def _log_normalize(X):
"""Normalize ``X`` according to Kluger's log-interactions scheme."""
X = make_nonnegative(X, min_value=1)
if issparse(X):
raise ValueError(
"Cannot compute log of a sparse matrix," " because log(x) diverges to -infinity as x" " goes to 0."
)
L = np.log(X)
row_avg = L.mean(axis=1)[:, np.newaxis]
col_avg = L.mean(axis=0)
avg = L.mean()
return L - row_avg - col_avg + avg
def _log_normalize(X):
"""Normalize ``X`` according to Kluger's log-interactions scheme."""
X = make_nonnegative(X, min_value=1)
if issparse(X):
raise ValueError("Cannot compute log of a sparse matrix,"
" because log(x) diverges to -infinity as x"
" goes to 0.")
L = np.log(X)
row_avg = L.mean(axis=1)[:, np.newaxis]
col_avg = L.mean(axis=0)
avg = L.mean()
return L - row_avg - col_avg + avg
def _scale_normalize(X):
"""Normalize ``X`` by scaling rows and columns independently.
Returns the normalized matrix and the row and column scaling
factors.
"""
X = make_nonnegative(X)
row_diag = np.asarray(1.0 / np.sqrt(X.sum(axis=1))).squeeze()
col_diag = np.asarray(1.0 / np.sqrt(X.sum(axis=0))).squeeze()
row_diag = np.where(np.isnan(row_diag), 0, row_diag)
col_diag = np.where(np.isnan(col_diag), 0, col_diag)
if issparse(X):
n_rows, n_cols = X.shape
r = dia_matrix((row_diag, [0]), shape=(n_rows, n_rows))
c = dia_matrix((col_diag, [0]), shape=(n_cols, n_cols))
an = r * X * c
else:
an = row_diag[:, np.newaxis] * X * col_diag
return an, row_diag, col_diag
def _scale_normalize(X):
"""Normalize ``X`` by scaling rows and columns independently.
Returns the normalized matrix and the row and column scaling
factors.
"""
X = make_nonnegative(X)
row_diag = np.asarray(1.0 / np.sqrt(X.sum(axis=1))).squeeze()
col_diag = np.asarray(1.0 / np.sqrt(X.sum(axis=0))).squeeze()
row_diag = np.where(np.isnan(row_diag), 0, row_diag)
col_diag = np.where(np.isnan(col_diag), 0, col_diag)
if issparse(X):
n_rows, n_cols = X.shape
r = dia_matrix((row_diag, [0]), shape=(n_rows, n_rows))
c = dia_matrix((col_diag, [0]), shape=(n_cols, n_cols))
an = r * X * c
else:
an = row_diag[:, np.newaxis] * X * col_diag
return an, row_diag, col_diag
def _bistochastic_normalize(X, max_iter=1000, tol=1e-5):
"""Normalize rows and columns of ``X`` simultaneously so that all
rows sum to one constant and all columns sum to a different
constant.
"""
# According to paper, this can also be done more efficiently with
# deviation reduction and balancing algorithms.
X = make_nonnegative(X)
X_scaled = X
dist = None
for _ in range(max_iter):
X_new, _, _ = _scale_normalize(X_scaled)
if issparse(X):
dist = norm(X_scaled.data - X.data)
else:
dist = norm(X_scaled - X_new)
X_scaled = X_new
if dist is not None and dist < tol:
break
return X_scaled
def _bistochastic_normalize(X, max_iter=1000, tol=1e-5):
"""Normalize rows and columns of ``X`` simultaneously so that all
rows sum to one constant and all columns sum to a different
constant.
"""
# According to paper, this can also be done more efficiently with
# deviation reduction and balancing algorithms.
X = make_nonnegative(X)
X_scaled = X
dist = None
for _ in range(max_iter):
X_new, _, _ = _scale_normalize(X_scaled)
if issparse(X):
dist = norm(X_scaled.data - X.data)
else:
dist = norm(X_scaled - X_new)
X_scaled = X_new
if dist is not None and dist < tol:
break
return X_scaled
