training/135-datatable.Rmd at master · bi-sdal/training · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
# data.table

```{r}
library(data.table)
library(nycflights13)
```

## Read into data.table

```{r, eval=FALSE}
data.table::fread()
```


## Convert to data.table

```{r}
flights <- as.data.table(flights)
```

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

## Working with data.table

DT[i, j, k]
DT[filter by row, calculations on columns, groupby variable]

"Take DT, subset rows using i, perfrom calulations with j, groupby k"


```{r}
flights[month == 11]
```


```{r}
flights[month == 11 | month == 12]
```

```{r}
flights[month %in% c(11, 12)]
```

```{r}
flights[, arr_delay]
```

### Select columns list() .()
```{r}
flights[, list(arr_delay)]
```


```{r}
flights[, list(arr_delay, dep_delay)]
```

using `list()` is exactly ths same as using `.()`

```{r}
flights[, .(arr_delay, dep_delay)]
```

### Functions on columns

```{r}
flights[, sum((arr_delay + dep_delay), na.rm = TRUE)]
```

```{r}
flights[origin == "JFK" & month == 6,
        .(m_arr = mean(arr_delay, na.rm = TRUE),
          m_dep = mean(dep_delay, na.rm = TRUE))]
```

```{r}
flights[origin == "JFK" & month == 6,.(m_arr = mean(arr_delay, na.rm = TRUE), m_dep = mean(dep_delay, na.rm = TRUE))]
```

### .N (counts)

```{r}
flights[origin == 'JFK' & month == 6, .N]
```


### Using dplyr

```{r}
library(dplyr)
```


```{r}
flights %>%
    filter(origin == 'JFK', month == 6) %>%
    summarize(count = n())
```

```{r}
flights[, .N, by = origin]
```


```{r}
flights[, .N, origin]
```

```{r}
flights %>%
    group_by(origin) %>%
    summarize(count = n())
```