50)
pv = pv.reduceByKey(lambda x, y:x * y)
# print pv.take(50)
print pv.filter(lambda (_, y):y % 2 == 0 and y % 3 == 0).count()
# movie = pv.filter(lambda (bid,url): url.startswith('/movie')).reduceByKey(lambda x,y:None)
# group = pv.filter(lambda (bid,url): url.startswith('/group')).reduceByKey(lambda x,y:None)
# print movie.join(group).count()
# print pv.map(lambda x:x.split(',')[2]).uniq().count()
# print pv.map(lambda x:(x.split(',')[2],None)).reduceByKey(lambda x,y:None).count()
# .filter(lambda uid:uid)
# print upv.count()
# print upv.reduceByKey(lambda x,y:x+y).count()
import sys
sys.path.append('../')
import logging
from dpark import DparkContext
dpark = DparkContext()
name = 'rating.txt'
def parse(line):
sid, uid, r, f = line.split('\t')
defaults = {'F': 4.5, 'P': 3.7, 'N': 4.0}
if r == 'None':
r = defaults[f]
return (sid, (uid, float(r)))
rating = dpark.textFile(name, numSplits=2).map(parse).groupByKey(2) #.cache()
#print 'us', rating.first()
print rating.count()
def reverse(it):
s = {}
for k, us in it:
for u, r in us:
s.setdefault(u, {})[k] = r
return s
#!/usr/bin/env python
from __future__ import absolute_import
from __future__ import print_function
import sys, os, os.path
from six.moves import map
from six.moves import range
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import random
from dpark import DparkContext
from vector import Vector
dpark = DparkContext()
def parseVector(line):
return Vector(list(map(float, line.strip().split(' '))))
def closestCenter(p, centers):
bestDist = p.squaredDist(centers[0])
bestIndex = 0
for i in range(1, len(centers)):
d = p.squaredDist(centers[i])
if d < bestDist:
bestDist = d
bestIndex = i
return bestIndex
if __name__ == '__main__':
#!/usr/bin/env python
import sys, os, os.path
import random
from dpark import DparkContext
dpark = DparkContext()
from vector import Vector
def parseVector(line):
num = map(int, line.strip().split('\t')[2:])
num = [n - num[0] for n in num]
return Vector(num[20:])
return Vector(map(int, line.strip().split('\t')[2:]))
def closestCenter(p, centers):
bestDist = p.squaredDist(centers[0])
bestIndex = 0
for i in range(1, len(centers)):
d = p.squaredDist(centers[i])
if d < bestDist:
bestDist = d
bestIndex = i
return bestIndex
def minDist(p, centers):
bestDist = p.squaredDist(centers[0])
for i in range(1, len(centers)):
d = p.squaredDist(centers[i])
if d < bestDist:
#!/usr/bin/env python
import os, sys
import re
from glob import glob
from dpark import DparkContext
from dpark.table import TableRDD, Globals, CachedTables
from prettytable import PrettyTable
ctx = DparkContext()
_locals = {}
def gen_table(expr, fields=None):
if '(' in expr and getattr(ctx, expr.split('(')[0], None):
rdd = eval('ctx.' + expr[:expr.rindex(')') + 1], globals(), _locals)
else:
rdd = eval(expr, globals(), _locals)
head = rdd.first()
if isinstance(head, str):
if '\t' in head:
rdd = rdd.fromCsv('excel-tab')
elif ',' in head:
rdd = rdd.fromCsv('excel')
else:
rdd = rdd.map(lambda l:l.split(' '))
row = rdd.first()
else:
row = head
if not isinstance(rdd, TableRDD):
