R Markdown

This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.

Note: this analysis was performed using the open source software R and Rstudio.

library(readr)
data <- read_csv('avocado.csv')
## Rows: 12628 Columns: 7
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (3): date, type, geography
## dbl (4): average_price, total_volume, year, Mileage
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
summary(data)
##      date           average_price    total_volume         type          
##  Length:12628       Min.   :0.500   Min.   :    253   Length:12628      
##  Class :character   1st Qu.:1.100   1st Qu.:  15733   Class :character  
##  Mode  :character   Median :1.320   Median :  94806   Mode  :character  
##                     Mean   :1.359   Mean   : 325259                     
##                     3rd Qu.:1.570   3rd Qu.: 430222                     
##                     Max.   :2.780   Max.   :5660216                     
##       year       geography            Mileage    
##  Min.   :2017   Length:12628       Min.   : 111  
##  1st Qu.:2018   Class :character   1st Qu.:1097  
##  Median :2019   Mode  :character   Median :2193  
##  Mean   :2019                      Mean   :1911  
##  3rd Qu.:2020                      3rd Qu.:2632  
##  Max.   :2020                      Max.   :2998
urlfile<-'https://raw.github.com/utjimmyx/resources/master/avocado_HAA.csv'
data<-read.csv(urlfile, fileEncoding="UTF-8-BOM")
summary(data)
##      date           average_price    total_volume         type          
##  Length:12628       Min.   :0.500   Min.   :    253   Length:12628      
##  Class :character   1st Qu.:1.100   1st Qu.:  15733   Class :character  
##  Mode  :character   Median :1.320   Median :  94806   Mode  :character  
##                     Mean   :1.359   Mean   : 325259                     
##                     3rd Qu.:1.570   3rd Qu.: 430222                     
##                     Max.   :2.780   Max.   :5660216                     
##       year       geography        
##  Min.   :2017   Length:12628      
##  1st Qu.:2018   Class :character  
##  Median :2019   Mode  :character  
##  Mean   :2019                     
##  3rd Qu.:2020                     
##  Max.   :2020
library(plyr)
str(data)
## 'data.frame':    12628 obs. of  6 variables:
##  $ date         : chr  "2017/12/3" "2017/12/3" "2017/12/3" "2017/12/3" ...
##  $ average_price: num  1.39 1.44 1.07 1.62 1.43 1.58 1.14 1.77 1.4 1.88 ...
##  $ total_volume : int  139970 3577 504933 10609 658939 38754 86646 1829 488588 21338 ...
##  $ type         : chr  "conventional" "organic" "conventional" "organic" ...
##  $ year         : int  2017 2017 2017 2017 2017 2017 2017 2017 2017 2017 ...
##  $ geography    : chr  "Albany" "Albany" "Atlanta" "Atlanta" ...
# Let's build a simple histogram
hist(data$average_price ,
     main = "Histogram of average_price",
     xlab = "Price in USD (US Dollar)")

library(ggplot2)
ggplot(data, aes(x = average_price, fill = type)) + 
  geom_histogram(bins = 30, col = "red") + 
  scale_fill_manual(values = c("purple", "pink")) +
  ggtitle("Frequency of Average Price - Oragnic vs. Conventional")

# Simple EFA with ggplot
ggplot() + 
  geom_col(data, mapping = aes(x = reorder(geography,total_volume), 
                               y = total_volume, fill = year )) +
  xlab("geography")+
  ylab("total_volume")+
  theme(axis.text.x = element_text(angle = 90, size = 7)) 

# Sample response for year 2017 - The plot shows that Los Angels has the highest amount of sales in 2017.