Is there a way to convert number words to Integers?
The majority of this code is to set up the numwords dict, which is only done on the first call.
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 + currentprint text2int("seven billion one hundred million thirty one thousand three hundred thirty seven")#7100031337
I have just released a python module to PyPI called word2number for the exact purpose. https://github.com/akshaynagpal/w2n
Install it using:
pip install word2number
make sure your pip is updated to the latest version.
Usage:
from word2number import w2nprint w2n.word_to_num("two million three thousand nine hundred and eighty four")2003984
If anyone is interested, I hacked up a version that maintains the rest of the string (though it may have bugs, haven't tested it too much).
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
Example:
>>> text2int("I want fifty five hot dogs for two hundred dollars.") I want 55 hot dogs for 200 dollars.
There could be issues if you have, say, "$200". But, this was really rough.