def predict(self, X, only_mean=False):
# X = check_array(X, accept_sparse='csr')
X = np.array(X)
X = self.normalize(X)
neigh_dist, neigh_ind = self.kneighbors(X)
weights = _get_weights(neigh_dist, self.weights)
_y = self._y
if _y.ndim == 1:
_y = _y.reshape((-1, 1))
if weights is None:
y_pred = np.mean(_y[neigh_ind], axis=1)
else:
y_pred = np.empty((X.shape[0], _y.shape[1]), dtype=np.float64)
denom = np.sum(weights, axis=1)
for j in range(_y.shape[1]):
num = np.sum(_y[neigh_ind, j] * weights, axis=1)
y_pred[:, j] = num / denom
if self._y.ndim == 1:
y_pred = y_pred.ravel()
if only_mean:
return y_pred
else:
return y_pred, np.amin(neigh_dist, axis=1)
def predict(self, X):
"""Predict the class labels for the provided data
Parameters
----------
X: array
A 2-D array representing the test points.
Returns
-------
labels: array
List of class labels (one for each data sample).
"""
X = np.atleast_2d(X)
neigh_dist, neigh_ind = self.kneighbors(X)
pred_labels = self._y[neigh_ind]
weights = _get_weights(neigh_dist, self.weights)
if weights is None:
mode, _ = smart_mode(pred_labels, axis=1)
else:
mode, _ = weighted_mode(pred_labels, weights, axis=1)
return mode.flatten().astype(np.int)
def predict_proba(self, X):
"""Return probability estimates for the test data X.
Parameters
----------
X : sktime-format pandas dataframe or array-like, shape (n_query, n_features), \
or (n_query, n_indexed) if metric == 'precomputed'
Test samples.
Returns
-------
p : array of shape = [n_samples, n_classes], or a list of n_outputs
of such arrays if n_outputs > 1.
The class probabilities of the input samples. Classes are ordered
by lexicographic order.
"""
X = check_data_sktime_tsc(X)
temp = check_array.__code__
check_array.__code__ = _check_array_ts.__code__
X = check_array(X, accept_sparse='csr')
neigh_dist, neigh_ind = self.kneighbors(X)
classes_ = self.classes_
_y = self._y
if not self.outputs_2d_:
_y = self._y.reshape((-1, 1))
classes_ = [self.classes_]
n_samples = X.shape[0]
weights = _get_weights(neigh_dist, self.weights)
if weights is None:
weights = np.ones_like(neigh_ind)
all_rows = np.arange(X.shape[0])
probabilities = []
for k, classes_k in enumerate(classes_):
pred_labels = _y[:, k][neigh_ind]
proba_k = np.zeros((n_samples, classes_k.size))
# a simple ':' index doesn't work right
for i, idx in enumerate(pred_labels.T): # loop is O(n_neighbors)
proba_k[all_rows, idx] += weights[:, i]
# normalize 'votes' into real [0,1] probabilities
normalizer = proba_k.sum(axis=1)[:, np.newaxis]
normalizer[normalizer == 0.0] = 1.0
proba_k /= normalizer
probabilities.append(proba_k)
if not self.outputs_2d_:
probabilities = probabilities[0]
check_array.__code__ = temp
return probabilities
def predict(self, X, idx=None):
neigh_dist, neigh_ind = self.kneighbors(X, idx)
pred_labels = self._y[neigh_ind]
weights = _get_weights(neigh_dist, self.weights)
if weights is None:
mode, _ = smart_mode(pred_labels, axis=1)
else:
mode, _ = weighted_mode(pred_labels, weights)
return mode.flatten().astype(np.int)
def _impute(self, dist, X, fitted_X, mask, mask_fx):
"""Helper function to find and impute missing values"""
# For each column, find and impute
n_rows_X, n_cols_X = X.shape
for c in range(n_cols_X):
if not np.any(mask[:, c], axis=0):
continue
# Row index for receivers and potential donors (pdonors)
receivers_row_idx = np.where(mask[:, c])[0]
pdonors_row_idx = np.where(~mask_fx[:, c])[0]
# Impute using column mean if n_neighbors are not available
if len(pdonors_row_idx) < self.n_neighbors:
warnings.warn("Insufficient number of neighbors! "
"Filling in column mean.")
