Sélectionner des lignes aléatoires dans un fichier

Question

Dans un script de Bash, je veux extraire N lignes aléatoires du fichier d'entrée et les sortir dans un autre fichier.

Comment cela peut-il être fait ?

Answer 1

# 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"