return _
class DemoOutputStream(ForEachDStream):
def __init__(self, parent, output):
ForEachDStream.__init__(self, parent, collect(output))
self.output = output
def __setstate__(self, state):
ForEachDStream.__setstate__(self, state)
self.output = []
self.func = collect(self.output)
sc = DparkContext(dpark_master)
class TestDStream(unittest.TestCase):
def _setupStreams(self, intput1, input2, operation):
ssc = StreamingContext(2, sc)
is1 = DemoInputStream(ssc, intput1)
ssc.registerInputStream(is1)
if input2:
is2 = DemoInputStream(ssc, input2)
ssc.registerInputStream(is2)
os = operation(is1, is2)
else:
os = operation(is1)
output = DemoOutputStream(os, [])
ssc.registerOutputStream(output)
if messageSum and messageSum[0]:
newValue = 0.15 / num + 0.85 * messageSum[0]
else:
newValue = self.value
terminate = (superstep >= 10 and
abs(newValue - self.value) < epsilon) or superstep > 30
outbox = [(edge.target_id, newValue / len(self.outEdges))
for edge in self.outEdges] if not terminate else []
return Vertex(self.id, newValue, self.outEdges, not terminate), outbox
return compute
if __name__ == '__main__':
inputFile = 'wikipedia.txt'
threshold = 0.01
dpark = DparkContext()
path = os.path.join(os.path.dirname(os.path.abspath(__file__)), inputFile)
input = dpark.textFile(path)
numVertex = input.count()
vertices = input.map(lambda line: parse_vertex(line, numVertex)).cache()
epsilon = 0.01 / numVertex
messages = dpark.parallelize([])
result = Bagel.run(dpark, vertices, messages,
gen_compute(numVertex, epsilon))
for id, v in result.filter(
lambda id_v: id_v[1].value > threshold).collect():
print(id, v)
def DownLoad(file_path):
dpark = DparkContext()
file_block = dpark.textFile(file_path, splitSize=16 << 20)
file_block.foreach(write_to_wav)
from dpark import DparkContext, optParser
dc = DparkContext()
options, args = optParser.parse_args()
infile = args[0]
outfile = args[1]
print("from {} to {}".format(infile, outfile))
def fm(x):
for w in x.strip().split():
yield (w, 1)
(dc.textFile(infile).flatMap(fm).reduceByKey(
lambda x, y: x + y,
numSplits=6).map(lambda x: " ".join(list(map(str, x)))).saveAsTextFile(
outfile, overwrite=False))
# -*- coding: utf-8 -*-
from dpark import DparkContext
def m(x):
return x
rdd = DparkContext().makeRDD([(1, 1)]).map(m).groupByKey()
rdd.map(m).collect()
rdd.map(m).collect()
for _, tid, v in lines]
return (id, Vertex(id, sys.maxint, outEdges, True))
def compute(self, vs, agg, superstep):
newValue = min(self.value, vs[0]) if vs else self.value
if newValue != self.value:
outbox = [(edge.target_id, newValue + edge.value)
for edge in self.outEdges]
else:
outbox = []
return Vertex(self.id, newValue, self.outEdges, False), outbox
if __name__ == '__main__':
ctx = DparkContext()
path = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'graph.txt')
lines = ctx.textFile(path).map(lambda line: line.split(' '))
vertices = lines.groupBy(lambda line: line[0]).map(to_vertex)
startVertex = str(0)
messages = ctx.makeRDD([(startVertex, 0)])
print('read', vertices.count(), 'vertices and ', messages.count(), 'messages.')
