以下是一个答案:
-
使用Python正则表达式语法解析ID(处理带有或不带连字符的情况,如果需要,可以调整以适应历史ID的其他特性)
-
将ID设置为正规格式
-
为ID组件添加列
-
基于ID组件进行排序,以便将行“分组”在一起(尽管不是熊猫的“groupby”意思)
import pandas as pd
df = pd.DataFrame({'BinLocation':['A0233B21', 'A02033B21', 'A02-033-B21', 'A02-33-B21', 'A02-33-B15', 'A02-30-B21', 'A01-33-B21']})
print(df)
print()
df['RawBinLocation'] = df['BinLocation']
import re
def parse(s):
m = re.match('^([A-Z])([0-9]{2})-?([0-9]+)-?([A-Z])([0-9]{2})$', s)
if not m:
return None
tup = m.groups()
colChar, colInt, rowInt, levelChar, levelInt = tup[0], int(tup[1]), int(tup[2]), tup[3], int(tup[4])
tup = (colChar, colInt, rowInt, levelChar, levelInt)
return pd.Series(tup)
df[['ColChar', 'ColInt', 'RowInt', 'LevChar', 'LevInt']] = df['BinLocation'].apply(parse)
df['BinLocation'] = df.apply(lambda x: f"{x.ColChar}{x.ColInt:02}-{x.RowInt:03}-{x.LevChar}{x.LevInt:02}", axis=1)
df.sort_values(by=['ColChar', 'ColInt', 'RowInt', 'LevChar', 'LevInt'], inplace=True, ignore_index=True)
print(df)
输出:
BinLocation
0 A0233B21
1 A02033B21
2 A02-033-B21
3 A02-33-B21
4 A02-33-B15
5 A02-30-B21
6 A01-33-B21
BinLocation RawBinLocation ColChar ColInt RowInt LevChar LevInt
0 A01-033-B21 A01-33-B21 A 1 33 B 21
1 A02-030-B21 A02-30-B21 A 2 30 B 21
2 A02-033-B15 A02-33-B15 A 2 33 B 15
3 A02-033-B21 A0233B21 A 2 33 B 21
4 A02-033-B21 A02033B21 A 2 33 B 21
5 A02-033-B21 A02-033-B21 A 2 33 B 21
6 A02-033-B21 A02-33-B21 A 2 33 B 21