NLP100本ノック2章のシェル

chap2.py

# -*- coding:utf-8 -*- 

def main():
    print(chap10())
    print(chap11())
    chap12()
    chap13()

def chap10():
    with open("./hightemp.txt", "r") as fin:
        return len([line for line in fin])

def chap11():
    with open("./hightemp.txt", "r") as fin:
        replaced = (line.replace("\t", " ").rstrip() for line in fin)
        return "\n".join(replaced)

def chap12():
    with open("./hightemp.txt", "r") as fin, open("./col1.txt", "w") as fout1, open("./col2.txt", "\w") as fout2:
        for line in fin:
            elems = line.rstrip().split()
            col1 = elems[0]
            col2 = elems[1]

            fout1.write(col1 + "\n")
            fout2.write(col2 + "\n")

def chap13():
    with open("./col1.txt", "r") as fin1, open("./col2.txt", "r") as fin2:
        for col1, col2 in zip(fin1, fin2):
            print(col1.rstrip(), col2.rstrip(), sep="\t")

if __name__ == "__main__":
    main()

gistfile1.sh

echo "10.行数のカウント"
wc -l hightemp.txt

echo "11.タブをスペース置換"
cat hightemp.txt | tr "\t" " "

echo "12.1列目をcol1.txtに，2列目をcol2.txtに保存"
cat hightemp.txt | cut -f1 > col1.txt && cat hightemp.txt | cut -f2 > col2.txt

echo "13.col1.txtとcol2.txtをマージ"
paste col1.txt col2.txt

echo "14. 先頭からN行を出力"
cat hightemp.txt|head -3

echo "15. 末尾のN行を出力"
cat hightemp.txt|tail -3

echo "16. ファイルをN分割する"
split hightemp.txt -n 3

echo "17. １列目の文字列の異なり"
cat hightemp.txt | cut -f1 | sort -u

echo "18. 各行を3コラム目の数値の降順にソート"
cat hightemp.txt | sort -nrk3

echo "19. 各行の1コラム目の文字列の出現頻度を求め，出現頻度の高い順に並べる"
cat hightemp.txt|cut -f1|sort|uniq -c|sort -nrk1