chelsyx

library(sn)
library(tidyverse)
perc.rank <- function(x) trunc(rank(x))/length(x)

# Create a skewed normal distribution
X <- seq(-1, 2, 0.001)
dist <- dsn(X, xi = 0.1, omega = 0.3, alpha = 5)
dist <- dist[dist>=0&dist<=1]

# Create dataset with scaled propensity (score) and group

chelsyx

Opening and closing an SSH tunnel in a shell script the smart way

I recently had the following problem:

• From an unattended shell script (called by Jenkins), run a command-line tool that accesses the MySQL database on another host.
• That tool doesn't know that the database is on another host, plus the MySQL port on that host is firewalled and not accessible from other machines.

We didn't want to open the MySQL port to the network, but it's possible to SSH from the Jenkins machine to the MySQL machine. So, basically you would do something like

ssh -L 3306:localhost:3306 remotehost

chelsyx

# WMF only:
if (file.exists("/etc/wikimedia-cluster")) {
  message('Detected that this script is being run on a WMF machine ("', Sys.info()["nodename"], '"). Setting proxies...')
  Sys.setenv("http_proxy" = "http://webproxy.eqiad.wmnet:8080")
  Sys.setenv("https_proxy" = "http://webproxy.eqiad.wmnet:8080")
}

# General use:
message("Checking for a personal library...")
if (!dir.exists(Sys.getenv("R_LIBS_USER"))) {

chelsyx

# Read Data
library(data.table)
train0 <- fread("adult.data.txt", na.strings="?", stringsAsFactors = T)
test0 <- fread("adult.test.txt", na.strings="?", stringsAsFactors = T)
var_name <- c("age","workclass","fnlwgt","education","education-num","marital-status","occupation","relationship",
              "race","sex","capital-gain","capital-loss","hours-per-week","native-country","income")
colnames(train0) <- var_name
colnames(test0) <- var_name

# Remove duplicates

chelsyx

git pull --rebase --autostash

chelsyx

#####
# Goal: 
# 1) suggest cutoff(no. of trips), and bonus($)
# 2) Expected no of additional trips
# 3) Total expenditure of the promotion
# 4) Other metrics to pay attention to
####

library(dplyr)
library(ggplot2)

chelsyx

library(data.table)
library(bit64)
library(plyr)
library(dplyr)
library(Hmisc)
library(mice)
library(vcd)
library(ggplot2)

data0 <- fread("INMAIL_MESSAGE_DATASET.csv")

chelsyx

chelsyx

#plot.stacked makes a stacked plot where each y series is plotted on top
#of the each other using filled polygons
#
#Arguments include:
#'x' - a vector of values
#'y' - a matrix of data series (columns) corresponding to x
#'order.method' = c("as.is", "max", "first") 
#  "as.is" - plot in order of y column
#  "max" - plot in order of when each y series reaches maximum value
#  "first" - plot in order of when each y series first value > 0

chelsyx

library(bnlearn)
require(Rgraphviz)

spec = "[req_date][category_id|req_date:location_id][location_id|req_date][quo_dum|req_date:category_id:location_id]"
net = model2network(spec)
class(net)
# graphviz.plot(net, shape = "ellipse")


train <- allData[,c("req_date","category_id","location_id","quo_dum")]