Add support for duckreg

[s3alfisc]

Example:

import numpy as np
import pandas as pd
from duckreg.estimators import DuckRegression
import duckdb

# Generate sample data
def generate_sample_data(N=10_000_000, seed=12345):
    rng = np.random.default_rng(seed)
    D = rng.choice([0, 1], size=(N, 1))
    X = rng.choice(range(20), (N, 2), True)
    Y = D + X @ np.array([1, 2]).reshape(2, 1) + rng.normal(size=(N, 1))
    Y2 = -1 * D + X @ np.array([1, 2]).reshape(2, 1) + rng.normal(size=(N, 1))
    df = pd.DataFrame(
        np.concatenate([Y, Y2, D, X], axis=1), columns=["Y", "Y2", "D", "f1", "f2"]
    ).assign(rowid=range(N))
    return df


# Function to create and populate DuckDB database
def create_duckdb_database(df, db_name="large_dataset.db", table="data"):
    conn = duckdb.connect(db_name)
    conn.execute(f"DROP TABLE IF EXISTS {table}")
    conn.execute(f"CREATE TABLE {table} AS SELECT * FROM df")
    conn.close()
    print(f"Data loaded into DuckDB database: {db_name}")

# Generate and save data
df = generate_sample_data()
db_name = "large_dataset.db"
create_duckdb_database(df, db_name)

db_name = "large_dataset.db"
conn = duckdb.connect(db_name)
query = "SELECT * FROM data limit 5"
conn.execute(query).fetchdf()

m1 = DuckRegression(
    db_name="large_dataset.db",
    table_name="data",
    formula="Y ~ D + f1 + f2",
    cluster_col="f1",
    n_bootstraps=100,
    seed=42,
)
m1.fit()
m1.fit_vcov()
results = m1.summary()

m2 = DuckRegression(
    db_name="large_dataset.db",
    table_name="data",
    formula="Y ~ D + f1",
    cluster_col="f1",
    n_bootstraps=100,
    seed=42,
)
m2.fit()
m2.fit_vcov()
results = m2.summary()

table = mt.ETable([m2, m1], digits = 6, caption = 'duckreg regressions')
table

[s3alfisc]

cc @apoorvalal ;-)