X[receivers_row_idx, c] = self.statistics_[c]
continue
# Get distance from potential donors
dist_pdonors = dist[receivers_row_idx][:, pdonors_row_idx]
dist_pdonors = dist_pdonors.reshape(-1, len(pdonors_row_idx))
# Argpartition to separate actual donors from the rest
pdonors_idx = np.argpartition(dist_pdonors,
self.n_neighbors - 1,
axis=1)
# Get final donors row index from pdonors
donors_idx = pdonors_idx[:, :self.n_neighbors]
# Get weights or None
dist_pdonors_rows = np.arange(len(donors_idx))[:, None]
weight_matrix = _get_weights(
dist_pdonors[dist_pdonors_rows, donors_idx], self.weights)
donor_row_idx_ravel = donors_idx.ravel()
# Retrieve donor values and calculate kNN score
fitted_X_temp = fitted_X[pdonors_row_idx]
donors = fitted_X_temp[donor_row_idx_ravel, c].reshape(
(-1, self.n_neighbors))
donors_mask = _get_mask(donors, self.missing_values)
donors = np.ma.array(donors, mask=donors_mask)
# Final imputation
imputed = np.ma.average(donors, axis=1, weights=weight_matrix)
X[receivers_row_idx, c] = imputed.data
return X
def predict(self, X, idx=None):
neigh_dist, neigh_ind = self.kneighbors(X,idx)
pred_labels = self._y[neigh_ind]
weights = _get_weights(neigh_dist, self.weights)
if weights is None:
mode, _ = stats.mode(pred_labels, axis=1)
else:
# Randomly permute the neighbors to tie-break randomly if necessary
perm = np.random.permutation(n_neighbors)
ind = ind[perm]
mode, _ = weighted_mode(pred_labels,weights,axis)
return mode.flatten().astype(np.int)
def predict(self, X, n_neighbors=None):
"""Predict the class labels for the provided data.
Parameters
----------
X : array-like, shape (n_queries, n_features), \
or (n_queries, n_indexed) if metric == 'precomputed'
Test samples.
Returns
-------
y : array of shape [n_queries] or [n_queries, n_outputs]
Class labels for each data sample.
"""
if n_neighbors is not None:
self.n_neighbors = n_neighbors
X = check_array(X, accept_sparse='csr')
X = X.astype(np.float32)
neigh_dist, neigh_ind = self.kneighbors(X)
classes_ = self.classes_
_y = self.train_label
if not self.outputs_2d_:
_y = self.train_label.reshape((-1, 1))
classes_ = [self.classes_]
n_outputs = len(classes_)
n_queries = X.shape[0]
weights = _get_weights(neigh_dist, self.weights)
y_pred = np.empty((n_queries, n_outputs), dtype=classes_[0].dtype)
for k, classes_k in enumerate(classes_):
if weights is None:
mode, _ = stats.mode(_y[neigh_ind, k], axis=1)
else:
mode, _ = weighted_mode(_y[neigh_ind, k], weights, axis=1)
mode = np.asarray(mode.ravel(), dtype=np.intp)
y_pred[:, k] = classes_k.take(mode)
if not self.outputs_2d_:
y_pred = y_pred.ravel()
return y_pred
return y_pred
def predict(self, X):
"""Predict the target for the provided data
It fits a weighted least squares linear model locally for the nearest neighbors
Parameters
----------
X : array-like, shape (n_query, n_features), \
or (n_query, n_indexed) if metric == 'precomputed'
Test samples.
Returns
-------
y : array of int, shape = [n_samples] or [n_samples, n_outputs]
Target values
"""
X = check_array(X, accept_sparse='csr')
# NN of X with respect to the train data (_fit_X)
neigh_dist, neigh_ind = self.kneighbors(X)
weights = _get_weights(neigh_dist, self.weights)
_y = self._y
_fit_X = self._fit_X
if _y.ndim == 1:
_y = _y.reshape((-1, 1))
y_pred = np.empty((X.shape[0], 1), dtype=np.float64)
# NN in the train data
X_nn = np.squeeze(_fit_X[neigh_ind])
y_nn = np.squeeze(_y[neigh_ind])
# loop over the samples, not ideal from a speed point of view
for i in range(X_nn.shape[0]):
linear = skl_lm.LinearRegression()
if weights is not None:
linear.fit(X_nn[i].reshape(-1, 1),
y_nn[i],
sample_weight=weights[i])
else:
linear.fit(X_nn[i].reshape(-1, 1), y_nn[i])
y_pred[i] = linear.predict(X[i].reshape(-1, 1))
if self._y.ndim == 1:
y_pred = y_pred.ravel()
return y_pred
def predict(self, X):
"""Predict the class labels for the provided data
Parameters
----------
X : sktime-format pandas dataframe or array-like, shape (n_query, n_features), \
or (n_query, n_indexed) if metric == 'precomputed'
Test samples.