result = Bagel.run(ctx, vertices, messages, compute, BasicCombiner(min), numSplits=2)
print('Shortest path from %s to all vertices:' % startVertex)
for id, v in result.collect():
if v.value == sys.maxint:
v.value = 'inf'
print(v.id, v.value)
#!/usr/bin/env python # encoding: utf-8 """ @version: v1.0 @author: W_H_J @license: Apache Licence @contact: [email protected] @site: @software: PyCharm @file: wordcount.py @time: 2018/6/5 18:10 @describe: 单词统计 """ from dpark import DparkContext ctx = DparkContext() file = ctx.textFile("./words.txt") words = file.flatMap(lambda x: x.split()).map(lambda x: (x, 1)) wc = words.reduceByKey(lambda x, y: x + y).collectAsMap() print(wc) # 统计单词出现的个数 def word_count(file_path, word): # 指定某个Mesos主机进行沟通 dpark = DparkContext() # 将分布式文件，构造成文件RDD,每块大小为16m f = dpark.textFile(file_path, splitSize=16 << 20) # 用map()转变成新的RDD,再用filter过滤出更新的RDD，最后用count()处理返回结果 print(
data = fs.get('/song/small/%s.mp3'%id)
binfile = open("output/%s.mp3" % (id),"wb")
binfile.write(data)
binfile.close()
m = RetrievalMusic(dptable, mode)
m.retrieving('output/%s.mp3'%id)
if mode != 2:
call("rm output/%s.mp3" % (id), shell=True)
def batchprocess(song_id, loaded, mode):
# dpark = DparkContext()
# dptable = dpark.broadcast(loaded)
# dpark.parallelize(song_id, 80).foreach(lambda(id):calculate_single(id, dptable, mode))
for id in song_id:
calculate_single(id, loaded, mode)
if mode == 2:
rearrange()
if __name__ == '__main__':
song_id = np.load("track_temp.npy")
mode = 1 # 1 for save, 2 for filter, and 0 for regular work
dpark = DparkContext()
dpark.parallelize(song_id, 50).foreach(lambda(id):calculate_single(id,0,mode))
import math
import random
import os, sys
from pprint import pprint
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from dpark import DparkContext
ctx = DparkContext()
# range
nums = ctx.parallelize(range(100), 4)
print nums.count()
print nums.reduce(lambda x, y: x + y)
# text search
f = ctx.textFile("./", ext='py').map(lambda x: x.strip())
log = f.filter(lambda line: 'logging' in line).cache()
print 'logging', log.count()
print 'error', log.filter(lambda line: 'error' in line).count()
for line in log.filter(lambda line: 'error' in line).collect():
print line
# word count
counts = f.flatMap(lambda x: x.split()).map(lambda x: (x, 1)).reduceByKey(
lambda x, y: x + y).cache()
pprint(counts.filter(lambda (_, v): v > 50).collectAsMap())
pprint(
sorted(
counts.filter(lambda (_, v): v > 20).map(
lambda (x, y): (y, x)).groupByKey().collect()))
pprint(counts.map(lambda v: "%s:%s" % v).saveAsTextFile("wc/"))
def main(argv):
# Dpark initialize
dpark = DparkContext()
# number of the training and testing set
num_train = 6000
num_test = 6000
# Loading the dataset
data = svm_read_problem('echo_liveness.01.libsvm')
y, x = data
# Preparing training and testing data
if len(x) != len(y):
print("The labels and features are not accorded!")
