def test_io_dfgenerator_wy_unlabeled():
X = pandas.DataFrame(numpy.random.randn(500, 13))
w = numpy.abs(numpy.random.randn(500))
y = numpy.random.randint(5, size=500) - 1
data = DataFrameGenerator(X, w, y)
X_ = numpy.concatenate([batch[0] for batch in data.unlabeled_batches()])
w_ = numpy.concatenate([batch[1] for batch in data.unlabeled_batches()])
assert_true(X.shape[0] > X_.shape[0])
assert_almost_equal(X.loc[y == -1], X_)
assert_almost_equal(w[y == -1], w_)
def test_io_predict_log_proba():
X2 = DataGenerator(X)
X3 = DataFrameGenerator(pandas.DataFrame(X))
y_hat1 = model.predict_log_proba(X)
y_hat2 = model.predict_log_proba(X2)
y_hat3 = model.predict_log_proba(X3)
assert_array_almost_equal(y_hat1, y_hat2)
assert_array_almost_equal(y_hat1, y_hat3)
def test_io_log_probability():
X2 = DataGenerator(X)
X3 = DataFrameGenerator(pandas.DataFrame(X))
logp1 = model.log_probability(X)
logp2 = model.log_probability(X2)
logp3 = model.log_probability(X3)
assert_array_almost_equal(logp1, logp2)
assert_array_almost_equal(logp1, logp3)
def test_io_dfgenerator_wy_str_labeled():
X = pandas.DataFrame(numpy.random.randn(500, 13))
X2 = X.copy()
w = numpy.abs(numpy.random.randn(500))
y = numpy.random.randint(5, size=500) - 1
X['w'] = w
X['y'] = y
data = DataFrameGenerator(X, 'w', 'y')
X_ = numpy.concatenate([batch[0] for batch in data.labeled_batches()])
y_ = numpy.concatenate([batch[1] for batch in data.labeled_batches()])
w_ = numpy.concatenate([batch[2] for batch in data.labeled_batches()])
assert_true(X.shape[0] > X_.shape[0])
assert_almost_equal(X2.loc[y != -1], X_)
assert_almost_equal(y[y != -1], y_)
assert_almost_equal(w[y != -1], w_)
def test_io_predict_log_proba(): X = numpy.random.randn(100, 5) + 0.5 X2 = DataGenerator(X) X3 = DataFrameGenerator(pandas.DataFrame(X)) d = MultivariateGaussianDistribution model = GeneralMixtureModel.from_samples(d, n_components=2, X=X) y_hat1 = model.predict_log_proba(X) y_hat2 = model.predict_log_proba(X2) y_hat3 = model.predict_log_proba(X3) assert_array_almost_equal(y_hat1, y_hat2) assert_array_almost_equal(y_hat1, y_hat3)
def test_io_log_probability(): X = numpy.random.randn(100, 5) + 0.5 X2 = DataGenerator(X) X3 = DataFrameGenerator(pandas.DataFrame(X)) d = MultivariateGaussianDistribution model = GeneralMixtureModel.from_samples(d, n_components=2, X=X) logp1 = model.log_probability(X) logp2 = model.log_probability(X2) logp3 = model.log_probability(X3) assert_array_almost_equal(logp1, logp2) assert_array_almost_equal(logp1, logp3)
def test_io_dfgenerator_wy_str_batches():
X = pandas.DataFrame(numpy.random.randn(500, 13))
X2 = X.copy()
w = numpy.abs(numpy.random.randn(500))
y = numpy.random.randint(5, size=500)
X['w'] = w
X['y'] = y
data = DataFrameGenerator(X, 'w', 'y')
X_ = numpy.concatenate([batch[0] for batch in data.batches()])
y_ = numpy.concatenate([batch[1] for batch in data.batches()])
w_ = numpy.concatenate([batch[2] for batch in data.batches()])
assert_almost_equal(X2.values, X_)
assert_almost_equal(y, y_)
assert_almost_equal(w, w_)
data = DataFrameGenerator(X, 'w', 'y', batch_size=123)
X_ = numpy.concatenate([batch[0] for batch in data.batches()])
y_ = numpy.concatenate([batch[1] for batch in data.batches()])
w_ = numpy.concatenate([batch[2] for batch in data.batches()])
assert_almost_equal(X2.values, X_)
assert_almost_equal(y, y_)
assert_almost_equal(w, w_)
data = DataFrameGenerator(X, 'w', 'y', batch_size=1)
X_ = numpy.concatenate([batch[0] for batch in data.batches()])
y_ = numpy.concatenate([batch[1] for batch in data.batches()])
w_ = numpy.concatenate([batch[2] for batch in data.batches()])
assert_almost_equal(X2.values, X_)
