更新15.mapreduce的使用注解

src/python/15.BigData_MapReduce/mrMean.py

@@ -1,3 +1,6 @@
+#!/usr/bin/python
+# coding:utf8
+
 '''
 Created on 2017-04-07
 
@@ -5,26 +8,27 @@ Created on 2017-04-07
 '''
 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): # 
+    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])
@@ -34,10 +38,10 @@ class MRmean(MRJob):
         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,)])
+        return ([self.mr(mapper=self.map, mapper_final=self.map_final, reducer=self.reduce,)])
+
 
 if __name__ == '__main__':
-    MRmean.run()
+    MRmean.run()

src/python/15.BigData_MapReduce/mrMeanMapper.py

@@ -1,3 +1,5 @@
+#!/usr/bin/python
+# coding:utf8
 '''
 Created on 2017-04-06
 Machine Learning in Action Chapter 18
@@ -30,4 +32,4 @@ sqInput = power(input,2)				# 将矩阵的数据分别求 平方，即 2次方
 
 # 输出 数据的个数，n个数据的均值，n个数据平方之后的均值
 print ("%d\t%f\t%f" % (numInputs, mean(input), mean(sqInput))) #计算均值
-print ("report: still alive", file=sys.stderr)
+print >> sys.stderr, "report: still alive"

src/python/15.BigData_MapReduce/mrMeanReducer.py

@@ -1,3 +1,6 @@
+#!/usr/bin/python
+# coding:utf8
+
 '''
 Created on 2017-04-06
 Machine Learning in Action Chapter 18
@@ -7,9 +10,9 @@ Map Reduce Job for Hadoop Streaming
 
 
 '''
-	mapper 接受原始的输入并产生中间值传递给 reducer。
-	很多的mapper是并行执行的，所以需要将这些mapper的输出合并成一个值。
-	即：将中间的 key/value 对进行组合。
+    mapper 接受原始的输入并产生中间值传递给 reducer。
+    很多的mapper是并行执行的，所以需要将这些mapper的输出合并成一个值。
+    即：将中间的 key/value 对进行组合。
 '''
 import sys
 from numpy import mat, mean, power
@@ -40,4 +43,4 @@ meanSq = cumSumSq/cumN
 
 #输出 数据总量，均值，平方的均值（方差）
 print ("%d\t%f\t%f" % (cumN, mean, meanSq))
-print ("report: still alive", file=sys.stderr) 
+print >> sys.stderr, "report: still alive"