read in the file
cacao <- read.csv("flavors_of_cacao.csv")
str(cacao)
## 'data.frame': 1795 obs. of 9 variables:
## $ Company...Maker.if.known. : chr "A. Morin" "A. Morin" "A. Morin" "A. Morin" ...
## $ Specific.Bean.Origin.or.Bar.Name: chr "Agua Grande" "Kpime" "Atsane" "Akata" ...
## $ REF : int 1876 1676 1676 1680 1704 1315 1315 1315 1319 1319 ...
## $ Review.Date : int 2016 2015 2015 2015 2015 2014 2014 2014 2014 2014 ...
## $ Cocoa.Percent : chr "63%" "70%" "70%" "70%" ...
## $ Company.Location : chr "France" "France" "France" "France" ...
## $ Rating : num 3.75 2.75 3 3.5 3.5 2.75 3.5 3.5 3.75 4 ...
## $ Bean.Type : chr " " " " " " " " ...
## $ Broad.Bean.Origin : chr "Sao Tome" "Togo" "Togo" "Togo" ...
cacao1 <- read.delim("flavors_of_cacao.txt")
summary(cacao)
## Company...Maker.if.known. Specific.Bean.Origin.or.Bar.Name REF
## Length:1795 Length:1795 Min. : 5
## Class :character Class :character 1st Qu.: 576
## Mode :character Mode :character Median :1069
## Mean :1036
## 3rd Qu.:1502
## Max. :1952
## Review.Date Cocoa.Percent Company.Location Rating
## Min. :2006 Length:1795 Length:1795 Min. :1.000
## 1st Qu.:2010 Class :character Class :character 1st Qu.:2.875
## Median :2013 Mode :character Mode :character Median :3.250
## Mean :2012 Mean :3.186
## 3rd Qu.:2015 3rd Qu.:3.500
## Max. :2017 Max. :5.000
## Bean.Type Broad.Bean.Origin
## Length:1795 Length:1795
## Class :character Class :character
## Mode :character Mode :character
##
##
##
summarize the data
summary(cacao)
## Company...Maker.if.known. Specific.Bean.Origin.or.Bar.Name REF
## Length:1795 Length:1795 Min. : 5
## Class :character Class :character 1st Qu.: 576
## Mode :character Mode :character Median :1069
## Mean :1036
## 3rd Qu.:1502
## Max. :1952
## Review.Date Cocoa.Percent Company.Location Rating
## Min. :2006 Length:1795 Length:1795 Min. :1.000
## 1st Qu.:2010 Class :character Class :character 1st Qu.:2.875
## Median :2013 Mode :character Mode :character Median :3.250
## Mean :2012 Mean :3.186
## 3rd Qu.:2015 3rd Qu.:3.500
## Max. :2017 Max. :5.000
## Bean.Type Broad.Bean.Origin
## Length:1795 Length:1795
## Class :character Class :character
## Mode :character Mode :character
##
##
##
preview the data
head(cacao, 10)
## Company...Maker.if.known. Specific.Bean.Origin.or.Bar.Name REF Review.Date
## 1 A. Morin Agua Grande 1876 2016
## 2 A. Morin Kpime 1676 2015
## 3 A. Morin Atsane 1676 2015
## 4 A. Morin Akata 1680 2015
## 5 A. Morin Quilla 1704 2015
## 6 A. Morin Carenero 1315 2014
## 7 A. Morin Cuba 1315 2014
## 8 A. Morin Sur del Lago 1315 2014
## 9 A. Morin Puerto Cabello 1319 2014
## 10 A. Morin Pablino 1319 2014
## Cocoa.Percent Company.Location Rating Bean.Type Broad.Bean.Origin
## 1 63% France 3.75 Sao Tome
## 2 70% France 2.75 Togo
## 3 70% France 3.00 Togo
## 4 70% France 3.50 Togo
## 5 70% France 3.50 Peru
## 6 70% France 2.75 Criollo Venezuela
## 7 70% France 3.50 Cuba
## 8 70% France 3.50 Criollo Venezuela
## 9 70% France 3.75 Criollo Venezuela
## 10 70% France 4.00 Peru
tail(cacao)
## Company...Maker.if.known. Specific.Bean.Origin.or.Bar.Name REF Review.Date
## 1790 Zotter Indianer, Raw 883 2012
## 1791 Zotter Peru 647 2011
## 1792 Zotter Congo 749 2011
## 1793 Zotter Kerala State 749 2011
## 1794 Zotter Kerala State 781 2011
## 1795 Zotter Brazil, Mitzi Blue 486 2010
## Cocoa.Percent Company.Location Rating Bean.Type Broad.Bean.Origin
## 1790 58% Austria 3.50
## 1791 70% Austria 3.75 Peru
## 1792 65% Austria 3.00 Forastero Congo
## 1793 65% Austria 3.50 Forastero India
## 1794 62% Austria 3.25 India
## 1795 65% Austria 3.00 Brazil
create a contingency table
sort(table(cacao$Company.Location), decreasing=TRUE)
##
## U.S.A. France Canada U.K.
## 764 156 125 96
## Italy Ecuador Australia Belgium
## 63 54 49 40
## Switzerland Germany Austria Spain
## 38 35 26 25
## Colombia Hungary Venezuela Brazil
## 23 22 20 17
## Japan Madagascar New Zealand Peru
## 17 17 17 17
## Denmark Vietnam Guatemala Scotland
## 15 11 10 10
## Argentina Costa Rica Israel Poland
## 9 9 9 8
## Honduras Lithuania Domincan Republic Nicaragua
## 6 6 5 5
## South Korea Sweden Amsterdam Fiji
## 5 5 4 4
## Ireland Mexico Netherlands Puerto Rico
## 4 4 4 4
## Sao Tome Grenada Iceland Portugal
## 4 3 3 3
## Singapore South Africa Bolivia Chile
## 3 3 2 2
## Finland St. Lucia Czech Republic Eucador
## 2 2 1 1
## Ghana India Martinique Niacragua
## 1 1 1 1
## Philippines Russia Suriname Wales
## 1 1 1 1
Indexing
cacao[8,]
## Company...Maker.if.known. Specific.Bean.Origin.or.Bar.Name REF Review.Date
## 8 A. Morin Sur del Lago 1315 2014
## Cocoa.Percent Company.Location Rating Bean.Type Broad.Bean.Origin
## 8 70% France 3.5 Criollo Venezuela
cacao[8,9]
## [1] "Venezuela"
Subsetting