添加15章代码和测试数据

2026-02-11 06:15:22 +08:00 · 2017-04-08 01:08:05 +08:00
parent 2528ec734c
commit 1cc59bfc71
18 changed files with 1514 additions and 0 deletions
--- a/input/15.BigData_MapReduce/err.txt
+++ b/input/15.BigData_MapReduce/err.txt
@@ -0,0 +1,40 @@
+No handlers could be found for logger "mrjob.job"
+using configs in c:/Users/Peter\.mrjob.conf
+creating tmp directory /scratch/$USER\mrSVM.Peter.20111230.181815.061000
+reading from STDIN
+> 'c:\Python27\python.exe' mrSVM.py --step-num=0 --mapper '/scratch/$USER\mrSVM.Peter.20111230.181815.061000\input_part-00000'
+writing to /scratch/$USER\mrSVM.Peter.20111230.181815.061000\step-0-mapper_part-00000
+> 'c:\Python27\python.exe' mrSVM.py --step-num=0 --mapper '/scratch/$USER\mrSVM.Peter.20111230.181815.061000\input_part-00001'
+writing to /scratch/$USER\mrSVM.Peter.20111230.181815.061000\step-0-mapper_part-00001
+STDERR: No handlers could be found for logger "mrjob.job"
+STDERR: No handlers could be found for logger "mrjob.job"
+Counters from step 1:
+  (no counters found)
+writing to /scratch/$USER\mrSVM.Peter.20111230.181815.061000\step-0-mapper-sorted
+> sort '/scratch/$USER\mrSVM.Peter.20111230.181815.061000\step-0-mapper_part-00000' '/scratch/$USER\mrSVM.Peter.20111230.181815.061000\step-0-mapper_part-00001'
+Piping files into sort for Windows compatibility
+> sort
+> 'c:\Python27\python.exe' mrSVM.py --step-num=0 --reducer '/scratch/$USER\mrSVM.Peter.20111230.181815.061000\input_part-00000'
+writing to /scratch/$USER\mrSVM.Peter.20111230.181815.061000\step-0-reducer_part-00000
+STDERR: No handlers could be found for logger "mrjob.job"
+Counters from step 1:
+  (no counters found)
+> 'c:\Python27\python.exe' mrSVM.py --step-num=1 --mapper '/scratch/$USER\mrSVM.Peter.20111230.181815.061000\input_part-00000'
+writing to /scratch/$USER\mrSVM.Peter.20111230.181815.061000\step-1-mapper_part-00000
+> 'c:\Python27\python.exe' mrSVM.py --step-num=1 --mapper '/scratch/$USER\mrSVM.Peter.20111230.181815.061000\input_part-00001'
+writing to /scratch/$USER\mrSVM.Peter.20111230.181815.061000\step-1-mapper_part-00001
+STDERR: No handlers could be found for logger "mrjob.job"
+STDERR: No handlers could be found for logger "mrjob.job"
+Counters from step 2:
+  (no counters found)
+writing to /scratch/$USER\mrSVM.Peter.20111230.181815.061000\step-1-mapper-sorted
+Piping files into sort for Windows compatibility
+> sort
+> 'c:\Python27\python.exe' mrSVM.py --step-num=1 --reducer '/scratch/$USER\mrSVM.Peter.20111230.181815.061000\input_part-00000'
+writing to /scratch/$USER\mrSVM.Peter.20111230.181815.061000\step-1-reducer_part-00000
+STDERR: No handlers could be found for logger "mrjob.job"
+Counters from step 2:
+  (no counters found)
+Moving /scratch/$USER\mrSVM.Peter.20111230.181815.061000\step-1-reducer_part-00000 -> /scratch/$USER\mrSVM.Peter.20111230.181815.061000\output\part-00000
+Streaming final output from /scratch/$USER\mrSVM.Peter.20111230.181815.061000\output
+removing tmp directory /scratch/$USER\mrSVM.Peter.20111230.181815.061000
--- a/input/15.BigData_MapReduce/junk.txt
+++ b/input/15.BigData_MapReduce/junk.txt
@@ -0,0 +1,3 @@
+jj I am so sick of TV
+ss jar jar got a purse
+22 shit ass 
--- a/input/15.BigData_MapReduce/kickStart.txt
+++ b/input/15.BigData_MapReduce/kickStart.txt
@@ -0,0 +1,101 @@
+["w", [0.001, 0.001]]
+["x", 79]
+["x", 115]
+["x", 107]
+["x", 109]
+["x", 109]
+["x", 88]
+["x", 56]
+["x", 94]
+["x", 50]
+["x", 86]
+["x", 75]
+["x", 30]
+["x", 20]
+["x", 157]
+["x", 15]
+["x", 19]
+["x", 63]
+["x", 124]
+["x", 132]
+["x", 3]
+["x", 140]
+["x", 139]
+["x", 127]
+["x", 98]
+["x", 30]
+["x", 16]
+["x", 4]
+["x", 2]
+["x", 75]
+["x", 123]
+["x", 42]
+["x", 16]
+["x", 94]
+["x", 163]
+["x", 159]
+["x", 23]
+["x", 16]
+["x", 160]
+["x", 5]
+["x", 42]
+["x", 53]
+["x", 83]
+["x", 46]
+["x", 121]
+["x", 73]
+["x", 123]
+["x", 93]
+["x", 99]
+["x", 106]
+["x", 173]
+["x", 192]
+["x", 132]
+["x", 57]
+["x", 47]
+["x", 164]
+["x", 157]
+["x", 199]
+["x", 62]
+["x", 175]
+["x", 154]
+["x", 110]
+["x", 0]
+["x", 116]
+["x", 49]
+["x", 76]
+["x", 121]
+["x", 178]
+["x", 75]
+["x", 167]
+["x", 41]
+["x", 105]
+["x", 71]
+["x", 5]
+["x", 135]
+["x", 80]
+["x", 116]
+["x", 198]
+["x", 164]
+["x", 105]
+["x", 98]
+["x", 156]
+["x", 72]
+["x", 54]
+["x", 62]
+["x", 57]
+["x", 87]
+["x", 68]
+["x", 163]
+["x", 140]
+["x", 40]
+["x", 70]
+["x", 120]
+["x", 172]
+["x", 71]
+["x", 82]
+["x", 168]
+["x", 42]
+["x", 144]
+["x", 27]
+["x", 36]
--- a/input/15.BigData_MapReduce/myfile.txt
+++ b/input/15.BigData_MapReduce/myfile.txt
@@ -0,0 +1,200 @@
+0.365032	2.465645	-1.000000	
+-2.494175	-0.292380	-1.000000	
+-3.039364	-0.123108	-1.000000	
+1.348150	0.255696	1.000000	
+2.768494	1.234954	1.000000	
+1.232328	-0.601198	1.000000	
+4.404247	3.393022	1.000000	
+0.697004	-2.009448	1.000000	
