urigoren

set splitbelow
nnoremap <F4> :set hlsearch! nohlsearch?<CR>
imap <F4> <C-O><F4>

nnoremap <F2> :let @/="qoXouQoz"<CR>:set invpaste paste?<CR>
set pastetoggle=<F2>
nnoremap <silent> <F3> :let @/ .= '\\|\<'.expand('<cword>').'\>'<cr>n
nnoremap <buffer> <F5> :w<cr>:exec '!/usr/bin/python3' shellescape(@%, 1)<cr>
syntax on

urigoren

import json, boto3
s3 = boto3.resource("s3").Bucket("bucket")
json.load_s3 = lambda f: json.load(s3.Object(key=f).get()["Body"])
json.dump_s3 = lambda obj, f: s3.Object(key=f).put(Body=json.dumps(obj))

urigoren

import sys, random, json
from gensim.models import Word2Vec
from argparse import ArgumentParser
from collections import Counter
from pathlib import Path

__dir__= Path(__file__).absolute().parent


class DirSentences(object):

urigoren

import sys, os, json, subprocess
from argparse import ArgumentParser

__dir__ = os.path.dirname(os.path.abspath(__file__))


def shell(cmd):
    """Run bash command"""
    process = subprocess.Popen(cmd, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
    stdout, stderr = process.communicate()

urigoren

categorical_data = [
    (0,1,2),
    (0,1),
    (0,1,3),
    (0,1,3),    
    (0,1,3),
    (0,1,2,3),
    (2, 3),
    (2, 3),
    (2, 3),

urigoren

import json, sys
from operator import itemgetter as at
fname = sys.argv[1]
assert fname.endswith('.json')
with open(fname, 'r') as f:
    d = json.load(f)
with open(fname.replace('.json', '.csv'), 'w') as f:
    f.write('{k},{v}\n'.format(k="key", v="val"))
    for k,v in sorted(d.items(), key=at(1), reverse=True):
        f.write('"{k}",{v}\n'.format(k=k.replace('"','""'), v=v))

urigoren

import re
from html import unescape
def html2text(htm):
    ret = unescape(htm)
    ret = ret.translate({
        8209: ord('-'),
        ord('`'): ord("'"),
        ord('’'): ord("'"),
        8220: ord('"'),
        8221: ord('"'),

urigoren

urigoren

"""
A python wrapper for the icount.co.il api
https://www.icount.co.il/api-v3/
"""
import json
from urllib import request, parse


def post(url, data):
    req = request.Request(url, data=parse.urlencode(data).encode())

urigoren

import numpy as np
import collections, itertools, string
from scipy.cluster import hierarchy
from scipy.spatial import distance
from sklearn.feature_extraction import text
from editdistance import distance as editdistance

def edit_pdist(toks, normalize=False):
    """Return pairwise editdistance matrix"""
    n = len(toks)