既有适合小白学习的零基础资料，也有适合3年以上经验的小伙伴深入学习提升的进阶课程，涵盖了95%以上大数据知识点，真正体系化！
由于文件比较多，这里只是将部分目录截图出来，全套包含大厂面经、学习笔记、源码讲义、实战项目、大纲路线、讲解视频，并且后续会持续更新
at org.apache.spark.rdd.RDDKaTeX parse error: Can't use function '$' in math mode at position 8: anonfun$̲partitions$2.ap…anonfun$partitions
2.
a
p
p
l
y
(
R
D
D
.
s
c
a
l
a
:
237
)
a
t
s
c
a
l
a
.
O
p
t
i
o
n
.
g
e
t
O
r
E
l
s
e
(
O
p
t
i
o
n
.
s
c
a
l
a
:
120
)
a
t
o
r
g
.
a
p
a
c
h
e
.
s
p
a
r
k
.
r
d
d
.
R
D
D
.
p
a
r
t
i
t
i
o
n
s
(
R
D
D
.
s
c
a
l
a
:
237
)
a
t
o
r
g
.
a
p
a
c
h
e
.
s
p
a
r
k
.
r
d
d
.
M
a
p
P
a
r
t
i
t
i
o
n
s
R
D
D
.
g
e
t
P
a
r
t
i
t
i
o
n
s
(
M
a
p
P
a
r
t
i
t
i
o
n
s
R
D
D
.
s
c
a
l
a
:
35
)
a
t
o
r
g
.
a
p
a
c
h
e
.
s
p
a
r
k
.
r
d
d
.
R
D
D
2.apply(RDD.scala:237) at scala.Option.getOrElse(Option.scala:120) at org.apache.spark.rdd.RDD.partitions(RDD.scala:237) at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35) at org.apache.spark.rdd.RDD
2.apply(RDD.scala:237)atscala.Option.getOrElse(Option.scala:120)atorg.apache.spark.rdd.RDD.partitions(RDD.scala:237)atorg.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)atorg.apache.spark.rdd.RDD
a
n
o
n
f
u
n
anonfun
anonfunpartitions
2.
a
p
p
l
y
(
R
D
D
.
s
c
a
l
a
:
239
)
a
t
o
r
g
.
a
p
a
c
h
e
.
s
p
a
r
k
.
r
d
d
.
R
D
D
2.apply(RDD.scala:239) at org.apache.spark.rdd.RDD
2.apply(RDD.scala:239)atorg.apache.spark.rdd.RDD
a
n
o
n
f
u
n
anonfun
anonfunpartitions
2.
a
p
p
l
y
(
R
D
D
.
s
c
a
l
a
:
237
)
a
t
s
c
a
l
a
.
O
p
t
i
o
n
.
g
e
t
O
r
E
l
s
e
(
O
p
t
i
o
n
.
s
c
a
l
a
:
120
)
a
t
o
r
g
.
a
p
a
c
h
e
.
s
p
a
r
k
.
r
d
d
.
R
D
D
.
p
a
r
t
i
t
i
o
n
s
(
R
D
D
.
s
c
a
l
a
:
237
)
a
t
o
r
g
.
a
p
a
c
h
e
.
s
p
a
r
k
.
P
a
r
t
i
t
i
o
n
e
r
2.apply(RDD.scala:237) at scala.Option.getOrElse(Option.scala:120) at org.apache.spark.rdd.RDD.partitions(RDD.scala:237) at org.apache.spark.Partitioner
2.apply(RDD.scala:237)atscala.Option.getOrElse(Option.scala:120)atorg.apache.spark.rdd.RDD.partitions(RDD.scala:237)atorg.apache.spark.Partitioner.defaultPartitioner(Partitioner.scala:65)
at org.apache.spark.rdd.PairRDDFunctionsKaTeX parse error: Can't use function '$' in math mode at position 8: anonfun$̲reduceByKey$3.a…anonfun$reduceByKey
3.
a
p
p
l
y
(
P
a
i
r
R
D
D
F
u
n
c
t
i
o
n
s
.
s
c
a
l
a
:
331
)
a
t
o
r
g
.
a
p
a
c
h
e
.
s
p
a
r
k
.
r
d
d
.
