datatypes.Rmd

---
title: "**Data Types R Notebook**"
output: html_notebook
---

# Data Types

```{r}
library(tidyverse)
library(nycflights13)

dataset = flights %>% 
  mutate( monthFactor = factor(month),
          big4 = ifelse(carrier %in% c("UA","AA","DL","WN"), T, F),
          air_time= air_time - 0.05)
```



```{r}
summary(dataset$tailnum)
dataset$tailnum[1:20]
```

```{r}
summary(dataset$arr_time)
dataset$arr_time[1:20]

```


```{r}
summary(dataset$big4)
dataset$big4[1:20]

```


```{r factors}
summary(dataset$monthFactor)
dataset$monthFactor[1:10]

```


```{r}
str(dataset$month) # makes less sense 
summary(dataset$month)

```


forcats

## datetimes
POSIXct is the class name
```{r}
str(dataset$time_hour) # seconds 

```
lubridate package makes dates easier to work with
```{r}
as.POSIXct(dataset$time_hour, tz= "EST")[1:4]

as.POSIXlt(dataset$time_hour, tz= "GMT")[1:4]
```


```{r}
is.character(4)
is.character("4")
as.character(4) # turns 4 into char
```



structures - atomic vectors 
```{r}
vectorChar = c('char1','char2','char3')
vectorNum = c(1,2,3)
vectorChar
vectorNum
```

matrix - same data type
```{r}

matrixChar = matrix( c("1","2","3","4"), nrow = 2, ncol = 2)
matrixChar

```

```{r}
matrxNum = matrix( c(1:24), nrow = 3, ncol = 8)
matrxNum
```

slice matrix
```{r}

matrxNum[1,] # row
matrxNum[,3] # column 
```


Dataframes 
```{r}

dfEx = data.frame(dataset)
dfEx[1:10]
```


arrays  (2x3) matrices * 4
```{r}
array(matrxNum, dim =  c(2,3,4), dimnames = list( c('row1','row2'),
      c('col1', 'col2','col3'),
      c('matrix1','matrix2', 'matrix3','matrix4')))

```

tibbles 
```{r}
dataset[1:20]  # tidyverse Tibble

```


list 
```{r}
list1 = list(3, TRUE, as.factor(1))
list2 = list(flights, dataset)
list3 = list(1, 4, flights )
list4 = list(list1, list2, list3)
```