Lab 3

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  
##  N.unique :  154   1st Qu.:1.100   1st Qu.:  15733   N.unique :    2  
##  N.blank  :    0   Median :1.320   Median :  94806   N.blank  :    0  
##  Min.nchar:    8   Mean   :1.359   Mean   : 325259   Min.nchar:    7  
##  Max.nchar:   10   3rd Qu.:1.570   3rd Qu.: 430222   Max.nchar:   12  
##                    Max.   :2.780   Max.   :5660216                    
##       year          geography        Mileage    
##  Min.   :2017   Length   :12628   Min.   : 111  
##  1st Qu.:2018   N.unique :   41   1st Qu.:1097  
##  Median :2019   N.blank  :    0   Median :2193  
##  Mean   :2019   Min.nchar:    5   Mean   :1911  
##  3rd Qu.:2020   Max.nchar:   20   3rd Qu.:2632  
##  Max.   :2020                     Max.   :2998

## DataViz
library(ggplot2)

ggplot(data, aes(x=average_price)) +
  geom_histogram(binwidth=10, fill="green")

ggplot(data, aes(x=date, y=average_price)) + 
  geom_point() + 
  geom_smooth() + 
  ggtitle("average_price as a function of date")

## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'