添加15章的一些代码

src/python/15.BigData_MapReduce/MR_inputFile.txt

@@ -0,0 +1,100 @@
+0.970413
+0.901817
+0.828698
+0.197744
+0.466887
+0.962147
+0.187294
+0.388509
+0.243889
+0.115732
+0.616292
+0.713436
+0.761446
+0.944123
+0.200903
+0.547166
+0.800028
+0.848790
+0.001641
+0.058010
+0.859900
+0.009178
+0.736598
+0.683586
+0.142515
+0.212120
+0.752769
+0.546184
+0.652227
+0.583803
+0.812863
+0.036862
+0.075076
+0.257536
+0.431278
+0.600214
+0.985564
+0.055846
+0.905295
+0.336262
+0.198738
+0.845815
+0.527989
+0.448650
+0.235313
+0.599749
+0.443923
+0.968723
+0.911076
+0.279338
+0.569492
+0.635985
+0.267532
+0.975018
+0.463698
+0.842340
+0.065590
+0.233049
+0.810390
+0.448260
+0.431967
+0.549648
+0.703612
+0.187974
+0.231709
+0.784160
+0.072283
+0.921053
+0.735468
+0.715923
+0.150431
+0.661089
+0.734955
+0.633709
+0.216102
+0.498474
+0.195620
+0.339548
+0.245314
+0.819848
+0.521242
+0.549276
+0.200906
+0.202525
+0.922876
+0.025404
+0.604032
+0.752204
+0.158860
+0.651622
+0.592898
+0.500392
+0.410614
+0.968388
+0.265918
+0.565707
+0.413670
+0.080507
+0.929978
+0.609755

src/python/15.BigData_MapReduce/mrMeanMapper.py

@@ -0,0 +1,33 @@
+'''
+Created on 2017-04-06
+Machine Learning in Action Chapter 18
+Map Reduce Job for Hadoop Streaming 
+@author: Peter Harrington/ApacheCn-xy
+'''
+
+
+'''
+	这个mapper文件按行读取所有的输入并创建一组对应的浮点数，然后得到数组的长度并创建NumPy矩阵。
+	再对所有的值进行平方，最后将均值和平方后的均值发送出去。这些值将用来计算全局的均值和方差。
+
+	Args：
+		file 输入数据
+	Return：
+		
+'''
+import sys
+from numpy import mat, mean, power
+
+def read_input(file):
+    for line in file:
+        yield line.rstrip()				# 返回值中包含输入文件的每一行的数据的一个大的List
+        
+input = read_input(sys.stdin)			# 创建一个输入的数据行的列表list
+input = [float(line) for line in input] # 将得到的数据转化为 float 类型
+numInputs = len(input)					# 获取数据的个数，即输入文件的数据的行数
+input = mat(input)						# 将 List 转换为矩阵
+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)

src/python/15.BigData_MapReduce/mrMeanReducer.py

@@ -0,0 +1,43 @@
+'''
+Created on 2017-04-06
+Machine Learning in Action Chapter 18
+Map Reduce Job for Hadoop Streaming 
+@author: Peter Harrington/ApacheCn-xy
+'''
+
+
+'''
+	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
+
+def read_input(file):
+    for line in file:
+        yield line.rstrip()						# 返回值中包含输入文件的每一行的数据的一个大的List
+       
+input = read_input(sys.stdin)					# 创建一个输入的数据行的列表list
+
+# 将输入行分割成单独的项目并存储在列表的列表中
+mapperOut = [line.split('\t') for line in input]
+print (mapperOut)
+
+# 累计样本总和，总和 和 总和 sq
+cumVal=0.0
+cumSumSq=0.0
+cumN=0.0
+for instance in mapperOut:
+    nj = float(instance[0])
+    cumN += nj
+    cumVal += nj*float(instance[1])
+    cumSumSq += nj*float(instance[2])
+    
+#计算均值
+mean = cumVal/cumN
+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)