def test6():
"""Additionally to test5 this test checks if the comparison file provides the
expected output when maxiter is set to zero and the estimation process uses the
initialization file values as start values.
"""
for _ in range(5):
constr = dict()
constr["DETERMINISTIC"], constr["MAXITER"], constr[
"AGENTS"] = False, 0, 15000
constr["START"], constr["SAME_SIZE"] = "init", True
dict_ = generate_random_dict(constr)
dict_["DIST"]["params"][1], dict_["DIST"]["params"][5] = 0.0, 1.0
print_dict(dict_)
simulate("test.grmpy.yml")
fit("test.grmpy.yml")
dict_ = read_desc("comparison.grmpy.info")
for section in ["ALL", "TREATED", "UNTREATED"]:
np.testing.assert_equal(len(set(dict_[section]["Number"])), 1)
np.testing.assert_almost_equal(
dict_[section]["Observed Sample"],
dict_[section]["Simulated Sample (finish)"],
0.001,
)
np.testing.assert_array_almost_equal(
dict_[section]["Simulated Sample (finish)"],
dict_[section]["Simulated Sample (start)"],
0.001,
)
def test1():
"""The test runs a loop to check the consistency of the random init file generating process
and the following simulation.
"""
for _ in range(10):
dict_ = generate_random_dict()
print_dict(dict_)
simulate('test.grmpy.ini')
def test5():
"""The test checks if the estimation process works properly when maxiter is set to zero."""
for _ in range(10):
constr = dict()
constr['DETERMINISTIC'], constr['MAXITER'] = False, 0
generate_random_dict(constr)
simulate('test.grmpy.ini')
estimate('test.grmpy.ini')
def test3():
"""The fourth test checks whether the simulation process works if there are only treated or
untreated Agents by setting the number of agents to one.
"""
constr = constraints(probability=0.0, agents=1)
for _ in range(10):
generate_random_dict(constr)
simulate('test.grmpy.ini')
def test5():
"""The test checks if the estimation process works properly when maxiter is set to
zero.
"""
for _ in range(10):
constr = constraints(probability=0.0, maxiter=0)
generate_random_dict(constr)
simulate('test.grmpy.ini')
estimate('test.grmpy.ini')
def test5():
"""The test checks if the estimation process works properly when maxiter is set to
zero.
"""
for _ in range(5):
constr = dict()
constr["DETERMINISTIC"], constr["MAXITER"] = False, 0
generate_random_dict(constr)
simulate("test.grmpy.yml")
fit("test.grmpy.yml")
def test4():
"""The test checks if the estimation process works if the Powell algorithm is specified as
the optimizer option.
"""
for _ in range(5):
constr = dict()
constr['DETERMINISTIC'], constr['AGENTS'], constr[
'start'] = False, 10000, 'init'
constr['optimizer'] = 'SCIPY-Powell'
generate_random_dict(constr)
simulate('test.grmpy.ini')
estimate('test.grmpy.ini')
def test4():
"""The test checks if the estimation process works if the Powell algorithm is specified as
the optimizer option.
"""
for _ in range(5):
constr = constraints(probability=0.0,
agents=10000,
start='init',
optimizer='SCIPY-POWELL')
generate_random_dict(constr)
simulate('test.grmpy.ini')
estimate('test.grmpy.ini')
def test9():
"""This test ensures that the random initialization file generating process, the read in process
and the simulation process works if the constraints function allows for different number of co-
variates for each treatment state and the occurence of cost-benefit shifters."""
for i in range(5):
constr = dict()
constr['DETERMINISTIC'], constr['AGENT'], constr[
'STATE_DIFF'] = False, 1000, True
constr['OVERLAP'] = True
generate_random_dict(constr)
read('test.grmpy.ini')
simulate('test.grmpy.ini')
estimate('test.grmpy.ini')
cleanup()
def test5():
"""The tests checks if the simulation process works even if the covariance between U1 and V
and U0 and V is equal. Further the test ensures that the mte_information function returns
the same value for each quantile.
"""
for _ in range(10):
generate_random_dict()
init_dict = read('test.grmpy.ini')
# We impose that the covariance between the random components of the potential
# outcomes and the random component determining choice is identical.
init_dict['DIST']['all'][2] = init_dict['DIST']['all'][4]
# Distribute information
coeffs_untreated = init_dict['UNTREATED']['all']
coeffs_treated = init_dict['TREATED']['all']
# Construct auxiliary information
cov = construct_covariance_matrix(init_dict)
df = simulate('test.grmpy.ini')
x = df.filter(regex=r'^X\_', axis=1)
q = [0.01] + list(np.arange(0.05, 1, 0.05)) + [0.99]
mte = mte_information(coeffs_treated, coeffs_untreated, cov, q, x)
# We simply test that there is a single unique value for the marginal treatment effect.
np.testing.assert_equal(len(set(mte)), 1)
def test1():
"""The first test tests whether the relationships in the simulated datasets are appropriate
in a deterministic and an un-deterministic setting.
