Catagorise text series

"""
Catagorise text series based on wherever specific string is contained within text
example 'I like big red apples' catagory = 'Red Apple'
"""

# example df

df = {
    "first_name": ['Bruce', 'Clark', 'Bruce', 'James', 'Nanny', 'Dot'],
    "last_name": ['Lee', 'Kent', 'Banner', 'Bond', 'Mc Phee', 'Cotton'],
    "title": ['mr', 'mr', 'mr', 'mr', 'mrs', 'mrs'],
    "text": ["He is a Kung Fu master", "Wears capes and tight Pants", "Cocktails shaken not stirred", "angry Green man", "suspect scottish accent", "East end legend"],
    "age": [32, 33, 28, 30, 42, 80]
}

"""
first_name     last_name title        text                   age
0      Bruce       Lee    Mr        He is a Kung Fu master   32
1      Clark      Kent    Mr   Wears capes and tight Pants   33
2      Bruce    Banner    Mr  Cocktails shaken not stirred   28
3      James      Bond    Mr               angry Green man   30
4      Nanny   Mc Phee   Mrs       suspect scottish accent   42
5        Dot    Cotton   Mrs               East end legend   80


"""


"""Create catagory dict
keys: extracted str that is contained within series text
vals: mapped assigned catagorys""""

category_dict = {
                 "Kung Fu":"Martial Art",
                 "capes":"Clothing",
                 "cocktails": "Drink",
                 "green": "Colour",
                 "scottish": "Scotland",
                 "East": "Direction"
                 }

cd= {k.lower(): v for k,v in category_dict.items()} # convert keys to lower case


# convert the extracted word to lowercase and then map with the lowercase dict
df['category'] = (
    df['text'].str.extract(
        fr"\b({'|'.join((category_dict.keys()))})\b",
        flags=re.IGNORECASE)[0].str.lower().map(cd)) # add .fillna('Other') to capture unassigned

# outputs

""""
first_name      last_name title      text                    age     category
0      Bruce       Lee    Mr        He is a Kung Fu master   32  Martial Art
1      Clark      Kent    Mr   Wears capes and tight Pants   33     Clothing
2      Bruce    Banner    Mr  Cocktails shaken not stirred   28        Drink
3      James      Bond    Mr               angry Green man   30       Colour
4      Nanny   Mc Phee   Mrs       suspect scottish accent   42     Scotland
5        Dot    Cotton   Mrs               East end legend   80    Direction

""""