def test_linear_regression():
"""Test making simple 1d linear regression and train it."""
x = np.arange(0, 10)
# Co-domain
y = x + 5
# Variables
a = tj.var(np.random.rand())
b = tj.var(np.random.rand())
err = tj.mse(y, a * x + b)
LOGGER.info("Optimizing a simple 2 linear regression.")
LOGGER.info(" X domain is [0, 1 .. 10]")
LOGGER.info(" Y domain is [5, 6, .. 15]")
LOGGER.info("before training: coefficient %s -- bias: %s -- mse: %s" %
(a, b, err.output()))
for i in range(1200):
g = tj.gradients(err, [a, b])
a.update(a.v - np.mean(g[0]) * 1e-2)
b.update(b.v - np.mean(g[1]) * 1e-2)
LOGGER.info("after training: coefficient %s -- bias: %s -- mse: %s" %
(a, b, err.output()))
def test_gd_on_linear_regression():
"""Test making simple 1d linear regression and train it."""
x = np.arange(0, 10)
# Co-domain
y = x + 5
# Variables
a = tj.var(np.random.rand())
b = tj.var(np.random.rand())
err = tj.mse(y, a * x + b)
LOGGER.info("Optimizing a simple 2 linear regression.")
LOGGER.info(" X domain is [0, 1 .. 10]")
LOGGER.info(" Y domain is [5, 6, .. 15]")
LOGGER.info("before training: coefficient %s -- bias: %s -- mse: %s" %
(a, b, err.output()))
opt = tj.opt.gd(err)
opt.rounds = 1200
opt.minimise([a, b])
LOGGER.info("after training: coefficient %s -- bias: %s -- mse: %s" %
(a, b, err.output()))
def test_logistic_regression():
"""Test making simple 1d linear regression and train it."""
x = np.random.rand(10) - 0.5
y = sigmoid(4 * x - 1)
a = tj.var(np.random.rand())
b = tj.var(np.random.rand())
o = tj.sigmoid(a * x + b)
err = tj.mse(y, o)
LOGGER.info("Optimizing a simple logistic regression.")
LOGGER.info(" X domain is (10, 2)")
LOGGER.info(" Y domain is (10, 1)")
LOGGER.info("before training: coefficient %s -- bias: %s -- mse: %s" %
(a, b, err.output()))
for i in range(5000):
g = tj.gradients(err, [a, b])
a.update(a.v - np.mean(g[0]) * 1e-0)
b.update(b.v - np.mean(g[1]) * 1e-0)
LOGGER.info("after training: coefficient %s -- bias: %s -- mse: %s" %
(a, b, err.output()))
LOGGER.info("perfect would be 4 and -1")
LOGGER.info("predictions %s", np.round(o.output()))
LOGGER.info("observations %s", np.round(y))
def test_gd_on_logistic_regression():
"""Test making simple 1d linear regression and train it."""
x = np.random.rand(10) - 0.5
y = sigmoid(4 * x - 1)
a = tj.var(np.random.rand())
b = tj.var(np.random.rand())
o = tj.sigmoid(a * x + b)
err = tj.mse(y, o)
LOGGER.info("Optimizing a simple logistic regression.")
LOGGER.info(" X domain is (10, 2)")
LOGGER.info(" Y domain is (10, 1)")
LOGGER.info("before training: coefficient %s -- bias: %s -- mse: %s" %
(a, b, err.output()))
opt = tj.opt.gd(err)
opt.dt = 1e-0
opt.rounds = 5000
opt.minimise([a, b])
LOGGER.info("after training: coefficient %s -- bias: %s -- mse: %s" %
(a, b, err.output()))
LOGGER.info("perfect would be 4 and -1")
LOGGER.info("predictions %s", np.round(o.output()))
LOGGER.info("observations %s", np.round(y))
def test_remove():
"""Test the graph remove functionality."""
LOGGER.info("Testing removing a functor.")
