def fit(self,
X,
y,
src_index,
tgt_index,
fit_params_src=None,
**fit_params_tgt):
"""
Fit RegularTransferNN
Parameters
----------
X : numpy array
Input data.
y : numpy array
Output data.
src_index : iterable
indexes of source labeled data in X, y.
tgt_index : iterable
indexes of target unlabeled data in X, y.
fit_params_src : dict, optional (default=None)
Arguments given to the fit method of the
source estimator (epochs, batch_size...).
If None, ``fit_params_src = fit_params_tgt``
fit_params_tgt : key, value arguments
Arguments given to the fit method of the
target estimator (epochs, batch_size...).
Returns
-------
self : returns an instance of self
"""
if fit_params_src is None:
fit_params_src = fit_params_tgt
check_indexes(src_index, tgt_index)
self.model_src_ = check_network(self.get_network,
"get_network",
input_shape=X.shape[1:],
output_shape=y.shape[1:],
**self.kwargs)
if self.fit_source:
self.model_src_.fit(X[src_index], y[src_index], **fit_params_src)
layers = self.model_src_.layers
lambdas, trainables = self._get_lambdas_and_trainables(layers)
self.model_tgt_ = _add_regularization(self.model_src_, lambdas,
trainables)
self.model_tgt_.fit(X[tgt_index], y[tgt_index], **fit_params_tgt)
return self
def fit(self,
X,
y,
src_index,
tgt_index,
tgt_index_labeled=None,
fit_params_src=None,
**fit_params_tgt):
"""
Fit ADDA.
Parameters
----------
X : numpy array
Input data.
y : numpy array
Output data.
src_index : iterable
indexes of source labeled data in X, y.
tgt_index : iterable
indexes of target unlabeled data in X, y.
tgt_index_labeled : iterable, optional (default=None)
indexes of target labeled data in X, y.
fit_params_src : dict, optional (default=None)
Arguments given to the fit process of source encoder
and task networks (epochs, batch_size...).
If None, ``fit_params_src = fit_params_tgt``
fit_params_tgt : key, value arguments
Arguments given to the fit method of the ADDA model,
i.e. fitting of target encoder and discriminator.
(epochs, batch_size...).
Returns
-------
self : returns an instance of self
"""
check_indexes(src_index, tgt_index, tgt_index_labeled)
if fit_params_src is None:
fit_params_src = fit_params_tgt
if tgt_index_labeled is None:
src_index_bis = src_index
else:
src_index_bis = np.concatenate((src_index, tgt_index_labeled))
self._create_model(X.shape[1:], y.shape[1:])
max_size = max(len(src_index_bis), len(tgt_index))
resize_tgt_ind = np.resize(tgt_index, max_size)
resize_src_ind = np.resize(src_index_bis, max_size)
self.src_model_.fit(X[src_index_bis], y[src_index_bis],
**fit_params_src)
self.tgt_model_.fit(
[self.src_encoder_.predict(X[resize_src_ind]), X[resize_tgt_ind]],
**fit_params_tgt)
return self
def fit(self,
X,
y,
src_index,
tgt_index,
tgt_index_labeled=None,
sample_weight=None,
**fit_params):
"""
Fit encoder and task networks.
Source data and unlabeled target data are used for the correlation
alignment in the encoded space.
Source data and labeled target data are used to learn the task.
Parameters
----------
X : numpy array
Input data.
y : numpy array
Output data.
src_index : iterable
indexes of source labeled data in X, y.
tgt_index : iterable
indexes of target unlabeled data in X, y.
tgt_index_labeled : iterable, optional (default=None)
indexes of target labeled data in X, y.
sample_weight : numpy array, optional (default=None)
Individual weights for each sample.
fit_params : key, value arguments
Arguments given to the fit method of the estimator
(epochs, batch_size...).
Returns
-------
self : returns an instance of self
"""
check_indexes(src_index, tgt_index, tgt_index_labeled)
self._create_model(X.shape[1:], y.shape[1:])
if tgt_index_labeled is None:
task_index = src_index
else:
task_index = np.concatenate((src_index, tgt_index_labeled))
max_size = max((len(src_index), len(tgt_index), len(task_index)))
resized_src_ind = np.resize(src_index, max_size)
resized_tgt_ind = np.resize(tgt_index, max_size)
resized_task_ind = np.resize(task_index, max_size)
self.model_.fit([
X[resized_src_ind], X[resized_tgt_ind], X[resized_task_ind],
y[resized_task_ind],
np.ones(max_size)
], **fit_params)
return self
def fit(self,
X,
y,
src_index,
tgt_index,
tgt_index_labeled=None,
sample_weight=None,
**fit_params):
"""
Perfrom correlation alignement on input source data to match
input target data (given by ``tgt_index``).