Returns
-------
y : array of shape [n_samples] or [n_samples, n_outputs]
Class labels for each data sample.
"""
X = check_data_sktime_tsc(X, dim_to_use=self.dim_to_use)
temp = check_array.__code__
check_array.__code__ = _check_array_ts.__code__
neigh_dist, neigh_ind = self.kneighbors(X)
classes_ = self.classes_
_y = self._y
if not self.outputs_2d_:
_y = self._y.reshape((-1, 1))
classes_ = [self.classes_]
n_outputs = len(classes_)
n_samples = X.shape[0]
weights = _get_weights(neigh_dist, self.weights)
y_pred = np.empty((n_samples, n_outputs), dtype=classes_[0].dtype)
for k, classes_k in enumerate(classes_):
if weights is None:
mode, _ = stats.mode(_y[neigh_ind, k], axis=1)
else:
mode, _ = weighted_mode(_y[neigh_ind, k], weights, axis=1)
mode = np.asarray(mode.ravel(), dtype=np.intp)
y_pred[:, k] = classes_k.take(mode)
if not self.outputs_2d_:
y_pred = y_pred.ravel()
check_array.__code__ = temp
return y_pred
def predict(self, X):
"""Predict the class labels for the provided data
Parameters
----------
X : array-like, shape (n_ts, sz, d)
Test samples.
"""
X_ = to_time_series_dataset(X)
neigh_dist, neigh_ind = self.kneighbors(X_)
weights = _get_weights(neigh_dist, self.weights)
if weights is None:
mode, _ = stats.mode(self._fit_y[neigh_ind], axis=1)
else:
mode, _ = weighted_mode(self._fit_y[neigh_ind], weights, axis=1)
return mode[:, 0]
def predict(self, X):
"""Predict the target for the provided data
Parameters
----------
X : array-like, shape (n_query, n_features), \
or (n_query, n_indexed) if metric == 'precomputed'
Test samples.
Returns
-------
y : array of int, shape = [n_samples] or [n_samples, n_outputs]
Target values
"""
if issparse(X) and self.metric == 'precomputed':
raise ValueError(
"Sparse matrices not supported for prediction with "
"precomputed kernels. Densify your matrix.")
X = check_array(X, accept_sparse='csr')
neigh_dist, neigh_ind = self.kneighbors(X)
weights = _get_weights(neigh_dist, self.weights)
_y = self._y
if _y.ndim == 1:
_y = _y.reshape((-1, 1))
if weights is None:
y_pred = np.median(_y[neigh_ind], axis=1)
else:
weights = weights / weights.sum()
num = _y[neigh_ind.flatten()].T * weights
cs = list(np.cumsum(num.flatten()))
ind = np.searchsorted(cs, cs[-1] / 2.0)
y_pred = _y[ind]
if self._y.ndim == 1:
y_pred = y_pred.ravel()
return y_pred
def predict(self, X):
"""Predict the class labels for the provided data
Parameters
----------
X : array-like, shape (n_ts, sz, d)
Test samples.
"""
if self.metric == "min_dist" and self.variables_size > 1:
X_ = X
else:
X_ = to_time_series_dataset(X,self.variables_size)
neigh_dist, neigh_ind = self.kneighbors(X_,self.multivariate_output,None,True)
weights = _get_weights(neigh_dist, self.weights)
if weights is None:
mode, _ = stats.mode(self._fit_y[neigh_ind], axis=1)
else:
mode, _ = weighted_mode(self._fit_y[neigh_ind], weights, axis=1)
return mode[:, 0]
