def main():
"""
Linear regression example with plot
"""
# Example data
x = np.array([
1000, 4000, 5000, 4500, 3000, 4000, 9000, 11000, 15000, 12000, 7000,
3000
])
y = np.array([
9914, 40487, 54324, 50044, 34719, 42551, 94871, 118914, 158484, 131348,
78504, 36284
])
x_ds = ds.array(x[:, np.newaxis], (4, 1))
y_ds = ds.array(y[:, np.newaxis], (4, 1))
reg = LinearRegression()
reg.fit(x_ds, y_ds)
coef = reg.coef_.collect()
intercept = reg.intercept_.collect()
print(coef, intercept)
# plot_result:
scatter(x, y, marker='x')
x_mesh = np.linspace(min(x), max(x), 1000)
plot(x_mesh, [coef * x + intercept for x in x_mesh])
show()
def test_fit_and_predict(self):
"""Tests LinearRegression's fit() and predict()"""
x_data = np.array([1, 2, 3, 4, 5]).reshape(-1, 1)
y_data = np.array([2, 1, 1, 2, 4.5]).reshape(-1, 1)
bn, bm = 2, 2
x = ds.array(x=x_data, block_size=(bn, bm))
y = ds.array(x=y_data, block_size=(bn, bm))
reg = LinearRegression()
reg.fit(x, y)
# y = 0.6 * x + 0.3
reg.coef_ = compss_wait_on(reg.coef_)
reg.intercept_ = compss_wait_on(reg.intercept_)
self.assertTrue(np.allclose(reg.coef_, 0.6))
self.assertTrue(np.allclose(reg.intercept_, 0.3))
x_test = np.array([3, 5]).reshape(-1, 1)
test_data = ds.array(x=x_test, block_size=(bn, bm))
pred = reg.predict(test_data).collect()
self.assertTrue(np.allclose(pred, [2.1, 3.3]))
def test_linear_regression(self):
""" Tests linear regression fit_predict and compares the result with
regular ds-arrays """
config.session.execute("TRUNCATE TABLE hecuba.istorage")
config.session.execute("DROP KEYSPACE IF EXISTS hecuba_dislib")
x_data = np.array([1, 2, 3, 4, 5]).reshape(-1, 1)
y_data = np.array([2, 1, 1, 2, 4.5]).reshape(-1, 1)
block_size = (x_data.shape[0] // 3, x_data.shape[1])
x = ds.array(x=x_data, block_size=block_size)
x.make_persistent(name="hecuba_dislib.test_array_x")
y = ds.array(x=y_data, block_size=block_size)
y.make_persistent(name="hecuba_dislib.test_array_y")
reg = LinearRegression()
reg.fit(x, y)
# y = 0.6 * x + 0.3
reg.coef_ = compss_wait_on(reg.coef_)
reg.intercept_ = compss_wait_on(reg.intercept_)
self.assertTrue(np.allclose(reg.coef_, 0.6))
self.assertTrue(np.allclose(reg.intercept_, 0.3))
x_test = np.array([3, 5]).reshape(-1, 1)
test_data = ds.array(x=x_test, block_size=block_size)
test_data.make_persistent(name="hecuba_dislib.test_array_test")
pred = reg.predict(test_data).collect()
self.assertTrue(np.allclose(pred, [2.1, 3.3]))
def test_sparse(self):
"""Tests LR raises NotImplementedError for sparse data."""
np.random.seed(0)
coo_matrix = sp_random(10, 1, density=0.5)
sparse_arr = ds.array(x=coo_matrix, block_size=(5, 1))
reg = LinearRegression()
with self.assertRaises(NotImplementedError):
reg.fit(sparse_arr, sparse_arr)
dense_arr = random_array((10, 1), (5, 1))
reg.fit(dense_arr, dense_arr)
with self.assertRaises(NotImplementedError):
reg.predict(sparse_arr)
def main():
x_kdd = ds.load_txt_file(
"/gpfs/projects/bsc19/COMPSs_DATASETS/dislib/kdd99/train.csv",
block_size=(11482, 122))
y_kdd = x_kdd[:, 121:122]
x_kdd = x_kdd[:, :121]
regression = LinearRegression(arity=48)
performance.measure("LR", "KDD99", regression.fit, x_kdd, y_kdd)
def test_multivariate_no_intercept(self):
"""Tests fit() and predict(), multivariate, fit_intercept=False."""
x_data = np.array([[1, 2], [2, 0], [3, 1], [4, 4], [5, 3]])
y_data = np.array([2, 1, 1, 2, 4.5])
bn, bm = 2, 2
x = ds.array(x=x_data, block_size=(bn, bm))
y = ds.array(x=y_data, block_size=(bn, 1))
reg = LinearRegression(fit_intercept=False)
reg.fit(x, y)
self.assertTrue(
np.allclose(reg.coef_.collect(), [0.48305085, 0.30367232]))
self.assertTrue(np.allclose(reg.intercept_.collect(), 0))
# Predict one sample
x_test = np.array([3, 2])
test_data = ds.array(x=x_test, block_size=(1, bm))
pred = reg.predict(test_data).collect()
self.assertTrue(np.allclose(pred, [2.05649718]))
# Predict multiple samples
x_test = np.array([[3, 2], [4, 4], [1, 3]])
test_data = ds.array(x=x_test, block_size=(bn, bm))
pred = reg.predict(test_data).collect()
self.assertTrue(np.allclose(pred, [2.05649718, 3.14689266, 1.3940678]))
def test_multivariate(self):
"""Tests fit() and predict(), multivariate."""