sys.exit()
x_live = [x[i] for i in find(y, 1.0)]
x_stu = [x[i] for i in find(y, 0.0)]
n_live = len(x_live)
n_stu = len(x_stu)
ind_live = range(n_live)
ind_stu = range(n_stu)
random.shuffle(ind_live)
random.shuffle(ind_stu)
x_te = [x_live[i] for i in ind_live[num_train : num_test + num_train]] + \
[x_stu[i] for i in ind_stu[num_train : num_test + num_train]]
y_te = [1.0] * len(ind_live[num_train : num_test + num_train]) + \
[-1.0]*len(ind_stu[num_train : num_test + num_train])
x_tr = [x_live[i] for i in ind_live[:num_train]] + \
[x_stu[i] for i in ind_stu[:num_train]]
y_tr = [1.0]*num_train + [-1.0]*num_train
# dpark version
def map_iter(i):
y_tr_examplar = [-1.0] * len(y_tr)
y_tr_examplar[i] = 1.0
# opt = '-t 0 -w1 ' + str(len(y_tr)) + ' -w-1 1 -b 1 -q'
# It is suggested in Efros' paper that:
# C1 0.5, C2 0.01
opt = '-t 0 -w1 0.5 -w-1 0.01 -b 1 -q'
m = svm_train(y_tr_examplar, list(x_tr), opt)
p_label, p_acc, p_val = svm_predict(y_te, x_te, m, '-b 1 -q')
p_val = np.array(p_val)
# p_val = np.delete(p_val,1,1) # shape = (N, 1)
p_val = p_val[:, 0] # shape = (N, )
return p_val
p_vals = dpark.makeRDD(
range(len(y_tr))
).map(
map_iter
).collect()
val = np.array(p_vals).T
# for-loop version
'''
# Examplar SVM Training
ensemble_model = []
# DPark
for i in range(len(y_tr)):
y_tr_examplar = [-1.0] * len(y_tr)
y_tr_examplar[i] = 1.0;
#opt = '-t 0 -w1 ' + str(len(y_tr)) + ' -w-1 1 -b 1 -q'
# It is suggested in Efros' paper that:
# C1 0.5, C2 0.01
opt = '-t 0 -w1 0.5 -w-1 0.01 -b 1 -q'
m = svm_train(y_tr_examplar, x_tr, opt)
ensemble_model.append(m)
print("The %s-th examplar SVM has been trained" %i)
# Calibaration, to be updated
# Since we adopt the probability estimation model of LIB_SVM, Calibrating seems unnecessary
# Ensembly Classify
val = np.zeros((len(y_te),1))
for m in ensemble_model:
p_label, p_acc, p_val = svm_predict(y_te, x_te, m, '-b 1 -q')
p_val = np.array(p_val)
p_val = np.delete(p_val,1, 1)
val = np.hstack((val, p_val))
if val.shape[1] != len(y_tr) + 1:
print "Chaos!"
val = np.delete(val,0,1)
print 'val.shape =', val.shape
'''
# KNN
k = num_train / 8
sorted_index = val.argsort(axis=1)
sorted_index = sorted_index.T[::-1].T
p_label = []
for index in sorted_index:
nearest_samples = []
for sample_index in index[:k]:
nearest_samples.append(y_tr[sample_index])
n,bins,dummy = plt.hist(nearest_samples, 2, normed=1,
facecolor='r', alpha=0.75)
if n[0] > n[1]:
p_label.append(-1.0)
else:
p_label.append(1.0)
# evaluation
rate, pos_rate, neg_rate = evaluation(y_te, p_label)
print("The Examplar SVM framework achieves a precision of %f" % rate)
import time
import unittest
import logging
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from dpark import DparkContext
from dpark.utils.nested_groupby import GroupByNestedIter
from dpark.shuffle import GroupByNestedIter, AutoBatchedSerializer
from dpark.utils.profile import profile
import dpark.conf
GroupByNestedIter.NO_CACHE = True
print_mem_incr = True
print_mem_incr = False
dc = DparkContext('mesos')
RC = dpark.conf.rddconf
M = 1024 * 1024
def rss_func(p):
if hasattr(p, "memory_info"):
mem_info = getattr(p, "memory_info")
else:
mem_info = getattr(p, 'get_memory_info')
def _():
return mem_info().rss / M
return _
def main(argv):
# Loading the dataset
data = svm_read_problem('echo_liveness.01.libsvm')
y, x = data
del data
num_train = 6000
num_test = 6000
# Preparing training and testing data
if len(x) != len(y):
print("Please examine the data set, for the labels and features are not accorded!")
