def _partial_fit(self,
X,
y,
classes=None,
_refit=False,
sample_weight=None):
if sample_weight is not None:
warn_unused_args("sample_weight")
# Store size of current X to apply differential privacy later on
self.new_n_samples = X.shape[0]
if self.bounds is None:
warnings.warn(
"Bounds have not been specified and will be calculated on the data provided. This will "
"result in additional privacy leakage. To ensure differential privacy and no additional "
"privacy leakage, specify bounds for each dimension.",
PrivacyLeakWarning)
self.bounds = list(zip(np.min(X, axis=0), np.max(X, axis=0)))
self.bounds = _check_bounds(self.bounds, X.shape[1])
super()._partial_fit(X, y, classes, _refit, sample_weight=None)
del self.new_n_samples
return self
def fit(self, X, y=None, sample_weight=None):
"""Computes k-means clustering with differential privacy.
Parameters
----------
X : array-like, shape=(n_samples, n_features)
Training instances to cluster.
y : Ignored
not used, present here for API consistency by convention.
sample_weight : Ignored
Not used in diffprivlib, present here for consistency with :obj:`sklearn.cluster.KMeans`. Specifying this
parameter will result in a :class:`.DiffprivlibCompatibilityWarning`.
Returns
-------
self : class
"""
if sample_weight is not None:
warn_unused_args("sample_weight")
del y
if X.ndim != 2:
raise ValueError(
"Expected 2D array, got array with %d dimensions instead. Reshape your data using array.reshape(-1, 1),"
"or array.reshape(1, -1) if your data contains only one sample." % X.ndim)
n_samples, n_dims = X.shape
iters = self._calc_iters(n_dims, n_samples)
if self.bounds is None:
warnings.warn("Bounds have not been specified and will be calculated on the data provided. This will "
"result in additional privacy leakage. To ensure differential privacy and no additional "
"privacy leakage, specify `bounds` for each dimension.", PrivacyLeakWarning)
self.bounds = list(zip(np.min(X, axis=0), np.max(X, axis=0)))
self.bounds = _check_bounds(self.bounds, n_dims)
centers = self._init_centers(n_dims)
labels = None
distances = None
# Run _update_centers first to ensure consistency of `labels` and `centers`, since convergence unlikely
for _ in range(-1, iters):
if labels is not None:
centers = self._update_centers(X, centers=centers, labels=labels, dims=n_dims, total_iters=iters)
distances, labels = self._distances_labels(X, centers)
self.cluster_centers_ = centers
self.labels_ = labels
self.inertia_ = distances[np.arange(len(labels)), labels].sum()
self.n_iter_ = iters
return self