Create lag features for time series analysis

lag_features.py

import pandas as pd
from sklearn.preprocessing import StandardScaler
from statsmodels.tsa.stattools import pacf

def create_lag_features(y):
   
    scaler = StandardScaler()
    features = pd.DataFrame()
    
    partial = pd.Series(data=pacf(y, nlags=48))
    lags = list(partial[np.abs(partial) >= 0.2].index)
    
    df = pd.DataFrame()
    
    # avoid to insert the time series itself
    lags.remove(0)
    
    for l in lags:
        df[f"lag_{l}"] = y.shift(l)
    
    features = pd.DataFrame(scaler.fit_transform(df[df.columns]),
                            columns=df.columns)
    features.index = y.index
    
    return features