def sklearn_comp(array):
self.logger.info("Original array is:\n{:}".format(array))
# Sklearn normalizer (requires float dtype input)
array_sk = array.astype(float).tondarray()
sk_norm = MinMaxScaler().fit(array_sk)
target = CArray(sk_norm.transform(array_sk))
# Our normalizer
our_norm = CNormalizerMinMax().fit(array)
result = our_norm.transform(array)
self.logger.info("Correct result is:\n{:}".format(target))
self.logger.info("Our result is:\n{:}".format(result))
self.assert_array_almost_equal(target, result)
# Testing out of range normalization
self.logger.info("Testing out of range normalization")
# Sklearn normalizer (requires float dtype input)
target = CArray(sk_norm.transform(array_sk * 2))
# Our normalizer
result = our_norm.transform(array * 2)
self.logger.info("Correct result is:\n{:}".format(target))
self.logger.info("Our result is:\n{:}".format(result))
self.assert_array_almost_equal(target, result)
def _dataset_creation(self):
"""Creates a blob dataset. """
self.n_features = 2 # Number of dataset features
self.seed = 42
self.n_tr = 50
self.n_ts = 100
self.n_classes = 2
loader = CDLRandomBlobs(n_samples=self.n_tr + self.n_ts,
n_features=self.n_features,
centers=[(-1, -1), (+1, +1)],
center_box=(-2, 2),
cluster_std=0.8,
random_state=self.seed)
self.logger.info("Loading `random_blobs` with seed: {:}".format(
self.seed))
dataset = loader.load()
splitter = CDataSplitterShuffle(num_folds=1,
train_size=self.n_tr,
random_state=3)
splitter.compute_indices(dataset)
self.tr = dataset[splitter.tr_idx[0], :]
self.ts = dataset[splitter.ts_idx[0], :]
normalizer = CNormalizerMinMax(feature_range=(-1, 1))
self.tr.X = normalizer.fit_transform(self.tr.X)
self.ts.X = normalizer.transform(self.ts.X)
self.lb = -1
self.ub = 1
self.grid_limits = [(self.lb - 0.1, self.ub + 0.1),
(self.lb - 0.1, self.ub + 0.1)]