First, generate a set of SSH keys:
ssh-keygen
Setup the ~/.ssh/config
so, by default, we login with a specific user (in this case, root
):
Host hadoop01
# coding: utf-8 | |
# http://stackoverflow.com/questions/26794029/how-to-remove-duplicate-letters-in-a-comma-separated-cell | |
# In[1]: | |
text = """A,B,B,C | |
G,G,A,T | |
G,A,A | |
T,T""" |
# http://stackoverflow.com/questions/26793632/beautifulsoup-unable-to-to-read-the-complete-html-table | |
# coding: utf-8 | |
# In[1]: | |
import urllib2 | |
from bs4 import BeautifulSoup | |
#!/usr/bin/env python | |
# suggested gmail code for StackOverflow question: http://stackoverflow.com/questions/26772416/how-to-write-a-program-to-check-website-for-a-string | |
import smtplib | |
from email.mime.text import MIMEText | |
from email.mime.application import MIMEApplication | |
from email.mime.multipart import MIMEMultipart | |
def sendEmail(fileName, emailTo): |
""" | |
http://stackoverflow.com/questions/26564513/python-valid-ips-from-each-line-on-a-text-file/26564920#26564920 | |
iplog.txt: | |
Host : 75.75.75.75 , DNS : resolved dns , Location : USA | |
Host : 266.266.266.266 , DNS : resolved dns , Location : USA | |
Host : 10.0.1.1 , DNS : resolved dns , Location : USA | |
ipclear.txt: | |
75.75.75.75 |
#http://stackoverflow.com/questions/26500406/why-when-add-where-clause-in-sql-statement-query-return-no-data | |
""" | |
create table tb_test | |
( | |
id integer, | |
name varchar(255), | |
date date | |
); | |
insert into tb_test (id, name, date) values (0,'Mike','2014-04-24'); |
# ssh into your AWS instance and setup s3fs: | |
sudo yum install git gcc libstdc++-devel gcc-c++ fuse fuse-devel curl-devel libxml2-devel openssl-devel mailcap automake | |
git clone git://github.com/s3fs-fuse/s3fs-fuse.git | |
cd s3fs-fuse/ | |
./autogen.sh | |
./configure --prefix=/usr | |
make |
""" | |
# http://stackoverflow.com/questions/26248943/mysql-sseparate-value-from-one-column-to-several-rows-and-join-with-other-column | |
setup the tables: | |
create table papers | |
( | |
paper_title varchar(10), | |
authors varchar(10), | |
year integer |
library(gputools) | |
library(e1071) | |
library(fueleconomy) | |
data(vehicles) | |
vehicles$id <- NULL | |
vehicles$hwy <- NULL | |
vehicles <- as.data.frame(unclass(vehicles)) | |
vehicles <- vehicles[complete.cases(vehicles), ] |
""" | |
This scrapes Amazon's distribution centers from the web and creates a file of markers for an interactive map created in Leaflet.js | |
For now (10/03/2014) it can be viewed at http://54.172.30.118/amzn-locations.html | |
""" | |
import urllib2 | |
from bs4 import BeautifulSoup | |
from pygeocoder import Geocoder | |
import time |