def fit(self, X, y):
""" Fit model with specified loss.
Parameters
----------
X : scipy.sparse.csc_matrix, (n_samples, n_features)
y : float | ndarray, shape = (n_samples, )
the targets have to be encodes as {-1, 1}.
"""
y = _validate_class_labels(y)
self.classes_ = np.unique(y)
if len(self.classes_) != 2:
raise ValueError("This solver only supports binary classification"
" but the data contains"
" class: %r" % self.classes_)
# fastFM-core expects labels to be in {-1,1}
y_train = y.copy()
i_class1 = (y_train == self.classes_[0])
y_train[i_class1] = -1
y_train[-i_class1] = 1
check_consistent_length(X, y)
y = y.astype(np.float64)
X = X.T
X = check_array(X, accept_sparse="csc", dtype=np.float64)
self.w0_, self.w_, self.V_ = ffm.ffm_sgd_fit(self, X, y)
return self
def fit_predict_proba(self, X_train, y_train, X_test):
"""Return average class probabilities of posterior estimates of the
test samples.
Use only with MCMC!
Parameters
----------
X_train : scipy.sparse.csc_matrix, (n_samples, n_features)
y_train : array, shape (n_samples)
the targets have to be encodes as {-1, 1}.
X_test : scipy.sparse.csc_matrix, (n_test_samples, n_features)
Returns
-------
y_pred : array, shape (n_test_samples)
Returns probability estimates for the class with lowest
classification label.
"""
self.task = "classification"
self.classes_ = np.unique(y_train)
if len(self.classes_) != 2:
raise ValueError("This solver only supports binary classification"
" but the data contains"
" class: %r" % self.classes_)
# fastFM-core expects labels to be in {-1,1}
y_train = y_train.copy()
i_class1 = (y_train == self.classes_[0])
y_train[i_class1] = -1
y_train[-i_class1] = 1
X_train, y_train, X_test = _validate_mcmc_fit_input(X_train, y_train,
X_test)
y_train = _validate_class_labels(y_train)
coef, y_pred = ffm.ffm_mcmc_fit_predict(self, X_train,
X_test, y_train)
self.w0_, self.w_, self.V_ = coef
return y_pred
