def _check_coltype(self, X):
for col in as_list(self.columns):
if isinstance(col, str):
if isinstance(X, np.ndarray):
raise ValueError(
f"column {col} is a string but datatype receive is numpy."
)
if isinstance(X, pd.DataFrame):
if col not in X.columns:
raise ValueError(f"column {col} is not in {X.columns}")
if isinstance(col, int):
if col not in range(np.atleast_2d(np.array(X)).shape[1]):
raise ValueError(
f"column {col} is out of bounds for input shape {X.shape}"
)
def fit(self, X, y=None):
"""Learn the projection required to make the dataset orthogonal to sensitive columns."""
self._check_coltype(X)
self.col_ids_ = [
v if isinstance(v, int) else self._col_idx(X, v)
for v in as_list(self.columns)
]
X = check_array(X, estimator=self)
X_fair = X.copy()
v_vectors = self._make_v_vectors(X, self.col_ids_)
# gram smidt process but only on sensitive attributes
for i, col in enumerate(X_fair.T):
for v in v_vectors.T:
X_fair[:, i] = X_fair[:, i] - _vector_projection(X_fair[:, i], v)
# we want to learn matrix P: X P = X_fair
# this means we first need to create X_fair in order to learn P
self.projection_, resid, rank, s = np.linalg.lstsq(X, X_fair, rcond=None)
return self