Then fit estimator on the aligned source data and the labeled
target ones (given by ``tgt_index_labeled``).
Parameters
----------
X : numpy array
Input data.
y : numpy array
Output data.
src_index : iterable
indexes of source labeled data in X, y.
tgt_index : iterable
indexes of target unlabeled data in X, y.
tgt_index_labeled : iterable, optional (default=None)
indexes of target labeled data in X, y.
sample_weight : numpy array, optional (default=None)
Individual weights for each sample.
fit_params : key, value arguments
Arguments given to the fit method of the estimator
(epochs, batch_size...).
Returns
-------
self : returns an instance of self
"""
check_indexes(src_index, tgt_index, tgt_index_labeled)
Xs = X[src_index]
ys = y[src_index]
Xt = X[tgt_index]
yt = y[tgt_index]
self.estimator_ = check_estimator(self.get_estimator, **self.kwargs)
self.Cs_ = np.cov(Xs,
rowvar=False) + self.lambdap * np.eye(Xs.shape[1])
self.Ct_ = np.cov(Xt,
rowvar=False) + self.lambdap * np.eye(Xt.shape[1])
Xs = np.matmul(Xs, linalg.inv(linalg.sqrtm(self.Cs_)))
Xs = np.matmul(Xs, linalg.sqrtm(self.Ct_))
if tgt_index_labeled is None:
X = Xs
y = ys
else:
X = np.concatenate((Xs, X[tgt_index_labeled]))
y = np.concatenate((ys, y[tgt_index_labeled]))
if sample_weight is None:
self.estimator_.fit(X, y, **fit_params)
else:
if tgt_index_labeled is None:
sample_weight = sample_weight[src_index]
else:
sample_weight = np.concatenate(
(sample_weight[src_index],
sample_weight[tgt_index_labeled]))
self.estimator_.fit(X,
y,
sample_weight=sample_weight,
**fit_params)
return self
def fit(self, X, y, src_index, tgt_index,
tgt_index_labeled=None, **fit_params):
"""
Fit KLIEP.
Parameters
----------
X : numpy array
Input data.
y : numpy array
Output data.
src_index : iterable
indexes of source labeled data in X, y.
tgt_index : iterable
indexes of target unlabeled data in X, y.
tgt_index_labeled : iterable, optional (default=None)
indexes of target labeled data in X, y.
fit_params : key, value arguments
Arguments given to the fit method of the estimator
(epochs, batch_size...).
Returns
-------
self : returns an instance of self
"""
check_indexes(src_index, tgt_index, tgt_index_labeled)
if tgt_index_labeled is None:
Xs = X[src_index]
ys = y[src_index]
else:
Xs = X[np.concatenate(
(src_index, tgt_index_labeled)
)]
ys = y[np.concatenate(
(src_index, tgt_index_labeled)
)]
Xt = X[tgt_index]
self.j_scores_ = []
if hasattr(self.sigmas, "__len__") and len(self.sigmas) > 1:
for sigma in self.sigmas:
split = int(len(tgt_index) / self.cv)
j_scores = []
for i in range(self.cv):
if i == self.cv-1:
test_index = tgt_index[i * split:]
else:
test_index = tgt_index[i * split:
(i + 1) * split]
train_index = np.array(
list(set(tgt_index) - set(test_index))
)
alphas, centers = self._fit(Xs,
X[train_index],
sigma)
j_score = (1 / len(test_index)) * np.sum(np.log(
np.dot(
np.transpose(alphas),
pairwise.rbf_kernel(centers,
X[test_index],
sigma)
)
))
j_scores.append(j_score)
self.j_scores_.append(np.mean(j_score))
self.sigma_ = self.sigmas[np.argmax(self.j_scores_)]
else:
try:
self.sigma_ = self.sigmas[0]
except:
self.sigma_ = self.sigmas
self.alphas_, self.centers_ = self._fit(Xs, Xt, self.sigma_)
self.weights_ = np.dot(
np.transpose(self.alphas_),
pairwise.rbf_kernel(self.centers_, Xs, self.sigma_)
).ravel()
self.estimator_ = check_estimator(self.get_estimator, **self.kwargs)
try:
self.estimator_.fit(Xs, ys,
sample_weight=self.weights_,
**fit_params)
except:
bootstrap_index = np.random.choice(
len(Xs), size=len(Xs), replace=True,
p=self.weights_ / self.weights_.sum())
self.estimator_.fit(Xs[bootstrap_index], ys[bootstrap_index],
**fit_params)
return self
def fit(self,
X,
y,
src_index,
tgt_index,
tgt_index_labeled=None,
**fit_params):
"""
Fit DANN.
