Introduction

In this assigment, I will briefly look at the “İzmir Fish Market Prices” data and try to make short inferences.

Let’s start

Installation of the package we need and the dataset we will be working with.

library(tidyverse)
hal <- read.csv("balik_hal_fiyatlari.csv",sep=';',fileEncoding = "utf-8")

Data Exploration

First 6 rows of the data

head(hal)

Structure of the data

str(hal)

Data type of TARIH columns is “character”. We need to change it to the “date” type to work with.

hal$TARIH <- as.Date(hal$TARIH)

Price Comparison of Deniz Çipurası vs. Kültür Çipurası

Deniz Çipurası

Monthly distribution of deniz çipurası price

denizcip <- hal %>% 
filter(MAL_TURU == "BALIK", MAL_ADI == "ÇIPURA (DENİZ)") %>%
mutate(avgdcipd = (ASGARI_UCRET + AZAMI_UCRET)/2) %>%
group_by(MAL_ADI,AY = lubridate::month(TARIH)) %>%
summarise(avgdcipm = mean(avgdcipd))

d_ay <- unique(denizcip$AY) 

ggplot(denizcip, aes(d_ay, avgdcipm)) + geom_line() +  scale_x_discrete(label = c("January", "February", "March", "April", "May", "June", "July", "August", "September", "October"), "Months", limits=c(1:10))

Kültür Çipurası

Monthly distribution of kültür çipurası price

kulturcip <- hal %>% 
filter(MAL_TURU == "KÜLTÜR", MAL_ADI == "ÇİPURA ( KÜLTÜR )") %>%
mutate(avgkcipd = (ASGARI_UCRET + AZAMI_UCRET)/2) %>%
group_by(MAL_ADI,AY = lubridate::month(TARIH)) %>%
summarise(avgkcipm = mean(avgkcipd))


k_ay <- unique(kulturcip$AY) 

ggplot(kulturcip, aes(k_ay, avgkcipm)) + geom_line() +  scale_x_discrete(label = c("January", "February", "March", "April", "May", "June", "July", "August", "September", "October"), "Months", limits=c(1:10))

Findinds

February is the best month to eat both deniz çipurası and kültür çipurası for cheap.

The average price of deniz çipurası is higher than the average price of kültür çipurası throughout the year.