I am running this code in Python, I don't know what its always error
import string
import nltk
from sklearn.pipeline import Pipeline
import pandas as pd
import numpy as np
import re
data = pd.read_csv(r'C:\Users\Prihantoro Tri N\OneDrive\Documents\file toro\MSIB\Magang\Hukumonline\Project\youtube comments\dataset_komentar_instagram_cyberbullying.csv', sep=',', encoding='utf-8')
def casefolding(comment):
comment = comment.lower()
comment = comment.strip(" ")
comment = re.sub(r'[?|$|.|!_:")(- ,]', '', comment)
return comment
data['comment'] = data['comment'].apply(casefolding)
data.head(100)
And the results give the following error:
NameError Traceback (most recent call last)
Input In [3], in <cell line: 8>()
6 comment = re.sub(r'[?|$|.|!_:")(- ,]', '', comment)
7 return comment
----> 8 data['comment'] = data['comment'].apply(casefolding)
9 data.head(100)
NameError: name 'data' is not defined
or the results are like this >> KeyError: 'comment'
CodePudding user response:
I think your dataframe don't have "comment"
column so please try check all the columns in your dataframe.
try to run this data.columns
CodePudding user response:
#lets say your is from a csv file
import pandas as pd
import re
df = pd.read_csv('your_csv_file.csv')
data = pd.DataFrame(df)
def casefolding(comment):
comment = comment.lower()
comment = comment.strip(" ")
comment = re.sub(r'[?|$|.|!_:")(- ,]', '', comment)
return comment
data['comment'] = data['comment'].apply(casefolding)
data.head(100)