Session1_Titanic_Follow_along.Rmd

---
title: "Session1_Titanic_Follow_along"
author: "Lauren Yee"
date: "13/07/2020"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
library(tidyverse)
```

#Example Data

##Titanic Data Set

```{r read, echo=FALSE, warning=FALSE, message=FALSE}
titanic<-read_csv("./Raw Data/titanic.csv")

```


```{r DT, echo=FALSE,out.width="50%",fig.align='center'}

knitr::kable(head(titanic),'html')

```


## `filter` to select a subset of rows

## passengers who were 35 years old

```{r, echo=TRUE, out.width="75%"}
titanic %>%
  filter(Age == 35) #<<
```

## `filter` for many conditions at once

## Age is 35 and Sex is female

```{r, echo=TRUE, out.width="75%"}
titanic %>%
  filter(Age == 35, Sex=="female")#<<
```
]



operator    | definition                   || operator     | definition
------------|------------------------------||--------------|----------------
`<`         | less than                    ||`x`&nbsp;&#124;&nbsp;`y`     | `x` OR `y` 
`<=`        |	less than or equal to        ||`is.na(x)`    | test if `x` is `NA`
`>`         | greater than                 ||`!is.na(x)`   | test if `x` is not `NA`
`>=`        |	greater than or equal to     ||`x %in% y`    | test if `x` is in `y`
`==`        |	exactly equal to             ||`!(x %in% y)` | test if `x` is not in `y`
`!=`        |	not equal to                 ||`!x`          | not `x`
`x & y`     | `x` AND `y`                  ||              |



## `select` to keep variables



```{r, echo=TRUE}
titanic %>%
  filter(Age == 35, Sex=="female")%>%
  select(Name, Sex, Age, Fare)#<<
```


## `select` to exclude variables

```{r, echo=TRUE}
titanic %>%
  select(-Embarked)
```


## `select` a range of variables


```{r, echo=TRUE}
titanic %>%
  select(PassengerId:Name)
```


## `slice` for certain row numbers

##First five
```{r, echo=TRUE}
titanic %>%
  slice(1:5)
```


## `slice` for certain row numbers

##Last five
```{r, echo=TRUE}
last_row <- nrow(titanic)
titanic %>%
  slice((last_row - 4):last_row)
```


## `pull` to extract a column as a vector

```{r, echo=TRUE}
titanic %>%
  slice(1:6) %>%
  pull(Fare)
```

##vs.

```{r, echo=TRUE}
titanic %>%
  slice(1:6) %>%
  select(Fare)
```



## `sample_n` / `sample_frac` for a random sample

## - `sample_n`: randomly sample 5 observations

```{r, echo=TRUE}
titanic_n5 <- titanic %>%
  sample_n(5, replace = FALSE)
dim(titanic_n5)
```

## - `sample_frac`: randomly sample 20% of observations

```{r, echo=TRUE}
titanic_perc20 <-titanic %>%
  sample_frac(0.2, replace = FALSE)
dim(titanic_perc20)
```

---
class: bg-main3 black

## `distinct` to filter for unique rows

##And `arrange` to order alphabetically

```{r, echo=TRUE}
titanic %>% 
  select(Pclass, Fare) %>% 
  distinct() %>% 
  arrange(Fare, Pclass)
```



## `summarise` to reduce variables to values

```{r, echo=TRUE}
titanic %>%
  summarise(avg_fare = mean(Fare,na.rm=T))
```


## `group_by` to do calculations on groups

```{r, echo=TRUE}
titanic %>%
  group_by(Sex) %>%
  summarize(avg_fare = mean(Fare,na.rm=T))
```


## `count` observations in groups

```{r, echo=TRUE}
titanic %>%
  count(Sex)
```

```{r, echo=TRUE}
titanic %>%
  count(Survived)
```