问在段落中查找字典值，如果段落没有字典值，则返回NA

EN

paragraphs = ['protein and carbohydrates Its is a little heavier pulsus widely used and is a versatile ingredient',
 'Tea contains the goodness of  Natural Ingredients Cardamom Ginger Tea bags Disclaimers As per Ayurvedic texts',
 'almonds are all natural supreme sized nuts they are highly nutritious and extremely healthy',
 'Camel milk can be consumed by lactose intolerant people and those allergic to cows milk',
 'Healthy Crunch  Almond with honey is an extra crunchy breakfast cereal for a delightful start to your mornings']

d = {'First': ['Tea', 'Coffee'],
     'Second':  ['Noodles', 'Pasta'],
     'Third': ['sandwich', 'honey'],
     'Fourth': ['Almond', 'apricot','blueberry']
}

words = set(w for lst in d.values() for w in lst)
match_stats = {'whole_text': [], 'matched_text': []}
for p in paragraphs:
    common_words = set(p.split()) & words
    if not common_words:
        match_stats['whole_text'].append(p)
        match_stats['matched_text'].append('NA')
    else:
        for w in common_words:
            match_stats['whole_text'].append(p)
            match_stats['matched_text'].append(w)

df = pd.DataFrame(match_stats)
print(df)

                                          whole_text matched_text
0  protein and carbohydrates Its is a little heav...           NA
1  Tea contains the goodness of  Natural Ingredie...          Tea
2  almonds are all natural supreme sized nuts the...           NA
3  Camel milk can be consumed by lactose intolera...           NA
4  Healthy Crunch  Almond with honey is an extra ...        honey
5  Healthy Crunch  Almond with honey is an extra ...       Almond

values = set(v for l in d.values() for v in l)
txt_and_label = []  # string of tuples

for line in t:
    # checks if v in line and assigning in the form of (line ,label_value)
    match = [(line, v) for v in values if v in line]
    if not match:
        match = [(line, 'NA')]
    txt_and_label.extend(match)

pd.DataFrame(txt_and_label, columns=["whole_text", "matched_text"])