janfait

######################################################################################################
# SETUP
######################################################################################################

#libraries
library(ggplot2)
library(scales)
library(dplyr)
library(reshape2)
library(stringr)

janfait

###############
# SETUP
###############
library(XML)
library(httr)
library(ggplot2)
library(dplyr)
#if a RDS file has been saved previously, 
lazyLoad <- T
###############

janfait

#################
# SETUP
#################

from pyspark import SparkConf, SparkContext
from pyspark.sql import SQLContext
from pyspark.sql import Row
from pyspark.sql.functions import lit
from pyspark.sql.functions import col, avg
from pyspark.sql.types import *

janfait

# -*- coding: utf-8 -*-
"""
Created on Sun Apr 30 20:26:43 2017

@author: Jan Fait, [email protected]
"""

import os
import requests
import datetime

janfait

mappDmp <- setRefClass("mappDmp",
                       fields=list(
                         debug = "logical",
                         root = "character",
                         endpoints = "list",
                         username = "character",
                         password = "character",
                         authentication = "list",

janfait

##############
# SETUP
##############

# run this file by submitting an R command system("python /home/r_shared/py_uaparser.py --infile /way/to/your/log/file.csv")
# the parsed file - if successful - will be created in the same directory, just file_parsed.csv 
# the structure of the input file must be consistent, there are no mechanisms that locate the UA string other than spliting 
# the line input by separators

import csv, json, re, sys, argparse, time

janfait

library(stringr)
library(RCurl)

#get current time string
thisMonth <- format(Sys.Date(),"%m")
thisYear  <- format(Sys.Date(),"%Y")
timeStamp <- paste0(thisMonth,thisYear)

#build a file pattern to search for by joining cluster names and timestamp
filePattern <- paste(c("EMC","LC"),timeStamp,sep="_",collapse="|")

janfait

userPreferences <- c(rep("mobile",6),rep("email",4))
contentTags <- c("email","mobile")

similarityIndex <- function(content_tags=NULL,user_preferences=NULL){
  #weighted intersect of content_tags and user_preference, returns a sum of weights of tags which are in both sets
  wi <- sum(sapply(intersect(content_tags,user_preferences),function(i) sum(i==user_preferences)))
  #weighted union of all items entering the computation (content_tags have a weight==1)
  wu <- length(user_preferences)+length(setdiff(content_tags,user_preferences))

janfait

ggsurv <- function(s, CI = 'def', plot.cens = T, surv.col = 'gg.def',
                   cens.col = 'red', lty.est = 1, lty.ci = 2,
                   cens.shape = 3, back.white = F, xlab = 'Time',
                   ylab = 'Survival', main = ''){
 
  library(ggplot2)
  strata <- ifelse(is.null(s$strata) ==T, 1, length(s$strata))
  stopifnot(length(surv.col) == 1 | length(surv.col) == strata)
  stopifnot(length(lty.est) == 1 | length(lty.est) == strata)
 

janfait

encrypt <- function(v) {
  
  #get uniques
  vU <- unique(v)
  vU <- vU[!is.na(vU) & vU!=""]

  #apply the encryption over a vector
  vE <- sapply(vU, function(x){
      oL <- c(LETTERS, letters)
      oN <- 0:9