def fit(self, X, y):
"""
Fit the logistic regression classifier to data.
:param X: example-by-features NumPy matrix
:param y: example-length vector of class labels
"""
self._means = np.mean(X, 0)
self._stds = np.std(X, 0)
Xold = X
X = self._standardize_inputs(X)
ymat = y.reshape((y.shape[0], 1))
if self._lambda is None:
self._lambda = internal_cross_validation(
LogisticRegression, {'schema': self._schema}, 'lambda',
[0, 0.001, 0.01, 0.1, 1, 10, 100], 'auc', Xold, y
)
optres = scipy.optimize.minimize(self.loss,
np.append(self._w, [self._b]),
args=(X, ymat), jac=self.jac,
method='Newton-CG')
self._w = optres.x[:-1]
self._w = self._w.reshape((self._w.shape[0], 1)) # make it a matrix
self._b = optres.x[-1]
def fit(self, X, y):
"""
Fit the logistic regression classifier to data.
:param X: example-by-features NumPy matrix
:param y: example-length vector of class labels
"""
self._means = np.mean(X, 0)
self._stds = np.std(X, 0)
Xold = X
X = self._standardize_inputs(X)
ymat = y.reshape((y.shape[0], 1))
if self._lambda is None:
self._lambda = internal_cross_validation(
LogisticRegression, {'schema': self._schema}, 'lambda',
[0, 0.001, 0.01, 0.1, 1, 10, 100], 'auc', Xold, y)
optres = scipy.optimize.minimize(self.loss,
np.append(self._w, [self._b]),
args=(X, ymat),
jac=self.jac,
method='Newton-CG')
self._w = optres.x[:-1]
self._w = self._w.reshape((self._w.shape[0], 1)) # make it a matrix
self._b = optres.x[-1]
def fit(self, X, y):
"""
Fit Naive Bayes classifier to the given data.
This uses the current values of self._params as our "prior estimates".
When smoothing is used, these will be used in the m-Estimate. Since
the params are initialized to 1/v, this will usually be LaPlace
smoothing, but if you were to fit this class multiple times, it would
use the previous model as a prior estimate, which may be interesting.
:param X: An examples-by-features NumPy matrix.
:param y: An array of +/- 1 class labels.
"""
# Standardize everything.
Xstd = self._standardize_inputs(X)
ystd = y.copy()
ystd[y == -1] = 0
yvals = np.bincount(ystd)
# Select parameter m by internal cross validation.
if self._m is None:
self._m = internal_cross_validation(
NaiveBayes, {'schema': self._schema}, 'm_value',
[0, 0.001, 0.001, 0.1, 1, 10, 100], 'auc', X, y
)
# Set the conditional probabilities using smoothing.
for i, matrix in enumerate(self._params):
mp = self._m * matrix
for yval, count in enumerate(yvals):
Xrel = Xstd[ystd == yval]
colbincount = np.bincount(Xrel[:, i], minlength=mp.shape[1])
matrix[yval] = (mp[yval] + colbincount)
matrix[yval] = matrix[yval] / (count + self._m)
self._params[i] = matrix
# Set the probabilities of y.
self._yparam = yvals / len(ystd)
def fit(self, X, y):
"""
Fit Naive Bayes classifier to the given data.
This uses the current values of self._params as our "prior estimates".
When smoothing is used, these will be used in the m-Estimate. Since
the params are initialized to 1/v, this will usually be LaPlace
smoothing, but if you were to fit this class multiple times, it would
use the previous model as a prior estimate, which may be interesting.
:param X: An examples-by-features NumPy matrix.
:param y: An array of +/- 1 class labels.
"""
# Standardize everything.
Xstd = self._standardize_inputs(X)
ystd = y.copy()
ystd[y == -1] = 0
yvals = np.bincount(ystd)
# Select parameter m by internal cross validation.
if self._m is None:
self._m = internal_cross_validation(
NaiveBayes, {'schema': self._schema}, 'm_value',
[0, 0.001, 0.001, 0.1, 1, 10, 100], 'auc', X, y)
# Set the conditional probabilities using smoothing.
for i, matrix in enumerate(self._params):
mp = self._m * matrix
for yval, count in enumerate(yvals):
Xrel = Xstd[ystd == yval]
colbincount = np.bincount(Xrel[:, i], minlength=mp.shape[1])
matrix[yval] = (mp[yval] + colbincount)
matrix[yval] = matrix[yval] / (count + self._m)
self._params[i] = matrix
# Set the probabilities of y.
self._yparam = yvals / len(ystd)