python操作txt文件中数据教程[2]-python提取txt文件

python操作txt文件中数据教程[2]-python提取txt文件中的行列元素

觉得有用的话,欢迎一起讨论相互学习~

我的微博我的github我的B站

  • 原始txt文件
  • 程序实现后结果-将txt中元素提取并保存在csv中

程序实现

import csv

filename = "./test/test.txt"
Sum_log_file = "./test/sumlog_test.csv"
Individual_log_file = "./test/Individual_test.csv"
DNA_log = []  # 精英种群个体日志mod9=1-8
Sum_log = []  # 精英种群总体日志mod9=0
DNA_Group = 7  # 表示每7条DNA组成一个组
# NO+'Sum 45.0 0.0 436.0 364.0 20.0\n'中属性一共6个属性,,则设为8列的二维数组
sum_evaindex = [[] for i in range(6)]
# 个体有8个属性,则设为8列的二维数组
Individual_evaindex = [[] for i in range(8)]

# 将txt中文件信息保存到Sum_log和DNA_log列表中
with open(filename, 'r') as f:
    i = 1
    for line in f.readlines():
        if i%9 == 0:
            Sum_log.append(line)
        else:
            DNA_log.append(line)
        i = i + 1
f.close()
# print(Sum_log)
# print(DNA_log)

# ['Sum 45.0 0.0 436.0 364.0 20.0\n', 'Sum 27.0 3.0 398.0 394.0 25.0\n', 'Sum 45.0 0.0 384.0 394.0 30.0']
# ['1\n', 'AAACAAGGAACAAACGCACA 18.0 0.0 58.0 50.0 52.5552 10.0\n', 'AAAGGACACAGTGAGAGACG 9.0 0.0 60.0 52.0 48.662 0.0\n',
#  'AGCCATTGTCGAGTCCGTTA 0.0 0.0 63.0 50.0 48.4427 0.0\n', 'GTGGTCACTCCTCGCAAATT 9.0 0.0 64.0 56.0 48.9881 0.0\n',
#  'TTCAACCATACAGGCCTCGT 0.0 0.0 63.0 53.0 48.9355 0.0\n', 'CAAATGTGAGGATTCGGACG 9.0 0.0 63.0 53.0 50.8708 0.0\n',
#  'CCGTGGTGAACTGGAGCGTT 0.0 0.0 65.0 50.0 44.924 10.0\n', '2\n', 'AAAGGACACAGTGAGAGACG 9.0 0.0 53.0 58.0 48.662 0.0\n',
#  'AGCCATTGTCGAGTCCGTTA 0.0 0.0 60.0 57.0 48.4427 0.0\n', 'CCACAACGCTCGAAGGCAAG 0.0 0.0 59.0 54.0 44.7269 10.0\n',
#  'AAGTACAGCGGGCCAATAGC 9.0 0.0 56.0 58.0 47.2114 5.0\n', 'CAAATGTGAGGATTCGGACG 9.0 0.0 59.0 53.0 50.8708 0.0\n',
#  'GAGAACGTTGAGTGAGCGTG 0.0 0.0 60.0 57.0 46.9033 5.0\n', 'GATGTTAAGTAGAGCAGAGG 0.0 3.0 51.0 57.0 52.383 5.0\n', '3\n',
#  'AAACAAGGAACAAACGCACA 18.0 0.0 45.0 57.0 52.5552 10.0\n', 'AAAGGACACAGTGAGAGACG 9.0 0.0 52.0 59.0 48.662 0.0\n',
#  'CCACAACGCTCGAAGGCAAG 0.0 0.0 52.0 60.0 44.7269 10.0\n', 'AAGTACAGCGGGCCAAGATC 9.0 0.0 54.0 56.0 46.8607 5.0\n',
#  'CTCAGAAGATCTCGATGGCT 0.0 0.0 63.0 53.0 47.5395 0.0\n', 'AGCCATTGTCGAGTCCGTTA 0.0 0.0 63.0 52.0 48.4427 0.0\n',
#  'TGCCGCAAACTACACACACG 9.0 0.0 55.0 57.0 47.45 5.0\n']

