我需要将
one1two2有没有办法通过图书馆或课程或其他东西来做到这一点？
此代码的大部分内容是设置 numwords 字典，这仅在第一次调用时完成。
def text2int(textnum, numwords={}):
if not numwords:
units = [
"zero", "one", "two", "three", "four", "five", "six", "seven", "eight",
"nine", "ten", "eleven", "twelve", "thirteen", "fourteen", "fifteen",
"sixteen", "seventeen", "eighteen", "nineteen",
]
tens = ["", "", "twenty", "thirty", "forty", "fifty", "sixty", "seventy", "eighty", "ninety"]
scales = ["hundred", "thousand", "million", "billion", "trillion"]
numwords["and"] = (1, 0)
for idx, word in enumerate(units): numwords[word] = (1, idx)
for idx, word in enumerate(tens): numwords[word] = (1, idx * 10)
for idx, word in enumerate(scales): numwords[word] = (10 ** (idx * 3 or 2), 0)
current = result = 0
for word in textnum.split():
if word not in numwords:
raise Exception("Illegal word: " + word)
scale, increment = numwords[word]
current = current * scale + increment
if scale > 100:
result += current
current = 0
return result + current
print text2int("seven billion one hundred million thirty one thousand three hundred thirty seven")
#7100031337
为了确切的目的，我刚刚向 PyPI 发布了一个名为 word2number 的 python 模块。 https://github.com/akshaynagpal/w2n
使用以下方法安装：
pip install word2number
确保您的pip已更新至最新版本。
用途：
from word2number import w2n
print w2n.word_to_num("two million three thousand nine hundred and eighty four")
2003984
我需要一些不同的东西，因为我的输入来自语音到文本的转换，并且解决方案并不总是对数字求和。例如，“我的邮政编码是一二三四五”不应转换为“我的邮政编码是 15”。
我采用了 Andrew 的 answer 并对其进行了调整，以处理人们突出显示为错误的其他一些情况，并且还添加了对我上面提到的邮政编码等示例的支持。下面显示了一些基本的测试用例，但我确信仍有改进的空间。
def is_number(x):
if type(x) == str:
x = x.replace(',', '')
try:
float(x)
except:
return False
return True
def text2int (textnum, numwords={}):
units = [
'zero', 'one', 'two', 'three', 'four', 'five', 'six', 'seven', 'eight',
'nine', 'ten', 'eleven', 'twelve', 'thirteen', 'fourteen', 'fifteen',
'sixteen', 'seventeen', 'eighteen', 'nineteen',
]
tens = ['', '', 'twenty', 'thirty', 'forty', 'fifty', 'sixty', 'seventy', 'eighty', 'ninety']
scales = ['hundred', 'thousand', 'million', 'billion', 'trillion']
ordinal_words = {'first':1, 'second':2, 'third':3, 'fifth':5, 'eighth':8, 'ninth':9, 'twelfth':12}
ordinal_endings = [('ieth', 'y'), ('th', '')]
if not numwords:
numwords['and'] = (1, 0)
for idx, word in enumerate(units): numwords[word] = (1, idx)
for idx, word in enumerate(tens): numwords[word] = (1, idx * 10)
for idx, word in enumerate(scales): numwords[word] = (10 ** (idx * 3 or 2), 0)
textnum = textnum.replace('-', ' ')
current = result = 0
curstring = ''
onnumber = False
lastunit = False
lastscale = False
def is_numword(x):
if is_number(x):
return True
if word in numwords:
return True
return False
def from_numword(x):
if is_number(x):
scale = 0
increment = int(x.replace(',', ''))
return scale, increment
return numwords[x]
for word in textnum.split():
if word in ordinal_words:
scale, increment = (1, ordinal_words[word])
current = current * scale + increment
if scale > 100:
result += current
current = 0
onnumber = True
lastunit = False
lastscale = False
else:
for ending, replacement in ordinal_endings:
if word.endswith(ending):
word = "%s%s" % (word[:-len(ending)], replacement)
if (not is_numword(word)) or (word == 'and' and not lastscale):
if onnumber:
# Flush the current number we are building
curstring += repr(result + current) + " "
curstring += word + " "
result = current = 0
onnumber = False
lastunit = False
lastscale = False
else:
scale, increment = from_numword(word)
onnumber = True
if lastunit and (word not in scales):
# Assume this is part of a string of individual numbers to
# be flushed, such as a zipcode "one two three four five"
curstring += repr(result + current)
result = current = 0
if scale > 1:
current = max(1, current)
current = current * scale + increment
if scale > 100:
result += current
current = 0
lastscale = False
lastunit = False
if word in scales:
lastscale = True
elif word in units:
lastunit = True
if onnumber:
curstring += repr(result + current)
return curstring
一些测试...
