import pandas as pd
import numpy as np
import nltk
df = pd.read_csv('data1.csv')



corp_data =df['Name'].tolist()
c=[]
for data in corp_data:
    c.append(word_tokenize(data))




from nltk.stem import WordNetLemmatizer
lem=WordNetLemmatizer()
token=[]
for data in c:
    for t in data :
        token.append(lem.lemmatize(t))
token 


from nltk.corpus import stopwords
 
nltk.download('stopwords')
stop_words=set(stopwords.words('english'))

token_filter=[]
for data in token:
    if data.lower() in stop_words:
        continue
    if data.lower() not in token_filter:
        token_filter.append(data.lower())