src/data/check_data.py

import pandas as pd

df = pd.read_csv("data/raw/bbc-text.csv")

print("\nFirst 5 Rows:")
print(df.head())

print("\nDataset Shape:")
print(df.shape)

print("\nColumns:")
print(df.columns)

print("\nMissing Values:")
print(df.isnull().sum())

print("\nClass Distribution:")
print(df["label_text"].value_counts())