def predict_probability(self, X):
"""Predict the probability of a target given features."""
if self.parameters is None or self.labels is None:
raise NotFitted("the model must be fitted before usage")
X = features_reshape(X)
if self.standardize is not None:
X = self.standardize(X)
X = np.concatenate((np.ones((X.shape[0], 1)), X), axis=1)
return self.hypothesis(X, self.parameters)
def score_samples(self, X):
"""Compute the log-likelihood of all samples."""
if self._U_reduced is None or self._mean is None:
raise NotFitted("the model must be fitted before usage")
X = features_reshape(X)
n_features = X.shape[1]
precision = np.linalg.inv(self._covariance_matrix)
residuals = X - self._mean
return -(1 / 2) * (-np.log(np.linalg.det(precision)) + np.sum(
(residuals * np.dot(residuals, precision)), axis=1) +
n_features * np.log(2 * np.pi))
def predict(self, X):
"""Predict a target given features."""
if self.X_fit is None or self.y_fit is None:
raise NotFitted("the model must be fitted before usage")
labels = []
for x in X:
distances_labels = [
(self.euclidian(x, x_fit), y_fit)
for x_fit, y_fit in zip(self.X_fit, self.y_fit)
]
neighbors = sorted(distances_labels, key=lambda d: d[0])[: self.n_neighbors]
neighbors_labels = [neighbor[1][0] for neighbor in neighbors]
labels.append(
sorted(
neighbors_labels, key=Counter(neighbors_labels).get, reverse=True
)[0]
)
return np.array(labels).reshape(-1, 1)
def score(self, X, y):
"""Score of the model."""
if self.parameters is None or self.labels is None:
raise NotFitted("the model must be fitted before usage")
return accuracy_score(self.predict(X), y)
def transform(self, X):
"""Transform the input."""
if self._U_reduced is None or self._mean is None:
raise NotFitted("the model must be fitted before usage")
return (X - self._mean).dot(self._U_reduced)