one two three -> 123
three forty five -> 345
three and forty five -> 3 and 45
three hundred and forty five -> 345
three hundred -> 300
twenty five hundred -> 2500
three thousand and six -> 3006
three thousand six -> 3006
nineteenth -> 19
twentieth -> 20
first -> 1
my zip is one two three four five -> my zip is 12345
nineteen ninety six -> 1996
fifty-seventh -> 57
one million -> 1000000
first hundred -> 100
I will buy the first thousand -> I will buy the 1000 # probably should leave ordinal in the string
thousand -> 1000
hundred and six -> 106
1 million -> 1000000
如果有人感兴趣，我编写了一个保留字符串其余部分的版本（尽管它可能有错误，但没有对其进行太多测试）。
def text2int (textnum, numwords={}):
if not numwords:
units = [
"zero", "one", "two", "three", "four", "five", "six", "seven", "eight",
"nine", "ten", "eleven", "twelve", "thirteen", "fourteen", "fifteen",
"sixteen", "seventeen", "eighteen", "nineteen",
]
tens = ["", "", "twenty", "thirty", "forty", "fifty", "sixty", "seventy", "eighty", "ninety"]
scales = ["hundred", "thousand", "million", "billion", "trillion"]
numwords["and"] = (1, 0)
for idx, word in enumerate(units): numwords[word] = (1, idx)
for idx, word in enumerate(tens): numwords[word] = (1, idx * 10)
for idx, word in enumerate(scales): numwords[word] = (10 ** (idx * 3 or 2), 0)
ordinal_words = {'first':1, 'second':2, 'third':3, 'fifth':5, 'eighth':8, 'ninth':9, 'twelfth':12}
ordinal_endings = [('ieth', 'y'), ('th', '')]
textnum = textnum.replace('-', ' ')
current = result = 0
curstring = ""
onnumber = False
for word in textnum.split():
if word in ordinal_words:
scale, increment = (1, ordinal_words[word])
current = current * scale + increment
if scale > 100:
result += current
current = 0
onnumber = True
else:
for ending, replacement in ordinal_endings:
if word.endswith(ending):
word = "%s%s" % (word[:-len(ending)], replacement)
if word not in numwords:
if onnumber:
curstring += repr(result + current) + " "
curstring += word + " "
result = current = 0
onnumber = False
else:
scale, increment = numwords[word]
current = current * scale + increment
if scale > 100:
result += current
current = 0
onnumber = True
if onnumber:
curstring += repr(result + current)
return curstring
示例：
>>> text2int("I want fifty five hot dogs for two hundred dollars.")
I want 55 hot dogs for 200 dollars.
如果您有“200 美元”，则可能会出现问题。但是，这真的很粗糙。
我需要处理一些额外的解析情况，例如序数词（“第一”、“第二”）、连字符词（“一百”）和连字符序数词（如“第五十七”），所以我添加了几行：
def text2int(textnum, numwords={}):
if not numwords:
units = [
"zero", "one", "two", "three", "four", "five", "six", "seven", "eight",
"nine", "ten", "eleven", "twelve", "thirteen", "fourteen", "fifteen",
"sixteen", "seventeen", "eighteen", "nineteen",
]
tens = ["", "", "twenty", "thirty", "forty", "fifty", "sixty", "seventy", "eighty", "ninety"]
scales = ["hundred", "thousand", "million", "billion", "trillion"]
numwords["and"] = (1, 0)
for idx, word in enumerate(units): numwords[word] = (1, idx)
for idx, word in enumerate(tens): numwords[word] = (1, idx * 10)
for idx, word in enumerate(scales): numwords[word] = (10 ** (idx * 3 or 2), 0)
ordinal_words = {'first':1, 'second':2, 'third':3, 'fifth':5, 'eighth':8, 'ninth':9, 'twelfth':12}
ordinal_endings = [('ieth', 'y'), ('th', '')]
textnum = textnum.replace('-', ' ')
current = result = 0
for word in textnum.split():
if word in ordinal_words:
