python - 如何在 Linux 上的 Python 中对该表进行排序

Question

这个问题已经有答案了:

Need help to sort processed mdb file in Python on Linux machine (1 个回答)

已关闭 10 年前。

import sys, subprocess, glob

mdbfiles = glob.glob('*.res')
for DATABASE in mdbfiles: 

    subprocess.call(["mdb-schema", DATABASE, "mysql"])

    table_names = subprocess.Popen(["mdb-tables", "-1", DATABASE],
                                   stdout=subprocess.PIPE).communicate()[0]
    tables = table_names.splitlines()

    sys.stdout.flush()

    a=str('Channel_Normal_Table')

    for table in tables:
        if table != '' and table==a:

            filename = DATABASE.replace(".res","") + ".csv"
            file = open(filename, 'w')
            print("Dumping " + table)
            contents = subprocess.Popen(["mdb-export", DATABASE, table],
                                        stdout=subprocess.PIPE).communicate()[0]

            # I NEED TO PUT SOMETHING HERE TO SORT AND EXTRACT THE DATA I NEED


            file.write(contents)
            file.close()

我有一个从数据库中提取的表。我们称之为table 。我需要执行以下操作，但有点卡住了:

Cycle Test_Time  Current    Voltage
1     7.80E-002 0.00E+000   1.21E-001
1     3.01E+001 0.00E+000   1.19E-001
1     6.02E+001 0.00E+000   1.17E-001
2     9.02E+001 0.00E+000   1.14E-001
2     1.20E+002 0.00E+000   1.11E-001
2     1.50E+002 0.00E+000   1.08E-001
2     1.80E+002 0.00E+000   1.05E-001
2     2.10E+002 0.00E+000   1.02E-001
3     2.40E+002 0.00E+000   9.93E-002
3     2.70E+002 0.00E+000   9.66E-002
3     3.00E+002 0.00E+000   9.38E-002
3     3.10E+002 4.00E-001   1.26E+000

1. 提取每个周期的最后(最新)行，或者更高级的是，对周期进行排序按时间并提取具有最新时间的周期的行。作为你可以看到，最后一行并不总是最新的时间，因为我们的测试机会出现故障，但通常都会出现。但越大时间越晚编号。
2. 提取最近五个周期的所有行
3. 提取从周期 4 到周期 30 的所有行。

我尝试了各种方法，例如根据我有限的 Python 知识创建和排序字典和列表，但没有一个得到所需的输出。这简直让我发疯。非常感谢!

Answer 1

这并不难，但你必须一步一步来:

from collections import defaultdict

table = """\
Cycle Test_Time  Current    Voltage
1     7.80E-002 0.00E+000   1.21E-001
1     3.01E+001 0.00E+000   1.19E-001
1     6.02E+001 0.00E+000   1.17E-001
2     9.02E+001 0.00E+000   1.14E-001
2     1.20E+002 0.00E+000   1.11E-001
2     1.50E+002 0.00E+000   1.08E-001
2     1.80E+002 0.00E+000   1.05E-001
2     2.10E+002 0.00E+000   1.02E-001
3     2.40E+002 0.00E+000   9.93E-002
3     2.70E+002 0.00E+000   9.66E-002
3     3.00E+002 0.00E+000   9.38E-002
3     3.10E+002 4.00E-001   1.26E+000"""

# Split into rows
table = table.splitlines()

# Split each row into values
table = [row.split() for row in table]

# Associate the column names with their index
headers = table.pop(0)
H = {x: i for i, x in enumerate(headers)}
time_index = H["Test_Time"]
cycle_index = H["Cycle"]

# Sort by Test_Time
table.sort(key=lambda row: float(row[time_index]))

# Associate each test with its cycle
D = defaultdict(list)
for row in table:
  D[int(row[cycle_index])].append(row)

# Present the information
print(*headers, sep='\t')
print("Latest row for each cycle")
for cycle in sorted(D.keys()):
  tests = D[cycle]
  latest_test = tests[-1]
  print(*latest_test, sep='\t')

print("All rows for last 5 cycles")
for cycle in sorted(D.keys())[-5:]:
  tests = D[cycle]
  for test in tests:
    print(*test, sep='\t')

print("All rows for cycles 4 through 30")
for cycle in sorted(D.keys()):
    if 4 <= cycle <= 30:
      tests = D[cycle]
      for test in tests:
        print(*test, sep='\t')