大数据实战手册-开发篇之RDD ：超详细RDD函数API

2.2 RDD:计算 transform->action

2.2.1 aggregate

x = sc.parallelize([2,3,4], 2)[Task不能跨分片，task数为2]
neutral_zero_value = (0,1) # sum: x+0 = x, product: 1*x = x
seqOp = (lambda aggregated, el: (aggregated[0] + el, aggregated[1] * el)) 
combOp = (lambda aggregated, el: (aggregated[0] + el[0], aggregated[1] * el[1]))
y = x.aggregate(neutral_zero_value,seqOp,combOp)[seqOp：各分片聚合计算
combOp：聚合各个分片
neutral_zero_value：初始化设定值，都要参与计算]  # computes (cumulative sum, cumulative product)
print(x.collect())
print(y)
 
[2, 3, 4]
(9, 24)

2.2.2 aggregateByKey

x = sc.parallelize([('B',1),('B',2),('A',3),('A',4),('A',5)])
zeroValue = [] # empty list is 'zero value' for append operation
mergeVal = (lambda aggregated, el: aggregated + [(el,el**2)])
mergeComb = (lambda agg1,agg2: agg1 + agg2 )
y = x.aggregateByKey(zeroValue,mergeVal,mergeComb)
print(x.collect())
print(y.collect())
 
[('B', 1), ('B', 2), ('A', 3), ('A', 4), ('A', 5)]
[('A', [(3, 9), (4, 16), (5, 25)]), ('B', [(1, 1), (2, 4)])]

2.2.3 cache（persistent）
2.2.4 cartesian（笛卡儿积）

# cartesian
x = sc.parallelize(['A','B'])
y = sc.parallelize(['C','D'])
z = x.cartesian(y)
print(x.collect())
print(y.collect())
print(z.collect())
 
['A', 'B']
['C', 'D']
[('A', 'C'), ('A', 'D'), ('B', 'C'), ('B', 'D')]

2.2.5 checkpoint
2.2.6 coalesce（合并分片）

# coalesce
x = sc.parallelize([1,2,3,4,5],2)
y = x.coalesce(numPartitions=1)
print(x.glom().collect())
print(y.glom().collect())
 
[[1, 2], [3, 4, 5]]
[[1, 2, 3, 4, 5]]

2.2.7 cogroup（按rdd分组）

# cogroup
x = sc.parallelize([('C',4),('B',(3,3)),('A',2),('A',(1,1))])
y = sc.parallelize([('A',8),('B',7),('A',6),('D',(5,5))])
z = x.cogroup(y)
print(x.collect())
print(y.collect())
for key,val in list(z.collect()):
    print(key, [list(i) for i in val])
 
[('C', 4), ('B', (3, 3)), ('A', 2), ('A', (1, 1))]
[('A', 8), ('B', 7), ('A', 6), ('D', (5, 5))]
A [[2, (1, 1)], [8, 6]]
C [[4], []]
B [[(3, 3)], [7]]
D [[], [(5, 5)]]

2.2.8 combineByKey

# combineByKey
x = sc.parallelize([('B',1),('B',2),('A',3),('A',4),('A',5)])
createCombiner = (lambda el: [(el,el**2)]) 
mergeVal = (lambda aggregated, el: aggregated + [(el,el**2)]) # append to aggregated
mergeComb = (lambda agg1,agg2: agg1 + agg2 )  # append agg1 with agg2
y = x.combineByKey(createCombiner,mergeVal,mergeComb)
print(x.collect())
print(y.collect())
 
[('B', 1), ('B', 2), ('A', 3), ('A', 4), ('A', 5)]
[('A', [(3, 9), (4, 16), (5, 25)]), ('B', [(1, 1), (2, 4)])]

2.2.9 context
2.2.10 countByKey
2.2.11 countByValue
2.2.12 distinct
2.2.13 filter

# filter
x = sc.parallelize([1,2,3])
y = x.filter(lambda x: x%2 == 1)  # filters out even elements
print(x.collect())
print(y.collect())
 
[1, 2, 3]
[1, 3]
2.2.14 first
备注：Return the first element of this rdd

2.2.15 flatMap（降维）

# flatMap
x = sc.parallelize([1,2,3])
y = x.flatMap(lambda x: (x, 100*x, x**2))
print(x.collect())
print(y.collect())
 
[1, 2, 3]
[1, 100, 1, 2, 200, 4, 3, 300, 9]