Parameters
----------
X : numpy array
Input data.
y : numpy array
Output data.
src_index : iterable
indexes of source labeled data in X, y.
tgt_index : iterable
indexes of target unlabeled data in X, y.
tgt_index_labeled : iterable, optional (default=None)
indexes of target labeled data in X, y.
fit_params : key, value arguments
Arguments given to the fit method of DANN model
(epochs, batch_size...).
Returns
-------
self : returns an instance of self
"""
check_indexes(src_index, tgt_index, tgt_index_labeled)
if self.lambdap is None:
self.lambdap = K.variable(0.)
self._create_model(X.shape[1:], y.shape[1:])
if tgt_index_labeled is None:
task_index = src_index
else:
task_index = np.concatenate((src_index, tgt_index_labeled))
disc_index = np.concatenate((src_index, tgt_index))
labels = np.array([0] * len(src_index) + [1] * len(tgt_index))
max_size = max(len(disc_index), len(task_index))
resized_task_ind = np.resize(task_index, max_size)
resized_disc_ind = np.resize(disc_index, max_size)
if self.lambdap is None:
callback = _IncreaseLambda(self.lambdap, self.gamma)
if "callbacks" in fit_prams:
fit_prams["callbacks"].append(callback)
else:
fit_prams["callbacks"] = [callback]
self.model_.fit([X[resized_task_ind], X[resized_disc_ind]],
[y[resized_task_ind], labels[resized_disc_ind]],
**fit_params)
return self
def fit(self,
X,
y,
src_index,
tgt_index,
fit_params_src=None,
**fit_params_tgt):
"""
Fit RegularTransferLR
Parameters
----------
X : numpy array
Input data.
y : numpy array
Output data. Binary {-1, 1}
src_index : iterable
indexes of source labeled data in X, y.
tgt_index : iterable
indexes of target unlabeled data in X, y.
fit_params_src : dict, optional (default=None)
Arguments given to the fit method of the
source estimator (epochs, batch_size...).
If None, ``fit_params_src = fit_params_tgt``
fit_params_tgt : key, value arguments
Arguments given to the fit method of the
target estimator (epochs, batch_size...).
Returns
-------
self : returns an instance of self
"""
if fit_params_src is None:
fit_params_src = fit_params_tgt
check_indexes(src_index, tgt_index)
if not np.all(
np.isin(y[np.concatenate((src_index, tgt_index))], [-1., 1.])):
raise ValueError("y values should be in {-1, 1}")
self.estimator_src_ = check_estimator(self.get_estimator,
**self.kwargs)
if (not isinstance(self.estimator_src_, LogisticRegression)
and not isinstance(self.estimator_src_, RidgeClassifier)):
raise ValueError("'get_estimator' should return a"
" LogisticRegression or RidgeClassifier"
" instance.")
if self.fit_source:
self.estimator_src_.fit(X[src_index], y[src_index],
**fit_params_src)
if self.intercept:
beta_src = np.concatenate(
(np.array([self.estimator_src_.intercept_[0]]),
self.estimator_src_.coef_[0]))
Xt = np.concatenate((np.ones((len(tgt_index), 1)), X[tgt_index]),
axis=1)
else:
beta_src = self.estimator_src_.coef_[0]
Xt = X[tgt_index]
yt = y[tgt_index]
# assert False, "%s"%str(beta_src)
def func(beta):
return (np.sum(
np.log(1 + np.exp(-yt * Xt.dot(beta.reshape(-1, 1)).ravel())))
+ self.lambdap * np.linalg.norm(beta - beta_src)**2)
beta_tgt = minimize(func, beta_src)['x']
if self.intercept:
self.intercept_ = beta_tgt[0]
self.coef_ = beta_tgt[1:]
else:
self.intercept_ = 0.
self.coef_ = beta_tgt
return self
def fit(self,
X,
y,
src_index,
tgt_index,
fit_params_src=None,
**fit_params_tgt):
"""
Fit RegularTransferLR
Parameters
----------
X : numpy array
Input data.
y : numpy array
Output data.
src_index : iterable
indexes of source labeled data in X, y.
tgt_index : iterable
indexes of target unlabeled data in X, y.
fit_params_src : dict, optional (default=None)
Arguments given to the fit method of the
source estimator (epochs, batch_size...).
