shiumachi

def f(num, max_num):
    """
    num: くじを引く回数
    max_num: くじの総数
    """
    p = 1.0
    for i in xrange(num):
        p = p * (float(max_num - i - 1) / (max_num - i))
    return p
    

shiumachi

[sho@demo]/opt/cloudera/parcels/CDH/share/hue% export HUE_APP_REG_DIR=/opt/cloudera/parcels/CDH/share/hue
[sho@demo]/opt/cloudera/parcels/CDH/share/hue% tools/app_reg/app_reg.py --list
Name               Version Author          Path
------------------ ------- --------------- -----------------------------------
about              2.5.0   Hue             ./apps/about
beeswax            2.5.0   Hue             ./apps/beeswax
filebrowser        2.5.0   Hue             ./apps/filebrowser
hbase              2.5.0   Hue             ./apps/hbase
help               2.5.0   Hue             ./apps/help
impala             2.5.0   Hue             ./apps/impala

shiumachi

% kaa
Traceback (most recent call last):
  File "/Users/sho/.virtualenvs/py3/bin/kaa", line 9, in <module>
    load_entry_point('kaaedit==0.26.1', 'console_scripts', 'kaa')()
  File "/Users/sho/.virtualenvs/py3/lib/python3.3/site-packages/pkg_resources.py", line 352, in load_entry_point
    return get_distribution(dist).load_entry_point(group, name)
  File "/Users/sho/.virtualenvs/py3/lib/python3.3/site-packages/pkg_resources.py", line 2307, in load_entry_point
    return ep.load()
  File "/Users/sho/.virtualenvs/py3/lib/python3.3/site-packages/pkg_resources.py", line 2021, in load
    entry = __import__(self.module_name, globals(),globals(), ['__name__'])

shiumachi

# text converter
# source file:
#  [string]: [string]
# convert to csv:
#  [string],[string]

import sys

for line in sys.stdin:
    name, word = line.rstrip().split(': ')

shiumachi

# TOKEN, ROOM_NAME は適宜置き換え
# 事前に pip install hypchat でパッケージをインストールしておくこと

import hypchat

hc = hypchat.HypChat(TOKEN)

for i in hc.rooms()['items']:
    if i['name'] == ROOM_NAME:
        room = hc.get_room(i['id'])

shiumachi

import re
import sys
import logging

logging.getLogger().setLevel(logging.DEBUG)

d = {}

def count(line, word):
    #logging.debug("line: {0}".format(line))

shiumachi

# sample of ast module
# reference:
#   http://docs.python.jp/2.7/library/ast.html
#   http://stackoverflow.com/questions/1515357/simple-example-of-how-to-use-ast-nodevisitor

import ast
import sys
import logging

shiumachi

date_string = "2014-01-05 22:20:50,307"

def convert_to_datetime(date_string):
    """ input: %Y-%m-%d %H:%M:%S,%f
        example: 2014-01-05 22:20:50,307
        return: datetime object
    """
    date_format = "%Y-%m-%d %H:%M:%S,%f"
    import datetime
    return datetime.datetime.strptime(date_string, date_format)

shiumachi

example = """2014-01-05 22:20:50,307 INFO org.apache.hadoop.hdfs.server.datanode.BlockPoolSliceScanner: Verification succeeded for BP-1337840909-192.168.0.1-1374311151785:blk_8462243608396789329_201176
"""

def parse_datetime_and_level(line):
    """ input: hadoop log
        output: [datetime, loglevel, message]
    """
    import re
    r = re.compile("(^\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2},\d{3}) ([A-Z]{4,5}) (.*)")
    m = r.match(line)

shiumachi

def print_arr_right_aligned(arr):
    """ input: string array ['a', 'ab', 'abc']
        output: None. print with right aligned.
          a:
         ab:
        abc:
    """
    len_a = max(map(lambda x: len(x), arr))
    for i in arr:
        print("{0:>{1}}: ".format(i, len_a))