CODEWITHSUNDEEP
pythonpandas
user14255498
user14255498

Reputation:

identify gender from the first name python

I have data set

first_name ajay amit raj mona sema

and I want to identify the there gender from there first name with a new column Gender so I used this code

!pip install gender_guesser
!pip install xlrd
!pip install openpyxl

import pandas as pd
import gender_guesser.detector as gender

df=pd.read_excel('adarsh.xlsx')

gd = gender.Detector()
df['Gender'] = df['first_name'].map(lambda x: gd.get_gender(x))
df['Gender']

output: 0 male

1 unknown

2 unknown

3 unknown

4 unknown

Name: Gender, dtype: object

how can get the complete output of gender

Upvotes: 2

Views: 8496

Answers (3)

Disha Jain
Disha Jain

Reputation: 1

Possible error is due to Capitalization, because by default gender-guesser is case sensitive. Try setting it off and then search. Check out the documentation https://pypi.org/project/gender-guesser/

>>> d = gender.Detector(case_sensitive=False)
>>> print(d.get_gender(u"sally"))
female
>>> print(d.get_gender(u"Sally"))
female

Upvotes: 0

CoffeeSyntax
CoffeeSyntax

Reputation: 79

in general, gender_guesser.detector requires properly capitalized names.

thus, just add an additional step to capitalize the names before passing them into the guesser.

df['Gender'] = df['first_name'].apply(str.capitalize).map(lambda x: gd.get_gender(x))

Upvotes: 1

ql.user2511
ql.user2511

Reputation: 389

unknown implies that the package cannot identify the gender from the names you have inserted.

For the first name, the gender has been identified.

You should have a look into the names that have been catered for in the gender-guesser Python library.

Upvotes: 0

Related Questions