jaklinger

import datetime
from googleapiclient.discovery import build
from httplib2 import Http
from oauth2client import file, client, tools
from collections import defaultdict
import json
from googleapiclient.errors import HttpError

# If modifying these scopes, delete the file token.json.
SCOPES = 'https://www.googleapis.com/auth/calendar.readonly'

jaklinger

from alphabet_detector import AlphabetDetector

ALPHABET_DETECTOR = AlphabetDetector()

def prepare_title(title):
    # Replace non-alphanums (allowing foreign characters)  
    result = "".join([x
                      if len(ALPHABET_DETECTOR.detect_alphabet(x)) > 0
                      or x.isnumeric()
                      else " " for x in title.lower()])

jaklinger

import requests
import json

def make_query(url, q, alg, field, shard_size=1000, size=25):
    """Get keywords relating to the input query, directly from Elasticsearch
    
    Args:
        url (str): The Elasticsearch endpoint you want to query
        q (str): The query you want to retrieve keywords for
        alg (str): An algorithm from https://www.elastic.co/guide/en/elasticsearch/reference/current/search-aggregations-bucket-significantterms-aggregation.html#_parameters

jaklinger

from sqlalchemy import create_engine
from sqlalchemy.engine.url import URL
from configparser import ConfigParser
import pandas as pd

def get_engine(config_path, database="production", **engine_kwargs):
    '''Get a SQL alchemy engine from config'''
    cp = ConfigParser()
    cp.read(config_path)
    cp = cp["client"]

jaklinger

import pandas as pd                                                                         
import os       
import json
	
TOPDIR = "path/to/opname_csv_gb/"                                         
HEADER_PATH = os.path.join(TOPDIR,'DOC','OS_Open_Names_Header.csv')                         

def extract_tree(df, levels, ilvl=0):
    lvl = levels[ilvl]
    entities = []

jaklinger

import pymongo
from pymongo import MongoClient
import pandas as pd

def mongo_to_files(usr_name, pwd, address, db_name, collection, 
                   out_path='out{}-{}.json', chunk_size=10000, port=27017):
    client = MongoClient(f'mongodb://{usr_name}:{pwd}@{address}', port)
    db = client[db_name]
    collection = db[collection]
    total = collection.count()

jaklinger

ALL_USERS="jklinger sgarasto jdjumali csleeman rleung"
TOPDIR=$PWD
for USERNAME in $ALL_USERS;
do
    cd $TOPDIR
    sudo useradd --create-home $USERNAME
    echo "$USERNAME" | sudo passwd --stdin $USERNAME
    sudo usermod -aG ec2-user $USERNAME
    sudo usermod -aG wheel $USERNAME
    sudo cp -rp $HOME/* /home/$USERNAME/

jaklinger

CREATE TEMPORARY TABLE tmp_skills_a
PRIMARY key doc_id
SELECT doc_id, skill_id 
FROM skills_link_table 
GROUP BY doc_id, skill_id;

CREATE TEMPORARY TABLE tmp_skills_b
PRIMARY key doc_id
SELECT doc_id, skill_id 
FROM skills_link_table 

jaklinger

import numpy as np

def assym(a):
    return 1 - (np.linalg.det(0.5*(a + a.T)) / np.linalg.det(a))

for a in ([[10,123,0],[123,10,0],[0,0,10]], [[10,123,0],[121,10,0],[0,0,10]],
          [[10,123,0],[50,10,0],[0,0,10]], [[10,123,0],[0,10,0],[23,0,10]],
          [[10,123,0],[-123,10,0],[5422,0,10]]):
    a = np.matrix(a)
    print(a)

jaklinger

def do_the_other_thing(run, output): 
    def wrap(self): 
        run(self) 
        output(self) 
    return wrap 
 
class A: 
    name='a' 
    def run(self): 
        pass