sys.exit()
# generating random training and testing set, to yield the ability of classifier more accurately.
x_live = [x[i] for i in find(y, 1.0)]
x_stu = [x[i] for i in find(y, 0.0)]
n_live = len(x_live)
n_stu = len(x_stu)
ind_live = range(n_live)
ind_stu = range(n_stu)
random.shuffle(ind_live)
random.shuffle(ind_stu)
x_te = [x_live[i] for i in ind_live[num_train : num_test + num_train]] + \
[x_stu[i] for i in ind_stu[num_train : num_test + num_train]]
y_te = [1.0] * len(ind_live[num_train : num_test + num_train]) + \
[-1.0]*len(ind_stu[num_train : num_test + num_train])
x_tr = [x_live[i] for i in ind_live[:num_train]] + \
[x_stu[i] for i in ind_stu[:num_train]]
y_tr = [1.0]*num_train + [-1.0]*num_train
# SVM and a 10-fold Cross Validation choosing the best parameters.
# gamma and c_reg are constructed in a parameter grid
# for-loop version
'''
gamma = np.arange(.01,20,.04)
c_reg = np.arange(.01,20,.04)
opt = []
best_para = {'gamma': 0, 'c': 0, 'precision': 0}
for g in gamma:
for c in c_reg:
opt = '-g '+ str(g) +' -c ' + str(c) + ' -v 10 -q'
pre = svm_train(y_tr,x_tr,opt)
if pre > best_para.get('precision'):
best_para['gamma'] = g
best_para['c'] = c
best_para['precision'] = pre
best_opt = '-g '+ str(best_para.get('gamma')) +' -c ' + str(best_para.get('c')) + ' -q'
m = svm_train(y_tr, x_tr, best_opt)
p_label, p_acc, p_val = svm_predict(y_te, x_te, m, '-q')
'''
# dpark version
dpark = DparkContext()
gamma = np.arange(.01, 5, .08)
c_reg = np.arange(.01, 5, .08)
opt = []
for g in gamma:
for c in c_reg:
opt.append('-g '+ str(g) +' -c ' + str(c) + ' -v 10 -q')
def map_iter(i):
pre = svm_train(y_tr, list(x_tr), opt[i])
return pre
#pres = dpark.makeRDD(range(len(opt)),100).map(map_iter).collect()
pres = dpark.makeRDD(range(len(opt))).map(map_iter).collect()
pres = np.array(pres)
best_opt_ind = pres.argsort()
best_opt = opt[best_opt_ind[-1]]
best_opt = best_opt[:best_opt.find('-v') - 1]
m = svm_train(y_tr, x_tr, best_opt)
p_label, p_acc, p_val = svm_predict(y_te, x_te, m, '-q')
print 'This SVM framework precision: %f' % p_acc[0]
# -*- coding: utf-8 -*-
from dpark import DparkContext
def m(x):
return x
rdd = DparkContext().makeRDD([(1,1)]).map(m).groupByKey()
rdd.map(m).collect()
rdd.map(m).collect()
return (title, Vertex(title, 1.0/numV, outEdges, True))
def gen_compute(num, epsilon):
def compute(self, messageSum, agg, superstep):
if messageSum and messageSum[0]:
newValue = 0.15 / num + 0.85 * messageSum[0]
else:
newValue = self.value
terminate = (superstep >= 10 and abs(newValue-self.value) < epsilon) or superstep > 30
outbox = [Message(edge.target_id, newValue / len(self.outEdges))
for edge in self.outEdges] if not terminate else []
return Vertex(self.id, newValue, self.outEdges, not terminate), outbox
return compute
if __name__ == '__main__':
inputFile = 'wikipedia.txt'
threshold = 0.01
dpark = DparkContext()
path = os.path.join(os.path.dirname(os.path.abspath(__file__)), inputFile)
input = dpark.textFile(path)
numVertex = input.count()
vertices = input.map(lambda line: parse_vertex(line, numVertex)).cache()
epsilon = 0.01 / numVertex
messages = dpark.parallelize([])
result = Bagel.run(dpark, vertices, messages,
gen_compute(numVertex, epsilon))
for v in result.filter(lambda x:x.value > threshold).collect():
print v.id, v.value
