###FOOD PRICE INDEX DATA FOR NEW ZEALAND##
###ORIGINALLY THREE DATA SETS ##
##PACKAGES I LOAD EVERYTIME##
pacman::p_load(pacman,dplyr,GGally,ggplot2,ggthemes,ggvis,httr,lubridate,
shiny,rmarkdown,stringr,tidyr,psych,plotly,rio)
##CONVERTING EACH DATA INTO DATA CHUNKS FOR EASY USE##
##INDEX NUMBER CHUNK
chunkSize <- 10000
con <- file(description =("C:\\Users\\xholi\\OneDrive\\Desktop\\New folder\\index_number.csv") ,open = "r")
index_data <- read.table(con, nrows = chunkSize, header = T, fill = T, sep = ",")
close(con)
##SEASONALLY ADJUSTED CHUNK
chunkSize<- 10000
con1 <- file(description = ("C:\\Users\\xholi\\OneDrive\\Desktop\\New folder\\seasonally_Adj.csv"),open = "r")
seasonal_data <- read.table(con1, nrows = chunkSize,header = T,fill = T,sep = ",")
close(con1)
##WEIGHTED AVARAGE PRICES CHUNK##
chunkSize <- 10000
con2 <- file(description = ("C:\\Users\\xholi\\OneDrive\\Desktop\\New folder\\weighted_ava_price.csv"),open = "r")
weigthed_data <- read.table(con2, nrows = chunkSize ,header = T,fill = T,sep = ",")
close(con2)
X1 <- rbind(index_data,weigthed_data) ###ROW BINDING OF THE INDEX CHUNK DATA AND THE WEIGHTED CHUNK DATA##
summary(X1)
## Series_reference Period Data_value STATUS
## Length:20000 Min. :1960 Min. : 0.90 Length:20000
## Class :character 1st Qu.:2006 1st Qu.: 3.68 Class :character
## Mode :character Median :2011 Median : 45.22 Mode :character
## Mean :2009 Mean : 402.19
## 3rd Qu.:2016 3rd Qu.: 830.53
## Max. :2020 Max. :1200.00
## NA's :4
## UNITS Subject Group Series_title_1
## Length:20000 Length:20000 Length:20000 Length:20000
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
summary(seasonal_data)
## Series_reference Period Data_value STATUS
## Length:3544 Min. :1999 Min. : 624.0 Length:3544
## Class :character 1st Qu.:2009 1st Qu.: 860.0 Class :character
## Mode :character Median :2013 Median : 958.0 Mode :character
## Mean :2013 Mean : 929.6
## 3rd Qu.:2017 3rd Qu.:1005.0
## Max. :2020 Max. :1125.0
## NA's :3
## UNITS Subject Group Series_title_1
## Length:3544 Length:3544 Length:3544 Length:3544
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
##CONVERTING OUR VARIABLES TO FACTORS##
X1$Series_reference<-as.factor(X1$Series_reference)
X1$Period<-as.factor(X1$Period)
X1$Data_value<-as.factor(X1$Data_value)
X1$STATUS<-as.factor(X1$STATUS)
X1$UNITS<-as.factor(X1$UNITS)
X1$Subject<-as.factor(X1$Subject)
X1$Group<-as.factor(X1$Group)
X1$Series_title_1<-as.factor(X1$Series_title_1)
summary(X1)
## Series_reference Period Data_value STATUS
## CPIM.SE901 : 730 2014.07: 94 1000 : 56 FINAL:20000
## CPIM.SE9012 : 658 2014.08: 94 1.08 : 46
## CPIM.SE9012014: 502 2014.09: 94 2.57 : 39
## CPIM.SE901202 : 502 2014.1 : 94 2.86 : 38
## CPIM.SE9012011: 382 2014.11: 94 1.78 : 37
## CPIM.SE9012012: 382 2014.12: 94 (Other):19780
## (Other) :16844 (Other):19436 NA's : 4
## UNITS Subject
## Dollars:10000 Consumers Price Index - CPI:20000
## Index :10000
##
##
##
##
##
## Group
## Food Price Index for New Zealand : 730
## Food Price Index Level 2 Subgroups for New Zealand : 1386
## Food Price Index Level 3 Classes for New Zealand : 2815
## Food Price Index Level 4 Sections for New Zealand : 5069
## Food Price Index Selected Monthly Weighted Average Prices for New Zealand:10000
##
##
## Series_title_1
## Food : 730
## Meat, poultry and fish : 658
## Fish and other seafood : 502
## Poultry (fresh, chilled or frozen) : 502
## Beef and veal (fresh, chilled or frozen): 382
## Bread : 382
## (Other) :16844
par(mfrow=c(3,1)) ###converting parameters to hold 3 charts in one screen###
plot(X1$Group,col= "blue", xlab= "GROUP",
ylab="FPI:Monthly weighted avarage prices",
main= "FOOD PRICE INDEX PER GROUP")
plot(X1$Period, col="red",xlab="Period",
ylab="Frequency",
main="Period plot")
plot(X1$Data_value,col="green",xlab="Data values",
ylab="Frequency",
main="Data Values")
par(mfrow=c(1,1)) ##reverting the parameters back to normal##
plot(X1$Series_title_1)
describe(seasonal_data)
## vars n mean sd median trimmed mad min max
## Series_reference* 1 3544 10.27 5.88 10.00 10.25 7.41 1.00 20.0
## Period 2 3544 2012.93 4.44 2013.06 2013.01 5.87 1999.06 2020.1
## Data_value 3 3541 929.63 101.30 958.00 937.97 88.96 624.00 1125.0
## STATUS* 4 3544 1.99 0.07 2.00 2.00 0.00 1.00 2.0
## UNITS* 5 3544 1.00 0.00 1.00 1.00 0.00 1.00 1.0
## Subject* 6 3544 1.00 0.00 1.00 1.00 0.00 1.00 1.0
## Group* 7 3544 2.61 0.62 3.00 2.73 0.00 1.00 3.0
## Series_title_1* 8 3544 1.00 0.00 1.00 1.00 0.00 1.00 1.0
## range skew kurtosis se
## Series_reference* 19.00 0.01 -1.22 0.10
## Period 21.04 -0.20 -0.72 0.07
## Data_value 501.00 -0.71 -0.23 1.70
## STATUS* 1.00 -13.19 172.11 0.00
## UNITS* 0.00 NaN NaN 0.00
## Subject* 0.00 NaN NaN 0.00
## Group* 2.00 -1.34 0.67 0.01
## Series_title_1* 0.00 NaN NaN 0.00
seasonal_data$Group <-as.factor(seasonal_data$Group)
seasonal_data$Series_reference <-as.factor(seasonal_data$Series_reference)
seasonal_data$Period <-as.factor(seasonal_data$Period)
seasonal_data$Data_value <-as.factor(seasonal_data$Data_value)
seasonal_data$STATUS <-as.factor(seasonal_data$STATUS)
seasonal_data$Subject <-as.factor(seasonal_data$Subject)
seasonal_data$Series_title_1 <-as.factor(seasonal_data$Series_title_1)
##SEASONALLY ADJUSTED data##
plot(seasonal_data$Group,col="pink")
plot(seasonal_data$Period)
plot(seasonal_data$Data_value,xlab="Data values:in Dollars",ylab="Frequency")
