soobrosa

# input is unicode

import unicodedata

def homogenize (text):
    text = unicodedata.normalize('NFKD', text).encode('ascii', 'ignore')
    text = text.lower()
    return text

soobrosa

# to export your miso history
# register an app at http://gomiso.com/oauth_clients
# gain your consumer_key and consumer_secret
# grab Gomiso Python from https://github.com/metabaron/Gomiso-Python
# and your ready to go
#
# cc 2013 soobrosa

from gomiso import gomiso
import json

soobrosa

fi = open ('vizallas.txt', 'r')
fo = open ('vizallas.tsv', 'w')

year = ''

for li in fi:
# fixup days not existing in a given month
  it = li.strip().replace('         ','   ...   ').split('   ')
	
  if len(it) < 2:

soobrosa

source.downloaded:
  mkdir source
  cd source && { curl -O "https://d396qusza40orc.cloudfront.net/dsscapstone/dataset/yelp_dataset_challenge_academic_dataset.zip" ; cd -; }

source.decompressed: source.downloaded
  unzip source/yelp_dataset_challenge_academic_dataset.zip

#
#   one record pretty printed from each file composed of lines of JSONs
#

soobrosa

import difflib

def neighbours(table, entry):
	neighbour_list = difflib.get_close_matches(entry, table)
	returns = {}
	for neighbour in neighbour_list:
		returns[neighbour] = difflib.SequenceMatcher(None, entry, neighbour).ratio()
	return returns

soobrosa

# parses directories for .twb files
# and extracts database connections
# rough and dirty

import os

for root, dirs, files in os.walk('.'):
  for file in files:
    if file.endswith('.twb'):
      f = open(root + '/' + file)

soobrosa

def daterange(start_date, end_date):
    for n in range(int ((end_date - start_date).days)):
        yield start_date + timedelta(n)

soobrosa

### Keybase proof

I hereby claim:

  * I am soobrosa on github.
  * I am soobrosa (https://keybase.io/soobrosa) on keybase.
  * I have a public key whose fingerprint is 19DA 1DE2 BEBD F91F 3EEA  A264 30F5 64DE 4D6E 279F

To claim this, I am signing this object:

soobrosa

import csv
import sys
infile = sys.argv[1]
outfile = sys.argv[2]

with open(infile) as f:
    reader = csv.reader(f)
    cols = []
    for row in reader:
        cols.append(row)