+-3.373117	-0.713336	-1.000000	
+2.723211	0.775903	1.000000	
+2.901695	1.707367	1.000000	
+-1.829946	0.607276	-1.000000	
+1.472144	-0.388337	1.000000	
+-1.032174	1.591800	-1.000000	
+-2.419741	-0.226650	-1.000000	
+1.336037	2.564594	-1.000000	
+-1.503680	1.256279	-1.000000	
+4.375646	2.089091	1.000000	
+-2.618399	-0.145791	-1.000000	
+0.175550	2.171503	-1.000000	
+-1.813659	0.861575	-1.000000	
+1.365379	-2.079521	1.000000	
+1.132693	-1.134835	1.000000	
+-1.909842	-0.203375	-1.000000	
+2.083515	-0.123439	1.000000	
+-2.942829	-0.263256	-1.000000	
+-0.550709	2.932391	-1.000000	
+2.345072	-0.738737	1.000000	
+-2.812098	0.556459	-1.000000	
+-0.517398	0.162645	-1.000000	
+-2.462396	0.010699	-1.000000	
+2.560602	-0.591844	1.000000	
+-2.232060	-1.372427	-1.000000	
+-0.228876	-3.268298	1.000000	
+3.941297	2.489183	1.000000	
+-2.858850	-1.349790	-1.000000	
+2.421014	-0.355223	1.000000	
+-1.112512	1.194459	-1.000000	
+-2.596897	-1.137791	-1.000000	
+2.238589	1.900233	1.000000	
+2.180268	1.177119	1.000000	
+-2.674983	-0.522555	-1.000000	
+-1.070534	-0.269203	-1.000000	
+0.634596	-1.968924	1.000000	
+-3.056496	-2.411444	-1.000000	
+-3.125469	-2.560011	-1.000000	
+-2.015606	0.258282	-1.000000	
+-1.742318	0.888477	-1.000000	
+1.321158	-0.087550	1.000000	
+0.931512	-1.726051	1.000000	
+-0.215167	1.522793	-1.000000	
+2.346521	0.316568	1.000000	
+2.138992	1.315335	1.000000	
+-3.631578	-1.493405	-1.000000	
+-0.713435	1.015818	-1.000000	
+-2.963170	-0.128725	-1.000000	
+-0.911295	1.120257	-1.000000	
+1.823362	1.383358	1.000000	
+3.912515	1.761468	1.000000	
+-3.142532	-1.332066	-1.000000	
+4.106318	2.468945	1.000000	
+2.208287	-0.357459	1.000000	
+-3.223791	-0.832623	-1.000000	
+-2.285363	-0.520775	-1.000000	
+2.565906	-0.456137	1.000000	
+-0.979234	1.913094	-1.000000	
+-2.389694	-2.358041	-1.000000	
+-2.652054	-1.866190	-1.000000	
+0.683886	-1.883523	1.000000	
+1.154997	-1.465108	1.000000	
+3.348935	0.365574	1.000000	
+2.987531	0.346268	1.000000	
+1.700014	-0.555228	1.000000	
+1.980124	0.139488	1.000000	
+0.978690	-1.633039	1.000000	
+2.593800	0.862643	1.000000	
+-2.251246	-0.353172	-1.000000	
+1.557428	-1.383201	1.000000	
+-2.597244	-1.826710	-1.000000	
+-2.886051	-1.337213	-1.000000	
+1.325410	0.845017	1.000000	
+1.837022	-0.151031	1.000000	
+-3.667084	-2.656341	-1.000000	
+-1.096365	0.149693	-1.000000	
+-2.971056	-2.411501	-1.000000	
+-2.465852	-0.235159	-1.000000	
+-2.394111	0.351272	-1.000000	
+1.515098	-0.965912	1.000000	
+2.158202	-0.966015	1.000000	
+-1.713482	-0.251601	-1.000000	
+-2.913806	-2.850934	-1.000000	
+1.705200	-0.789277	1.000000	
+3.421766	0.864792	1.000000	
+-1.762714	1.500557	-1.000000	
+-2.955547	0.049390	-1.000000	
+2.717396	1.466253	1.000000	
+-2.359607	-1.360212	-1.000000	
+2.573551	0.246011	1.000000	
+-2.515645	-1.120265	-1.000000	
+0.678309	-3.889064	1.000000	
+1.629286	-0.451862	1.000000	
+-1.484039	-0.211054	-1.000000	
+-3.791016	-0.954143	-1.000000	
+-2.843098	-0.847371	-1.000000	
+-2.170293	1.091531	-1.000000	
+-2.422544	-2.382615	-1.000000	
+-3.703473	-3.821757	-1.000000	
+-2.392575	2.190457	-1.000000	
+-1.311822	-1.069374	-1.000000	
+2.844847	1.022544	1.000000	
+1.123290	-0.470348	1.000000	
+0.459137	-2.125968	1.000000	
+4.034205	1.542917	1.000000	
+-0.934692	0.334676	-1.000000	
+-0.531720	2.098752	-1.000000	
+1.579150	-1.497762	1.000000	
+-3.052029	0.297103	-1.000000	
+0.259368	-0.931559	1.000000	
+2.223190	0.019637	1.000000	
+1.695683	-0.067089	1.000000	
+3.783554	2.380405	1.000000	
+-0.742719	1.599089	-1.000000	
+-3.034314	-1.068352	-1.000000	
+-2.603808	-0.125287	-1.000000	
+-3.444958	-3.611816	-1.000000	
+2.045444	-0.443405	1.000000	
+3.128574	0.859356	1.000000	
+0.690041	-0.852001	1.000000	
+2.055697	0.696273	1.000000	
+-2.772761	-1.353757	-1.000000	
+-2.989774	-1.698669	-1.000000	
+-2.376270	-1.554052	-1.000000	
+2.696921	1.840741	1.000000	
+1.808514	0.574293	1.000000	
+0.758408	0.621123	-1.000000	
+0.087100	-2.424081	1.000000	
+-1.965351	0.714902	-1.000000	
+-2.455455	-0.864560	-1.000000	
+2.242510	2.271935	1.000000	
+3.768713	1.966209	1.000000	
+1.781191	-1.035869	1.000000	
+3.428376	4.010583	1.000000	
+1.126828	0.854183	1.000000	
+-3.438612	-2.229961	-1.000000	
+-1.677236	1.302989	-1.000000	
+-0.457661	2.454553	-1.000000	
+-1.253217	0.094550	-1.000000	
+3.631693	-0.584668	1.000000	
+1.325739	-1.474299	1.000000	
+-2.468865	-0.954717	-1.000000	
+0.373049	-0.744924	1.000000	
+-2.724934	-1.931014	-1.000000	
+2.315489	1.487273	1.000000	
+-1.004495	0.396042	-1.000000	
+-2.633016	-2.421408	-1.000000	
+0.892135	-3.181581	1.000000	
+-2.142382	-1.194070	-1.000000	
+1.429072	4.755911	-1.000000	
+-1.470911	-0.587141	-1.000000	
+2.857367	0.926472	1.000000	
+2.209276	-0.856140	1.000000	
+0.636235	-1.853421	1.000000	
+-1.609996	1.717916	-1.000000	
+1.825889	-0.367680	1.000000	
+-1.300348	0.535824	-1.000000	
+1.234706	1.175943	1.000000	
