From efdea1c5e1d7226b03b12c594c02a9c8567f9d3c Mon Sep 17 00:00:00 2001 From: cloudera_vm <cloudera@quickstart.cloudera> Date: Sun, 19 Mar 2017 09:22:57 -0700 Subject: [PATCH] clearing files for Qa --- Assign2/bin/SetSimilarityJoins/Qa.class | Bin 2768 -> 0 bytes Assign2/src/SetSimilarityJoins/Qa.java | 100 ------------------------ 2 files changed, 100 deletions(-) delete mode 100644 Assign2/bin/SetSimilarityJoins/Qa.class delete mode 100644 Assign2/src/SetSimilarityJoins/Qa.java diff --git a/Assign2/bin/SetSimilarityJoins/Qa.class b/Assign2/bin/SetSimilarityJoins/Qa.class deleted file mode 100644 index 2253ae7c5baf77a777bf125943765ca96db84654..0000000000000000000000000000000000000000 GIT binary patch literal 0 HcmV?d00001 literal 2768 zcmX^0Z`VEs1_on>DeMePj0~c|sU^XgxtTeMMVTd)Uiq1M#rlDX><lc742t<h>H3KU ziOCtM`WcBS`S}I<$@zI{`p)@zX_@JzMX4$53~Y=H(wNFhOEPoxL-O-;7#Y}XGV?M^ z>=+rCH8jH*8Cab2Q&PDYm>IZv7}yy&7#a9|GV@aXN^_G^i$W5Ua#9%?gnaUo6LZ26 zi!wocs31#8MrJW1gSZb?=UOu|u;eCY<}oseX+-;EC6*=X=OpH(>j#$<W#*+@gDmE9 ztw>HSD9OyvD`sa9VPp_SsDjIIGKeuqurr7=G6*1KgDZ<mQgeA2BpIX_8JP1+OBfkM zAy#DO>jxBN=9L7O6s0EST5~bTFvzhp$ij4k1HrMVD6z7bhe4h}fsuiuBp>1;Mh0~h zclsw~r6!kHYeLLLb~+b>5`zjmgEGv)sCM!&s4}QAGO!nboRO2q$RMhLX@q7NJA(!z zg9>Iep~Pk)C~UYG)ET(B7#Kl>4uc*$gD%!&0QMRveuGN$@=}X<81xwo7#Wz0O7j>Q zA~k%7vB?^XD!8%M*do!Bi$RRRh=;+L!Gw{4CAA{6gpq+o!xI#_EQv+w#f%KXShRth zm0HZm!03r9ad@&bSTi!nV>&uFv7jh5r8GHJ-zz@}6ezYl40a6mj127QsU@IHz{sGX zp^3#GnBi*8!QjZqz!R7l@95(bAK>U26wJk7#o!Fe1TKsW*2IPxQnG|4ZIC%`JPhs( z9*hjU#i=D;iA7G8&N+$2#f%Ih$jJdLW(`UWUW^QqnBL9I*AGdpC;^%0!^7YUGEcBL zwZy-)q@c9KI~8IkJA*$Xg928~o_QtVMVTd_Obaq2kcS}%WQH)@jIhL<(p0c3*cn0? z86>f0WfkAV0+9AF9)@s`cD~}&65qsvg480Y&PYZE8SFZPz>x*g9L>WJ1JcZ2oLT}A zh3SrCWH7~aJtC%aGL!T(^9o8!z+vGDV!7oP<tBoIC4q+_5o9dLOGr{shb1#Im=iKO z9~_uqvmxP%Fg%rqAq`}>2t2$Xa!}JVu*O+hv3@{eNd^}~IztvHEva!a<S^v1GvpHO zO}EUPR3yLfFyu27Ff#BYrlf#HL8db@*kendh(PnoPr{a+p^mfG4C7)bVklu}C?-CH zK+ZxAAs&WOkh?$$93l*I7#Bl1LnS*y1=ie~R;&*)1Xg@kF;p`$aOb6#d*&6FB<3Zj zGBS8#^A(o7i!F<zm~IVnNG%UT9YZ}M16yiEW^qX|BZC|^<KbZv1=7>V!_dUg%*eo& zlA4oRlFG;+k55mOW)vuKxAHKwF|;!>2$m;imbm2?Ip^mV<fMX1Z%}y{r5VM@z?_wz z#K@qCrD#HpG)4wKNQwl76evU)8Kkjjf;pOzfhnyRySb?0!N|ZHT#}fa?VDHtt-rZ~ z^Gl18Q$hAHGO!0G>VZl!Mg|^FQ2hZ;;-EsB**CF(k%0}8Wf>G17#Wxu7#Ua@7{D|; z0|x^m11AFmgFXWz10w?i1FP0{2Cj_^3=B*RJPZsBY+yl223`gR1|Be*m4T0epMima zlR<z%kb#Loh=GBDg@KVl7;H=u12Y2?0|SH7CI(Th9SqXj7!-Fis7G#R(A>?y7`dH6 zOKS&%wvF@-21A4$LJTYn3=Gl?pxR!RL5@L@K^|<M7{nw7QwB2z1_oIMRt9qh3$Qcw z87$FlX4GI{1$(P$6N9KW%x0@dt!)f8LJr#*oP2eJ7`HLF>IivmWAN4y^4rD`pd%E# zjUiM=C}JB!l#WpBHimc|p`>jLDZ3fcBehwKwlie<>44eHAodQ1Y#rSl422*QcQBM$ zu}HG$ZeysK$-phiqRX<4p&?v{WgA0FIP)5C;DSQWjX{usfkBypi$R4!f<cu*jzNt< zg+ZM`i$RmYfI*AFj6s*dhCz?PiNT1$m%)S~n!