Ettore Rizza ettorerizza

## Search_Wikipedia.py
# -*- coding: utf-8 -*-

######################################################
#
# Ce script récupère une liste de noms et vérifie
# d'abord s'il existent dans Wikipedia.fr, puis
# dans Wikipedia.nl
#
######################################################

## create_column_openrefine.py
#!/usr/bin/python3
import json

with open("test.json", "r") as infile:
    data = json.load(infile)

def transform_to_addcolumn(data):
    data_trans = dict(data)
    data_trans["op"] = "core/column-addition"
    data_trans["expression"] = (

## refinetranslator.py
#!/usr/bin/python3
import json
import sys

with open(sys.argv[1], "r") as infile:
    data = json.load(infile)

outfile = open(sys.argv[1]+".txt", 'w')
count = 1

## merge_and_reshape_topics_matrice.R
library(dplyr)
library(data.table)
library(stringr)

#dossier contenant les fichiers
setwd("C:/Users/ettor/Desktop/Eurovoc Topicmodeling/presidencies")

#on merge les trois
files <- list.files(path = getwd(),
                    pattern = ".txt")

## Open Refine fingerprint function in R
#' Get key collision fingerprints
#'
#' Given a character vector as input, get the key collision fingerprint for
#' each element.
#'
#' Operations in order :
#'
#'-remove leading and trailing whitespace
#'-change all characters to their lowercase representation
#'-remove all punctuation and control characters

## parse_jrc-acquis
library(XML)
library(dplyr)
library(stringr)
library(readr)
library(readxl)
library(tidyr)

#liste des fichiers XML du corpus JRC Acquis version anglaise (http://optima.jrc.it/Acquis/JRC-Acquis.3.0/corpus/jrc-en.tgz)
liste <-
  list.files(

## levenshtein.py
def call_counter(func):
    def helper(*args, **kwargs):
        helper.calls += 1
        return func(*args, **kwargs)
    helper.calls = 0
    helper.__name__= func.__name__
    return helper
memo = {}
@call_counter
def levenshtein(s, t):

## postag_refine.py
import sys
sys.path.append(r'D:\jython2.7.0\Lib\site-packages')
from pattern.fr import parsetree

sentences = parsetree(value, relations=True, lemmata=True)

liste = []
for s in sentences:
    for chunk in s.chunks:
        for w in chunk.words:

## sparql_refine.py
import sys
sys.path.append(r'D:\jython2.7.0\Lib\site-packages')
from SPARQLWrapper import SPARQLWrapper, JSON
from langdetect import detect

dbpedia_version = "http://dbpedia.org/sparql"

#TEST
value = "comptoir"

## extract_names.py
from unidecode import unidecode

with open(r"C:\Users\Boulot\Desktop\prenoms.txt", 'r') as f:
    prenoms = [name.strip().lower() for name in f]

CHARS = "abcdefghijklmnopqrstuvwxyzéèàçüûùABCDEFGHIJKLMNOPQRSTUVWXYZ- "

family_joint = ["d'", "de", "du", "der", "den", "vander", "vanden", "van", "le"]

#TEST
	# -- coding: utf-8 --

	######################################################
	#
	# Ce script récupère une liste de noms et vérifie
	# d'abord s'il existent dans Wikipedia.fr, puis
	# dans Wikipedia.nl
	#
	######################################################
	#!/usr/bin/python3
	import json

	with open("test.json", "r") as infile:
	data = json.load(infile)

	def transform_to_addcolumn(data):
	data_trans = dict(data)
	data_trans["op"] = "core/column-addition"
	data_trans["expression"] = (
	#!/usr/bin/python3
	import json
	import sys

	with open(sys.argv[1], "r") as infile:
	data = json.load(infile)

	outfile = open(sys.argv[1]+".txt", 'w')
	count = 1
	library(dplyr)
	library(data.table)
	library(stringr)

	#dossier contenant les fichiers
	setwd("C:/Users/ettor/Desktop/Eurovoc Topicmodeling/presidencies")

	#on merge les trois
	files <- list.files(path = getwd(),
	pattern = ".txt")
	#' Get key collision fingerprints
	#'
	#' Given a character vector as input, get the key collision fingerprint for
	#' each element.
	#'
	#' Operations in order :
	#'
	#'-remove leading and trailing whitespace
	#'-change all characters to their lowercase representation
	#'-remove all punctuation and control characters
	library(XML)
	library(dplyr)
	library(stringr)
	library(readr)
	library(readxl)
	library(tidyr)

	#liste des fichiers XML du corpus JRC Acquis version anglaise (http://optima.jrc.it/Acquis/JRC-Acquis.3.0/corpus/jrc-en.tgz)
	liste <-
	list.files(
	def call_counter(func):
	def helper(args, *kwargs):
	helper.calls += 1
	return func(args, *kwargs)
	helper.calls = 0
	helper.__name__= func.__name__
	return helper
	memo = {}
	@call_counter
	def levenshtein(s, t):
	import sys
	sys.path.append(r'D:\jython2.7.0\Lib\site-packages')
	from pattern.fr import parsetree

	sentences = parsetree(value, relations=True, lemmata=True)

	liste = []
	for s in sentences:
	for chunk in s.chunks:
	for w in chunk.words:
	import sys
	sys.path.append(r'D:\jython2.7.0\Lib\site-packages')
	from SPARQLWrapper import SPARQLWrapper, JSON
	from langdetect import detect

	dbpedia_version = "http://dbpedia.org/sparql"

	#TEST
	value = "comptoir"
	from unidecode import unidecode

	with open(r"C:\Users\Boulot\Desktop\prenoms.txt", 'r') as f:
	prenoms = [name.strip().lower() for name in f]

	CHARS = "abcdefghijklmnopqrstuvwxyzéèàçüûùABCDEFGHIJKLMNOPQRSTUVWXYZ- "

	family_joint = ["d'", "de", "du", "der", "den", "vander", "vanden", "van", "le"]

	#TEST