def test_transform_target_regressor_functions_multioutput():
X = friedman[0]
y = np.vstack((friedman[1], friedman[1] ** 2 + 1)).T
regr = TransformedTargetRegressor(regressor=LinearRegression(),
func=np.log, inverse_func=np.exp)
y_pred = regr.fit(X, y).predict(X)
# check the transformer output
y_tran = regr.transformer_.transform(y)
assert_allclose(np.log(y), y_tran)
assert_allclose(y, regr.transformer_.inverse_transform(y_tran))
assert y.shape == y_pred.shape
assert_allclose(y_pred, regr.inverse_func(regr.regressor_.predict(X)))
# check the regressor output
lr = LinearRegression().fit(X, regr.func(y))
assert_allclose(regr.regressor_.coef_.ravel(), lr.coef_.ravel())
def test_transform_target_regressor_functions_multioutput():
X = friedman[0]
y = np.vstack((friedman[1], friedman[1] ** 2 + 1)).T
regr = TransformedTargetRegressor(regressor=LinearRegression(),
func=np.log, inverse_func=np.exp)
y_pred = regr.fit(X, y).predict(X)
# check the transformer output
y_tran = regr.transformer_.transform(y)
assert_allclose(np.log(y), y_tran)
assert_allclose(y, regr.transformer_.inverse_transform(y_tran))
assert y.shape == y_pred.shape
assert_allclose(y_pred, regr.inverse_func(regr.regressor_.predict(X)))
# check the regressor output
lr = LinearRegression().fit(X, regr.func(y))
assert_allclose(regr.regressor_.coef_.ravel(), lr.coef_.ravel())
def test_transform_target_regressor_functions():
X, y = friedman
regr = TransformedTargetRegressor(regressor=LinearRegression(),
func=np.log, inverse_func=np.exp)
y_pred = regr.fit(X, y).predict(X)
# check the transformer output
y_tran = regr.transformer_.transform(y.reshape(-1, 1)).squeeze()
assert_allclose(np.log(y), y_tran)
assert_allclose(y, regr.transformer_.inverse_transform(
y_tran.reshape(-1, 1)).squeeze())
assert y.shape == y_pred.shape
assert_allclose(y_pred, regr.inverse_func(regr.regressor_.predict(X)))
# check the regressor output
lr = LinearRegression().fit(X, regr.func(y))
assert_allclose(regr.regressor_.coef_.ravel(), lr.coef_.ravel())
def test_transform_target_regressor_functions():
X, y = friedman
regr = TransformedTargetRegressor(regressor=LinearRegression(),
func=np.log, inverse_func=np.exp)
y_pred = regr.fit(X, y).predict(X)
# check the transformer output
y_tran = regr.transformer_.transform(y.reshape(-1, 1)).squeeze()
assert_allclose(np.log(y), y_tran)
assert_allclose(y, regr.transformer_.inverse_transform(
y_tran.reshape(-1, 1)).squeeze())
assert y.shape == y_pred.shape
assert_allclose(y_pred, regr.inverse_func(regr.regressor_.predict(X)))
# check the regressor output
lr = LinearRegression().fit(X, regr.func(y))
assert_allclose(regr.regressor_.coef_.ravel(), lr.coef_.ravel())
class SemiSup_RandomizedSearchCV(BaseEstimator):
def __init__(self, estimator, param_distributions, n_iter=100, cv=5, scoring=metrics.accuracy_score, pseudo=True):
# We initialize our class similar to sklearn randomized search
self.estimator = estimator
self.scoring = scoring
self.pseudo = pseudo
self.transformedtargetestimator = TransformedTargetRegressor(regressor=estimator,
func=lambda x: x if np.random.rand() > 1/cv else -1,
inverse_func=lambda x: x, check_inverse=False)
self.scoring = scoring
self.sampler = ParameterSampler(param_distributions, n_iter)
self.cv_results_ = pd.DataFrame({'mean_test_score': np.empty(shape=[0]),
'std_test_score': np.empty(shape=[0]),
'mean_score_time': np.empty(shape=[0]),
'std_score_time': np.empty(shape=[0]),
'params': None})
self.folds = KFold(n_splits=cv)
def fit(self, X, y, sample_weight=None):
for params in self.sampler:
# Update Parameters
self.estimator.set_params(**params)
# Reset Scores
scores = []
times = []
for train_index, test_index in self.folds.split(X):
#Create Semisupervised Sampler
self.transformedtargetestimator = TransformedTargetRegressor(regressor=self.estimator,
func=lambda x: np.where(np.in1d(x.index,train_index),x,-1),
inverse_func=lambda x: x, check_inverse=False)
#Fit
if self.pseudo:
self.transformedtargetestimator.regressor.pseudo_fit = pseudo_fit.__get__(self.transformedtargetestimator.regressor)
self.transformedtargetestimator = self.transformedtargetestimator.regressor.pseudo_fit(X, self.transformedtargetestimator.func(y))
else:
self.transformedtargetestimator.fit(X, y, sample_weight)
#Score
score_index = np.in1d(y.index,test_index)
start = time()
scores.append(self.scoring(y[score_index], self.transformedtargetestimator.predict(X=X[score_index])))
times.append(time()-start)
self.cv_results_ = self.cv_results_.append(pd.DataFrame({'mean_test_score': np.mean(scores),
'std_test_score': np.std(scores),
'mean_score_time': np.mean(times),
'std_score_time': np.std(times),
'params': [params]}))
self.cv_results_ = self.cv_results_.sort_values('mean_test_score', ascending=False).reset_index(drop=True)
return self