+-2.958675	-2.503623	-1.000000	
+-3.104957	-0.401067	-1.000000	
+-3.257189	0.883429	-1.000000	
+1.748296	-2.783532	1.000000	
+-2.858730	-1.187591	-1.000000	
+2.776790	1.009201	1.000000	
+-3.020057	-1.590170	-1.000000	
+-2.758262	-0.589067	-1.000000	
+2.254778	-0.419287	1.000000	
+3.959366	2.400563	1.000000	
+0.042104	1.919803	-1.000000	
+-2.036118	0.639606	-1.000000	
+0.879784	-0.726036	1.000000	
+-2.004450	-0.741610	-1.000000	
+1.695901	-1.279977	1.000000	
+1.083409	-1.833836	1.000000	
+-0.910787	-0.004560	-1.000000	
+1.781328	-1.148702	1.000000	
+-1.977490	0.922950	-1.000000	
+-3.231551	-2.366104	-1.000000	
+-1.613525	0.913540	-1.000000	
+3.775281	3.594941	1.000000	
+-2.147825	2.515202	-1.000000	
+2.357556	-0.453303	1.000000	
+2.101682	1.621048	1.000000	
+2.583247	1.999725	1.000000	
+-0.701349	3.523552	-1.000000	
+-2.996146	-1.187950	-1.000000	
+2.993353	1.271228	1.000000	
+-1.773598	1.032358	-1.000000	
+-1.806425	0.713270	-1.000000	
+4.134091	2.962575	1.000000	
+-0.379995	0.272405	-1.000000	
+2.601370	1.032435	1.000000	
--- a/input/15.BigData_MapReduce/myout.txt
+++ b/input/15.BigData_MapReduce/myout.txt
@@ -0,0 +1,303 @@
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 79]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 115]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 107]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 109]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 109]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 88]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 56]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 94]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 50]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 86]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 75]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 30]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 20]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 157]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 15]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 19]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 63]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 124]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 132]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 3]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 140]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 139]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 127]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 98]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 30]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 16]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 4]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 2]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 75]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 123]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 42]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 16]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 94]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 163]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 159]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 23]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 16]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 160]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 5]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 42]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 53]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 83]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 46]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 121]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 73]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 123]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 93]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 99]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 106]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 173]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 192]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 132]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 57]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 47]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 164]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 157]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 199]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 62]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 175]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 154]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 110]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 0]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 116]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 