Question

我有一个防火墙日志文件，其中包括日期，小时，src_address，dest_address和all_attemps，max_byte，avg_byte和活动率。我想删除不包含的行。（点）在src_address columnin r这是我的文件;

    src_address  dest_address all_attemps max_byte avg_byte activity_rate
    2       1.11.201.19 172.16.16.100           1       60       60   0.005434783
    3       1.119.43.90 172.16.16.100           1       60       60   0.005434783
    4       1.119.43.90 172.16.16.153           1       60       60   0.005434783
    5       1.119.43.90 192.168.1.112           1       60       60   0.005434783
    6      1.171.43.133   172.16.16.5           2       52       48   0.010869565
    7      1.179.191.82   172.16.16.5           1       60       60   0.005434783
    8      1.179.191.82 192.168.1.111           2       60       60   0.010869565
    9      1.179.191.82 192.168.1.112           2       60       60   0.010869565
    10     1.180.72.186 172.16.16.153           2       60       60   0.010869565
    11     1.202.165.40 172.16.16.153           1       60       60   0.005434783
    12      1.203.84.52   172.16.16.5           1       60       60   0.005434783
    13      1.203.84.52 192.168.1.112           1       60       60   0.005434783
    14      1.209.171.4 192.168.1.111           1       60       60   0.005434783
    15     1.214.34.114 172.16.16.100           2       60       60   0.010869565
    16     1.214.34.114 172.16.16.153           2       60       60   0.010869565
    37   101.53.137.245   172.16.16.5           2       60       60   0.010869565
    47     101100148143 192.168.1.111           2       60       60   0.010869565
    48     101100148143 192.168.1.112           2       60       60   0.010869565
    49     101231185170 172.16.16.100           1       60       60   0.005434783
    50     101231185170 172.16.16.153           1       60       60   0.005434783
    51     101231185170 192.168.1.112           1       60       60   0.005434783
    52     103.1.94.102 192.168.1.112           1       52       52   0.005434783
    53   103.12.195.158   172.16.16.5           1       52       52   0.005434783

这是我的期望;

         src_address  dest_address all_attemps max_byte avg_byte activity_rate
2       1.11.201.19 172.16.16.100           1       60       60   0.005434783
3       1.119.43.90 172.16.16.100           1       60       60   0.005434783
4       1.119.43.90 172.16.16.153           1       60       60   0.005434783
5       1.119.43.90 192.168.1.112           1       60       60   0.005434783
6      1.171.43.133   172.16.16.5           2       52       48   0.010869565
7      1.179.191.82   172.16.16.5           1       60       60   0.005434783
8      1.179.191.82 192.168.1.111           2       60       60   0.010869565
9      1.179.191.82 192.168.1.112           2       60       60   0.010869565
10     1.180.72.186 172.16.16.153           2       60       60   0.010869565
11     1.202.165.40 172.16.16.153           1       60       60   0.005434783
12      1.203.84.52   172.16.16.5           1       60       60   0.005434783
13      1.203.84.52 192.168.1.112           1       60       60   0.005434783
14      1.209.171.4 192.168.1.111           1       60       60   0.005434783
15     1.214.34.114 172.16.16.100           2       60       60   0.010869565
16     1.214.34.114 172.16.16.153           2       60       60   0.010869565
37   101.53.137.245   172.16.16.5           2       60       60   0.010869565
52     103.1.94.102 192.168.1.112           1       52       52   0.005434783
53   103.12.195.158   172.16.16.5           1       52       52   0.005434783

Answer 1

我们可以在这里使用grepl作为基本R选项：

df <- df[grepl("\\.", df$src_address), ]

Answer 2

您可以使用stringi执行类似的操作：

library(stringi)
df[stri_detect_fixed(df$src_address, "."),]

或者如果你想使用grepl，你可以使用fixed = TRUE，这样你就不需要逃避＆＃34;。＆＃34;：

df[grepl(".", df$src_address, fixed = TRUE), ]

数据：

df <- structure(list(src_address = c("1.11.201.19", "1.119.43.90", "1.119.43.90", "1.119.43.90", "1.171.43.133", "1.179.191.82", "1.179.191.82", "1.179.191.82", "1.180.72.186", "1.202.165.40", "1.203.84.52", "1.203.84.52", "1.209.171.4", "1.214.34.114", "1.214.34.114", "101.53.137.245", "101100148143", "101100148143", "101231185170", "101231185170", "101231185170", "103.1.94.102", "103.12.195.158"), dest_address = c("172.16.16.100", "172.16.16.100", "172.16.16.153", "192.168.1.112", "172.16.16.5", "172.16.16.5", "192.168.1.111", "192.168.1.112", "172.16.16.153", "172.16.16.153", "172.16.16.5", "192.168.1.112", "192.168.1.111", "172.16.16.100", "172.16.16.153", "172.16.16.5", "192.168.1.111", "192.168.1.112", "172.16.16.100", "172.16.16.153", "192.168.1.112", "192.168.1.112", "172.16.16.5"), all_attemps = c(1L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L), max_byte = c(60L, 60L, 60L, 60L, 52L, 60L, 60L, 60L, 60L, 60L, 60L, 60L, 60L, 60L, 60L, 60L, 60L, 60L, 60L, 60L, 60L, 52L, 52L), avg_byte = c(60L, 60L, 60L, 60L, 48L, 60L, 60L, 60L, 60L, 60L, 60L, 60L, 60L, 60L, 60L, 60L, 60L, 60L, 60L, 60L, 60L, 52L, 52L), activity_rate = c(0.005434783, 0.005434783, 0.005434783, 0.005434783, 0.010869565, 0.005434783, 0.010869565, 0.010869565, 0.010869565, 0.005434783, 0.005434783, 0.005434783, 0.005434783, 0.010869565, 0.010869565, 0.010869565, 0.010869565, 0.010869565, 0.005434783, 0.005434783, 0.005434783, 0.005434783, 0.005434783)), .Names = c("src_address", "dest_address", "all_attemps", "max_byte", "avg_byte", "activity_rate"), row.names = c(NA, -23L), class = "data.frame")

Answer 3

非常接近@Mike H.回答。

在stringr包中有一个很好的函数（str_detect）也可能有用：

library(stringr)
df[str_detect(df$src_address, "\\."), ]

使用R删除特定变量中不包含。（点）的行

3 个答案: