GitHub - shantanuo/easystemmer: Stemmer for Indian Names

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 24 Commits
README.py		README.py
compare_names.ipynb		compare_names.ipynb
compare_names_example.ipynb		compare_names_example.ipynb
compare_names_updated.ipynb		compare_names_updated.ipynb
compare_names_updated_jaccard.py		compare_names_updated_jaccard.py
easystemmer.py		easystemmer.py

Repository files navigation

# easystemmer
#Stemmer for Indian Names

from easystemmer import IndianNameStemmer
import pandas as pd

s = IndianNameStemmer()
#s.stem(['savithabai'])

df=pd.read_excel('my_file.xlsx')
df.columns=['wrong', 'correct']

df['updated']=df['wrong'].astype(str).apply(lambda x: x.split()).apply(s.stem)
df['updated1']=df['correct'].astype(str).apply(lambda x: x.split()).apply(s.stem)

ndf=df[df['updated'] != df['updated1']]
ndf[['wrong', 'correct']].to_excel('to_study.xlsx')