LOGGER.info("Building Graph.")
tj.tjgraph.clear()
a = tj.var(5)
b = tj.sigmoid(a)
c = tj.sigmoid(b)
c = tj.sigmoid(c)
d = c + 5
d = d + 5
assert len(tj.tjgraph.nodes) == 6, "Graph should contain 5 nodes "\
+ "Graph contains %s nodes" % len(tj.tjgraph.nodes)
tj.tjgraph.remove(a)
assert len(tj.tjgraph.nodes) == 1, "Graph should contain 1 monoid "\
+ "Graph contains %s nodes" % len(tj.tjgraph.nodes)
o = d.output()
assert d.output() == 10, ("Output should be 5 is %s" % o)
def test_1d_simples():
"""Test trivial gradient updates."""
LOGGER.info("Testing Addition.")
a = tj.var(np.ones(3) * 5)
b = tj.var(np.ones(3) * 10)
c = tj.add(a, b)
for i in range(5):
g = tj.gradients(c, [a])
LOGGER.info("%s *** a: %s -- b: %s -- g: %s -- dt: 0.1" % (i, a, b, g))
a.update(a.v + g[0] * 1e-1)
assert _true(a.v > 5.0), "A should be larger than 5 but is %s" % a
LOGGER.info("Testing Subtraction.")
a = tj.var(np.ones(3) * 5)
b = tj.var(np.ones(3) * 10)
c = tj.sub(a, b)
for i in range(5):
g = tj.gradients(c, [b])
LOGGER.info("%s *** a: %s -- b: %s -- g: %s -- dt: 0.1" % (i, a, b, g))
b.update(b.v + g[0] * 1e-1)
assert _true(b.v < 10.0), "A should be smaller than 10 but is %s" % a
LOGGER.info("Testing Multiplication.")
a = tj.var(np.ones(3) * 5)
b = tj.var(np.ones(3) * 10)
c = tj.mul(a, b)
for i in range(5):
g = tj.gradients(c, [a])
LOGGER.info("%s *** a: %s -- b: %s -- g: %s -- dt: 0.1" % (i, a, b, g))
a.update(a.v + g[0] * 1e-1)
assert _true(a.v > 5.0), "A should be larger than 5 but is %s" % a
LOGGER.info("Testing Division.")
a = tj.var(np.ones(3) * 5)
b = tj.var(np.ones(3) * 10)
c = tj.div(a, b)
for i in range(5):
g = tj.gradients(c, [b])
LOGGER.info("%s *** a: %s -- b: %s -- g: %s -- dt: 0.1" % (i, a, b, g))
b.update(b.v + g[0] * 1e-1)
assert _true(b.v < 10.0), "B should be smaller than 10 but is %s" % a
def test_convex():
"""Test optimising a simple convex function."""
LOGGER.info("Testing simple convex: x^2")
for s in [1, 3]:
a = tj.var(np.ones(s))
b = tj.mul(a, a)
LOGGER.info("Initial a: %s" % a)
for i in range(100):
g = tj.gradients(b, [a])
a.update(a.v - g[0] * 1e-1)
LOGGER.info("Final a: %s" % a)
assert _true(
abs(a.v) < 1.0), "A should be smaller than 1 but is %s" % a
LOGGER.info("Testing more complex convex: (x * 5 + 3 - x)^2")
for s in [1, 3]:
a = tj.var(np.ones(s))
b = tj.var(5)
c = tj.mul(a, b)
c = tj.add(c, 3)
c = tj.sub(c, a)
c = tj.mul(c, c)
LOGGER.info("Initial a: %s" % a)
for i in range(100):
g = tj.gradients(c, [a])
a.update(a.v - g[0] * 1e-2)
LOGGER.info("Final a: %s" % a.v)
assert _true(
abs(a.v) < 1.0), "A should be smaller than 1 but is %s" % a
def test_adding_monoids():
"""See if monoids is added to graph."""
tj.tjgraph.clear()
LOGGER.info("Checking right number of nodes.")