# -*- coding: utf-8 -*-
from dpark import DparkContext
dc = DparkContext()
def get_rdd():
return dc.makeRDD([(1, 1)])
rdd1 = get_rdd()
rdd2 = dc.union([get_rdd() for i in range(2)])
rdd3 = get_rdd().groupByKey()
dc.union([rdd1, rdd2, rdd3]).collect()
import glob
from dpark import DparkContext
RATING_PATH = '/nfs/wuhong/offline_use/rating_new/'
TRAINING_PATH = '/nfs/wuhong/paracel/data/als_fm/train'
TEST_PATH = '/nfs/wuhong/paracel/data/als_fm/test'
dpark = DparkContext()
def local_filter1(line):
tmp = line.strip().split(',')[1]
if tmp.endswith('0') or tmp.endswith('1') or tmp.endswith('2'):
return False
return True
def local_filter2(line):
tmp = line.strip().split(',')[1]
if tmp.endswith('0') or tmp.endswith('1') or tmp.endswith('2'):
return True
return False
dpark.textFile(glob.glob(RATING_PATH)).filter(
local_filter1
).saveAsTextFile(TRAINING_PATH)
dpark.textFile(glob.glob(RATING_PATH)).filter(
local_filter2
).saveAsTextFile(TEST_PATH)
from __future__ import absolute_import
from __future__ import print_function
import sys
sys.path.append('../')
from dpark import DparkContext
dpark = DparkContext()
name = '/mfs/tmp/weblog-pre-20111019.csv'
name = '/mfs/tmp/weblog-20111019.csv'
name = '/tmp/weblog-20111019.csv.small'
#name = '/tmp/weblog-20111019.csv.medium'
pv = dpark.textFile(name)
pv = pv.map(lambda x:x.split(',')).map(lambda l:(l[3],l[7]))
pv = pv.flatMap(lambda i_u:(i_u[1].startswith('/movie') and [(i_u[0],2)]
or i_u[1].startswith('/group') and [(i_u[0],3)]
or []))
#print pv.take(50)
pv = pv.reduceByKey(lambda x,y:x*y)
#print pv.take(50)
print(pv.filter(lambda __y:__y[1]%2==0 and __y[1]%3==0).count())
#movie = pv.filter(lambda (bid,url): url.startswith('/movie')).reduceByKey(lambda x,y:None)
#group = pv.filter(lambda (bid,url): url.startswith('/group')).reduceByKey(lambda x,y:None)
#print movie.join(group).count()
#print pv.map(lambda x:x.split(',')[2]).uniq().count()
#print pv.map(lambda x:(x.split(',')[2],None)).reduceByKey(lambda x,y:None).count()
#.filter(lambda uid:uid)
#print upv.count()
#print upv.reduceByKey(lambda x,y:x+y).count()
from dpark import DparkContext
dpark = DparkContext()
count = dpark.accumulator(0)
def random_once(*args, **kwrgs):
x = random() * 2 - 1
y = random() * 2 - 1
if x * x + y * y < 1:
count.add(1)
depark.parallelize(range(0, N), 10).foreach(random_once)
print 'PI is roughly ', 4.0 * count.value / N
from __future__ import absolute_import
from __future__ import print_function
import math
import random
import os, sys
from pprint import pprint
from six.moves import map
from six.moves import range
from six.moves import zip
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from dpark import DparkContext
dpark = DparkContext()
# range
nums = dpark.parallelize(list(range(100)), 4)
print(nums.count())
print(nums.reduce(lambda x, y: x + y))
# text search
f = dpark.textFile("./", ext='py').map(lambda x: x.strip())
log = f.filter(lambda line: 'logging' in line).cache()
print('logging', log.count())
print('error', log.filter(lambda line: 'error' in line).count())
for line in log.filter(lambda line: 'error' in line).collect():
print(line)
# word count
counts = f.flatMap(lambda x: x.split()).map(lambda x: (x, 1)).reduceByKey(lambda x, y: x + y).cache()
pprint(counts.filter(lambda __v1: __v1[1] > 50).collectAsMap())
