Todd Cook todd-cook

## wikidata.employers.sample.data.csv

          
            employer_item_id
            count
            text_data
            class_type
             context

            
              2944031
              9
              Counter Terrorist Unit
              employer
              fictional branch of the CIA from the television series 24

            
              214126
              53
              Los Angeles Police Department
              employer
              municipal police

            
              37230
              493
              Central Intelligence Agency
              employer
              national intelligence agency of the United States

            
              9531
              1520
              BBC
              employer
              British public service broadcaster

            
              134995
              57
              bibliography
              employer

            
              21198
              842
              computer science
              employer
              study of the theoretical foundations of information and computation

            
              5962346
              1
              classification system
              employer
              organisation of objects into classes

            
              482
              1218
              poetry
              employer
              form of literary art

## wikidata.occupations.sample.data.csv

          
            occupation_item_id
            count
            text_data
            class_type
            context

            
              82955
              606008
              politician
              occupation
              person involved in politics or person who holds or seeks positions in government

            
              189290
              33481
              military officer
              occupation
              member of an armed force or uniformed service who holds a position of authority

            
              131512
              8887
              farmer
              occupation
              person that works in agriculture

            
              1734662
              2012
              cartographer
              occupation
              person preparing geographical maps

            
              294126
              323
              land surveyor
              occupation
              profession

            
              81096
              34500
              engineer
              occupation
              professional practitioner of engineering and its sub classes

            
              372436
              3790
              statesperson
              occupation
              politician in high government offices

            
              5446967
              29
              field agent
              occupation
              agent who works in the field as opposed to one who works at the office or headquarters

            
              4991371
              6642
              soldier
              occupation
              one who serves as part of an organized armed force

## auto.label.results.top.csv

          
            model
            lowest_confidence
            text_data
            class_type
            corrected_class_type

            
              linear
              1
              deputy
              employer
              UNK

            
              linear
              2
              chef
              UNK
              UNK

            
              linear
              3
              VRP
              occupation
              UNK

            
              polynomial
              1
              pen
              employer
              UNK

            
              polynomial
              2
              mayor
              employer
              UNK

            
              polynomial
              3
              art theft
              occupation
              UNK

            
              radial basis
              1
              Academy of Finland
              UNK
              UNK

            
              radial basis
              2
              Cultural Institutions Studies
              UNK
              UNK

            
              radial basis
              3
              University of Helsinki
              UNK
              UNK

## testlog.py
import logging.config
import sys


def trylog(l):
    for e in range(0, 50, 10):
        l.log(e, 'level %s' % e)


if __name__ == '__main__':

## gist:feddb1d50baa0f2550520a1eeca62e5e
%matplotlib inline
import matplotlib.pyplot as plt
import numpy as np
dates_infections = {'3/1': 89,
'3/2': 105,
'3/3': 125,
'3/4': 159,
'3/5': 227,
'3/6': 331,
'3/7': 444,

## gist:6cd9696b6b3c89c0a7b81387d7e08c54
spondaic 'at si staret' ait 'caelebs sine palmite truncus,
spondaic Aeneae genetrix, vidit quoque triste parari
spondaic Has ubi verborum poenas mentisque profanae
spondaic Hunc ubi laudatos iactantem in sanguine vultus
spondaic Maenala transieram latebris horrenda ferarum
spondaic adiectoque cavae supplentur corpore rugae,
spondaic admotumque fretum remis tellusque repulsa est,
spondaic aversata gemit; certa est exquirere nutrix
spondaic bella instructa gerunt, multumque ab utraque cruoris
spondaic bellaque non transfert, et sunt, qui parcere Troiae

## gist:39027e4514df9edaa63875ec6be2864f
# Some notes on this gist:
# all abstract and base class stuff has been moved to the top of the file so that import resolution
# and IDEs won't complain unnecessarily.
# _get_model_path is default method
# tokenize has been promoted to be a default method, and signatures downstream were made consistent with this;
#   -- whether this is a great idea is open to debate
# The default list argument, a subtle bug, has been corrected, e.g. see https://docs.python-guide.org/writing/gotchas/
# the self : object annotation has been removed as it is implied and it confuses IDE.


## gist:f1d7d3ecb62e0da079aaa1418ac49cfa
# Add to .bash_profile

function gittitle() {
 echo -n -e "\033]0;`git status | awk 'NR==1 {print $3}'`\007"
 }

parse_git_branch() {
    git branch 2> /dev/null | sed -e '/^[^*]/d' -e 's/* \(.*\)/ (\1)/'
}

## gist:834364b2ff3b6fe92b13162862f24143
# rotate text in a file, such as banner text
# surprised this isn't a library function, for silly text operations

import sys
import re

def create_matrix(height):
    matr = list()
    for i in range(0, height):
        matr.append(list())

