feature-engineering

import pandas as pd
from sklearn.compose import ColumnTransformer
from sklearn.impute import SimpleImputer
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import OneHotEncoder, StandardScaler

WITH ordered_events AS (
  SELECT
    customer_id,
    event_time,
    revenue,
    ROW_NUMBER() OVER (PARTITION BY customer_id ORDER BY event_time DESC) AS event_rank,

import pandas as pd

orders = pd.read_parquet('orders.parquet')
orders['ordered_at'] = pd.to_datetime(orders['ordered_at'])

reference_date = orders['ordered_at'].max() + pd.Timedelta(days=1)

import numpy as np

features = np.array([
    [120.0, 3.0, 10.0],
    [90.0, 5.0, 7.0],
    [150.0, 2.0, 14.0],