mattiasostmar

{
 "metadata": {
  "name": "Playing with MySql"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {

mattiasostmar

{
 "metadata": {
  "name": "CSV read with Pandas"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {

mattiasostmar

import re
import sys

_, infile, outfile = sys.argv

s_pat_row = r'''
    "([^"]+)"          # match column; this is group 1
    \s*\t\s*           # match separating tab and any optional white space
    ([^\t]+)           # match a string of non-tab chars; this is group 2
    \s*\t\s*           # match separating tab and any optional white space

mattiasostmar

# define the function to split the file into smaller chunks
def splitFile(inputFile,chunkSize):
	#read the contents of the file
	f = open(inputFile, 'rb')
	data = f.read()
	f.close()

# get the length of data, ie size of the input file in bytes
	bytes = len(data)

mattiasostmar

{
 "metadata": {
  "name": ""
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {

mattiasostmar

README is empty

mattiasostmar

import regex
import logging
import gensim
from gensim import corpora, models

logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.INFO)

class MySentences(object):
    def __init__(self, fname):
        self.fname = fname

mattiasostmar

Working:

import requests
text = "Fördomen har alltid sin rot i vardagslivet - Olof Palme 🙈🙈🙌🙆👪👏yüá🎧ÖÅÄê"
r = requests.post("http://json-tagger.herokuapp.com/tag",data=dict(data=text))
r.json()

{'entities': [{'token_ids': ['tok:0:8', 'tok:0:9', 'tok:0:10'], 'word_form': 'Olof Palme 🙈🙈🙌🙆👪👏yüá🎧ÖÅÄê'}], 'sentences': [[{'morph_feat': 'UTR|SIN|DEF|NOM',

mattiasostmar

"0307.n.0003": {
        "cats": null,
        "meta_cats": null,
        "filename": "Utgrävningar_i_Teotihuacan_(1932)_-_SMVK_-_0307.n.0003",
        "info": "{{photograph\n|photographer       =  {{creator:Sigvald_Linné}}\n|title              = \n|description       = {{sv|Chichén Itzá, Dzitas. Utgrävningar i Teotihuacan (1932).}}\n{{en|Images from the 1932 Sigvald Linné archeological expedition at Teotihuacán, Mexico.}}\n|depicted place     = Chichén Itzá, Dzitas\n|date               = 1932\n|medium             = \n|dimensions         = \n|institution        = {{Institution:Statens museer för världskultur}}\n|department         = [[:d:Q1371375|Etnografiska muséet]]\n|references         = \n|object history     = \n|exhibition history = \n|credit line        = \n|inscriptions       = \n|notes              = \n|accession number   = {{SMVK-EM-link|1=foto|2=2803890|3=0307.n.0003}}\n|source             = Original file name, as received from SMVK:  <br /> '''0307.n.0003.tif'''\n{{SMVK_cooperation_project|COH|museu

mattiasostmar

/Users/mos/anaconda/bin/python /Users/mos/PycharmProjects/Medelhavsmuseet_2016-08/check_pages_without_images_smvk-em.py

--- [[commons:File:Från utgrävningarna vid Xolalpan - SMVK - 0307.a.0154.tif]]
{{speedydelete|broken file upload}}
{{photograph
|photographer       = {{creator:Sigvald_Linné}}
|title              = 
|description        = {{sv|Från utgrävningarna vid Xolalpan. Teotihuacan. Utgrävningar i Teotihuacan (1932).}}
{{en|Images from the 1932 Sigvald Linné archeological expedition at Teotihuacán, Mexico.}}
|depicted place     = Q172613