scale, increment = (1, ordinal_words[word])
else:
for ending, replacement in ordinal_endings:
if word.endswith(ending):
word = "%s%s" % (word[:-len(ending)], replacement)
if word not in numwords:
raise Exception("Illegal word: " + word)
scale, increment = numwords[word]
current = current * scale + increment
if scale > 100:
result += current
current = 0
return result + current`
这是简单案例的方法：
>>> number = {'one':1,
... 'two':2,
... 'three':3,}
>>>
>>> number['two']
2
或者您正在寻找可以处理“一万二千，一百七十二”的东西？
def parse_int(string):
ONES = {'zero': 0,
'one': 1,
'two': 2,
'three': 3,
'four': 4,
'five': 5,
'six': 6,
'seven': 7,
'eight': 8,
'nine': 9,
'ten': 10,
'eleven': 11,
'twelve': 12,
'thirteen': 13,
'fourteen': 14,
'fifteen': 15,
'sixteen': 16,
'seventeen': 17,
'eighteen': 18,
'nineteen': 19,
'twenty': 20,
'thirty': 30,
'forty': 40,
'fifty': 50,
'sixty': 60,
'seventy': 70,
'eighty': 80,
'ninety': 90,
}
numbers = []
for token in string.replace('-', ' ').split(' '):
if token in ONES:
numbers.append(ONES[token])
elif token == 'hundred':
numbers[-1] *= 100
elif token == 'thousand':
numbers = [x * 1000 for x in numbers]
elif token == 'million':
numbers = [x * 1000000 for x in numbers]
return sum(numbers)
使用 1 到 100 万范围内的 700 个随机数进行测试，效果良好。
使用Python包：WordToDigits
pip install wordtodigits
它可以找到句子中以单词形式出现的数字，然后将其转换为正确的数字格式。还处理小数部分（如果存在）。 数字的单词表示可以出现在段落中的任何位置。
如果您想要解析的数字数量有限，可以轻松将其硬编码到字典中。
对于稍微复杂的情况，您可能希望基于相对简单的数字语法自动生成此字典。类似的东西（当然，广义的......）
for i in range(10):
myDict[30 + i] = "thirty-" + singleDigitsDict[i]
如果您需要更广泛的东西，那么您似乎需要自然语言处理工具。 这篇文章可能是一个很好的起点。
进行了更改，以便 text2int(scale) 将返回正确的转换。例如，text2int("hunred") => 100。
import re
numwords = {}
def text2int(textnum):
if not numwords:
units = [ "zero", "one", "two", "three", "four", "five", "six",
"seven", "eight", "nine", "ten", "eleven", "twelve",
"thirteen", "fourteen", "fifteen", "sixteen", "seventeen",
"eighteen", "nineteen"]
tens = ["", "", "twenty", "thirty", "forty", "fifty", "sixty",
"seventy", "eighty", "ninety"]
scales = ["hundred", "thousand", "million", "billion", "trillion",
'quadrillion', 'quintillion', 'sexillion', 'septillion',
'octillion', 'nonillion', 'decillion' ]
numwords["and"] = (1, 0)
for idx, word in enumerate(units): numwords[word] = (1, idx)
for idx, word in enumerate(tens): numwords[word] = (1, idx * 10)
for idx, word in enumerate(scales): numwords[word] = (10 ** (idx * 3 or 2), 0)
ordinal_words = {'first':1, 'second':2, 'third':3, 'fifth':5,
'eighth':8, 'ninth':9, 'twelfth':12}
ordinal_endings = [('ieth', 'y'), ('th', '')]
current = result = 0
tokens = re.split(r"[\s-]+", textnum)
for word in tokens:
if word in ordinal_words:
scale, increment = (1, ordinal_words[word])
else:
for ending, replacement in ordinal_endings:
if word.endswith(ending):
word = "%s%s" % (word[:-len(ending)], replacement)
if word not in numwords:
raise Exception("Illegal word: " + word)
scale, increment = numwords[word]
if scale > 1:
current = max(1, current)
current = current * scale + increment
if scale > 100:
result += current
current = 0
return result + current
一个快速的解决方案是使用 inflect.py 生成用于翻译的字典。
inflect.py 有一个
number_to_words()2'two'>>> import inflect
>>> p = inflect.engine()
>>> word_to_number_mapping = {}
>>>
>>> for i in range(1, 100):
... word_form = p.number_to_words(i) # 1 -> 'one'
... word_to_number_mapping[word_form] = i
...
