我的首选是非常快的，我采样了一个以制表符分隔的数据文件，它有13列，23.1万行，2.0GB未压缩。

# randomly sample select 5% of lines in file
# including header row, exclude blank lines, new seed

time \
awk 'BEGIN  {srand()} 
     !/^$/  { if (rand() <= .05 || FNR==1) print > "data-sample.txt"}' data.txt

# awk  tsv004  3.76s user 1.46s system 91% cpu 5.716 total

只是为了完整起见，因为它可以从Arch的社区repos中获得:还有一个名为shuffle的工具，但它没有任何命令行开关来限制行数，并在手册页中警告:“由于shuffle将输入读取到内存中，它可能会在非常大的文件上失败。”

下面的“c”是要从输入中选择的行数。根据需要修改:

#!/bin/sh

gawk '
BEGIN   { srand(); c = 5 }
c/NR >= rand() { lines[x++ % c] = $0 }
END { for (i in lines)  print lines[i] }

' "$@"

# Function to sample N lines randomly from a file
# Parameter $1: Name of the original file
# Parameter $2: N lines to be sampled 
rand_line_sampler() {
    N_t=$(awk '{print $1}' $1 | wc -l) # Number of total lines

    N_t_m_d=$(( $N_t - $2 - 1 )) # Number oftotal lines minus desired number of lines

    N_d_m_1=$(( $2 - 1)) # Number of desired lines minus 1

    # vector to have the 0 (fail) with size of N_t_m_d 
    echo '0' > vector_0.temp
    for i in $(seq 1 1 $N_t_m_d); do
            echo "0" >> vector_0.temp
    done

    # vector to have the 1 (success) with size of desired number of lines
    echo '1' > vector_1.temp
    for i in $(seq 1 1 $N_d_m_1); do
            echo "1" >> vector_1.temp
    done

    cat vector_1.temp vector_0.temp | shuf > rand_vector.temp

    paste -d" " rand_vector.temp $1 |
    awk '$1 != 0 {$1=""; print}' |
    sed 's/^ *//' > sampled_file.txt # file with the sampled lines

    rm vector_0.temp vector_1.temp rand_vector.temp
}

rand_line_sampler "parameter_1" "parameter_2"

seq 1 100 | python3 -c 'print(__import__("random").choice(__import__("sys").stdin.readlines()))'

我的首选是非常快的，我采样了一个以制表符分隔的数据文件，它有13列，23.1万行，2.0GB未压缩。

# randomly sample select 5% of lines in file
# including header row, exclude blank lines, new seed

time \
awk 'BEGIN  {srand()} 
     !/^$/  { if (rand() <= .05 || FNR==1) print > "data-sample.txt"}' data.txt

# awk  tsv004  3.76s user 1.46s system 91% cpu 5.716 total