2.2.16 flatMapValues

x = sc.parallelize([("a", ["x", "y", "z"]), ("b", ["p", "r"])])
 def f(x): return x
 x.flatMapValues(f).collect()
[('a', 'x'), ('a', 'y'), ('a', 'z'), ('b', 'p'), ('b', 'r')]

2.2.17 fold

# fold
x = sc.parallelize([1,2,3])
neutral_zero_value = 0  # 0 for sum, 1 for multiplication
y = x.fold(neutral_zero_value,lambda obj, accumulated: accumulated + obj) # computes cumulative sum
print(x.collect())
print(y)
 
[1, 2, 3]
6

2.2.18 foldByKey

>>> rdd = sc.parallelize([("a", 1), ("b", 1), ("a", 1)])
>>> from operator import add[python标准库：常用运算函数库]
>>> sorted(rdd.foldByKey(0, add).collect())
[('a', 2), ('b', 1)]

2.2.19 foreach

>>> def f(x): print(x)
>>> sc.parallelize([1, 2, 3, 4, 5]).foreach(f)[循环rdd的所有元素，无返回值]

2.2.20 foreachPartition [循环rdd的分片]

# foreachPartition
from __future__ import print_function
x = sc.parallelize([1,2,3],5)
def f(parition):
    '''side effect: append the current RDD partition contents to a file'''
    f1=open("./foreachPartitionExample.txt", 'a+') 
    print([el for el in parition],file=f1)
 
# first clear the file contents
open('./foreachPartitionExample.txt', 'w').close()  
 
y = x.foreachPartition(f) # writes into foreachExample.txt
 
print(x.glom().collect())
print(y)  # foreach returns 'None'
# print the contents of foreachExample.txt
with open("./foreachPartitionExample.txt", "r") as foreachExample:
    print (foreachExample.read())
 
[[], [1], [], [2], [3]]
None
[]
[]
[1]
[2]
[3]

2.2.21 fullOuterJoin

备注：Perform a right outer join of self and other.
2.2.22 glom()[合并rdd的分片的所有元素]
2.2.23 groupby

# groupBy
x = sc.parallelize([1,2,3])
y = x.groupBy(lambda x: 'A' if (x%2 == 1) else 'B' )
print(x.collect())
# y is nested, this iterates through it
print([(j[0],[i for i in j[1]]) for j in y.collect()]) 
 
[1, 2, 3]
[('A', [1, 3]), ('B', [2])]

2.2.24 groupbykey

# groupByKey
x = sc.parallelize([('B',5),('B',4),('A',3),('A',2),('A',1)])
y = x.groupByKey()
print(x.collect())
print([(j[0],[i for i in j[1]]) for j in y.collect()])
 
[('B', 5), ('B', 4), ('A', 3), ('A', 2), ('A', 1)]
[('A', [3, 2, 1]), ('B', [5, 4])]

2.2.25 groupwith(Alias for cogroup)

# groupWith
x = sc.parallelize([('C',4),('B',(3,3)),('A',2),('A',(1,1))])
y = sc.parallelize([('B',(7,7)),('A',6),('D',(5,5))])
z = sc.parallelize([('D',9),('B',(8,8))])
a = x.groupWith(y,z)
print(x.collect())
print(y.collect())
print(z.collect())
print("Result:")
for key,val in list(a.collect()): 
    print(key, [list(i) for i in val])
 
[('C', 4), ('B', (3, 3)), ('A', 2), ('A', (1, 1))]
[('B', (7, 7)), ('A', 6), ('D', (5, 5))]
[('D', 9), ('B', (8, 8))]
Result:
D [[], [(5, 5)], [9]]
C [[4], [], []]
B [[(3, 3)], [(7, 7)], [(8, 8)]]
A [[2, (1, 1)], [6], []]