"""
constr = dict()
for case in ['deterministic', 'undeterministic']:
if case == 'deterministic':
constr['DETERMINISTIC'] = True
else:
constr['DETERMINISTIC'] = False
for _ in range(10):
generate_random_dict(constr)
df = simulate('test.grmpy.ini')
dict_ = read('test.grmpy.ini')
x_treated = df[[
dict_['varnames'][i - 1] for i in dict_['TREATED']['order']
]]
y_treated = pd.DataFrame.sum(dict_['TREATED']['all'] * x_treated,
axis=1) + df.U1
x_untreated = df[[
dict_['varnames'][i - 1] for i in dict_['UNTREATED']['order']
]]
y_untreated = pd.DataFrame.sum(
dict_['UNTREATED']['all'] * x_untreated, axis=1) + df.U0
np.testing.assert_array_almost_equal(df.Y1, y_treated, decimal=5)
np.testing.assert_array_almost_equal(df.Y0, y_untreated, decimal=5)
np.testing.assert_array_equal(df.Y[df.D == 1], df.Y1[df.D == 1])
np.testing.assert_array_equal(df.Y[df.D == 0], df.Y0[df.D == 0])
def test1():
"""The first test tests whether the relationships in the simulated datasets are
appropriate in a deterministic and an un-deterministic setting.
"""
constr = dict()
for case in ["deterministic", "undeterministic"]:
if case == "deterministic":
constr["DETERMINISTIC"] = True
else:
constr["DETERMINISTIC"] = True
for _ in range(10):
generate_random_dict(constr)
df = simulate("test.grmpy.yml")
dict_ = read("test.grmpy.yml")
x_treated = df[dict_["TREATED"]["order"]]
y_treated = (pd.DataFrame.sum(
dict_["TREATED"]["params"] * x_treated, axis=1) + df.U1)
x_untreated = df[dict_["UNTREATED"]["order"]]
y_untreated = (pd.DataFrame.sum(
dict_["UNTREATED"]["params"] * x_untreated, axis=1) + df.U0)
np.testing.assert_array_almost_equal(df.Y1, y_treated, decimal=5)
np.testing.assert_array_almost_equal(df.Y0, y_untreated, decimal=5)
np.testing.assert_array_equal(df.Y[df.D == 1], df.Y1[df.D == 1])
np.testing.assert_array_equal(df.Y[df.D == 0], df.Y0[df.D == 0])
def test4():
"""The test checks if the estimation process works if the Powell algorithm is
specified as the optimizer option.
"""
for _ in range(5):
constr = dict()
constr["DETERMINISTIC"], constr["AGENTS"], constr["start"] = (
False,
10000,
"init",
)
constr["optimizer"] = "SCIPY-Powell"
generate_random_dict(constr)
simulate("test.grmpy.yml")
fit("test.grmpy.yml")
def check_vault(num_tests=100):
"""This function checks the complete regression vault that is distributed as part of
the package.
"""
fname = (os.path.dirname(grmpy.__file__) +
"/test/resources/old_regression_vault.grmpy.json")
tests = json.load(open(fname))
if num_tests > len(tests):
print("The specified number of evaluations is larger than the number"
" of entries in the regression_test vault.\n"
"Therefore the test runs the complete test battery.")
else:
tests = [tests[i] for i in np.random.choice(len(tests), num_tests)]
for test in tests:
stat, dict_, criteria = test
print_dict(dict_transformation(dict_))
init_dict = read("test.grmpy.yml")
df = simulate("test.grmpy.yml")
_, X1, X0, Z1, Z0, Y1, Y0 = process_data(df, init_dict)
x0 = start_values(init_dict, df, "init")
criteria_ = calculate_criteria(init_dict, X1, X0, Z1, Z0, Y1, Y0, x0)
np.testing.assert_almost_equal(criteria_, criteria)
np.testing.assert_almost_equal(np.sum(df.sum()), stat)
cleanup("regression")
def test5():
"""The tests checks if the simulation process works even if the covariance between
U1 and V and U0 and V is equal. Further the test ensures that the mte_information
function returns the same value for each quantile.
"""
for _ in range(10):
generate_random_dict()
init_dict = read("test.grmpy.yml")
# We impose that the covariance between the random components of the potential
# outcomes and the random component determining choice is identical.
init_dict["DIST"]["params"][2] = init_dict["DIST"]["params"][4]
# Distribute information
coeffs_untreated = init_dict["UNTREATED"]["params"]
coeffs_treated = init_dict["TREATED"]["params"]
# Construct auxiliary information
cov = construct_covariance_matrix(init_dict)
df = simulate("test.grmpy.yml")
x = df[list(
set(init_dict["TREATED"]["order"] +
init_dict["UNTREATED"]["order"]))]
q = [0.01] + list(np.arange(0.05, 1, 0.05)) + [0.99]
mte = mte_information(coeffs_treated, coeffs_untreated, cov, q, x,
init_dict)
# We simply test that there is a single unique value for the marginal treatment
# effect.
np.testing.assert_equal(len(set(mte)), 1)
def test9():
"""This test ensures that the random initialization file generating process, the
read in process and the simulation process works if the constraints function allows
for different number of covariates for each treatment state and the occurence of
cost-benefit shifters."""
for _ in range(5):
constr = dict()
constr["DETERMINISTIC"], constr["AGENT"], constr["STATE_DIFF"] = (
False,
1000,
True,
)
constr["OVERLAP"] = True
generate_random_dict(constr)
read("test.grmpy.yml")
simulate("test.grmpy.yml")
fit("test.grmpy.yml")
cleanup()
def simulate_test_data():
"""
Simulate test dict_ and data.
