How to read a text and label each word of it in Python

Question

data = ("Thousands of demonstrators have marched through London to protest the war in Iraq and demand the withdrawal of British troops from that country. Many people have been killed that day.",
        {"entities": [(48, 54, 'Category 1'), (77, 81, 'Category 1'), (111, 118, 'Category 2'), (150, 173, 'Category 3')]})

data[1]['entities'][0] = (48, 54, 'Category 1') stands for (start_offset, end_offset, entity).

I want to read each word of data[0] in a sequential manner and tag each word according to data[1] entities. I am expecting to have as final output,

{
'Thousands': 'O', 
'of': 'O',
'demonstrators': 'O',
'have': 'O',
'marched': 'O',
'through': 'O',
'London': 'S-1',
'to': 'O', 
'protest': 'O', 
'the': 'O', 
'war': 'O', 
'in': 'O', 
'Iraq': 'S-1',
'and': 'O' 
'demand': 'O', 
'the': 'O', 
'withdrawal': 'O', 
'of': 'O', 
'British': 'S-2', 
'troops': 'O', 
'from': 'O',
'that': 'O', 
'country': 'O',
'.': 'O',
'Many': 'O', 
'people': 'S-3', 
'have': 'B-3', 
'been': 'B-3', 
'killed': 'E-3', 
'that': 'O', 
'day': 'O',
'.': 'O'
}

Here, 'O' stands for 'OutOfEntity', 'S' stands for 'Start', 'B' stands for 'Between', and 'E' stands for 'End' and are unique for every given text.

---

I tried the following:

def ner(data):
    entities = {}
    offsets = data[1]['entities']
    for entity in offsets:
        entities[data[0][int(entity[0]):int(entity[1])]] = re.findall('[0-9]+', entity[2])[0]
    
    tags = []
    for key, value in entities.items():
        entity = key.split()
        if len(entity) > 1:
            bEntity = entity[1:-1]
            tags.append((entity[0], 'S-'+value))
            for item in bEntity:
                tags.append((item, 'B-'+value))
            tags.append((entity[-1], 'E-'+value))
        else:
            tags.append((entity[0], 'S-'+value))
    
    tokens = nltk.word_tokenize(data[0])
    OTokens = [(token, 'O') for token in tokens if token not in [token[0] for token in tags]]
    for token in OTokens:
        tags.append(token)
    
    return tags

But the above function does not work properly in case I have some words that are the same as those in data[1]['entities'] offsets but not part of the offsets will be ignored instead they should be labeled as 'O'.

Answer 1

Not sure if the final format is json, yet below is an example to process the data into the print format, i.e.

# sample output
'''
{
'Thousands': 'O',
'of': 'O',
'demonstrators': 'O',
'have': 'O',
'marched': 'O',
'through': 'O',
'London': 'S-1',
'to': 'O',
'protest': 'O',
'the': 'O',
'war': 'O',
'in': 'O',
'Iraq': 'S-1',
'and': 'O',
'demand': 'O',
'the': 'O',
'withdrawal': 'O',
'of': 'O',
'British': 'S-2',
'troops': 'O',
'from': 'O',
'that': 'O',
'country.': 'O',
'Many': 'O',
'people': 'S-3',
'have': 'B-3',
'been': 'B-3',
'killed': 'E-3',
'that': 'O',
'day.': 'O'
}
'''
# sample code
data = ("Thousands of demonstrators have marched through London to protest the war in Iraq and demand the withdrawal of British troops from that country. Many people have been killed that day.",
        {"entities": [(48, 54, 'Category 1'), (77, 81, 'Category 1'), (111, 118, 'Category 2'), (150, 173, 'Category 3')]})

print("{")
pre = 0
for i in (data[1].values())[0]:
        a = data[0][i[0]:i[1]].split()
        t = pre + i[1]
        #print(pre, i[0])
        b = data[0][pre:i[0]].split()
        for j in b:
                print("'%s': '%s'," % (j, "O"))
        pre = i[1]
        for j in range(len(a)): 
                if j == 0:
                        print("'%s': '%s-%s'," % (a[j], "S", i[2][-1]))
                elif j == len(a) - 1:
                        print("'%s': '%s-%s'," % (a[j], "E", i[2][-1]))
                else:
                        print("'%s': '%s-%s'," % (a[j], "B", i[2][-1]))
#print(i[1], las)
las = len(data[0])
c = data[0][i[1]:las].split()
for j in range(len(c)):
        if j == len(c) - 1:
                print("'%s': '%s'" % (c[j], "O"))
        else:
                print("'%s': '%s'," % (c[j], "O"))
print("}")