python
sentences = [
"Hello, I need medicine for a cold.",
"Do you have anything for a cough?",
"I have a fever and a sore throat.",
"Can you recommend something mild?",
"Is this safe for children?",
"How many times a day should I take it?",
"Should I take it before or after meals?",
"Does it make you sleepy?",
"Are there any side effects?",
"I am allergic to penicillin.",
"I need a cream for skin rash.",
"My prescription is ready, please.",
"How much is this bottle?",
"Can I buy it without a prescription?",
"Where is the nearest pharmacy?"
]
import re
words = []
for s in sentences:
    tokens = re.findall(r"[a-zA-Z']+", s.lower())
    words.extend(tokens)
uniq = sorted(set(words), key=lambda x: (x))
len(uniq), uniq[:10]


(62,
 ['a',
  'after',
  'allergic',
  'am',
  'and',
  'any',
  'anything',
  'are',
  'before',
  'bottle'])

python
uniq


['a',
 'after',
 'allergic',
 'am',
 'and',
 'any',
 'anything',
 'are',
 'before',
 'bottle',
 'buy',
 'can',
 'children',
 'cold',
 'cough',
 'cream',
 'day',
 'do',
 'does',
 'effects',
 'fever',
 'for',
 'have',
 'hello',
 'how',
 'i',
 'is',
 'it',
 'make',
 'many',
 'meals',
 'medicine',
 'mild',
 'much',
 'my',
 'nearest',
 'need',
 'or',
 'penicillin',
 'pharmacy',
 'please',
 'prescription',
 'rash',
 'ready',
 'recommend',
 'safe',
 'should',
 'side',
 'skin',
 'sleepy',
 'something',
 'sore',
 'take',
 'the',
 'there',
 'this',
 'throat',
 'times',
 'to',
 'where',
 'without',
 'you']

python
print(len(uniq))
print(", ".join(uniq))

python
for i,w in enumerate(sorted(set(words))):
    print(i+1, w)

python
uniq_sorted = sorted(set(words))
chunks = [uniq_sorted[i:i+20] for i in range(0,len(uniq_sorted),20)]
for ch in chunks:
    print(ch)

python
words_list = ["a","after","allergic","am","and","any","anything","are","before","bottle","buy","can","children","cold","cough","cream","day","do","does","effects","fever","for","have","hello","how","i","is","it","make","many","meals","much","my","nearest","need","or","penicillin","pharmacy","please","prescription","rash","ready","recommend","safe","should","side","skin","sleepy","something","sore","take","the","there","this","throat","times","to","where","without","you"]
len(words_list)


60

python
orig = set(words)
ours = set(words_list)
missing = sorted(list(orig - ours))
extra = sorted(list(ours - orig))
missing, extra


(['medicine', 'mild'], [])

python
words_list.extend(["medicine","mild"])
len(words_list)


62