pyhdfe

import numpy as np import pandas as pd from pyhdfe import hdfe # Create some dummy data np.random.seed(42) n_obs = 1000 n_fixed_effects = 3 X = pd.DataFrame(np.random.rand(n_obs, 5), columns=[f'x{i}' for i in range(5)]) y = pd.Series(np.random.rand(n_obs)) fixed_effects_data = [] for i in range(n_fixed_effects): n_levels = np.random.randint(50, 200) # Varying number of levels fixed_effects_data.append(pd.Series(np.random.randint(0, n_levels, n_obs))) # Absorb fixed effects from X and y # fixed_effects is a list of 1D arrays/Series representing each fixed effect column # absorb_cols specifies which columns from X to transform # drop_cols specifies columns to drop before transformation (often the intercept) X_transformed, y_transformed = hdfe.hdfe_cluster_col( X, y, fixed_effects=fixed_effects_data, absorb_cols=X.columns.tolist(), # Absorb all X columns drop_cols=[], # No columns to drop in this example get_residuals=True ) print(f"Original X shape: {X.shape}") print(f"Transformed X shape: {X_transformed.shape}") print(f"Original y shape: {y.shape}") print(f"Transformed y shape: {y_transformed.shape}")