# utils/preprocessing.py
import pandas as pd
from sklearn.preprocessing import StandardScaler
from utils import feature_engineering

def preprocess_data_for_streamlit(data_path):
    df = pd.read_csv(data_path)
    df = feature_engineering(df)  # Assuming feature_engineering is defined
    X = df.drop('label', axis=1)
    scaler = StandardScaler()
    X_scaled = scaler.fit_transform(X)
    return df, X_scaled
# utils/preprocessing.py
import pandas as pd
from sklearn.model_selection import train_test_split

def preprocess_data(data_path, test_size=0.2, random_state=42):
    df = pd.read_csv(data_path)
    df = feature_engineering(df)
    X = df.drop('label', axis=1)
    y = df['label']
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=test_size, random_state=random_state)
    scaler = StandardScaler()
    X_train_scaled = scaler.fit_transform(X_train)
    X_test_scaled = scaler.transform(X_test)
    return X_train_scaled, X_test_scaled, y_train, y_test