这是名单：
x = ["111,222","111.222","111,222.11","111.222,11","111111","111.22"]
我希望它能在不使用语言环境的情况下正确转换，并且能与上面的集合一起工作，因为原始数据集是一团糟
我试过了
正则表达式
float("".join(["".join([i for i in list(s)[0:-3] if i not in [".",","]]),"".join(list(s)[-3:]).replace(",",".")]) if list(s)[-3] in [".",","] else "".join(list(s)))r = re.sub('[^0-9]', '', s) export = float(r[0:-2]+'.'+r[-2:]) comma = ","
dot = "."
last_comma_index = s.rfind(comma)
last_dot_index = s.rfind(dot)
if last_comma_index > last_dot_index:
last_index = last_comma_index
else:
last_index = last_dot_index
before_point = s[:last_index]
no_commas = "".join(before_point.split(comma))
no_dots = "".join(no_commas.split(dot))
export = no_dots + dot + s[last_index + 1:]
s = "".join(c for c in s if c.isdigit() or c in [",", "."])
if "," in s:
decimal_sep = ","
thousands_sep = "."
else:
decimal_sep = "."
thousands_sep = ","
s = s.replace(decimal_sep, ".")
s = re.sub(f"\\{thousands_sep}(?=[0-9])", "", s)
export = s
def parseNumber(text):
try:
# First we return None if we don't have something in the text:
if text is None:
return None
if isinstance(text, int) or isinstance(text, float):
return text
text = text.strip()
if text == "":
return None
# Next we get the first "[0-9,. ]+":
n = re.search("-?[0-9]*([,. ]?[0-9]+)+", text).group(0)
n = n.strip()
if not re.match(".*[0-9]+.*", text):
return None
# Then we cut to keep only 2 symbols:
while " " in n and "," in n and "." in n:
index = max(n.rfind(','), n.rfind(' '), n.rfind('.'))
n = n[0:index]
n = n.strip()
# We count the number of symbols:
symbolsCount = 0
for current in [" ", ",", "."]:
if current in n:
symbolsCount += 1
# If we don't have any symbol, we do nothing:
if symbolsCount == 0:
pass
# With one symbol:
elif symbolsCount == 1:
# If this is a space, we just remove all:
if " " in n:
n = n.replace(" ", "")
# Else we set it as a "." if one occurence, or remove it:
else:
theSymbol = "," if "," in n else "."
if n.count(theSymbol) > 1:
n = n.replace(theSymbol, "")
else:
n = n.replace(theSymbol, ".")
else:
# Now replace symbols so the right symbol is "." and all left are "":
rightSymbolIndex = max(n.rfind(','), n.rfind(' '), n.rfind('.'))
rightSymbol = n[rightSymbolIndex:rightSymbolIndex+1]
if rightSymbol == " ":
return parseNumber(n.replace(" ", "_"))
n = n.replace(rightSymbol, "R")
leftSymbolIndex = max(n.rfind(','), n.rfind(' '), n.rfind('.'))
leftSymbol = n[leftSymbolIndex:leftSymbolIndex+1]
n = n.replace(leftSymbol, "L")
n = n.replace("L", "")
n = n.replace("R", ".")
# And we cast the text to float or int:
n = float(n)
if n > 5000000:
return 0
elif n.is_integer():
return int(n)
else:
return n
except: pass
return None
十进制
现场
结果应该是这样的：
x = [111222,111222,111222.11,111222.11,111111,111.22]
期待任何建议。