If None, ``fit_params_src = fit_params_tgt``
fit_params_tgt : key, value arguments
Arguments given to the fit method of the
target estimator (epochs, batch_size...).
Returns
-------
self : returns an instance of self
"""
if fit_params_src is None:
fit_params_src = fit_params_tgt
check_indexes(src_index, tgt_index)
self.estimator_src_ = check_estimator(self.get_estimator,
**self.kwargs)
if (not isinstance(self.estimator_src_, LinearRegression)
and not isinstance(self.estimator_src_, Ridge)):
raise ValueError("'get_estimator' should return a"
" LinearRegression or Ridge instance.")
if self.fit_source:
self.estimator_src_.fit(X[src_index], y[src_index],
**fit_params_src)
if self.intercept:
beta_src = np.concatenate(
(np.array([self.estimator_src_.intercept_]),
self.estimator_src_.coef_))
Xt = np.concatenate((np.ones((len(tgt_index), 1)), X[tgt_index]),
axis=1)
else:
beta_src = self.estimator_src_.coef_
Xt = X[tgt_index]
yt = y[tgt_index]
def func(beta):
return (np.linalg.norm(Xt.dot(beta.reshape(-1, 1)) - yt)**2 +
self.lambdap * np.linalg.norm(beta - beta_src)**2)
beta_tgt = minimize(func, beta_src)['x']
if self.intercept:
self.intercept_ = beta_tgt[0]
self.coef_ = beta_tgt[1:]
else:
self.intercept_ = 0.
self.coef_ = beta_tgt
return self
def fit(self,
X,
y,
src_index,
tgt_index,
tgt_index_labeled=None,
fit_params_ae=None,
**fit_params):
"""
Fit mSDA.
Parameters
----------
X : numpy array
Input data.
y : numpy array
Output data.
src_index : iterable
indexes of source labeled data in X, y.
tgt_index : iterable
indexes of target unlabeled data in X, y.
tgt_index_labeled : iterable, optional (default=None)
indexes of target labeled data in X, y.
fit_params_ae : dict, optional (default=None)
Arguments given to the fit process of the autoencoder
(epochs, batch_size...).
If None, ``fit_params_ae = fit_params``
fit_params : key, value arguments
Arguments given to the fit method of the estimator
(epochs, batch_size...).
Returns
-------
self : returns an instance of self
"""
check_indexes(src_index, tgt_index, tgt_index_labeled)
if fit_params_ae is None:
fit_params_ae = fit_params
ae_index = np.concatenate((src_index, tgt_index))
if tgt_index_labeled is None:
task_index = src_index
else:
task_index = np.concatenate((src_index, tgt_index_labeled))
self.encoder_ = check_network(self.get_encoder,
"get_encoder",
input_shape=X.shape[1:],
**self.enc_params)
self.decoder_ = check_network(
self.get_decoder,
"get_decoder",
input_shape=self.encoder_.output_shape[1:],
output_shape=X.shape[1:],
**self.dec_params)
self.estimator_ = check_estimator(self.get_estimator,
**self.est_params)
inputs = Input(X.shape[1:])
noised = GaussianNoise(self.noise_lvl)(inputs)
encoded = self.encoder_(noised)
decoded = self.decoder_(encoded)
self.autoencoder_ = Model(inputs, decoded, name="AutoEncoder")
compil_params = copy.deepcopy(self.compil_params)
if not "loss" in compil_params:
compil_params["loss"] = "mean_squared_error"
if not "optimizer" in compil_params:
compil_params["optimizer"] = "adam"
self.autoencoder_.compile(**compil_params)
self.autoencoder_.fit(X[ae_index], X[ae_index], **fit_params_ae)
self.estimator_.fit(self.encoder_.predict(X[task_index]),
y[task_index], **fit_params)
return self
def fit(self,
X,
y,
src_index,
tgt_index,
tgt_index_labeled=None,
**fit_params):
"""
Fit KMM.