%JIfx(<1lfjaqh{1}Xiouqlfx#Xe z8YU3mK|`N`p$Qx=j0_SCSqvQvoeWG2z6_=eT@2j}%nX?fk_<fzy$mc2eGCi?d<=~L v7^>JAtk@aS*%`_im>BxO@jHQGA_D`15CaoKFasmQBnD1~2nI%m$qbwTxfbo> diff --git a/Assign2/src/SetSimilarityJoins/Qa.java b/Assign2/src/SetSimilarityJoins/Qa.java deleted file mode 100644 index 1215f84..0000000 --- a/Assign2/src/SetSimilarityJoins/Qa.java +++ /dev/null @@ -1,100 +0,0 @@ -package SetSimilarityJoins; - -import java.io.IOException; -import java.nio.file.Files; -import java.nio.file.Paths; -import java.util.Arrays; - -import org.apache.hadoop.conf.Configuration; -import org.apache.hadoop.conf.Configured; -import org.apache.hadoop.fs.FileSystem; -import org.apache.hadoop.fs.Path; -import org.apache.hadoop.io.LongWritable; -import org.apache.hadoop.io.IntWritable; -import org.apache.hadoop.io.Text; -import org.apache.hadoop.mapreduce.Job; -import org.apache.hadoop.mapreduce.Mapper; -import org.apache.hadoop.mapreduce.Reducer; -import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; -import org.apache.hadoop.mapreduce.lib.input.TextInputFormat; -import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; -import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat; -import org.apache.hadoop.util.Tool; -import org.apache.hadoop.util.ToolRunner; - -public class Qa extends Configured implements Tool { - public static void main(String[] args) throws Exception { - System.out.println(Arrays.toString(args)); - int res = ToolRunner.run(new Configuration(), new Qa(), args); - - System.exit(res); - } - - @Override - public int run(String[] args) throws Exception { - System.out.println(Arrays.toString(args)); - Job job = new Job(getConf(), "Qa_ALL_PAIRS"); - job.setJarByClass(Qa.class); - job.setOutputKeyClass(Text.class); - job.setOutputValueClass(IntWritable.class); - - job.setMapperClass(Map.class); - job.setReducerClass(Reduce.class); - - - job.setInputFormatClass(TextInputFormat.class); - job.setOutputFormatClass(TextOutputFormat.class); - - - - Path outputFilePath = new Path(args[1]); - - FileInputFormat.addInputPath(job, new Path(args[0])); - FileOutputFormat.setOutputPath(job, outputFilePath); - - FileSystem fs = FileSystem.newInstance(getConf()); - - if (fs.exists(outputFilePath)) { - fs.delete(outputFilePath, true); - } - - job.waitForCompletion(true); - - return 0; - } - - public static class Map extends Mapper<LongWritable, Text, Text, IntWritable> { - private final static IntWritable ONE = new IntWritable(1); - private Text word = new Text(); - String stopwords_file = "/home/cloudera/workspace/bpa/Assign2/stopwords/stopwords"; - String stopwords = new String(Files.readAllBytes(Paths.get(stopwords_file))); - - public Map() throws IOException{ - System.out.println(stopwords); - } - @Override - public void map(LongWritable key, Text value, Context context) - throws IOException, InterruptedException { - - for (String token: value.toString().replaceAll("[^A-Za-z0-9 ]", " ").split("\\s+")) { - if (!stopwords.contains(token)) { - word.set(token); - context.write(word, ONE); - } - } - } - } - - public static class Reduce extends Reducer<Text, IntWritable, Text, IntWritable> { - @Override - public void reduce(Text key, Iterable<IntWritable> values, Context context) - throws IOException, InterruptedException { - int sum = 0; - for (IntWritable val : values) { - sum += val.get(); - } - context.write(key, new IntWritable(sum)); - - } - } -} \ No newline at end of file -- GitLab