49]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 76]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 121]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 178]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 75]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 167]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 41]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 105]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 71]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 5]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 135]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 80]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 116]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 198]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 164]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 105]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 98]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 156]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 72]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 54]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 62]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 57]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 87]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 68]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 163]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 140]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 40]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 70]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 120]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 172]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 71]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 82]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 168]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 42]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 144]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 27]
+shape(self.w):  (2,)
+shape(X[index,:]) (1, 2)
+1	["u", 36]
+in the map_fin
+1	["w", [0.001, 0.001]]
+1	["t", 1]
--- a/input/15.BigData_MapReduce/svmDat2.txt
+++ b/input/15.BigData_MapReduce/svmDat2.txt
--- a/input/15.BigData_MapReduce/svmDat26
+++ b/input/15.BigData_MapReduce/svmDat26
--- a/input/15.BigData_MapReduce/svmDat27
+++ b/input/15.BigData_MapReduce/svmDat27
--- a/input/15.BigData_MapReduce/svmData.txt
+++ b/input/15.BigData_MapReduce/svmData.txt
--- a/input/15.BigData_MapReduce/testSet.txt
+++ b/input/15.BigData_MapReduce/testSet.txt
@@ -0,0 +1,200 @@
+0.365032	2.465645	-1
+-2.494175	-0.292380	-1
+-3.039364	-0.123108	-1
+1.348150	0.255696	1
+2.768494	1.234954	1
+1.232328	-0.601198	1
+4.404247	3.393022	1
+0.697004	-2.009448	1
+-3.373117	-0.713336	-1
+2.723211	0.775903	1
+2.901695	1.707367	1
+-1.829946	0.607276	-1
+1.472144	-0.388337	1
+-1.032174	1.591800	-1
+-2.419741	-0.226650	-1
+1.336037	2.564594	-1
+-1.503680	1.256279	-1
+4.375646	2.089091	1
+-2.618399	-0.145791	-1
+0.175550	2.171503	-1
+-1.813659	0.861575	-1
+1.365379	-2.079521	1
+1.132693	-1.134835	1
+-1.909842	-0.203375	-1
+2.083515	-0.123439	1
+-2.942829	-0.263256	-1
+-0.550709	2.932391	-1
+2.345072	-0.738737	1
+-2.812098	0.556459	-1
+-0.517398	0.162645	-1
+-2.462396	0.010699	-1
+2.560602	-0.591844	1
+-2.232060	-1.372427	-1
+-0.228876	-3.268298	1
+3.941297	2.489183	1
+-2.858850	-1.349790	-1
+2.421014	-0.355223	1
+-1.112512	1.194459	-1
+-2.596897	-1.137791	-1
+2.238589	1.900233	1
+2.180268	1.177119	1
+-2.674983	-0.522555	-1
+-1.070534	-0.269203	-1
+0.634596	-1.968924	1
+-3.056496	-2.411444	-1
+-3.125469	-2.560011	-1
+-2.015606	0.258282	-1
+-1.742318	0.888477	-1
+1.321158	-0.087550	1
+0.931512	-1.726051	1
+-0.215167	1.522793	-1
+2.346521	0.316568	1
+2.138992	1.315335	1
+-3.631578	-1.493405	-1
+-0.713435	1.015818	-1
+-2.963170	-0.128725	-1
+-0.911295	1.120257	-1
+1.823362	1.383358	1
+3.912515	1.761468	1
+-3.142532	-1.332066	-1
+4.106318	2.468945	1
+2.208287	-0.357459	1
+-3.223791	-0.832623	-1
+-2.285363	-0.520775	-1
+2.565906	-0.456137	1
+-0.979234	1.913094	-1
+-2.389694	-2.358041	-1
+-2.652054	-1.866190	-1
+0.683886	-1.883523	1
+1.154997	-1.465108	1
+3.348935	0.365574	1
+2.987531	0.346268	1
+1.700014	-0.555228	1
+1.980124	0.139488	1
+0.978690	-1.633039	1
+2.593800	0.862643	1
+-2.251246	-0.353172	-1
+1.557428	-1.383201	1
+-2.597244	-1.826710	-1
+-2.886051	-1.337213	-1
+1.325410	0.845017	1
+1.837022	-0.151031	1
+-3.667084	-2.656341	-1
+-1.096365	0.149693	-1
+-2.971056	-2.411501	-1
+-2.465852	-0.235159	-1
+-2.394111	0.351272	-1
+1.515098	-0.965912	1
+2.158202	-0.966015	1
+-1.713482	-0.251601	-1
+-2.913806	-2.850934	-1
+1.705200	-0.789277	1
+3.421766	0.864792	1
+-1.762714	1.500557	-1
+-2.955547	0.049390	-1
+2.717396	1.466253	1
+-2.359607	-1.360212	-1
+2.573551	0.246011	1
+-2.515645	-1.120265	-1
+0.678309	-3.889064	1