# 遍历行,并将列属性保存到对应列中
Sum_no = 1
for Sum in Sum_log:
    # print(Sum.split("\n")[0].split(" ")[1:])
    # ['45.0', '0.0', '436.0', '364.0', '20.0']
    # ['27.0', '3.0', '398.0', '394.0', '25.0']
    # ['45.0', '0.0', '384.0', '394.0', '30.0']
    sum_eva_index = Sum.split("\n")[0].split(" ")[1:]
    sum_evaindex[0].append(int(Sum_no))
    sum_evaindex[1].append(float(sum_eva_index[0]))  # Con
    sum_evaindex[2].append(float(sum_eva_index[1]))  # HP
    sum_evaindex[3].append(float(sum_eva_index[2]))  # Hm
    sum_evaindex[4].append(float(sum_eva_index[3]))  # Si
    sum_evaindex[5].append(float(sum_eva_index[4]))  # GC
    Sum_no = Sum_no + 1
# print(sum_evaindex[0])  # [45.0, 27.0, 45.0]


# 遍历个体信息,并将其保存到Individual_evaindex列表中
dna_log_no = 0
for dna_log in DNA_log:
    if (dna_log_no + 1)%8 == 1:
        # print(int(dna_log.split("\n")[0]))
        # 以列存储序号值,并且重复DNA_Group次
        for i in range(DNA_Group):
            Individual_evaindex[0].append(int(dna_log.split("\n")[0]))
    else:
        Individual_evaindex[1].append(dna_log.split("\n")[0].split(" ")[0])  # 所有DNA序列全部记载,使用原有的str字符串类型记载
        Individual_evaindex[2].append(float(dna_log.split("\n")[0].split(" ")[1]))  # DNA序列的连续值Con,注意要转换为浮点数类型
        Individual_evaindex[3].append(float(dna_log.split("\n")[0].split(" ")[2]))  # Hp茎区匹配
        Individual_evaindex[4].append(float(dna_log.split("\n")[0].split(" ")[3]))  # H-measure
        Individual_evaindex[5].append(float(dna_log.split("\n")[0].split(" ")[4]))  # Similarity
        Individual_evaindex[6].append(float(dna_log.split("\n")[0].split(" ")[5]))  # TM
        Individual_evaindex[7].append(float(dna_log.split("\n")[0].split(" ")[6]))  # GC

