import pandas as pd
import numpy as np
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.model_selection import train_test_split
from sklearn.svm import SVC
from sklearn.metrics import classification_report
from sklearn.pipeline import Pipeline
from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import StandardScaler
import joblib

# Load Dataset
data = pd.read_csv(load_dataset("nikesh66/Sarcasm-dataset"))
data['user_feature'] = data['user_feature'].fillna(0)

from datasets import load_dataset



# Preprocessing
text_vectorizer = TfidfVectorizer(max_features=5000, stop_words='english')
scaler = StandardScaler()
preprocessor = ColumnTransformer(
    transformers=[
        ('text', text_vectorizer, 'text'),
        ('user_features', scaler, ['user_feature']),
    ]
)

# Model