2.2.26 histogram

rdd = sc.parallelize(range(51))
 rdd.histogram(2)
([0, 25, 50], [25, 26])
rdd.histogram([0, 5, 25, 50])
([0, 5, 25, 50], [5, 20, 26])[分组区间，每区间元素个数]
rdd.histogram([0, 15, 30, 45, 60])  # evenly spaced buckets
([0, 15, 30, 45, 60], [15, 15, 15, 6])
rdd = sc.parallelize(["ab", "ac", "b", "bd", "ef"])
 rdd.histogram(("a", "b", "c"))
(('a', 'b', 'c'), [2, 2])

2.2.27 join

# join
 x = sc.parallelize([('C',4),('B',3),('A',2),('A',1)])
  y = sc.parallelize([('A',8),('B',7),('A',6),('D',5)]) z = x.join(y)
   print(x.collect())
    print(y.collect())
    print(z.collect())
    [('C', 4), ('B', 3), ('A', 2), ('A', 1)]
    [('A', 8), ('B', 7), ('A', 6), ('D', 5)]
     [('A', (2, 8)), ('A', (2, 6)), ('A', (1, 8)), ('A', (1, 6)), ('B', (3, 7))]

2.2.28 leftoutjoin

# leftOuterJoin
x = sc.parallelize([('C',4),('B',3),('A',2),('A',1)])
y = sc.parallelize([('A',8),('B',7),('A',6),('D',5)])
z = x.leftOuterJoin(y)
print(x.collect())
print(y.collect())
print(z.collect())
 
[('C', 4), ('B', 3), ('A', 2), ('A', 1)]
[('A', 8), ('B', 7), ('A', 6), ('D', 5)]
[('A', (2, 8)), ('A', (2, 6)), ('A', (1, 8)), ('A', (1, 6)), ('C', (4, None)), ('B', (3, 7))]

2.2.29 rightoutjoin

# rightOuterJoin
x = sc.parallelize([('C',4),('B',3),('A',2),('A',1)])
y = sc.parallelize([('A',8),('B',7),('A',6),('D',5)])
z = x.rightOuterJoin(y)
print(x.collect())
print(y.collect())
print(z.collect())
 
[('C', 4), ('B', 3), ('A', 2), ('A', 1)]
[('A', 8), ('B', 7), ('A', 6), ('D', 5)]
[('A', (2, 8)), ('A', (2, 6)), ('A', (1, 8)), ('A', (1, 6)), ('B', (3, 7)), ('D', (None, 5))]

2.2.30 keyby

# keyBy
x = sc.parallelize([1,2,3])
y = x.keyBy(lambda x: x**2)
print(x.collect())
print(y.collect())
 
[1, 2, 3]
[(1, 1), (4, 2), (9, 3)]
2.2.31 lookup（key）

2.2.32 mapPartitions

# mapPartitions
x = sc.parallelize([1,2,3], 2)
def f(iterator): yield sum(iterator)
y = x.mapPartitions(f)
# glom() flattens elements on the same partition
print(x.glom().collect())  
print(y.glom().collect())
 
[[1], [2, 3]]
[[1], [5]]

2.2.33 mapPartitionsWithIndex

# mapPartitionsWithIndex
x = sc.parallelize([1,2,3], 2)
def f(partitionIndex, iterator): yield (partitionIndex,sum(iterator))
y = x.mapPartitionsWithIndex(f)
 
# glom() flattens elements on the same partition
print(x.glom().collect())  
print(y.glom().collect())
 
[[1], [2, 3]]
[[(0, 1)], [(1, 5)]]

2.2.34 map、max、min、mean、name
2.2.35 mapValues

>>> x = sc.parallelize([("a", ["apple", "banana", "lemon"]), ("b", ["grapes"])])
>>> def f(x): return len(x)
>>> x.mapValues(f).collect()
[('a', 3), ('b', 1)]

2.2.36 partitionby

# partitionBy
x = sc.parallelize([(0,1),(1,2),(2,3)],2)
y = x.partitionBy(numPartitions = 3, partitionFunc = lambda x: x)
# only key is passed to paritionFunc
print(x.glom().collect())
print(y.glom().collect())
 
[[(0, 1)], [(1, 2), (2, 3)]]
[[(0, 1)], [(1, 2)], [(2, 3)]]

2.2.37 persist

 # rdd持久化，降低内存消耗
reqrdd.persist(storageLevel=StorageLevel.MEMORY_AND_DISK_SER)
Cache：
Persist this RDD with the default storage level (MEMORY_ONLY).

