wednesday.Rmd

---
title: "Wdnesday_Chapter4"
author: "Luca Mannino"
date: "21/09/2022"
output: html_document
---

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

```{r}
library(nycflights13)
library(tidyverse)
```
```{r}
library(tidyverse)
library(nycflights13)
by_dest <- group_by(flights, dest)
delay <- summarise(by_dest,
                   count = n(),
                   dist = mean(distance, na.rm = TRUE),
                   delay = mean(arr_delay, na.rm = TRUE)
)
#> `summarise()` ungrouping output (override with `.groups` argument)
delay <- filter(delay, count > 20, dest != "HNL")# It looks like delays increase with distance up to ~750 miles
# and then decrease. Maybe as flights get longer there's more
# ability to make up delays in the air?
ggplot(data = delay, mapping = aes(x = dist, y = delay)) +
  geom_point(aes(size = count), alpha = 1/3) +
  geom_smooth(se = FALSE)
#> `geom_smooth()` using method = 'loess' and formula 'y ~ x'count(flights, dest)
flights %>%
  group_by(dest) %>%
  summarise(n = n())
class(flights)
daily <- group_by(flights, year, month, day)
class(daily)
(per_day   <- summarise(daily, flights = n(), .groups = "keep"))
flights_rowwise <- flights %>%
  rowwise()
microbenchmark::microbenchmark(
  mutate(flights_rowwise, arr_time2 = arr_time + 1),
  mutate(flights, arr_time2 = arr_time + 1),
  times = 5)
mutate(flights_rowwise, arr_time2 = arr_time + 1) %>%
  ungroup()
```

```{r}
not_cancelled <- flights %>% 
  filter(!is.na(dep_delay), !is.na(arr_delay))

not_cancelled %>% 
  group_by(year, month, day) %>% 
  summarise(mean = mean(dep_delay))
```


delays <- not_cancelled %>% 
  group_by(tailnum) %>% 
  summarise(
    delay = mean(arr_delay)
  )
#> `summarise()` ungrouping output (override with `.groups` argument)

ggplot(data = delays, mapping = aes(x = delay)) + 
  geom_freqpoly(binwidth = 10)
```{r}
delays <- not_cancelled %>% 
  group_by(tailnum) %>% 
  summarise(
    delay = mean(arr_delay)
  )
#> `summarise()` ungrouping output (override with `.groups` argument)

ggplot(data = delays, mapping = aes(x = delay)) + 
  geom_freqpoly(binwidth = 10)
```
  Brainstorm at least 5 different ways to assess the typical delay characteristics of a group of flights. Consider the following scenarios:

    A flight is 15 minutes early 50% of the time, and 15 minutes late 50% of the time.

    A flight is always 10 minutes late.

    A flight is 30 minutes early 50% of the time, and 30 minutes late 50% of the time.

    99% of the time a flight is on time. 1% of the time it’s 2 hours late.

```{r}
class(flights)
?flights


flights %>% 
  group_by(flight) %>% 
  summarise(med_delay = median(arr_delay, na.rm=TRUE)) %>% 
  filter(med_delay <= -15)

flights %>% 
  group_by(flight) %>% 
  summarise(prop_delay = mean(arr_delay, na.rm=TRUE)) %>% 
  filter(prop_delay <= -15)
```
```{r}
flights %>%
  group_by(flight) %>%
  summarise(prop_very_early = mean(arr_delay <= -15, na.rm = TRUE),
            n = n()) %>%
  filter(prop_very_early >= 0.5, n >= 20) %>%
  arrange(desc(prop_very_early))
```


```{r}
flights %>%
  group_by(flight) %>%
  summarise(prop_very_early = mean(arr_delay <= -15, na.rm = TRUE),
            n = n()) %>%
  filter(prop_very_early == 1) %>% 
  arrange(desc(n))
```
not_cancelled %>% count(dest) and not_cancelled %>% count(tailnum, wt = distance) (without using count())

```{r}
not_cancelled %>% count(dest)
```
wt = weighted sum
```{r}
not_cancelled %>%
  group_by(dest) %>% 
  summarise(destination = unique(dest)#, na.rm = TRUE),
            ,n = n())
not_cancelled %>%
  group_by(dest) %>% 
  summarise(n = n())
  
  
```

```{r}
not_cancelled %>% count(tailnum, wt = distance)
```
```{r}
not_cancelled %>%
  group_by(tailnum) %>% 
  summarise(destination = unique(dest)#, na.rm = TRUE),
            ,n = n())
```

```{r}
table(dep = is.na(flights$dep_delay), ar = is.na(flights$arr_delay))
```


```{r}
not_cancelled2 <- filter(flights, !is.na(arr_delay))
microbenchmark::microbenchmark(
any(is.na(not_cancelled2)),
anyNA(not_cancelled2),
times = 10)
```

```{r}
mean(complete.cases(not_cancelled2))
```


```{r}
table(dep = is.na(flights$dep_delay),
      arr = is.na(flights$arr_delay))
not_cancelled2 <- filter(flights, !is.na(arr_delay))
microbenchmark::microbenchmark(
  any(is.na(not_cancelled2)),
  anyNA(not_cancelled2),
  times = 10
)
mean(complete.cases(not_cancelled2))
flights %>%
  filter(., complete.cases(.))
f(x, y)
y %>% f(x, .)
```

```{r}
flights %>% 
  group_by(year, month, day) %>% 
  summarise(nb_canceled = sum(is.na(dep_delay)),
            n = n()) %>%
  arrange(desc(nb_canceled))
```

```{r}
flights %>%
  group_by(year, month, day) %>%
  summarize(prop_canceled = mean(is.na(dep_delay)),
            avg_delay = mean(dep_delay, na.rm = TRUE)) %>%
  ggplot(aes(prop_canceled, avg_delay)) +
  geom_point() +
  theme_bw(13) +
  geom_smooth()
```
sum depends on group operators don't

