Is there a way to convert number words to Integers

Question

I need to convert one into 1, two into 2 and so on.

Is there a way to do this with a library or a class or anything?

Answer 1

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 w2n

print w2n.word_to_num("two million three thousand nine hundred and eighty four")
2003984

Answer 2

Thanks for the code snippet... saved me a lot of time!

I needed to handle a couple extra parsing cases, such as ordinal words ("first", "second"), hyphenated words ("one-hundred"), and hyphenated ordinal words like ("fifty-seventh"), so I added a couple lines:

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`

Answer 3

Made change so that text2int(scale) will return correct conversion. Eg, text2int("hundred") => 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

Answer 4

This is the c# implementation of the code in 1st answer:

public static double ConvertTextToNumber(string text)
{
    string[] units = new string[] {
        "zero", "one", "two", "three", "four", "five", "six", "seven", "eight",
        "nine", "ten", "eleven", "twelve", "thirteen", "fourteen", "fifteen",
        "sixteen", "seventeen", "eighteen", "nineteen",
    };

    string[] tens = new string[] {"", "", "twenty", "thirty", "forty", "fifty", "sixty", "seventy", "eighty", "ninety"};

    string[] scales = new string[] { "hundred", "thousand", "million", "billion", "trillion" };

    Dictionary<string, ScaleIncrementPair> numWord = new Dictionary<string, ScaleIncrementPair>();
    numWord.Add("and", new ScaleIncrementPair(1, 0));
    for (int i = 0; i < units.Length; i++)
    {
        numWord.Add(units[i], new ScaleIncrementPair(1, i));
    }

    for (int i = 1; i < tens.Length; i++)
    {
        numWord.Add(tens[i], new ScaleIncrementPair(1, i * 10));                
    }

    for (int i = 0; i < scales.Length; i++)
    {
        if(i == 0)
            numWord.Add(scales[i], new ScaleIncrementPair(100, 0));
        else
            numWord.Add(scales[i], new ScaleIncrementPair(Math.Pow(10, (i*3)), 0));
    }

    double current = 0;
    double result = 0;

    foreach (var word in text.Split(new char[] { ' ', '-', '—'}))
    {
        ScaleIncrementPair scaleIncrement = numWord[word];
        current = current * scaleIncrement.scale + scaleIncrement.increment;
        if (scaleIncrement.scale > 100)
        {
            result += current;
            current = 0;
        }
    }
    return result + current;
}


public struct ScaleIncrementPair
{
    public double scale;
    public int increment;
    public ScaleIncrementPair(double s, int i)
    {
        scale = s;
        increment = i;
    }
}

Answer 5

This code works only for numbers below 99.
both word to Int and int to word.
(for rest need to implement 10-20 lines of code and simple logic. This is just simple code for beginners)


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<-----")

Answer 6

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.