## gist:32fdb6abdac3fcd0e59189ffc9188574
>>> import keyword
>>> keyword.kwlist
['False', 'None', 'True', 'and', 'as', 'assert', 'break', 'class', 'continue', 'def', 'del', 'elif', 'else', 'except', 'finally', 'for', 'from', 'global', 'if', 'import', 'in', 'is', 'lambda', 'nonlocal', 'not', 'or', 'pass', 'raise', 'return', 'try', 'while', 'with', 'yield']
>>> import builtins
>>> dir(builtins)
['ArithmeticError', 'AssertionError', 'AttributeError', 'BaseException', 'BlockingIOError', 'BrokenPipeError', 'BufferError', 'BytesWarning', 'ChildProcessError', 'ConnectionAbortedError', 'ConnectionError', 'ConnectionRefusedError', 'ConnectionResetError', 'DeprecationWarning', 'EOFError', 'Ellipsis', 'EnvironmentError', 'Exception', 'False', 'FileExistsError', 'FileNotFoundError', 'FloatingPointError', 'FutureWarning', 'GeneratorExit', 'IOError', 'ImportError', 'ImportWarning', 'IndentationError', 'IndexError', 'InterruptedError', 'IsADirectoryError', 'KeyError', 'KeyboardInterrupt', 'LookupError', 'MemoryError', 'NameError', 'None', 'NotADirectoryError', 'Not
employer_item_id	count	text_data	class_type	context
2944031	9	Counter Terrorist Unit	employer	fictional branch of the CIA from the television series 24
214126	53	Los Angeles Police Department	employer	municipal police
37230	493	Central Intelligence Agency	employer	national intelligence agency of the United States
9531	1520	BBC	employer	British public service broadcaster
134995	57	bibliography	employer
21198	842	computer science	employer	study of the theoretical foundations of information and computation
5962346	1	classification system	employer	organisation of objects into classes
482	1218	poetry	employer	form of literary art
occupation_item_id	count	text_data	class_type	context
82955	606008	politician	occupation	person involved in politics or person who holds or seeks positions in government
189290	33481	military officer	occupation	member of an armed force or uniformed service who holds a position of authority
131512	8887	farmer	occupation	person that works in agriculture
1734662	2012	cartographer	occupation	person preparing geographical maps
294126	323	land surveyor	occupation	profession
81096	34500	engineer	occupation	professional practitioner of engineering and its sub classes
372436	3790	statesperson	occupation	politician in high government offices
5446967	29	field agent	occupation	agent who works in the field as opposed to one who works at the office or headquarters
4991371	6642	soldier	occupation	one who serves as part of an organized armed force
model	lowest_confidence	text_data	class_type	corrected_class_type
linear	1	deputy	employer	UNK
linear	2	chef	UNK	UNK
linear	3	VRP	occupation	UNK
polynomial	1	pen	employer	UNK
polynomial	2	mayor	employer	UNK
polynomial	3	art theft	occupation	UNK
radial basis	1	Academy of Finland	UNK	UNK
radial basis	2	Cultural Institutions Studies	UNK	UNK
radial basis	3	University of Helsinki	UNK	UNK
	import logging.config
	import sys


	def trylog(l):
	for e in range(0, 50, 10):
	l.log(e, 'level %s' % e)


	if __name__ == '__main__':
	%matplotlib inline
	import matplotlib.pyplot as plt
	import numpy as np
	dates_infections = {'3/1': 89,
	'3/2': 105,
	'3/3': 125,
	'3/4': 159,
	'3/5': 227,
	'3/6': 331,
	'3/7': 444,
	spondaic 'at si staret' ait 'caelebs sine palmite truncus,
	spondaic Aeneae genetrix, vidit quoque triste parari
	spondaic Has ubi verborum poenas mentisque profanae
	spondaic Hunc ubi laudatos iactantem in sanguine vultus
	spondaic Maenala transieram latebris horrenda ferarum
	spondaic adiectoque cavae supplentur corpore rugae,
	spondaic admotumque fretum remis tellusque repulsa est,
	spondaic aversata gemit; certa est exquirere nutrix
	spondaic bella instructa gerunt, multumque ab utraque cruoris
	spondaic bellaque non transfert, et sunt, qui parcere Troiae
	# Some notes on this gist:
	# all abstract and base class stuff has been moved to the top of the file so that import resolution
	# and IDEs won't complain unnecessarily.
	# _get_model_path is default method
	# tokenize has been promoted to be a default method, and signatures downstream were made consistent with this;
	# -- whether this is a great idea is open to debate
	# The default list argument, a subtle bug, has been corrected, e.g. see https://docs.python-guide.org/writing/gotchas/
	# the self : object annotation has been removed as it is implied and it confuses IDE.
	# Add to .bash_profile

	function gittitle() {
	echo -n -e "\033]0;`git status \| awk 'NR==1 {print $3}'`\007"
	}

	parse_git_branch() {
	git branch 2> /dev/null \| sed -e '/^[^]/d' -e 's/ \(.*\)/ (\1)/'
	}
	# rotate text in a file, such as banner text
	# surprised this isn't a library function, for silly text operations

	import sys
	import re

	def create_matrix(height):
	matr = list()
	for i in range(0, height):
	matr.append(list())
	>>> import keyword
	>>> keyword.kwlist
	['False', 'None', 'True', 'and', 'as', 'assert', 'break', 'class', 'continue', 'def', 'del', 'elif', 'else', 'except', 'finally', 'for', 'from', 'global', 'if', 'import', 'in', 'is', 'lambda', 'nonlocal', 'not', 'or', 'pass', 'raise', 'return', 'try', 'while', 'with', 'yield']
	>>> import builtins
	>>> dir(builtins)
	['ArithmeticError', 'AssertionError', 'AttributeError', 'BaseException', 'BlockingIOError', 'BrokenPipeError', 'BufferError', 'BytesWarning', 'ChildProcessError', 'ConnectionAbortedError', 'ConnectionError', 'ConnectionRefusedError', 'ConnectionResetError', 'DeprecationWarning', 'EOFError', 'Ellipsis', 'EnvironmentError', 'Exception', 'False', 'FileExistsError', 'FileNotFoundError', 'FloatingPointError', 'FutureWarning', 'GeneratorExit', 'IOError', 'ImportError', 'ImportWarning', 'IndentationError', 'IndexError', 'InterruptedError', 'IsADirectoryError', 'KeyError', 'KeyboardInterrupt', 'LookupError', 'MemoryError', 'NameError', 'None', 'NotADirectoryError', 'Not