>>> print word_to_number_mapping['one']
1
>>> print word_to_number_mapping['eleven']
11
>>> print word_to_number_mapping['forty-three']
43
如果您愿意投入一些时间，也许可以检查 inflect.py 的
number_to_words()Marc Burns 的红宝石可以做到这一点。我最近分叉了它以增加多年来的支持。您可以从 python 调用 ruby 代码。
require 'numbers_in_words'
require 'numbers_in_words/duck_punch'
nums = ["fifteen sixteen", "eighty five sixteen", "nineteen ninety six",
"one hundred and seventy nine", "thirteen hundred", "nine thousand two hundred and ninety seven"]
nums.each {|n| p n; p n.in_numbers}
结果：
"fifteen sixteen"
1516
"eighty five sixteen"
8516
"nineteen ninety six"
1996
"one hundred and seventy nine"
179
"thirteen hundred"
1300
"nine thousand two hundred and ninety seven"
9297我一直在寻找一个库来帮助我支持所有上述以及更多边缘情况场景，例如序数（第一，第二），更大的数字，运算符等，我发现了这个numwords-to-nums
您可以通过安装
pip install numwords_to_nums
这是一个基本示例
from numwords_to_nums.numwords_to_nums import NumWordsToNum
num = NumWordsToNum()
result = num.numerical_words_to_numbers("twenty ten and twenty one")
print(result) # Output: 2010 and 21
eval_result = num.evaluate('Hey calculate 2+5')
print(eval_result) # Output: 7
result = num.numerical_words_to_numbers('first')
print(result) # Output: 1st
我采用了 @recursive 的 logic 并转换为 Ruby。我还对查找表进行了硬编码，因此它不是那么酷，但可能会帮助新手了解发生了什么。
WORDNUMS = {"zero"=> [1,0], "one"=> [1,1], "two"=> [1,2], "three"=> [1,3],
"four"=> [1,4], "five"=> [1,5], "six"=> [1,6], "seven"=> [1,7],
"eight"=> [1,8], "nine"=> [1,9], "ten"=> [1,10],
"eleven"=> [1,11], "twelve"=> [1,12], "thirteen"=> [1,13],
"fourteen"=> [1,14], "fifteen"=> [1,15], "sixteen"=> [1,16],
"seventeen"=> [1,17], "eighteen"=> [1,18], "nineteen"=> [1,19],
"twenty"=> [1,20], "thirty" => [1,30], "forty" => [1,40],
"fifty" => [1,50], "sixty" => [1,60], "seventy" => [1,70],
"eighty" => [1,80], "ninety" => [1,90],
"hundred" => [100,0], "thousand" => [1000,0],
"million" => [1000000, 0]}
def text_2_int(string)
numberWords = string.gsub('-', ' ').split(/ /) - %w{and}
current = result = 0
numberWords.each do |word|
scale, increment = WORDNUMS[word]
current = current * scale + increment
if scale > 100
result += current
current = 0
end
end
return result + current
end
我正在寻找处理像
two thousand one hundred and forty-six这可以处理印度风格单词中的数字、一些分数、数字和单词的组合以及加法。
def words_to_number(words):
numbers = {"zero":0, "a":1, "half":0.5, "quarter":0.25, "one":1,"two":2,
"three":3, "four":4,"five":5,"six":6,"seven":7,"eight":8,
"nine":9, "ten":10,"eleven":11,"twelve":12, "thirteen":13,
"fourteen":14, "fifteen":15,"sixteen":16,"seventeen":17,
"eighteen":18,"nineteen":19, "twenty":20,"thirty":30, "forty":40,
"fifty":50,"sixty":60,"seventy":70, "eighty":80,"ninety":90}
groups = {"hundred":100, "thousand":1_000,
"lac":1_00_000, "lakh":1_00_000,
"million":1_000_000, "crore":10**7,
"billion":10**9, "trillion":10**12}
split_at = ["and", "plus"]
n = 0
skip = False
words_array = words.split(" ")
for i, word in enumerate(words_array):
if not skip:
if word in groups:
n*= groups[word]
elif word in numbers:
n += numbers[word]
elif word in split_at:
skip = True
remaining = ' '.join(words_array[i+1:])
n+=words_to_number(remaining)
else:
try:
n += float(word)
