def test_MLPClassifier(irisDataSet, irisClassificationTestCase, testResources):
featureNames = irisDataSet.getInputOutputData().inputs.columns
dftNorm = DFTNormalisation([DFTNormalisation.Rule(re.escape(f)) for f in featureNames], defaultTransformerFactory=sklearn.preprocessing.StandardScaler)
model = sensai.torch.models.MultiLayerPerceptronVectorClassificationModel(hiddenDims=(50,25,8), cuda=False, epochs=100, optimiser="adam",
batchSize=200, normalisationMode=NormalisationMode.NONE, hidActivationFunction=torch.tanh) \
.withName("torchMLPClassifier") \
.withInputTransformers([dftNorm]) \
.withFeatureGenerator(FeatureGeneratorTakeColumns())
irisClassificationTestCase.testMinAccuracy(model, 0.8)
def test_multiColumnSingleRule(self):
arr = np.array([1, 5, 10])
df = pd.DataFrame({"foo": arr, "bar": arr * 100})
dft = DFTNormalisation([
DFTNormalisation.Rule(
r"foo|bar",
transformer=sklearn.preprocessing.MaxAbsScaler(),
independentColumns=False)
])
df2 = dft.fitApply(df)
assert np.all(df2.foo == arr / 1000) and np.all(df2.bar == arr / 10)
def test_arrayValued(self):
arr = np.array([1, 5, 10])
df = pd.DataFrame({"foo": [arr, 2 * arr, 10 * arr]})
dft = DFTNormalisation([
DFTNormalisation.Rule(
r"foo|bar",
transformer=sklearn.preprocessing.MaxAbsScaler(),
arrayValued=True)
])
df2 = dft.fitApply(df)
assert np.all(df2.foo.iloc[0] == arr /
100) and np.all(df2.foo.iloc[-1] == arr / 10)