daroczig

## #############################################################################
## PCA demo on image processing
## #############################################################################

download.file('http://bit.ly/nasa-image-pca', 'image.jpg') # mode = »bw«

library(jpeg)
img <- readJPEG('image.jpg')
str(img)

daroczig

#!/usr/bin/env python

import dbus, dbus.exceptions
import sys
import re

try:
    bus = dbus.SessionBus()
    timetracker = bus.get_object('org.gnome.Shell', '/timepp/zagortenay333/TimeTracker')
except dbus.exceptions.DBusException as e:

daroczig

## #############################################################################
## intro slides: http://bit.ly/CRUNCH-R-2018

## #############################################################################
## intro to R

## basic operations
1 + 3
3 * 2

daroczig

## generate transactional tables
set.seed(42)
library(data.table)
tx <- data.table(
    item   = sample(letters[1:3], 10, replace = TRUE),
    time   = as.POSIXct(as.Date('2016-01-01')) - runif(10) * 36*60^2,
    amount = rpois(10, 25))
prices <- data.table(
    item  = letters[1:3],
    date  = as.Date('2016-01-01') - 1:2,

daroczig

m1 <- lm(mpg ~ hp, data = mtcars)
m2 <- lm(mpg ~ hp + drat, data = mtcars)
m3 <- lm(mpg ~ hp + drat + factor(gear), data = mtcars)

library(pander); library(memisc)
panderOptions('table.alignment.rownames', 'left')
pander(relabel(
    mtable(m1, m2, m3,
           summary.stats=c('N', 'R-squared', 'F')),
    '(Intercept)'       = 'Constant',

daroczig

library(XML)

html  <- htmlParse(readLines('https://www.meetup.com/topics/r-project-for-statistical-computing/all/'))
names <- xpathSApply(html, '//li[@class="gridList-item"]/a/span', xmlValue)
attrs <- xpathSApply(html, '//li[@class="gridList-item"]/span[@class="text--secondary text--small chunk"]', xmlValue)
attrs <- gsub('\\n|\\t', '', attrs)
users <- as.numeric(gsub(',', '', sub('^([0-9,]*) .*', '\\1', attrs)))
geo   <- sub('.* \\| ', '', attrs)

data.frame(name = names, location, members)

daroczig

## intro slides: http://bit.ly/r-intro-slide

## basic operations
1 + 3
3*2
3^2

## constants
pi
"pi"

daroczig

## intro slides: http://bit.ly/CRUNCH-R-2017

## basic operations
1 + 3
3*2
3^2

## constants
pi
"pi"

daroczig

# demo transactions data
library(data.table)
txns <- data.table(
  rpid = rep(1:3, times = 4),
  txid = 1:12,
  time = c(10, 10, 10, 11, 15, 20, 12, 16, 25, 13, 21, 30))

## overlap join to see which transactions happened withing 3 time units on the same rpid
## let's define the time periods for the overlap
txns[, start := time - 3]

daroczig

#' Connect and query Imapala via SSH and Impala-shell
#' @param query SQL query to run
#' @param host server hostname or IP
#' @param log enable or disable logging of debug/trace messages
#' @return data.table object
#' @export
query_impala <- function(query, host = 'localhost', log = require(futile.logger)) {

    ## measure time of query
    timer <- proc.time()