+1.629286	-0.451862	1
+-1.484039	-0.211054	-1
+-3.791016	-0.954143	-1
+-2.843098	-0.847371	-1
+-2.170293	1.091531	-1
+-2.422544	-2.382615	-1
+-3.703473	-3.821757	-1
+-2.392575	2.190457	-1
+-1.311822	-1.069374	-1
+2.844847	1.022544	1
+1.123290	-0.470348	1
+0.459137	-2.125968	1
+4.034205	1.542917	1
+-0.934692	0.334676	-1
+-0.531720	2.098752	-1
+1.579150	-1.497762	1
+-3.052029	0.297103	-1
+0.259368	-0.931559	1
+2.223190	0.019637	1
+1.695683	-0.067089	1
+3.783554	2.380405	1
+-0.742719	1.599089	-1
+-3.034314	-1.068352	-1
+-2.603808	-0.125287	-1
+-3.444958	-3.611816	-1
+2.045444	-0.443405	1
+3.128574	0.859356	1
+0.690041	-0.852001	1
+2.055697	0.696273	1
+-2.772761	-1.353757	-1
+-2.989774	-1.698669	-1
+-2.376270	-1.554052	-1
+2.696921	1.840741	1
+1.808514	0.574293	1
+0.758408	0.621123	-1
+0.087100	-2.424081	1
+-1.965351	0.714902	-1
+-2.455455	-0.864560	-1
+2.242510	2.271935	1
+3.768713	1.966209	1
+1.781191	-1.035869	1
+3.428376	4.010583	1
+1.126828	0.854183	1
+-3.438612	-2.229961	-1
+-1.677236	1.302989	-1
+-0.457661	2.454553	-1
+-1.253217	0.094550	-1
+3.631693	-0.584668	1
+1.325739	-1.474299	1
+-2.468865	-0.954717	-1
+0.373049	-0.744924	1
+-2.724934	-1.931014	-1
+2.315489	1.487273	1
+-1.004495	0.396042	-1
+-2.633016	-2.421408	-1
+0.892135	-3.181581	1
+-2.142382	-1.194070	-1
+1.429072	4.755911	-1
+-1.470911	-0.587141	-1
+2.857367	0.926472	1
+2.209276	-0.856140	1
+0.636235	-1.853421	1
+-1.609996	1.717916	-1
+1.825889	-0.367680	1
+-1.300348	0.535824	-1
+1.234706	1.175943	1
+-2.958675	-2.503623	-1
+-3.104957	-0.401067	-1
+-3.257189	0.883429	-1
+1.748296	-2.783532	1
+-2.858730	-1.187591	-1
+2.776790	1.009201	1
+-3.020057	-1.590170	-1
+-2.758262	-0.589067	-1
+2.254778	-0.419287	1
+3.959366	2.400563	1
+0.042104	1.919803	-1
+-2.036118	0.639606	-1
+0.879784	-0.726036	1
+-2.004450	-0.741610	-1
+1.695901	-1.279977	1
+1.083409	-1.833836	1
+-0.910787	-0.004560	-1
+1.781328	-1.148702	1
+-1.977490	0.922950	-1
+-3.231551	-2.366104	-1
+-1.613525	0.913540	-1
+3.775281	3.594941	1
+-2.147825	2.515202	-1
+2.357556	-0.453303	1
+2.101682	1.621048	1
+2.583247	1.999725	1
+-0.701349	3.523552	-1
+-2.996146	-1.187950	-1
+2.993353	1.271228	1
+-1.773598	1.032358	-1
+-1.806425	0.713270	-1
+4.134091	2.962575	1
+-0.379995	0.272405	-1
+2.601370	1.032435	1
--- a/input/15.BigData_MapReduce/testSet200.txt
+++ b/input/15.BigData_MapReduce/testSet200.txt
@@ -0,0 +1,200 @@
+2.566588	-0.566564	1
+3.813758	2.148214	1
+3.803649	2.297096	1
+2.996947	-1.156863	1
+2.018915	-0.905604	1
+2.722914	2.050793	1
+2.992540	0.604431	1
+1.973198	-0.416027	1
+4.231757	2.197621	1
+-3.423482	-1.666829	-1
+3.017583	-0.852549	1
+2.378933	-0.068925	1
+2.827171	0.112122	1
+3.099968	-0.314056	1
+-1.237312	2.041868	-1
+5.192917	2.756125	1
+-2.572959	-1.407749	-1
+-1.972541	0.113997	-1
+3.410411	-1.471934	1
+3.635269	-1.067406	1
+-5.139639	-2.996639	-1
+-1.880483	-0.648054	-1
+-2.168873	0.526882	-1
+5.642283	1.221138	1
+4.229408	1.263818	1
+-2.563922	-0.132134	-1
+-3.001167	-0.958829	-1
+-5.180670	-0.967162	-1
+3.264381	0.843975	1
+2.925061	0.211085	1
+3.208235	0.049203	1
+2.109814	1.020155	1
+4.043111	0.038868	1
+-2.993809	-0.153942	-1
+-4.343854	0.002387	-1
+2.770473	0.027766	1
+-2.071658	1.145849	-1
+-3.521452	0.245865	-1
+-3.271004	0.002030	-1
+-1.343470	4.378228	-1
+2.276676	0.155982	1
+-4.068011	-0.647258	-1
+-1.850638	2.210614	-1
+-4.639977	-1.031178	-1
+-4.684251	-3.087190	-1
+2.940128	0.940271	1
+1.863125	-0.838375	1
+2.568502	0.070915	1
+2.899899	-1.277806	1
+3.352340	-0.713969	1
+-4.317466	0.852795	-1
+3.201230	0.976139	1
+3.822834	0.069645	1
+2.692972	-0.176728	1
+-1.146605	2.081193	-1
+2.998234	1.141442	1
+2.312164	-1.269429	1
+3.396265	0.862029	1
+3.274000	-0.696190	1
+-2.595839	-0.263462	-1
+-1.812287	1.673161	-1
+0.969156	-1.931523	1
+-2.221344	0.203244	-1
+0.501463	-2.583951	1
+-3.150028	1.235862	-1
+-4.268858	0.071051	-1
+-3.349838	0.678968	-1
+-3.126228	-0.393941	-1
+-2.573798	0.267638	-1
+4.109014	1.710147	1
+-2.843759	0.484696	-1
+3.707519	-0.370216	1
+-4.195957	-0.277812	-1
+2.675081	-0.573838	1
+-3.125774	0.081851	-1
+1.971943	-0.468073	1
+3.407029	0.515338	1
+-2.104839	2.804795	-1
+0.874914	-1.404919	1
+3.112299	1.175667	1
+-2.829713	0.662682	-1
+3.568705	4.168130	1
+4.616527	2.518176	1
+1.795161	-1.250346	1
+4.008731	2.757045	1
+-4.508237	-3.536722	-1
+-2.456205	1.371719	-1
+2.002132	-1.389533	1
+2.837388	0.193087	1
+3.332083	-1.083519	1
+3.116535	-0.303645	1
+3.586091	1.202891	1
+4.075176	-1.392830	1
+-2.686817	-0.295541	-1
+-4.347040	-0.238252	-1
+-2.216701	0.192294	-1
+-3.698974	-1.535749	-1
+-2.550443	-1.304260	-1
+-3.184541	-0.694387	-1
+3.541460	1.293369	1
+2.861718	-1.539216	1
+-3.297277	0.120904	-1
+-2.877627	2.168402	-1
+1.971946	-1.934373	1
+1.691137	-0.128856	1
+-2.894363	-1.081141	-1
+3.737381	-0.295484	1
+-2.915021	0.450760	-1
+3.166039	-0.984355	1
+-2.232850	2.234037	-1