R
D
D
O
p
e
r
a
t
i
o
n
S
c
o
p
e
3.apply(PairRDDFunctions.scala:331) at org.apache.spark.rdd.RDDOperationScope
3.apply(PairRDDFunctions.scala:331)atorg.apache.spark.rdd.RDDOperationScope.withScope(RDDOperationScope.scala:150)
at org.apache.spark.rdd.RDDOperationScope
.
w
i
t
h
S
c
o
p
e
(
R
D
D
O
p
e
r
a
t
i
o
n
S
c
o
p
e
.
s
c
a
l
a
:
111
)
a
t
o
r
g
.
a
p
a
c
h
e
.
s
p
a
r
k
.
r
d
d
.
R
D
D
.
w
i
t
h
S
c
o
p
e
(
R
D
D
.
s
c
a
l
a
:
316
)
a
t
o
r
g
.
a
p
a
c
h
e
.
s
p
a
r
k
.
r
d
d
.
P
a
i
r
R
D
D
F
u
n
c
t
i
o
n
s
.
r
e
d
u
c
e
B
y
K
e
y
(
P
a
i
r
R
D
D
F
u
n
c
t
i
o
n
s
.
s
c
a
l
a
:
330
)
a
t
c
n
.
i
t
c
a
s
t
.
s
p
a
r
k
.
W
C
.withScope(RDDOperationScope.scala:111) at org.apache.spark.rdd.RDD.withScope(RDD.scala:316) at org.apache.spark.rdd.PairRDDFunctions.reduceByKey(PairRDDFunctions.scala:330) at cn.itcast.spark.WC
.withScope(RDDOperationScope.scala:111)atorg.apache.spark.rdd.RDD.withScope(RDD.scala:316)atorg.apache.spark.rdd.PairRDDFunctions.reduceByKey(PairRDDFunctions.scala:330)atcn.itcast.spark.WC.main(WC.scala:16)
at cn.itcast.spark.WC.main(WC.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at com.intellij.rt.execution.application.AppMain.main(AppMain.java:140)
16/06/20 11:05:58 INFO SparkContext: Invoking stop() from shutdown hook
16/06/20 11:05:58 INFO SparkUI: Stopped Spark web UI at http://192.168.2.109:4040
16/06/20 11:05:58 INFO MapOutputTrackerMasterEndpoint: MapOutputTrackerMasterEndpoint stopped!
16/06/20 11:05:58 INFO MemoryStore: MemoryStore cleared
16/06/20 11:05:58 INFO BlockManager: BlockManager stopped
16/06/20 11:05:58 INFO BlockManagerMaster: BlockManagerMaster stopped
16/06/20 11:05:58 INFO OutputCommitCoordinator$OutputCommitCoordinatorEndpoint: OutputCommitCoordinator stopped!
16/06/20 11:05:58 INFO SparkContext: Successfully stopped SparkContext
16/06/20 11:05:58 INFO ShutdownHookManager: Shutdown hook called
16/06/20 11:05:58 INFO ShutdownHookManager: Deleting directory /private/var/folders/z_/thb8h2gd4hqdcz9z5r9xzl140000gn/T/spark-81bc4c8a-5f7f-45c0-97ab-a82b88619ee5
Process finished with exit code 1
===================================================================================================================================
我的pom.xml几个重要的包得版本如下：
做了几个测试，其他版本不变，hadoop.version 为 2.4.0，2.4.1，2.5.2，2.6.1，2.6.4 都会报上面的错误，不知道是不是hadoop的bug，有人说将hadoop的源码重新编译一下就行，但我没试。
解决办法：
把hadoop version改成2.2.0就可以了，测了一下2.7.2也可以，所以估计是hadoop的一个坑，2.7.2就修复了。其他版本没试
网上学习资料一大堆，但如果学到的知识不成体系，遇到问题时只是浅尝辄止，不再深入研究，那么很难做到真正的技术提升。
一个人可以走的很快，但一群人才能走的更远！不论你是正从事IT行业的老鸟或是对IT行业感兴趣的新人，都欢迎加入我们的的圈子（技术交流、学习资源、职场吐槽、大厂内推、面试辅导），让我们一起学习成长！
可以走的很快，但一群人才能走的更远！不论你是正从事IT行业的老鸟或是对IT行业感兴趣的新人，都欢迎加入我们的的圈子（技术交流、学习资源、职场吐槽、大厂内推、面试辅导），让我们一起学习成长！**
3万+
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
