prasanthkothuri

# first foray into R, for data science and visualizations
# treemap of CERN contributions
url <- "https://www.dropbox.com/s/4g7m67xhubizoxe/cern_contributions.csv?dl=1"
CERN <- read.csv(url, header=TRUE, sep=",")
CERN$Contribution <- as.numeric(CERN$Contribution)
library(treemap)
treemap(CERN, 
        index=c("Country"), 
        vSize="Contribution",
        palette = "Set1",

prasanthkothuri

imgurl <- "/Users/prasanth/logo_swan_letters.png"
sticker(imgurl, package="", s_x=1, s_y=1, s_width=.6, s_height=.518,
        h_fill="#ffffff", h_color="#0053A1", h_size=1, filename="/Users/prasanth/hex_logo_swan_letters.png")

imgurl <- "/Users/prasanth/logo_swan_letters.png"
sticker(imgurl, package="", s_x=1, s_y=1, s_width=.6, s_height=.518,
        h_fill="#ffffff", h_color="#FB6700", h_size=1, filename="/Users/prasanth/hex_logo_swan_letters_1.png")
	
imgurl <- "/Users/prasanth/logo_swan_letters.png"
sticker(imgurl, package="", s_x=1, s_y=1, s_width=.6, s_height=.518, url="https://swan.cern.ch", u_x=1.15, u_y=0.15, u_color="#0053A1",

prasanthkothuri

#Determine the active namenode of HDFS, this is required as the webHDFS implementation doesn't redirect to active namenode

import os
import json
import xml.etree.ElementTree as ET
try:
    from urllib import urlopen
except ImportError:
    from urllib.request import urlopen

prasanthkothuri

From Spark 2.0 onwards column names are no longer case sensitive in some scenarios, this can be demonstrated by the following example

**Spark 1.6**

-bash-4.2$ cat /tmp/sample.json
{"test": "first test", "key": "key1"}
{"Test": "second test", "key": "key2"}

scala> val jDF = sqlContext.read.json("/tmp/sample.json")
scala> jDF.printSchema

prasanthkothuri

# Build docker image, assumes Dockerfile is in the current directory
docker build -t <name>:<tag> .

# Get bash into docker image
docker run -it <image> /bin/bash

# Get bash into running container
docker exec -it <image> /bin/bash

# Tail the docker logs