import io
import pandas as pd
file_path = "fwf.txt"
widths = [len("# Column1 "), len("Column2")]
names = ["Column1", "Column2"]
class FileLike(io.TextIOBase):
def __init__(self, iterable):
self.iterable = iterable
def readline(self):
return next(self.iterable)
with open(file_path, 'r') as f:
lines = (line for line in f if line.strip())
data = pd.read_fwf(FileLike(lines), widths=widths, names=names,
comment='#')
print(data)
prints
Column1 Column2
0 123 abc
1 456 def
with open(file_path, 'r') as f:
lines = (line for line in f if line.strip())
定义一个生成器表达式(即一个可迭代的),它产生
文件中删除了空行的行。
The pd.read_fwf
函数可以接受TextIOBase
对象。你可以子类化TextIOBase
以便其readline
方法从可迭代对象返回行:
class FileLike(io.TextIOBase):
def __init__(self, iterable):
self.iterable = iterable
def readline(self):
return next(self.iterable)
将这两者放在一起为您提供了一种操作/修改文件行的方法
在将它们传递给之前pd.read_fwf
.