memory.size()
## [1] 14.28
memory.limit()
## [1] 1535
getwd()
## [1] "C:/Users/dell/Desktop"
ls()
## character(0)
rm(list=ls())
gc()
## used (Mb) gc trigger (Mb) max used (Mb)
## Ncells 291003 7.8 592000 15.9 350000 9.4
## Vcells 321668 2.5 786432 6.0 677564 5.2
setwd("C:/Users/dell/Desktop")
dir(pattern = "\\.(csv|CSV)$")
## [1] "Analytics decisionstats.com Audience Overview 20110617-20120717.csv"
## [2] "BigDiamonds.csv"
## [3] "Boston.csv"
## [4] "ccFraud.csv"
## [5] "test.csv"
library(arules)
## Loading required package: Matrix
##
## Attaching package: 'arules'
##
## The following objects are masked from 'package:base':
##
## %in%, write
library(arulesViz)
## Loading required package: grid
##
## Attaching package: 'arulesViz'
##
## The following object is masked from 'package:base':
##
## abbreviate
data("Groceries")
Groceries
## transactions in sparse format with
## 9835 transactions (rows) and
## 169 items (columns)
inspect(Groceries[1:5])
## items
## 1 {citrus fruit,
## semi-finished bread,
## margarine,
## ready soups}
## 2 {tropical fruit,
## yogurt,
## coffee}
## 3 {whole milk}
## 4 {pip fruit,
## yogurt,
## cream cheese ,
## meat spreads}
## 5 {other vegetables,
## whole milk,
## condensed milk,
## long life bakery product}
itemFrequencyPlot(Groceries,topN=20,type="absolute")
rules.all=apriori(Groceries, parameter = list(supp = 0.001, conf = 0.8))
##
## Parameter specification:
## confidence minval smax arem aval originalSupport support minlen maxlen
## 0.8 0.1 1 none FALSE TRUE 0.001 1 10
## target ext
## rules FALSE
##
## Algorithmic control:
## filter tree heap memopt load sort verbose
## 0.1 TRUE TRUE FALSE TRUE 2 TRUE
##
## apriori - find association rules with the apriori algorithm
## version 4.21 (2004.05.09) (c) 1996-2004 Christian Borgelt
## set item appearances ...[0 item(s)] done [0.00s].
## set transactions ...[169 item(s), 9835 transaction(s)] done [0.01s].
## sorting and recoding items ... [157 item(s)] done [0.00s].
## creating transaction tree ... done [0.01s].
## checking subsets of size 1 2 3 4 5 6 done [0.07s].
## writing ... [410 rule(s)] done [0.01s].
## creating S4 object ... done [0.01s].
inspect(rules.all[1:5])
## lhs rhs support confidence lift
## 1 {liquor,
## red/blush wine} => {bottled beer} 0.001931876 0.9047619 11.235269
## 2 {curd,
## cereals} => {whole milk} 0.001016777 0.9090909 3.557863
## 3 {yogurt,
## cereals} => {whole milk} 0.001728521 0.8095238 3.168192
## 4 {butter,
## jam} => {whole milk} 0.001016777 0.8333333 3.261374
## 5 {soups,
## bottled beer} => {whole milk} 0.001118454 0.9166667 3.587512
plot(rules.all[1:5],method="graph",interactive = F)
plot(rules.all[1:15],method="graph",interactive = T)
library(ggplot2)
data(diamonds)
head(diamonds)
## carat cut color clarity depth table price x y z
## 1 0.23 Ideal E SI2 61.5 55 326 3.95 3.98 2.43
## 2 0.21 Premium E SI1 59.8 61 326 3.89 3.84 2.31
## 3 0.23 Good E VS1 56.9 65 327 4.05 4.07 2.31
## 4 0.29 Premium I VS2 62.4 58 334 4.20 4.23 2.63
## 5 0.31 Good J SI2 63.3 58 335 4.34 4.35 2.75
## 6 0.24 Very Good J VVS2 62.8 57 336 3.94 3.96 2.48
diamonds2=diamonds[c("carat","price")]
clus=kmeans(diamonds2,7)
summary(clus)
## Length Class Mode
## cluster 53940 -none- numeric
## centers 14 -none- numeric
## totss 1 -none- numeric
## withinss 7 -none- numeric
## tot.withinss 1 -none- numeric
## betweenss 1 -none- numeric
## size 7 -none- numeric
## iter 1 -none- numeric
## ifault 1 -none- numeric
table(clus$cluster)
##
## 1 2 3 4 5 6 7
## 1821 8902 2452 20698 5337 3366 11364
plot(diamonds2$carat,diamonds2$price,col=clus$cluster)
library(rpart, quietly=TRUE)
library(rattle)
## Loading required package: RGtk2
## Rattle: A free graphical interface for data mining with R.
## Version 3.5.0 Copyright (c) 2006-2015 Togaware Pty Ltd.
## Type 'rattle()' to shake, rattle, and roll your data.
data("weather")
minsplit=10
treemodel <- rpart(RainTomorrow ~ .,
,data=weather)
asRules(treemodel)
##
## Rule number: 3 [RainTomorrow=Yes cover=66 (18%) prob=1.00]
## RISK_MM>=1.1
##
## Rule number: 2 [RainTomorrow=No cover=300 (82%) prob=0.00]
## RISK_MM< 1.1
library(rpart.plot)
fancyRpartPlot(treemodel, main="Decision Tree weather $ RainTomorrow")