+-2.339145	-0.623513	-1
+-2.333595	0.962038	-1
+3.786374	0.586053	1
+1.782042	-2.219559	1
+3.739798	0.344508	1
+2.145958	-1.419122	1
+3.664095	-0.196319	1
+-3.043546	-0.507600	-1
+-0.928765	2.070607	-1
+-3.124872	1.695632	-1
+-3.020885	0.577177	-1
+2.590275	0.779679	1
+-2.523241	-0.919172	-1
+4.082839	0.662608	1
+-4.190252	-3.116115	-1
+3.360103	1.046061	1
+-2.793587	0.366979	-1
+3.400676	1.675726	1
+-2.612133	-1.848598	-1
+2.564818	-1.149425	1
+-4.625269	-1.246603	-1
+-2.158414	0.905748	-1
+3.190204	1.617466	1
+5.670475	2.859713	1
+-3.140959	-1.565962	-1
+3.275399	-0.385732	1
+-2.882785	0.764198	-1
+2.444832	-1.744333	1
+3.494718	-0.185378	1
+2.971542	0.185532	1
+3.683797	-0.827936	1
+-2.073568	2.713617	-1
+5.229803	2.581358	1
+-3.097377	1.369309	-1
+-3.340725	1.226798	-1
+0.804569	-1.763511	1
+2.002499	-1.253770	1
+-4.441054	-1.504076	-1
+4.840372	1.159494	1
+-2.074033	1.334349	-1
+2.739732	-1.093691	1
+1.093710	-1.804169	1
+-1.815973	1.270033	-1
+-1.535024	1.307626	-1
+-2.609744	-1.331401	-1
+2.213643	-0.386181	1
+-0.193909	-3.182715	1
+3.981292	1.726516	1
+-2.199386	0.939470	-1
+-4.044809	-0.093401	-1
+-3.633603	-0.601417	-1
+4.289107	-0.685719	1
+-3.743011	-2.264532	-1
+-4.045259	-0.425302	-1
+1.623011	-1.831822	1
+3.056557	0.096257	1
+1.922710	-1.220852	1
+1.809512	-1.326957	1
+1.835936	-0.825311	1
+-3.798285	-0.592936	-1
+-2.425223	1.389336	-1
+2.377227	-1.696811	1
+1.478822	-2.004391	1
+3.126443	0.449490	1
+-4.576405	-1.053316	-1
+-3.061546	1.008689	-1
+-2.861879	0.191511	-1
+-2.264559	1.292387	-1
+3.804691	-0.408870	1
+-5.390695	-4.685284	-1
+-4.015686	-1.698655	-1
+-1.811922	2.826242	-1
+-0.977725	2.446878	-1
+-3.722234	-2.148840	-1
+-2.336758	-0.426078	-1
+2.881292	0.538803	1
+-2.603340	1.172457	-1
+3.420185	1.261315	1
+3.122753	-1.022180	1
+-2.160948	-0.760109	-1
+3.147356	-0.138635	1
+3.321314	0.799222	1
+3.358796	1.791473	1
+2.645603	0.644191	1
+1.140846	-1.296675	1
+2.645462	0.289605	1
+2.876090	1.010588	1
+2.514470	-1.731317	1
+2.588991	0.687835	1
+-2.404388	0.563167	-1
--- a/src/python/15.BigData_MapReduce/mrMean.py
+++ b/src/python/15.BigData_MapReduce/mrMean.py
@@ -0,0 +1,43 @@
+'''
+Created on 2017-04-07
+
+@author: Peter/ApacheCN-xy
+'''
+from mrjob.job import MRJob
+
+class MRmean(MRJob):
+    def __init__(self, *args, **kwargs): # 对数据初始化
+        super(MRmean, self).__init__(*args, **kwargs)
+        self.inCount = 0
+        self.inSum = 0
+        self.inSqSum = 0
+    
+    def map(self, key, val): # 需要 2 个参数，求数据的和与平方和
+        if False: yield
+        inVal = float(val)
+        self.inCount += 1
+        self.inSum += inVal
+        self.inSqSum += inVal*inVal
+        
+    def map_final(self): # 计算数据的平均值，平方的均值，并返回
+        mn = self.inSum/self.inCount
+        mnSq = self.inSqSum/self.inCount
+        yield (1, [self.inCount, mn, mnSq])
+
+    def reduce(self, key, packedValues): # 
+        cumVal=0.0; cumSumSq=0.0; cumN=0.0
+        for valArr in packedValues: # 从输入流中获取值
+            nj = float(valArr[0])
+            cumN += nj
+            cumVal += nj*float(valArr[1])
+            cumSumSq += nj*float(valArr[2])
+        mean = cumVal/cumN
+        var = (cumSumSq - 2*mean*cumVal + cumN*mean*mean)/cumN
+        yield (mean, var) # 发出平均值和方差
+        
+    def steps(self):
+        return ([self.mr(mapper=self.map, mapper_final=self.map_final,\
+                          reducer=self.reduce,)])
+
+if __name__ == '__main__':
+    MRmean.run()
--- a/src/python/15.BigData_MapReduce/mrSVM.py
+++ b/src/python/15.BigData_MapReduce/mrSVM.py
@@ -0,0 +1,78 @@
+'''
+Created on 2017-04-07
+MapReduce version of Pegasos SVM
+Using mrjob to automate job flow
+@author: Peter/ApacheCN-xy
+'''
+from mrjob.job import MRJob
+
+import pickle
+from numpy import *
+
+class MRsvm(MRJob):
+    DEFAULT_INPUT_PROTOCOL = 'json_value'
+    
+    def __init__(self, *args, **kwargs):
+        super(MRsvm, self).__init__(*args, **kwargs)
+        self.data = pickle.load(open('C:\Users\Peter\machinelearninginaction\Ch15\svmDat27'))
+        self.w = 0
+        self.eta = 0.69
+        self.dataList = []
+        self.k = self.options.batchsize
+        self.numMappers = 1
+        self.t = 1  #iteration number
+                                                 
+    def configure_options(self):
+        super(MRsvm, self).configure_options()
+        self.add_passthrough_option(
+            '--iterations', dest='iterations', default=2, type='int',
+            help='T: number of iterations to run')
+        self.add_passthrough_option(
+            '--batchsize', dest='batchsize', default=100, type='int',
+            help='k: number of data points in a batch')
+    
+    def map(self, mapperId, inVals): # 需要 2 个参数
+        #input: nodeId, ('w', w-vector) OR nodeId, ('x', int)
+        if False: yield
+        if inVals[0]=='w':                  # 积累 w向量