2.2.38 pipe

# pipe
x = sc.parallelize(['A', 'Ba', 'C', 'AD'])
y = x.pipe('grep -i "A"') # calls out to grep, may fail under Windows 
print(x.collect())
print(y.collect())
['A', 'Ba', 'C', 'AD']
['A', 'Ba', 'AD']

2.2.40 randomSplit
2.2.41 reduce

# reduce
x = sc.parallelize([1,2,3])
y = x.reduce(lambda obj, accumulated: obj + accumulated)  # computes a cumulative sum
print(x.collect())
print(y)
 
[1, 2, 3]
6

2.2.42 reducebykey

# reduceByKey
x = sc.parallelize([('B',1),('B',2),('A',3),('A',4),('A',5)])
y = x.reduceByKey(lambda agg, obj: agg + obj)
print(x.collect())
print(y.collect())
 
[('B', 1), ('B', 2), ('A', 3), ('A', 4), ('A', 5)]
[('A', 12), ('B', 3)]

2.2.43 reduceByKeyLocally

# reduceByKeyLocally
x = sc.parallelize([('B',1),('B',2),('A',3),('A',4),('A',5)])
y = x.reduceByKeyLocally(lambda agg, obj: agg + obj)
print(x.collect())
print(y)
 
[('B', 1), ('B', 2), ('A', 3), ('A', 4), ('A', 5)]
{'A': 12, 'B': 3}
备注：This will also perform the merging locally on each mapper before sending results to a reducer, similarly to a “combiner” in  MapReduce.

2.2.44 repartition

# repartition
x = sc.parallelize([1,2,3,4,5],2)
y = x.repartition(numPartitions=3)
print(x.glom().collect())
print(y.glom().collect())
[[1, 2], [3, 4, 5]]
[[], [1, 2, 3, 4], [5]]

2.2.45 repartitionAndSortWithinPartitions

rdd = sc.parallelize([(0, 5), (3, 8), (2, 6), (0, 8), (3, 8), (1, 3)])
rdd2 = rdd.repartitionAndSortWithinPartitions(2, lambda x: x % 2, True)
rdd2.glom().collect()
[[(0, 5), (0, 8), (2, 6)], [(1, 3), (3, 8), (3, 8)]]

2.2.46 smaple

# sample
x = sc.parallelize(range(7))
# call 'sample' 5 times
ylist = [x.sample(withReplacement=False, fraction=0.5) for i in range(5)] 
print('x = ' + str(x.collect()))
for cnt,y in zip(range(len(ylist)), ylist):
    print('sample:' + str(cnt) + ' y = ' +  str(y.collect()))
 
x = [0, 1, 2, 3, 4, 5, 6]
sample:0 y = [0, 2, 5, 6]
sample:1 y = [2, 6]
sample:2 y = [0, 4, 5, 6]
sample:3 y = [0, 2, 6]
sample:4 y = [0, 3, 4]

2.2.47 sampleByKey

# sampleByKey
x = sc.parallelize([('A',1),('B',2),('C',3),('B',4),('A',5)])
y = x.sampleByKey(withReplacement=False, fractions={'A':0.5, 'B':1, 'C':0.2})
print(x.collect())
print(y.collect())
 
[('A', 1), ('B', 2), ('C', 3), ('B', 4), ('A', 5)]
[('B', 2), ('C', 3), ('B', 4)]

2.2.48 sampleStdev

# sampleStdev
x = sc.parallelize([1,3,2])
y = x.sampleStdev() # divides by N-1
print(x.collect())
print(y)
[1, 3, 2]
1.0

2.2.49 sampleVariance

# sampleVariance
x = sc.parallelize([1,3,2])
y = x.sampleVariance()  # divides by N-1
print(x.collect())
print(y)
[1, 3, 2]
1.0

2.2.50 sortByKey

# sortByKey
x = sc.parallelize([('B',1),('A',2),('C',3)])
y = x.sortByKey()
print(x.collect())
print(y.collect())
 
[('B', 1), ('A', 2), ('C', 3)]
[('A', 2), ('B', 1), ('C', 3)]