    dna_log_no = dna_log_no + 1
# print(Individual_evaindex[0]) #[1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 3, 3]
# print(Individual_evaindex[1])
# print(Individual_evaindex[2])
# print(Individual_evaindex[3])
# print(Individual_evaindex[4])
# print(Individual_evaindex[5])
# print(Individual_evaindex[6])
# print(Individual_evaindex[7])
# ['AAACAAGGAACAAACGCACA', 'AAAGGACACAGTGAGAGACG', 'AGCCATTGTCGAGTCCGTTA', 'GTGGTCACTCCTCGCAAATT', 'TTCAACCATACAGGCCTCGT',
#  'CAAATGTGAGGATTCGGACG', 'CCGTGGTGAACTGGAGCGTT', 'AAAGGACACAGTGAGAGACG', 'AGCCATTGTCGAGTCCGTTA', 'CCACAACGCTCGAAGGCAAG',
#  'AAGTACAGCGGGCCAATAGC', 'CAAATGTGAGGATTCGGACG', 'GAGAACGTTGAGTGAGCGTG', 'GATGTTAAGTAGAGCAGAGG', 'AAACAAGGAACAAACGCACA',
#  'AAAGGACACAGTGAGAGACG', 'CCACAACGCTCGAAGGCAAG', 'AAGTACAGCGGGCCAAGATC', 'CTCAGAAGATCTCGATGGCT', 'AGCCATTGTCGAGTCCGTTA',
#  'TGCCGCAAACTACACACACG']
# [18.0, 9.0, 0.0, 9.0, 0.0, 9.0, 0.0, 9.0, 0.0, 0.0, 9.0, 9.0, 0.0, 0.0, 18.0, 9.0, 0.0, 9.0, 0.0, 0.0, 9.0]
# [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 3.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0]
# [58.0, 60.0, 63.0, 64.0, 63.0, 63.0, 65.0, 53.0, 60.0, 59.0, 56.0, 59.0, 60.0, 51.0, 45.0, 52.0, 52.0, 54.0, 63.0, 63.0,
#  55.0]
# [50.0, 52.0, 50.0, 56.0, 53.0, 53.0, 50.0, 58.0, 57.0, 54.0, 58.0, 53.0, 57.0, 57.0, 57.0, 59.0, 60.0, 56.0, 53.0, 52.0,
#  57.0]
# [52.5552, 48.662, 48.4427, 48.9881, 48.9355, 50.8708, 44.924, 48.662, 48.4427, 44.7269, 47.2114, 50.8708, 46.9033,
#  52.383, 52.5552, 48.662, 44.7269, 46.8607, 47.5395, 48.4427, 47.45]
# [10.0, 0.0, 0.0, 0.0, 0.0, 0.0, 10.0, 0.0, 0.0, 10.0, 5.0, 0.0, 5.0, 5.0, 10.0, 0.0, 10.0, 5.0, 0.0, 0.0, 5.0]


Sum_log_file_header = ["No", "Continuity", "Hairpin", "H-measure", "Similarity", "GC"]
# 将数据写入csv日志文件中
with open(Sum_log_file, "w", newline='') as f:
    writer = csv.writer(f)
    writer.writerow(Sum_log_file_header)  # 注意,此处使用writerow而不是使用writerows
    for i in range(sum_evaindex[0][-1]):  # i 取(0,1,2)
        writer.writerow(
            [sum_evaindex[0][i], sum_evaindex[1][i], sum_evaindex[2][i], sum_evaindex[3][i], sum_evaindex[4][i],
             sum_evaindex[5][i]])
    f.close()
Individual_log_file_header = ["No", "DNAstructure", "Continuity", "Hairpin", "H-measure", "Similarity", "TM", "GC"]
with open(Individual_log_file, "w", newline='') as f:
    writer = csv.writer(f)
    writer.writerow(Individual_log_file_header)  # 注意,此处使用writerow而不是使用writerows
    for i in range(sum_evaindex[0][-1]*DNA_Group):
        writer.writerow(
            [Individual_evaindex[0][i], Individual_evaindex[1][i], Individual_evaindex[2][i], Individual_evaindex[3][i],
             Individual_evaindex[4][i], Individual_evaindex[5][i], Individual_evaindex[6][i],
             Individual_evaindex[7][i]])
    f.close()

测试版本

filename = "./test.txt"
DNA_log = []  # 精英种群个体日志mod9=2-8
Sum_log = []  # 精英种群总体日志mod9=0
Num_log = []  # 序号日志mod9=1
Num_int = []  # 截取序号为int类型
sum_evaindex = [[] for i in range(5)]
Individual_evaindex = [[] for i in range(8)]
with open(filename, 'r') as f:
    i = 1
    for line in f.readlines():
        if i%9 == 1:
            Num_log.append(line)
        elif i%9 == 0:
            Sum_log.append(line)
        else:
            DNA_log.append(line)
        i = i + 1
f.close()
print(Num_log)
print(Num_log[1])  # 其中存着的不是数字1,而是字符串'2\n',所以会有空行的情况
# ['1\n', '2\n', '3\n']
# 2
#
#
print(Sum_log)
print(DNA_log)

