semyont

// Use Gists to store code you would like to remember later on
console.log(window); // log the "window" object to the console

semyont

from pyspark.sql.functions import split, regexp_extract
split_df = base_df.select(regexp_extract('value', r'^([^\s]+\s)', 1).alias('host'),
                          regexp_extract('value', r'^.*\[(\d\d/\w{3}/\d{4}:\d{2}:\d{2}:\d{2} -\d{4})]', 1).alias('timestamp'),
                          regexp_extract('value', r'^.*"\w+\s+([^\s]+)\s+HTTP.*"', 1).alias('path'),
                          regexp_extract('value', r'^.*"\s+([^\s]+)', 1).cast('integer').alias('status'),
                          regexp_extract('value', r'^.*\s+(\d+)$', 1).cast('integer').alias('content_size'))
split_df.show(truncate=False)

semyont

import logging
import hashlib

from elasticsearch import Elasticsearch
from elasticsearch import helpers

from tqdm import tqdm


class Storage:

semyont

import logging
logging.basicConfig(
    format='%(asctime)s,%(msecs)05.1f (%(funcName)s) %(message)s',
    datefmt='%H:%M:%S')
log = logging.getLogger()
log.setLevel(logging.INFO)
 
import threading
import os
import time

semyont

# List unique values in a DataFrame column
pd.unique(df.column_name.ravel())

# Convert Series datatype to numeric, getting rid of any non-numeric values
df['col'] = df['col'].astype(str).convert_objects(convert_numeric=True)

# Grab DataFrame rows where column has certain values
valuelist = ['value1', 'value2', 'value3']
df = df[df.column.isin(valuelist)]

semyont

version: '2'

services:
   db:
     image: mysql:5.7
     volumes:
       - db_data:/var/lib/mysql
     restart: always
     environment:
       MYSQL_ROOT_PASSWORD: wordpress

semyont

# Convert wide format csv to long format csv
# Time Temp1 Temp2 Temp3 Temp4 Temp5
# 00   21     32   33    21    23
# 10   34     23   12    08    23
# 20   12     54   33    54    55

with open("in.csv") as f,open("out.csv","w") as out:
     headers = next(f).split()[1:]  # keep headers/Time Temp1 Temp2 Temp3 Temp4 Temp5
     for row in f:

semyont

# GET /_search
{
  "query": { 
    "bool": { 
      "must": [
        { "match": { "doc.title":   "Search"        }}, 
        { "match": { "doc.content": "Elasticsearch" }}  
      ],
      "filter": [ 
        { "term":  { "doc.status": "published" }}, 

semyont

# use un-analyzed fields

{
    "aggs" : {
        "domain" : {
             "terms" : {
                 "field" : "doc.domain.keyword",
                 "size" : 4,
                 "collect_mode" : "breadth_first"
             },

semyont

# Do this as early as possible in your application:
from gevent import monkey; monkey.patch_all()
from tornado.web import RequestHandler, asynchronous

import gevent
 
class MyHandler(RequestHandler):
    @asynchronous
    def get(self, *args, **kwargs):
        def async_task():