ettorerizza

import sys
sys.path.append(r'D:\jython2.7.0\Lib\site-packages')
from unidecode import unidecode

#TEST
value = "carette leuven"


with open(r"C:\Users\Boulot\Desktop\communes.tsv", 'r', encoding="utf8") as f:
    lieux = [unidecode(name.strip().lower().replace("-", " ")) for name in f]

ettorerizza

library(stringr)
library(purrr)
library(rvest)

#------------------------------------------------------------------------------#
# Author: Andrew Do
# Purpose: A bunch of utility functions for the main ScrapeCityToPage The goal
# is to be able to scrape up to a specified page number for a given city and
# then to store that information as a data frame.  The resulting data frame will
# be raw and will require additional cleaning, but the structure is more or less

ettorerizza

#! python3
import json
import sys
import os

#prend en entrée un Json de "cluster and edit" et renvoye du code R
if len(sys.argv) < 2:
 print("USAGE: ./utils/open_refine_to_R.py [edits.json] > r_file.R")
 exit(1)
json_file = sys.argv[-1]

ettorerizza

#! python3
import requests
from bs4 import BeautifulSoup
import string
import pandas as pd

url = "http://patrom.fltr.ucl.ac.be/contemporain/query.cfm"

letters = list(string.ascii_lowercase)

ettorerizza

import urllib
data = set(row['record']['cells']['extract_persons']['value'])
liste = []
for el in data:
    liste.append('"%s"' %el)
terms = "+".join(liste)

if len(terms) > 1:
    return "https://www.googleapis.com/books/v1/volumes?q=" + urllib.quote(terms.encode('utf8')) + "&key="

ettorerizza

import pandas as pd
import simplejson as json
import gzip

def getTargetIds(jsonData):
    data = json.loads(jsonData)
    return (str(data.get('id', 'null')),
            str(data.get('norm_name', 'null')),
            str(data.get('description', 'null')),
            str(data.get('date_birth', 'null')),

ettorerizza

import csv
import copy
import os
import sys
import glob

os.chdir(r"FOLDER_PATH")
names={}
for fn in glob.glob('*.txt'):
    with open(fn, encoding="utf8") as f:

ettorerizza

# -*- coding: utf-8 -*-
import requests
from bs4 import BeautifulSoup

array = ["Q32815", "Q34627"]


query = {"query": """
SELECT ?classe ?classeLabel WHERE { 
wd:%s wdt:P279* ?classe . 

ettorerizza

library(jqr)

data <- readr::read_file("tweets.json")

data %>% keys()

data %>% jq("{id: .id, hashtag: .entities.hashtags[].text}", 
  "[.id, .hashtag]") %>% jsonlite::toJSON()

stri <- "--h"

ettorerizza

# -*- coding: utf-8 -*-
""" 
Test du Stanford NER tagger avec les modèles CRF d'Europeana
entrainés sur des journaux :
http://lab.kbresearch.nl/static/html/eunews.html
La fonction est lente --> songer au multiprocessing
"""

from nltk.tag import StanfordNERTagger
from nltk.tokenize import word_tokenize