mirror of
https://github.com/apachecn/ailearning.git
synced 2026-06-15 23:06:32 +08:00
33
src/python/15.BigData_MapReduce/mrMeanMapper.py
Normal file
33
src/python/15.BigData_MapReduce/mrMeanMapper.py
Normal file
@@ -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)
|
||||
43
src/python/15.BigData_MapReduce/mrMeanReducer.py
Normal file
43
src/python/15.BigData_MapReduce/mrMeanReducer.py
Normal file
@@ -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)
|
||||
Reference in New Issue
Block a user