jtmancilla

#!/usr/bin/env bash
# https://developers.supportbee.com/blog/setting-up-cucumber-to-run-with-Chrome-on-Linux/
# https://gist.github.com/curtismcmullan/7be1a8c1c841a9d8db2c
# http://stackoverflow.com/questions/10792403/how-do-i-get-chrome-working-with-selenium-using-php-webdriver
# http://stackoverflow.com/questions/26133486/how-to-specify-binary-path-for-remote-chromedriver-in-codeception
# http://stackoverflow.com/questions/40262682/how-to-run-selenium-3-x-with-chrome-driver-through-terminal
# http://askubuntu.com/questions/760085/how-do-you-install-google-chrome-on-ubuntu-16-04

# Versions
CHROME_DRIVER_VERSION=`curl -sS chromedriver.storage.googleapis.com/LATEST_RELEASE`

jtmancilla

# load the "orders" table from Hive into a DataFrame
orders_df=sqlCtx.sql("select * from orders")
orders_df.printSchema()

# 1) calculate number of orders in SUSPECTED_FRAUD status
sqlCtx.select("select count(order_id) from orders where order_status='SUSPECTED_FRAUD'").show(5)

# load the "order_items" table from Hive into a DataFrame
order_items_df=sqlCtx.sql("select * from order_items")
order_items_df.printSchema()

jtmancilla

#initialize
library(datasets)
library(ggplot2) 

#helper function (convert vector to named list)
namel<-function (vec){
		tmp<-as.list(vec)
		names(tmp)<-as.character(unlist(vec))
		tmp
	}