2.2.51 sortBy

tmp = [('a', 1), ('b', 2), ('1', 3), ('d', 4), ('2', 5)]
sc.parallelize(tmp).sortBy(lambda x: x[0]).collect()
[('1', 3), ('2', 5), ('a', 1), ('b', 2), ('d', 4)]
sc.parallelize(tmp).sortBy(lambda x: x[1]).collect()
[('a', 1), ('b', 2), ('1', 3), ('d', 4), ('2', 5)]

2.2.52 stats、stdev、sum
2.2.53 subtract

x = sc.parallelize([("a", 1), ("b", 4), ("b", 5), ("a", 3)])
y = sc.parallelize([("a", 3), ("c", None)])
sorted(x.subtract(y).collect())
[('a', 1), ('b', 4), ('b', 5)]
2.2.54 subtractByKey
x = sc.parallelize([("a", 1), ("b", 4), ("b", 5), ("a", 2)])
y = sc.parallelize([("a", 3), ("c", None)])
sorted(x.subtractByKey(y).collect())
[('b', 4), ('b', 5)]

2.2.55 take

# take
x = sc.parallelize([1,3,1,2,3])
y = x.take(num = 3)
print(x.collect())
print(y)
 
[1, 3, 1, 2, 3]
[1, 3, 1]

2.2.56 takeOrder

# takeOrdered
x = sc.parallelize([1,3,1,2,3])
y = x.takeOrdered(num = 3)
print(x.collect())
print(y)
 
[1, 3, 1, 2, 3]
[1, 1, 2]

2.2.57 takeSample

# takeSample
x = sc.parallelize(range(7))
# call 'sample' 5 times
ylist = [x.takeSample(withReplacement=False, num=3) for i in range(5)]  
print('x = ' + str(x.collect()))
for cnt,y in zip(range(len(ylist)), ylist):
    print('sample:' + str(cnt) + ' y = ' +  str(y))  # no collect on y
 
x = [0, 1, 2, 3, 4, 5, 6]
sample:0 y = [0, 2, 6]
sample:1 y = [6, 4, 2]
sample:2 y = [2, 0, 4]
sample:3 y = [5, 4, 1]
sample:4 y = [3, 1, 4]

2.2.58 treeAggregate

 add = lambda x, y: x + y
 rdd = sc.parallelize([-5, -4, -3, -2, -1, 1, 2, 3, 4], 10)
 rdd.treeAggregate(0, add, add)
-5
 rdd.treeAggregate(0, add, add, 1)
-5
 rdd.treeAggregate(0, add, add, 2)
-5
 rdd.treeAggregate(0, add, add, 5)
-5
 rdd.treeAggregate(0, add, add, 10)
-5

2.2.59 treeReduce

add = lambda x, y: x + y
 rdd = sc.parallelize([-5, -4, -3, -2, -1, 1, 2, 3, 4], 10)
 rdd.treeReduce(add)
-5
 rdd.treeReduce(add, 1)
-5
 rdd.treeReduce(add, 2)
-5
 rdd.treeReduce(add, 5)
-5
 rdd.treeReduce(add, 10)
-5

2.2.60 uion、unpersist、values、variance
2.2.61 zip

# zip
x = sc.parallelize(['B','A','A'])
# zip expects x and y to have same #partitions and #elements/partition
y = x.map(lambda x: ord(x))  
z = x.zip(y)
print(x.collect())
print(y.collect())
print(z.collect())
 
['B', 'A', 'A']
[66, 65, 65]
[('B', 66), ('A', 65), ('A', 65)]

2.2.62 zipWithIndex

# zipWithIndex
x = sc.parallelize(['B','A','A'],2)
y = x.zipWithIndex()
print(x.glom().collect())
print(y.collect())
 
[['B'], ['A', 'A']]
[('B', 0), ('A', 1), ('A', 2)]

2.2.63 zipWithUniqueId

# zipWithUniqueId
x = sc.parallelize(['B','A','A'],2)
y = x.zipWithUniqueId()
print(x.glom().collect())
print(y.collect())
 
[['B'], ['A', 'A']]
[('B', 0), ('A', 1), ('A', 3)]

-狼

发布了30 篇原创文章 · 获赞 9 · 访问量 2万+

私信关注

大数据实战手册-开发篇之RDD ： 超详细RDD函数API

猜你喜欢

大数据实战手册-开发篇之RDD ：超详细RDD函数API