def test_supervisedpcaClassifier():
iris=datasets.load_iris()
X = iris.data
Y = iris.target
spca = SupervisedPCAClassifier()
spca.fit(X, Y,threshold=1,n_components=2)
assert_array_equal(spca._leavouts,[0,1])
assert_almost_equal(spca._model.coef_[0][0], -2.43973048)
def test_supervisedpcaClassifier():
iris = datasets.load_iris()
X = iris.data
Y = iris.target
spca = SupervisedPCAClassifier()
spca.fit(X, Y, threshold=1, n_components=2)
assert_array_equal(spca._leavouts, [0, 1])
assert_almost_equal(spca._model.coef_[0][0], -2.43973048)
def test_supervisedpcaClassifier_predict():
iris=datasets.load_iris()
X = iris.data
Y = iris.target
spca = SupervisedPCAClassifier()
spca.fit(X, Y)
predictions = spca.predict(X)
error=np.mean(sum(abs(predictions-Y))/float(len(predictions)))
assert_almost_equal(error,0.08666666)
def test_supervisedpcaClassifier_predict():
iris = datasets.load_iris()
X = iris.data
Y = iris.target
spca = SupervisedPCAClassifier()
spca.fit(X, Y)
predictions = spca.predict(X)
error = np.mean(sum(abs(predictions - Y)) / float(len(predictions)))
assert_almost_equal(error, 0.08666666)
from SupervisedPCA import SupervisedPCARegressor from SupervisedPCA import SupervisedPCAClassifier from sklearn.utils.testing import assert_almost_equal from sklearn.utils.testing import assert_array_equal from sklearn import datasets import numpy as np diabetes = datasets.load_iris() X = diabetes.data Y = diabetes.target spca = SupervisedPCAClassifier() spca.fit(X, Y, threshold=1.7) print(spca._model.coef_)