x_data = np.array([[1, 2], [2, 0], [3, 1], [4, 4], [5, 3]])
y_data = np.array([2, 1, 1, 2, 4.5])
bn, bm = 2, 2
x = ds.array(x=x_data, block_size=(bn, bm))
y = ds.array(x=y_data, block_size=(bn, 1))
reg = LinearRegression()
reg.fit(x, y)
self.assertTrue(np.allclose(reg.coef_.collect(), [0.421875, 0.296875]))
self.assertTrue(np.allclose(reg.intercept_.collect(), 0.240625))
# Predict one sample
x_test = np.array([3, 2])
test_data = ds.array(x=x_test, block_size=(1, bm))
pred = reg.predict(test_data).collect()
self.assertTrue(np.allclose(pred, 2.1))
# Predict multiple samples
x_test = np.array([[3, 2], [4, 4], [1, 3]])
test_data = ds.array(x=x_test, block_size=(bn, bm))
pred = reg.predict(test_data).collect()
self.assertTrue(np.allclose(pred, [2.1, 3.115625, 1.553125]))
def test_univariate_no_intercept(self):
"""Tests fit() and predict(), univariate, fit_intercept=False."""
x_data = np.array([1, 2, 3, 4, 5])
y_data = np.array([2, 1, 1, 2, 4.5])
bn, bm = 2, 1
x = ds.array(x=x_data, block_size=(bn, bm))
y = ds.array(x=y_data, block_size=(bn, bm))
reg = LinearRegression(fit_intercept=False)
reg.fit(x, y)
self.assertTrue(np.allclose(reg.coef_.collect(), 0.68181818))
self.assertTrue(np.allclose(reg.intercept_.collect(), 0))
# Predict one sample
x_test = np.array([3])
test_data = ds.array(x=x_test, block_size=(1, 1))
pred = reg.predict(test_data).collect()
self.assertTrue(np.allclose(pred, 2.04545455))
# Predict multiple samples
x_test = np.array([3, 5, 6])
test_data = ds.array(x=x_test, block_size=(bn, bm))
pred = reg.predict(test_data).collect()
self.assertTrue(np.allclose(pred, [2.04545455, 3.4090909, 4.0909091]))
def test_univariate(self):
"""Tests fit() and predict(), univariate."""
x_data = np.array([1, 2, 3, 4, 5])
y_data = np.array([2, 1, 1, 2, 4.5])
bn, bm = 2, 1
x = ds.array(x=x_data, block_size=(bn, bm))
y = ds.array(x=y_data, block_size=(bn, bm))
reg = LinearRegression()
reg.fit(x, y)
self.assertTrue(np.allclose(reg.coef_.collect(), 0.6))
self.assertTrue(np.allclose(reg.intercept_.collect(), 0.3))
# Predict one sample
x_test = np.array([3])
test_data = ds.array(x=x_test, block_size=(1, 1))
pred = reg.predict(test_data).collect()
self.assertTrue(np.allclose(pred, 2.1))
# Predict multiple samples
x_test = np.array([3, 5, 6])
test_data = ds.array(x=x_test, block_size=(bn, bm))
pred = reg.predict(test_data).collect()
self.assertTrue(np.allclose(pred, [2.1, 3.3, 3.9]))
def main():
"""
Linear regression example with plot
"""
# Example data
x = np.array([
1000, 4000, 5000, 4500, 3000, 4000, 9000, 11000, 15000, 12000, 7000,
3000
])
y = np.array([
9914, 40487, 54324, 50044, 34719, 42551, 94871, 118914, 158484, 131348,
78504, 36284
])
ds = load_data(x=x[:, np.newaxis], y=y, subset_size=4)
reg = LinearRegression()
reg.fit(ds)
reg.coef_ = compss_wait_on(reg.coef_)
reg.intercept_ = compss_wait_on(reg.intercept_)
print(reg.coef_, reg.intercept_)
# plot_result:
scatter(x, y, marker='x')
x_mesh = np.linspace(min(x), max(x), 1000)
plot(x_mesh, [reg.coef_ * x + reg.intercept_ for x in x_mesh])
show()
def test_multivariate_multiobjective(self):
"""Tests fit() and predict(), multivariate, multiobjective."""
x_data = np.array([[1, 2, 3], [2, 0, 4], [3, 1, 8], [4, 4, 2],
[5, 3, 1], [2, 7, 1]])
y_data = np.array([[2, 0, 3], [1, 5, 2], [1, 3, 4], [2, 7, 9],
[4.5, -1, 4], [0, 0, 0]])
bn, bm = 2, 2
x = ds.array(x=x_data, block_size=(bn, bm))
y = ds.array(x=y_data, block_size=(bn, bm))
reg = LinearRegression()
reg.fit(x, y)
# Predict one sample
x_test = np.array([3, 2, 1])
test_data = ds.array(x=x_test, block_size=(1, bm))
pred = reg.predict(test_data).collect()
self.assertTrue(np.allclose(pred, [3.0318415, 1.97164872, 3.85410906]))
# Predict multiple samples
x_test = np.array([[3, 2, 1], [4, 3, 3], [1, 1, 1]])
test_data = ds.array(x=x_test, block_size=(bn, bm))
pred = reg.predict(test_data).collect()
self.assertTrue(
np.allclose(pred, [[3.0318415, 1.97164872, 3.85410906],
[2.5033157, 2.65809327, 5.05310495],
[2.145797, 1.4840121, 1.5739791]]))
# Check attributes values
self.assertTrue(
np.allclose(reg.coef_.collect(),
[[0.65034768, 0.34673933, 1.22176283],
[-0.41465084, -0.20584208, -0.16339571],
[-0.38211131, 0.27277365, 0.07031439]]))
self.assertTrue(
np.allclose(reg.intercept_.collect(),
[2.29221145, 1.07034124, 0.44529761]))