search

appeler / ethnicolr

Predict Race and Ethnicity Based on the Sequence of Characters in a Name
http://ethnicolr.readthedocs.io
MIT License
234 stars 66 forks source link

many Null values #64

Closed barslan16 closed 2 years ago

barslan16 commented 2 years ago

I used odf = pred_wiki_name(df, 'lastname' , 'firstname')

It gives NaN values for 6500 rows out of a dataset of approximately 10000 rows.

Screen Shot 2022-05-09 at 01 36 17
soodoku commented 2 years ago

will need more data. for instance, a sample of the entries.

barslan16 commented 2 years ago

will need more data. for instance, a sample of the entries.

I just realized that the problem is caused by the indexes of my dataframe. Thanks for your quick reply!