def test_few_compiled(self):
num_features = 20
num_examples = 1000
X1 = np.random.normal(size=(num_examples, num_features))
X1 = X1.astype(np.float32)
y1 = np.random.normal(size=num_examples)
X2 = np.random.normal(size=(num_examples, num_features))
X2 = X2.astype(np.float32)
y2 = np.random.normal(size=num_examples)
rf1 = ensemble.RandomForestRegressor()
rf1.fit(X1, y1)
rf2 = ensemble.RandomForestRegressor()
rf2.fit(X2, y2)
rf1_compiled = CompiledRegressionPredictor(rf1)
rf2_compiled = CompiledRegressionPredictor(rf2)
assert_array_almost_equal(rf1.predict(X1),
rf1_compiled.predict(X1),
decimal=10)
assert_array_almost_equal(rf2.predict(X2),
rf2_compiled.predict(X2),
decimal=10)
def test_predictions_with_non_contiguous_input(self):
num_features = 100
num_examples = 100
X_non_contiguous = np.random.normal(size=(num_features, num_examples)).T
X_non_contiguous = X_non_contiguous.astype(np.float32)
self.assertFalse(X_non_contiguous.flags['C_CONTIGUOUS'])
y = np.random.normal(size=num_examples)
rf = ensemble.RandomForestRegressor()
rf.fit(X_non_contiguous, y)
rf_compiled = CompiledRegressionPredictor(rf)
try:
rf_compiled.predict(X_non_contiguous)
except ValueError as e:
self.fail("predict(X) raised ValueError")
X_contiguous = np.ascontiguousarray(X_non_contiguous)
self.assertTrue(X_contiguous.flags['C_CONTIGUOUS'])
assert_array_equal(rf_compiled.predict(X_non_contiguous), rf_compiled.predict(X_contiguous))
def test_float32_and_float_64_predictions_are_equal(self):
num_features = 100
num_examples = 100
X = np.random.normal(size=(num_features, num_examples))
X_32 = X.astype(np.float32)
X_64 = X.astype(np.float64)
y = np.random.normal(size=num_examples)
# fit on X_32
rf = ensemble.RandomForestRegressor()
rf.fit(X_32, y)
rf = CompiledRegressionPredictor(rf)
assert_array_equal(rf.predict(X_32), rf.predict(X_64))
# fit on X_64
rf = ensemble.RandomForestRegressor()
rf.fit(X_64, y)
rf = CompiledRegressionPredictor(rf)
assert_array_equal(rf.predict(X_32), rf.predict(X_64))
def test_many_trees(self):
num_features = 20
num_examples = 1000
X1 = np.random.normal(size=(num_examples, num_features))
X1 = X1.astype(np.float32)
y1 = np.random.normal(size=num_examples)
rf1 = ensemble.RandomForestRegressor(n_estimators=500, max_depth=2)
rf1.fit(X1,y1)
rf1_compiled = CompiledRegressionPredictor(rf1)
assert_array_almost_equal(rf1.predict(X1), rf1_compiled.predict(X1), decimal=10)
def test_float32_and_float_64_predictions_are_equal(self):
num_features = 100
num_examples = 100
X = np.random.normal(size=(num_features, num_examples))
X_32 = X.astype(np.float32)
X_64 = X.astype(np.float64)
y = np.random.normal(size=num_examples)
# fit on X_32
rf = ensemble.RandomForestRegressor()
rf.fit(X_32, y)
rf = CompiledRegressionPredictor(rf)
assert_array_equal(rf.predict(X_32), rf.predict(X_64))
# fit on X_64
rf = ensemble.RandomForestRegressor()
rf.fit(X_64, y)
rf = CompiledRegressionPredictor(rf)
assert_array_equal(rf.predict(X_32), rf.predict(X_64))
def test_few_compiled(self):
num_features = 20
num_examples = 1000
X1 = np.random.normal(size=(num_examples, num_features))
X1 = X1.astype(np.float32)
y1 = np.random.normal(size=num_examples)
X2 = np.random.normal(size=(num_examples, num_features))
X2 = X2.astype(np.float32)
y2 = np.random.normal(size=num_examples)
rf1 = ensemble.RandomForestRegressor()
rf1.fit(X1,y1)
rf2 = ensemble.RandomForestRegressor()
rf2.fit(X2,y2)
rf1_compiled = CompiledRegressionPredictor(rf1)
rf2_compiled = CompiledRegressionPredictor(rf2)
assert_array_almost_equal(rf1.predict(X1), rf1_compiled.predict(X1), decimal=10)
assert_array_almost_equal(rf2.predict(X2), rf2_compiled.predict(X2), decimal=10)
def test_predictions_with_non_contiguous_input(self):
num_features = 100
num_examples = 100
X_non_contiguous = np.random.normal(size=(num_features,
num_examples)).T
X_non_contiguous = X_non_contiguous.astype(np.float32)
self.assertFalse(X_non_contiguous.flags['C_CONTIGUOUS'])
y = np.random.normal(size=num_examples)
rf = ensemble.RandomForestRegressor()
rf.fit(X_non_contiguous, y)
rf_compiled = CompiledRegressionPredictor(rf)
try:
rf_compiled.predict(X_non_contiguous)
except ValueError as e:
self.fail("predict(X) raised ValueError")
X_contiguous = np.ascontiguousarray(X_non_contiguous)
self.assertTrue(X_contiguous.flags['C_CONTIGUOUS'])
assert_array_equal(rf_compiled.predict(X_non_contiguous),
rf_compiled.predict(X_contiguous))
def test_many_trees(self):
num_features = 20
num_examples = 1000
X1 = np.random.normal(size=(num_examples, num_features))
X1 = X1.astype(np.float32)
y1 = np.random.normal(size=num_examples)
rf1 = ensemble.RandomForestRegressor(n_estimators=500, max_depth=2)
rf1.fit(X1, y1)
rf1_compiled = CompiledRegressionPredictor(rf1)
assert_array_almost_equal(rf1.predict(X1),
rf1_compiled.predict(X1),
decimal=10)
def assert_equal_predictions(cls, X, y):
clf = cls()
clf.fit(X, y)
compiled = CompiledRegressionPredictor(clf)
assert_array_almost_equal(clf.predict(X), compiled.predict(X))