assert_almost_equal(y, y_)
assert_almost_equal(w, w_)
data = DataFrameGenerator(X, 'w', 'y', batch_size=506)
X_ = numpy.concatenate([batch[0] for batch in data.batches()])
y_ = numpy.concatenate([batch[1] for batch in data.batches()])
w_ = numpy.concatenate([batch[2] for batch in data.batches()])
assert_almost_equal(X2.values, X_)
assert_almost_equal(y, y_)
assert_almost_equal(w, w_)
def test_io_dfgenerator_wy_batches():
X = pandas.DataFrame(numpy.random.randn(500, 13))
w = numpy.abs(numpy.random.randn(500))
y = numpy.random.randint(5, size=500)
data = DataFrameGenerator(X, w, y)
X_ = numpy.concatenate([batch[0] for batch in data.batches()])
y_ = numpy.concatenate([batch[1] for batch in data.batches()])
w_ = numpy.concatenate([batch[2] for batch in data.batches()])
assert_almost_equal(X.values, X_)
assert_almost_equal(y, y_)
assert_almost_equal(w, w_)
data = DataFrameGenerator(X, w, y, batch_size=123)
X_ = numpy.concatenate([batch[0] for batch in data.batches()])
y_ = numpy.concatenate([batch[1] for batch in data.batches()])
w_ = numpy.concatenate([batch[2] for batch in data.batches()])
assert_almost_equal(X.values, X_)
assert_almost_equal(y, y_)
assert_almost_equal(w, w_)
data = DataFrameGenerator(X, w, y, batch_size=1)
X_ = numpy.concatenate([batch[0] for batch in data.batches()])
y_ = numpy.concatenate([batch[1] for batch in data.batches()])
w_ = numpy.concatenate([batch[2] for batch in data.batches()])
assert_almost_equal(X.values, X_)
assert_almost_equal(y, y_)
assert_almost_equal(w, w_)
data = DataFrameGenerator(X, w, y, batch_size=506)
X_ = numpy.concatenate([batch[0] for batch in data.batches()])
y_ = numpy.concatenate([batch[1] for batch in data.batches()])
w_ = numpy.concatenate([batch[2] for batch in data.batches()])
assert_almost_equal(X.values, X_)
assert_almost_equal(y, y_)
assert_almost_equal(w, w_)
def test_io_dfgenerator_x_batches():
X = pandas.DataFrame(numpy.random.randn(500, 13))
w = numpy.ones(500)
data = DataFrameGenerator(X)
X_ = numpy.concatenate([batch[0] for batch in data.batches()])
w_ = numpy.concatenate([batch[1] for batch in data.batches()])
assert_almost_equal(X.values, X_)
assert_almost_equal(w, w_)
data = DataFrameGenerator(X, batch_size=123)
X_ = numpy.concatenate([batch[0] for batch in data.batches()])
w_ = numpy.concatenate([batch[1] for batch in data.batches()])
assert_almost_equal(X.values, X_)
assert_almost_equal(w, w_)
data = DataFrameGenerator(X, batch_size=1)
X_ = numpy.concatenate([batch[0] for batch in data.batches()])
w_ = numpy.concatenate([batch[1] for batch in data.batches()])
assert_almost_equal(X.values, X_)
assert_almost_equal(w, w_)
data = DataFrameGenerator(X, batch_size=506)
X_ = numpy.concatenate([batch[0] for batch in data.batches()])
w_ = numpy.concatenate([batch[1] for batch in data.batches()])
assert_almost_equal(X.values, X_)
assert_almost_equal(w, w_)
def test_io_dfgenerator_str_classes():
X = pandas.DataFrame(numpy.random.randn(500, 13))
X['y'] = numpy.random.randint(5, size=500)
data = DataFrameGenerator(X, y='y')
assert_array_equal(data.classes, [0, 1, 2, 3, 4])
def test_io_dfgenerator_pandas_classes():
X = pandas.DataFrame(numpy.random.randn(500, 13))
y = pandas.Series(numpy.random.randint(5, size=500))
data = DataFrameGenerator(X, y=y)
assert_array_equal(data.classes, [0, 1, 2, 3, 4])
def test_io_dfgenerator_classes_fail():
X = pandas.DataFrame(numpy.random.randn(500, 13))
data = DataFrameGenerator(X)
assert_raises(ValueError, lambda data: data.classes, data)
def test_io_dfgenerator_shape():
X = pandas.DataFrame(numpy.random.randn(500, 13))
data = DataFrameGenerator(X)
assert_array_equal(data.shape, X.shape)