except ValueError as e:
raise ValueError(f"Invalid word {word}") from e
return n
测试：
print(words_to_number("a million and one"))
>> 1000001
print(words_to_number("one crore and one"))
>> 1000,0001
print(words_to_number("0.5 million one"))
>> 500001.0
print(words_to_number("half million and one hundred"))
>> 500100.0
print(words_to_number("quarter"))
>> 0.25
print(words_to_number("one hundred plus one"))
>> 101
我发现更快的方法：
Da_Unità_a_Cifre = {'one': 1, 'two': 2, 'three': 3, 'four': 4, 'five': 5, 'six': 6, 'seven': 7, 'eight': 8, 'nine': 9, 'ten': 10, 'eleven': 11,
'twelve': 12, 'thirteen': 13, 'fourteen': 14, 'fifteen': 15, 'sixteen': 16, 'seventeen': 17, 'eighteen': 18, 'nineteen': 19}
Da_Lettere_a_Decine = {"tw": 20, "th": 30, "fo": 40, "fi": 50, "si": 60, "se": 70, "ei": 80, "ni": 90, }
elemento = input("insert the word:")
Val_Num = 0
try:
elemento.lower()
elemento.strip()
Unità = elemento[elemento.find("ty")+2:] # è uguale alla str: five
if elemento[-1] == "y":
Val_Num = int(Da_Lettere_a_Decine[elemento[0] + elemento[1]])
print(Val_Num)
elif elemento == "onehundred":
Val_Num = 100
print(Val_Num)
else:
Cifre_Unità = int(Da_Unità_a_Cifre[Unità])
Cifre_Decine = int(Da_Lettere_a_Decine[elemento[0] + elemento[1]])
Val_Num = int(Cifre_Decine + Cifre_Unità)
print(Val_Num)
except:
print("invalid input")
此代码适用于一系列数据：
import pandas as pd
mylist = pd.Series(['one','two','three'])
mylist1 = []
for x in range(len(mylist)):
mylist1.append(w2n.word_to_num(mylist[x]))
print(mylist1)
此代码仅适用于99以下的数字。无论是word到int还是int到word（其余的需要实现10-20行代码和简单的逻辑。这只是初学者的简单代码）：
num = input("Enter the number you want to convert : ")
mydict = {'1': 'One', '2': 'Two', '3': 'Three', '4': 'Four', '5': 'Five','6': 'Six', '7': 'Seven', '8': 'Eight', '9': 'Nine', '10': 'Ten','11': 'Eleven', '12': 'Twelve', '13': 'Thirteen', '14': 'Fourteen', '15': 'Fifteen', '16': 'Sixteen', '17': 'Seventeen', '18': 'Eighteen', '19': 'Nineteen'}
mydict2 = ['', '', 'Twenty', 'Thirty', 'Fourty', 'fifty', 'sixty', 'Seventy', 'Eighty', 'Ninty']
if num.isdigit():
if(int(num) < 20):
print(" :---> " + mydict[num])
else:
var1 = int(num) % 10
var2 = int(num) / 10
print(" :---> " + mydict2[int(var2)] + mydict[str(var1)])
else:
num = num.lower()
dict_w = {'one': 1, 'two': 2, 'three': 3, 'four': 4, 'five': 5, 'six': 6, 'seven': 7, 'eight': 8, 'nine': 9, 'ten': 10, 'eleven': 11, 'twelve': 12, 'thirteen': 13, 'fourteen': 14, 'fifteen': 15, 'sixteen': 16, 'seventeen': '17', 'eighteen': '18', 'nineteen': '19'}
mydict2 = ['', '', 'twenty', 'thirty', 'fourty', 'fifty', 'sixty', 'seventy', 'eighty', 'ninty']
divide = num[num.find("ty")+2:]
if num:
if(num in dict_w.keys()):
print(" :---> " + str(dict_w[num]))
elif divide == '' :
for i in range(0, len(mydict2)-1):
if mydict2[i] == num:
print(" :---> " + str(i * 10))
else :
str3 = 0
str1 = num[num.find("ty")+2:]
str2 = num[:-len(str1)]
for i in range(0, len(mydict2)):
if mydict2[i] == str2:
str3 = i
if str2 not in mydict2:
print("----->Invalid Input<-----")
else:
try:
print(" :---> " + str((str3*10) + dict_w[str1]))
except:
print("----->Invalid Input<-----")
else:
print("----->Please Enter Input<-----")