a = tj.var(np.random.rand(1, 5))
b = tj.var(np.random.rand(1, 5))
c = tj.add(a, b, name="first-addition")
nodes = tj.tjgraph.get_nodes()
vars = tj.tjgraph.get_variables()
assert len(nodes) == 3, "Nodes should be 3 is %s" % len(nodes)
assert len(vars) == 2, "Vars should be 2 is %s" % len(vars)
LOGGER.info("Checking names.")
var_names = [v.name for v in vars]
node_names = [n.name for n in nodes]
assert "first-addition" in node_names,\
"first-addition should be in %s" % node_names
assert "first-addition" not in var_names,\
"first-addition should not be in %s" % var_names
d = tj.mul(c, b, name="first-multiplication")
nodes = tj.tjgraph.get_nodes()
node_names = [n.name for n in nodes]
LOGGER.info("Checking more right number of nodes.")
assert len(nodes) == 4, "Nodes should be 4 is %s" % len(nodes)
assert "first-addition" in node_names,\
"first-addition should be in %s" % node_names
tj.tjgraph.clear()
nodes = tj.tjgraph.get_nodes()
vars = tj.tjgraph.get_variables()
LOGGER.info("Testing clearing")
assert len(nodes) == 0, "Nodes should be 0 is %s" % len(nodes)
assert len(vars) == 0, "Vars should be 0 is %s" % len(vars)
a = tj.var(np.random.rand(1, 5))
b = tj.var(np.random.rand(1, 5))
c = tj.add(a, b)
c = tj.add(c, a)
c = tj.add(c, b)
d = tj.mul(c, b, name="cookie")
e = tj.sub(c, d)
f = tj.div(d, e, name="milk")
f = tj.add(f, f)
nodes = tj.tjgraph.get_nodes()
vars = tj.tjgraph.get_variables()
var_names = [v.name for v in vars]
node_names = [n.name for n in nodes]
LOGGER.info("Test adding a lot of monoids")
assert len(nodes) == 9, "Nodes should be 9 is %s" % len(nodes)
assert len(vars) == 2, "Vars should be 2 is %s" % len(vars)
LOGGER.info("Checking names")
assert "cookie" in node_names,\
"cookie should be in %s" % node_names
assert "cookie" not in var_names,\
"cookie should not be in %s" % var_names
assert "milk" in node_names,\
"milk should be in %s" % node_names
assert "milk" not in var_names,\
"milk should not be in %s" % var_names
tj.tjgraph.clear()
nodes = tj.tjgraph.get_nodes()
vars = tj.tjgraph.get_variables()
LOGGER.info("Testing clearing")
assert len(nodes) == 0, "Nodes should be 0 is %s" % len(nodes)
assert len(vars) == 0, "Vars should be 0 is %s" % len(vars)
def test_cache():
"""Test the cache functionality of the graph."""
LOGGER.info("Testing cache.")
LOGGER.info("Running logistic regression test.")
x = np.random.rand(10) - 0.5
y = sigmoid(4 * x - 1)
a = tj.var(np.random.rand())
b = tj.var(np.random.rand())
o = tj.sigmoid(a * x + b)
err = tj.mse(y, o)
LOGGER.info("Optimizing a simple logistic regression.")
LOGGER.info(" X domain is (10, 2)")
LOGGER.info(" Y domain is (10, 1)")
LOGGER.info("before training: coefficient %s -- bias: %s -- mse: %s" %
(a, b, err.output()))
opt = tj.opt.gd(err)
opt.dt = 1e-0
opt.rounds = 5000
opt.minimise([a, b])
LOGGER.info("after training: coefficient %s -- bias: %s -- mse: %s" %
(a, b, err.output()))
""" ------------ """
LOGGER.info("Enabling cache and running the same calculations.")