+            self.w = inVals[1]
+        elif inVals[0]=='x':
+            self.dataList.append(inVals[1])# 累积数据点计算
+        elif inVals[0]=='t': self.t = inVals[1] 
+        else: self.eta=inVals # 这用于 debug， eta未在map中使用
+        
+    def map_fin(self):
+        labels = self.data[:,-1]; X=self.data[:,0:-1]# 将数据重新形成 X 和 Y
+        if self.w == 0: self.w = [0.001]*shape(X)[1] # 在第一次迭代时，初始化 w
+        for index in self.dataList:
+            p = mat(self.w)*X[index,:].T #calc p=w*dataSet[key].T 
+            if labels[index]*p < 1.0:
+                yield (1, ['u', index])# 确保一切数据包含相同的key                           
+        yield (1, ['w', self.w])       # 它们将在同一个 reducer
+        yield (1, ['t', self.t])
+
+    def reduce(self, _, packedVals):
+        for valArr in packedVals: # 从流输入获取值
+            if valArr[0]=='u':  self.dataList.append(valArr[1])
+            elif valArr[0]=='w': self.w = valArr[1]
+            elif valArr[0]=='t':  self.t = valArr[1] 
+        labels = self.data[:,-1]; X=self.data[:,0:-1]
+        wMat = mat(self.w);   wDelta = mat(zeros(len(self.w)))
+        for index in self.dataList:
+            wDelta += float(labels[index])*X[index,:] #wDelta += label*dataSet
+        eta = 1.0/(2.0*self.t)       #calc new: eta
+        #calc new: w = (1.0 - 1/t)*w + (eta/k)*wDelta
+        wMat = (1.0 - 1.0/self.t)*wMat + (eta/self.k)*wDelta
+        for mapperNum in range(1,self.numMappers+1):
+            yield (mapperNum, ['w', wMat.tolist()[0] ]) #发出 w
+            if self.t < self.options.iterations:
+                yield (mapperNum, ['t', self.t+1])# 增量 T
+                for j in range(self.k/self.numMappers):#emit random ints for mappers iid
+                    yield (mapperNum, ['x', random.randint(shape(self.data)[0]) ])
+        
+    def steps(self):
+        return ([self.mr(mapper=self.map, reducer=self.reduce, 
+                         mapper_final=self.map_fin)]*self.options.iterations)
+
+if __name__ == '__main__':
+    MRsvm.run()
--- a/src/python/15.BigData_MapReduce/mrSVMkickStart.py
+++ b/src/python/15.BigData_MapReduce/mrSVMkickStart.py
@@ -0,0 +1,13 @@
+'''
+Created on Feb 27, 2011
+
+@author: Peter
+'''
+from mrjob.protocol import JSONProtocol
+from numpy import *
+
+fw=open('kickStart2.txt', 'w')
+for i in [1]:
+    for j in range(100):
+        fw.write('["x", %d]\n' % random.randint(200))
+fw.close()
--- a/src/python/15.BigData_MapReduce/pegasos.py
+++ b/src/python/15.BigData_MapReduce/pegasos.py
@@ -0,0 +1,77 @@
+'''
+Created on 2017-04-07
+Sequential Pegasos 
+the input T is k*T in Batch Pegasos
+@author: Peter/ApacheCN-xy
+'''
+
+from numpy import *
+
+def loadDataSet(fileName):
+    dataMat = []; labelMat = []
+    fr = open(fileName)
+    for line in fr.readlines():
+        lineArr = line.strip().split('\t')
+        #dataMat.append([float(lineArr[0]), float(lineArr[1]), float(lineArr[2])])
+        dataMat.append([float(lineArr[0]), float(lineArr[1])])
+        labelMat.append(float(lineArr[2]))
+    return dataMat,labelMat
+
+def seqPegasos(dataSet, labels, lam, T):
+    m,n = shape(dataSet); w = zeros(n)
+    for t in range(1, T+1):
+        i = random.randint(m)
+        eta = 1.0/(lam*t)
+        p = predict(w, dataSet[i,:])
+        if labels[i]*p < 1:
+            w = (1.0 - 1/t)*w + eta*labels[i]*dataSet[i,:]
+        else:
+            w = (1.0 - 1/t)*w
+        print w
+    return w
+        
+def predict(w, x):
+    return w*x.T
+
+def batchPegasos(dataSet, labels, lam, T, k):
+    m,n = shape(dataSet); w = zeros(n); 
+    dataIndex = range(m)
+    for t in range(1, T+1):
+        wDelta = mat(zeros(n)) # 重置 wDelta
+        eta = 1.0/(lam*t)
+        random.shuffle(dataIndex)
+        for j in range(k):# 全部的训练集
+            i = dataIndex[j]
+            p = predict(w, dataSet[i,:])        # mapper 代码
+            if labels[i]*p < 1:                 # mapper 代码
+                wDelta += labels[i]*dataSet[i,:].A # 累积变化  
+        w = (1.0 - 1/t)*w + (eta/k)*wDelta       # 在每个 T上应用更改
+    return w
+
+datArr,labelList = loadDataSet('testSet.txt')
+datMat = mat(datArr)
+#finalWs = seqPegasos(datMat, labelList, 2, 5000)
+finalWs = batchPegasos(datMat, labelList, 2, 50, 100)
+print finalWs
+
+import matplotlib
+import matplotlib.pyplot as plt
+fig = plt.figure()
+ax = fig.add_subplot(111)
+x1=[]; y1=[]; xm1=[]; ym1=[]
+for i in range(len(labelList)):
+    if labelList[i] == 1.0:
+        x1.append(datMat[i,0]); y1.append(datMat[i,1])
+    else:
+        xm1.append(datMat[i,0]); ym1.append(datMat[i,1])
+ax.scatter(x1, y1, marker='s', s=90)
+ax.scatter(xm1, ym1, marker='o', s=50, c='red')
+x = arange(-6.0, 8.0, 0.1)
+y = (-finalWs[0,0]*x - 0)/finalWs[0,1]
+#y2 = (0.43799*x)/0.12316
+y2 = (0.498442*x)/0.092387 #2 iterations
+ax.plot(x,y)
+ax.plot(x,y2,'g-.')