which plane has the worst on time regord
```{r}
flights %>% 
  group_by(tailnum) %>% 
  filter(sum(!is.na(arr_delay))>0) %>% 
  summarise(max_arr_delay = max(arr_delay, na.rm = TRUE)) %>% 
  arrange(tailnum)
```

```{r}
flights %>%
  group_by(tailnum) %>%
  filter(sum(!is.na(arr_delay)) > 0) %>%
  summarise(max_delay = max(arr_delay, na.rm = TRUE)) %>%
  arrange(desc(max_delay)) %>% 
  slice_max(max_delay, n = 1)
```

What time of day should you fly if you want to avoid delays as much as possible?



```{r}
flights %>% 
  group_by(hour) %>% 
  summarise(avg_delay = mean(arr_delay, na.rm=TRUE, n =n() %>% 
                               ggplot()))
```

```{r}

```
mutate join



```{r}
flights2 <- flights %>% 
  select(year:day, hour, origin, dest, tailnum, carrier)
flights2
```
airlines is anothe table
```{r}
flights2 %>%
  select(-origin, -dest) %>% 
  left_join(airlines, by = "carrier")
```


Compute the average delay by destination, then join on the airports data frame so you can show the spatial distribution of delays. Here’s an easy way to draw a map of the United States:




```{r} 
#should have added na.rm= true as shown in next snip
flights2 <- flights %>% 
  group_by(dest) %>% 
  filter(arr_delay>0) %>% 
  summarise(avg_arr_delay = mean(arr_delay))# %>% 
  #filter(avg_arr_delay > 0)

flights2

airports %>% 
  left_join(flights2, c("faa" = "dest"))


airports %>%
  semi_join(flights, c("faa" = "dest")) %>%
  left_join(flights2,c("faa" = "dest"))%>%
  ggplot(aes(lon, lat)) +
    borders("state") +
    geom_point(aes(size=avg_arr_delay)) +
    #scale_color_viridis_c()+
    coord_quickmap()

```
remmber na.rm = true
```{r}
avg_delay_per_dest <- flights %>%
  group_by(dest) %>%
  summarize(avg_delay = mean(arr_delay, na.rm = TRUE)) %>%
  print()
avg_delay_per_dest %>%
  left_join(airports, by = c("dest" = "faa")) %>%
  ggplot(aes(lon, lat, size = avg_delay, color = avg_delay)) +
  borders("state") +
  geom_point() +
  coord_quickmap() +
  theme_bw(13) +
  scale_color_viridis_c(direction = -1)
```




```{r}
flights %>%
  left_join(select(airports, c(faa, lat, lon)),
            by = c("dest" = "faa")) %>%
  left_join(select(airports, c(faa, lat, lon)),
            by = c("origin" = "faa"),  suffix = c("_dest", "_origin"))

```



```{r}

```