File size: 312 Bytes
7721643
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
import pandas as pd

# Function to preprocess input text
def preprocess_text(text):
    if pd.isna(text):
        return ""
    return text.strip().lower()  # Simple lowercase cleaning

# Function to preprocess dataset
def preprocess_dataset(df):
    df["text"] = df["text"].apply(preprocess_text)
    return df