+ax.axis([-6,8,-4,5])
+ax.legend(('50 Iterations', '2 Iterations') )
+plt.show()
--- a/src/python/15.BigData_MapReduce/proximalSVM.py
+++ b/src/python/15.BigData_MapReduce/proximalSVM.py
@@ -0,0 +1,52 @@
+'''
+Created on Feb 25, 2011
+
+@author: Peter
+'''
+import numpy
+
+def map(key, value):
+   # input key= class for one training example, e.g. "-1.0"
+   classes = [float(item) for item in key.split(",")]   # e.g. [-1.0]
+   D = numpy.diag(classes)
+ 
+   # input value = feature vector for one training example, e.g. "3.0, 7.0, 2.0"
+   featurematrix = [float(item) for item in value.split(",")]
+   A = numpy.matrix(featurematrix)
+ 
+   # create matrix E and vector e
+   e = numpy.matrix(numpy.ones(len(A)).reshape(len(A),1))
+   E = numpy.matrix(numpy.append(A,-e,axis=1)) 
+ 
+   # create a tuple with the values to be used by reducer
+   # and encode it with base64 to avoid potential trouble with '\t' and '\n' used
+   # as default separators in Hadoop Streaming
+   producedvalue = base64.b64encode(pickle.dumps( (E.T*E, E.T*D*e) )    
+ 
+   # note: a single constant key "producedkey" sends to only one reducer
+   # somewhat "atypical" due to low degree of parallism on reducer side
+   print "producedkey\t%s" % (producedvalue)
+   
+def reduce(key, values, mu=0.1):
+  sumETE = None
+  sumETDe = None
+ 
+  # key isn't used, so ignoring it with _ (underscore).
+  for _, value in values:
+    # unpickle values
+    ETE, ETDe = pickle.loads(base64.b64decode(value))
+    if sumETE == None:
+      # create the I/mu with correct dimensions
+      sumETE = numpy.matrix(numpy.eye(ETE.shape[1])/mu)
+    sumETE += ETE
+ 
+    if sumETDe == None:
+      # create sumETDe with correct dimensions
+      sumETDe = ETDe
+    else:
+      sumETDe += ETDe
+ 
+    # note: omega = result[:-1] and gamma = result[-1]
+    # but printing entire vector as output
+    result = sumETE.I*sumETDe
+    print "%s\t%s" % (key, str(result.tolist()))
--- a/src/python/15.BigData_MapReduce/py27dbg.py
+++ b/src/python/15.BigData_MapReduce/py27dbg.py
@@ -0,0 +1,25 @@
+'''
+Created on Feb 27, 2011
+MapReduce version of Pegasos SVM
+Using mrjob to automate job flow
+@author: Peter
+'''
+from mrjob.job import MRJob
+
+import pickle
+from numpy import *
+
+class MRsvm(MRJob):
+                                                 
+    def map(self, mapperId, inVals): #needs exactly 2 arguments
+        if False: yield
+        yield (1, 22)
+
+    def reduce(self, _, packedVals):
+        yield "fuck ass" 
+        
+    def steps(self):
+        return ([self.mr(mapper=self.map, reducer=self.reduce)])
+
+if __name__ == '__main__':
+    MRsvm.run()
--- a/src/python/15.BigData_MapReduce/wc.py
+++ b/src/python/15.BigData_MapReduce/wc.py
@@ -0,0 +1,31 @@
+from mrjob.job import MRJob
+import json
+
+
+class MRWordCountUtility(MRJob):
+
+    def __init__(self, *args, **kwargs):
+        super(MRWordCountUtility, self).__init__(*args, **kwargs)
+        self.chars = 0
+        self.words = 0
+        self.lines = 0
+
+    def mapper(self, _, line):
+        if False:
+            yield  # I'm a generator!
+
+        self.chars += len(line) + 1  # +1 for newline
+        self.words += sum(1 for word in line.split() if word.strip())
+        self.lines += 1
+
+    def mapper_final(self):
+        yield('chars', self.chars)
+        yield('words', self.words)
+        yield('lines', self.lines)
+
+    def reducer(self, key, values):
+        yield(key, sum(values))
+
+
+if __name__ == '__main__':
+    MRWordCountUtility.run()