practice.md

Keep worst by group

Other 2 examples

Method 1

import string
def printWst(s):
   lookup = string.ascii_uppercase
   b = [x.split() for x in input.split('\n')]
   b = filter(None, b)
   rst = {}
   for i, x in enumerate(b):
       key, value = x[0], x[1]
       if i == 0:
           print key, value
       else:
           current = lookup.index(value)
           if key not in rst or (key in rst and current > lookup.index(rst[key])):
               rst[key] = value
   for k in sorted(rst):
       print k, rst[k]

if __name__ == "__main__":
   test1 = """
       Account_number    Flag
       1            A
       1            B
       2            A
       2            B
       2            C
       3            A
       3            C
       """
 printWst(test1)

Method 2

#!/usr/bin/env python
# coding=utf-8
from string import ascii_uppercase
def lookup(x):
   return ascii_uppercase.index(x)

with open('c:/temp/test.txt') as infile:
   carry = ['-1', '99']
   for i, line in enumerate(infile):
       lineLst = line.split()
       key, value = lineLst[0], lineLst[1]
       if key != carry[0]:
           if i != 0:
               print carry
           carry = lineLst
       else:
           if lookup(value) > lookup(carry[1]):
               carry[1] = value
   print carry

Method 3

Want to find the rating for each account number.

sample.txt
Account_number    Rating
1            A
1            B
2            A
2            B
2            C
3            A
3            C

import pyspark

sc = pyspark.SparkContext()
rdd = sc.textFile('sample.txt')
result = rdd.map(lambda x: x.split()).filter(x: x[0].isdigit()).reduceByKey(max)
for x in result.collect(): 
    print x
    
sc.stop()