tj.tjgraph.cache()
a.update(np.random.rand())
b.update(np.random.rand())
LOGGER.info("before training: coefficient %s -- bias: %s -- mse: %s" %
(a, b, err.output()))
opt = tj.opt.gd(err)
opt.dt = 1e-0
opt.rounds = 5000
opt.minimise([a, b])
LOGGER.info("after training: coefficient %s -- bias: %s -- mse: %s" %
(a, b, err.output()))
""" ------------ """
LOGGER.info("Disableing cache and running the same calculations.")
tj.tjgraph.no_cache()
a.update(np.random.rand())
b.update(np.random.rand())
LOGGER.info("before training: coefficient %s -- bias: %s -- mse: %s" %
(a, b, err.output()))
opt = tj.opt.gd(err)
opt.dt = 1e-0
opt.rounds = 5000
opt.minimise([a, b])
LOGGER.info("after training: coefficient %s -- bias: %s -- mse: %s" %
(a, b, err.output()))
""" ------------ """
LOGGER.info("Testing if cache makes a difference performance wise.")
"""Make a loong graph."""
a = tj.var(np.random.rand())
b = tj.var(np.random.rand())
sys.setrecursionlimit(5000)
timestamp = time.time()
c = a + b
for _ in range(2000):
c = a + b + c
LOGGER.info("Making graph with %s ops took %s seconds" %
(3 * 2000, time.time() - timestamp))
iters = 200
timestamp = time.time()
for _ in range(iters):
c.output()
LOGGER.info("Running %s iters without cache took %s seconds" %
(iters, time.time() - timestamp))
timestamp = time.time()
tj.tjgraph.cache()
LOGGER.info("Cacheing graph took %s seconds" % (time.time() - timestamp))
timestamp = time.time()
for _ in range(iters):
c.output()
LOGGER.info("Running %s iters with cache took %s seconds" %
(iters, time.time() - timestamp))
timestamp = time.time()
for _ in range(iters):
a.update(np.random.rand())
c.output()
LOGGER.info("Running %s iters with cache and update took %s seconds" %
(iters, time.time() - timestamp))
tj.tjgraph.no_cache()
timestamp = time.time()
for _ in range(iters):
a.update(np.random.rand())
c.output()
LOGGER.info("Running %s iters with no cache and update took %s seconds" %
(iters, time.time() - timestamp))
def test_adding_variables():
"""See if variables is added to graph."""
LOGGER.info("Adding variables.")
tj.tjgraph.clear()
tj.var(np.random.rand())
tj.var(np.random.rand(1, 10))
tj.var(np.random.rand(5, 5))
tj.var(np.random.rand(), name="Hello")
LOGGER.info("Getting variables.")
vars = tj.tjgraph.get_variables()
assert len(vars) == 4, "Variables should be len 4 not %s" % len(vars)
assert "Hello" in [v.name for v in vars],\
"Hello should be in vars found: %s" % [v.name for v in vars]
LOGGER.info("Clearing variables.")
tj.tjgraph.clear()
vars = tj.tjgraph.get_variables()
assert len(vars) == 0, "Cleared graph contained %s vars" % len(vars)
tj.var(np.random.rand())
tj.var(np.random.rand(1, 10))
tj.var(np.random.rand(5, 5))
tj.var(np.random.rand(), name="Hello")
LOGGER.info("Getting specific variable.")
vars = tj.tjgraph.get_variables(names=["Hello"])
assert len(vars) == 1,\
"Should only be on variable named 'Hello' found %s"\
% [v.name for v in vars]
assert "Hello" in [v.name for v in vars],\
"'Hello' should be in %s" % [v.name for v in vars]
LOGGER.info("Create two variables with same name: 'Hi' and 'Hi'")
v1 = tj.var(np.random.rand(), name="Hi")
v2 = tj.var(np.random.rand(), name="Hi")
assert v1.name != v2.name,\
"name collision %s and %s" % (v1.name, v2.name)
LOGGER.info("Name after creation: %s and %s" % (v1.name, v2.name))
tj.tjgraph.clear()