Parameters
----------
X : numpy array
Input data.
y : numpy array
Output data.
src_index : iterable
indexes of source labeled data in X, y.
tgt_index : iterable
indexes of target unlabeled data in X, y.
tgt_index_labeled : iterable, optional (default=None)
indexes of target labeled data in X, y.
fit_params : key, value arguments
Arguments given to the fit method of the estimator
(epochs, batch_size...).
Returns
-------
self : returns an instance of self
"""
check_indexes(src_index, tgt_index, tgt_index_labeled)
if tgt_index_labeled is None:
Xs = X[src_index]
ys = y[src_index]
else:
Xs = X[np.concatenate((src_index, tgt_index_labeled))]
ys = y[np.concatenate((src_index, tgt_index_labeled))]
Xt = X[tgt_index]
n_s = len(Xs)
n_t = len(Xt)
# Get epsilon
if self.epsilon is None:
self.epsilon = (np.sqrt(n_s) - 1) / np.sqrt(n_s)
# Compute Kernel Matrix
K = pairwise.pairwise_kernels(Xs,
Xs,
metric=self.kernel,
**self.kernel_params)
K = (1 / 2) * (K + K.transpose())
# Compute q
kappa = pairwise.pairwise_kernels(Xs,
Xt,
metric=self.kernel,
**self.kernel_params)
kappa = (n_s / n_t) * np.dot(kappa, np.ones((n_t, 1)))
constraints = LinearConstraint(np.ones((1, n_s)),
lb=n_s * (1 - self.epsilon),
ub=n_s * (1 + self.epsilon))
def func(x):
return (1 / 2) * x.T @ (K @ x) - kappa.T @ x
weights = minimize(func,
x0=np.ones((n_s, 1)),
bounds=[(0, self.B)] * n_s,
constraints=constraints)['x']
self.weights_ = np.array(weights).ravel()
self.estimator_ = check_estimator(self.get_estimator, **self.kwargs)
try:
self.estimator_.fit(Xs,
ys,
sample_weight=self.weights_,
**fit_params)
except:
bootstrap_index = np.random.choice(len(Xs),
size=len(Xs),
replace=True,
p=self.weights_ /
self.weights_.sum())
self.estimator_.fit(Xs[bootstrap_index], ys[bootstrap_index],
**fit_params)
return self
def fit(self,
X,
y,
src_index,
tgt_index,
sample_weight=None,
**fit_params):
"""
Fit TwoStageTrAdaBoostR2.
Parameters
----------
X : numpy array
Input data.
y : numpy array
Output data.
src_index : iterable
indexes of source labeled data in X, y.
tgt_index : iterable
indexes of target unlabeled data in X, y.
sample_weight : numpy array, optional (default=None)
Individual weights for each sample.
fit_params : key, value arguments
Arguments given to the fit method of the estimator
(epochs, batch_size...).
Returns
-------
self : returns an instance of self
"""
check_indexes(src_index, tgt_index)
n_s = len(src_index)
n_t = len(tgt_index)
if sample_weight is None:
sample_weight_src = np.ones(n_s) / (n_s + n_t)
sample_weight_tgt = np.ones(n_t) / (n_s + n_t)
else:
sum_weights = (sample_weight[src_index].sum() +
sample_weight[tgt_index].sum())
sample_weight_src = sample_weight[src_index] / sum_weights
sample_weight_tgt = sample_weight[tgt_index] / sum_weights
self.sample_weights_src_ = []
self.sample_weights_tgt_ = []
self.estimators_ = []
self.estimator_errors_ = []
for iboost in range(self.n_estimators):
self.sample_weights_src_.append(np.copy(sample_weight_src))
self.sample_weights_tgt_.append(np.copy(sample_weight_tgt))
cv_score = self._cross_val_score(X, y, src_index, tgt_index,
sample_weight_src,
sample_weight_tgt, **fit_params)
self.estimator_errors_.append(cv_score.mean())
sample_weight_src, sample_weight_tgt = self._boost(
iboost, X, y, src_index, tgt_index, sample_weight_src,
sample_weight_tgt, **fit_params)
if sample_weight_src is None:
break
sum_weights = (sample_weight_src.sum() + sample_weight_tgt.sum())
sample_weight_src = sample_weight_src / sum_weights
sample_weight_tgt = sample_weight_tgt / sum_weights
self.estimator_errors_ = np.array(self.estimator_errors_)
return self