# ['Sum 45.0 0.0 436.0 364.0 20.0\n', 'Sum 27.0 3.0 398.0 394.0 25.0\n', 'Sum 45.0 0.0 384.0 394.0 30.0']
# ['AAACAAGGAACAAACGCACA 18.0 0.0 58.0 50.0 52.5552 10.0\n', 'AAAGGACACAGTGAGAGACG 9.0 0.0 60.0 52.0 48.662 0.0\n',
#  'AGCCATTGTCGAGTCCGTTA 0.0 0.0 63.0 50.0 48.4427 0.0\n', 'GTGGTCACTCCTCGCAAATT 9.0 0.0 64.0 56.0 48.9881 0.0\n',
#  'TTCAACCATACAGGCCTCGT 0.0 0.0 63.0 53.0 48.9355 0.0\n', 'CAAATGTGAGGATTCGGACG 9.0 0.0 63.0 53.0 50.8708 0.0\n',
#  'CCGTGGTGAACTGGAGCGTT 0.0 0.0 65.0 50.0 44.924 10.0\n', 'AAAGGACACAGTGAGAGACG 9.0 0.0 53.0 58.0 48.662 0.0\n',
#  'AGCCATTGTCGAGTCCGTTA 0.0 0.0 60.0 57.0 48.4427 0.0\n', 'CCACAACGCTCGAAGGCAAG 0.0 0.0 59.0 54.0 44.7269 10.0\n',
#  'AAGTACAGCGGGCCAATAGC 9.0 0.0 56.0 58.0 47.2114 5.0\n', 'CAAATGTGAGGATTCGGACG 9.0 0.0 59.0 53.0 50.8708 0.0\n',
#  'GAGAACGTTGAGTGAGCGTG 0.0 0.0 60.0 57.0 46.9033 5.0\n', 'GATGTTAAGTAGAGCAGAGG 0.0 3.0 51.0 57.0 52.383 5.0\n',
#  'AAACAAGGAACAAACGCACA 18.0 0.0 45.0 57.0 52.5552 10.0\n', 'AAAGGACACAGTGAGAGACG 9.0 0.0 52.0 59.0 48.662 0.0\n',
#  'CCACAACGCTCGAAGGCAAG 0.0 0.0 52.0 60.0 44.7269 10.0\n', 'AAGTACAGCGGGCCAAGATC 9.0 0.0 54.0 56.0 46.8607 5.0\n',
#  'CTCAGAAGATCTCGATGGCT 0.0 0.0 63.0 53.0 47.5395 0.0\n', 'AGCCATTGTCGAGTCCGTTA 0.0 0.0 63.0 52.0 48.4427 0.0\n',
#  'TGCCGCAAACTACACACACG 9.0 0.0 55.0 57.0 47.45 5.0\n']
for no in Num_log:
    # print(no[0])  # 字符形式的数字1,这是错的,因为有可能序号超过一位数
    # Num_int.append(int(no.split("\n"))) ['1', '']
    Num_int.append(int(no.split("\n")[0]))
for Sum in Sum_log:
    # print(Sum.split("\n")[0].split(" ")[1:])
    # ['45.0', '0.0', '436.0', '364.0', '20.0']
    # ['27.0', '3.0', '398.0', '394.0', '25.0']
    # ['45.0', '0.0', '384.0', '394.0', '30.0']
    sum_eva_index = Sum.split("\n")[0].split(" ")[1:]
    sum_evaindex[0].append(float(sum_eva_index[0]))
    sum_evaindex[1].append(float(sum_eva_index[1]))
    sum_evaindex[2].append(float(sum_eva_index[2]))
    sum_evaindex[3].append(float(sum_eva_index[3]))
    sum_evaindex[4].append(float(sum_eva_index[4]))
print(sum_evaindex[0])  # [45.0, 27.0, 45.0]

已标记关键词 清除标记
©️2020 CSDN 皮肤主题: 酷酷鲨 设计师:CSDN官方博客 返回首页