"""
fname = TEST_RESOURCES_DIR + "/tutorial.grmpy.yml"
data = simulate(fname)
dict_ = read(fname)
dict_, data = check_append_constant(
TEST_RESOURCES_DIR + "/tutorial.grmpy.yml", dict_, data, semipar=True
)
return dict_, data
def create_vault(num_tests=100, seed=123):
"""This function creates a new regression vault."""
np.random.seed(seed)
tests = []
for _ in range(num_tests):
dict_ = generate_random_dict()
df = simulate('test.grmpy.ini')
stat = np.sum(df.sum())
tests += [(stat, dict_)]
cleanup()
json.dump(tests, open('regression_vault.grmpy.json', 'w'))
def test_rslt_dictionary():
"""
This test checks if the elements of the estimation dictionary are equal
to their expected values when the initialization file of the
semipar tutorial is used.
"""
fname = TEST_RESOURCES_DIR + "/tutorial-semipar.grmpy.yml"
simulate(fname)
rslt = fit(fname, semipar=True)
expected_rslt = pickle.load(
open(TEST_RESOURCES_DIR + "/tutorial-semipar-results.pkl", "rb"))
np.testing.assert_equal(rslt["quantiles"], expected_rslt["quantiles"])
np.testing.assert_almost_equal(rslt["mte"], expected_rslt["mte"], 7)
np.testing.assert_almost_equal(rslt["mte_u"], expected_rslt["mte_u"], 7)
np.testing.assert_almost_equal(rslt["mte_min"], expected_rslt["mte_min"],
5)
np.testing.assert_almost_equal(rslt["mte_max"], expected_rslt["mte_max"],
5)
np.testing.assert_almost_equal(rslt["b0"], expected_rslt["b0"], 7)
np.testing.assert_almost_equal(rslt["b1"], expected_rslt["b1"], 7)
def check_vault():
"""This function checks the complete regression vault that is distributed as part of the
package.
"""
fname = os.path.dirname(
grmpy.__file__) + '/test/resources/regression_vault.grmpy.json'
tests = json.load(open(fname))
for test in tests:
stat, dict_, criteria = test
print_dict(dict_)
df = simulate('test.grmpy.ini')
np.testing.assert_almost_equal(np.sum(df.sum()), stat)
cleanup('regression')
def test6():
"""Additionally to test5 this test checks if the descriptives file provides the expected
output when maxiter is set to zero and the estimation process uses the initialization file
values as start values.
"""
for _ in range(5):
constr = constraints(probability=0.0,
maxiter=0,
agents=1000,
start='init')
generate_random_dict(constr)
simulate('test.grmpy.ini')
estimate('test.grmpy.ini')
dict_ = read_desc('descriptives.grmpy.txt')
for key_ in ['All', 'Treated', 'Untreated']:
np.testing.assert_equal(len(set(dict_[key_]['Number'])), 1)
np.testing.assert_array_equal(
dict_[key_]['Observed Sample'],
dict_[key_]['Simulated Sample (finish)'])
np.testing.assert_array_equal(
dict_[key_]['Simulated Sample (finish)'],
dict_[key_]['Simulated Sample (start)'])
cleanup()
def test2():
"""The third test checks whether the relationships hold if the coefficients are zero in
different setups.
"""
for _ in range(10):
for i in ['ALL', 'TREATED', 'UNTREATED', 'COST', 'TREATED & UNTREATED']:
constr = constraints(probability=0.0)
dict_ = generate_random_dict(constr)
if i == 'ALL':
for key_ in ['TREATED', 'UNTREATED', 'COST']:
dict_[key_]['coeff'] = np.array([0.] * len(dict_[key_]['coeff']))
elif i == 'TREATED & UNTREATED':
for key_ in ['TREATED', 'UNTREATED']:
dict_[key_]['coeff'] = np.array([0.] * len(dict_[key_]['coeff']))
else:
dict_[i]['coeff'] = np.array([0.] * len(dict_[i]['coeff']))
print_dict(dict_)
dict_ = read('test.grmpy.ini')
df = simulate('test.grmpy.ini')
x = df.filter(regex=r'^X\_', axis=1)
if i == 'ALL':
np.testing.assert_array_equal(df.Y1, df.U1)
np.testing.assert_array_equal(df.Y0, df.U0)
elif i == 'TREATED & UNTREATED':
np.testing.assert_array_equal(df.Y1, df.U1)
np.testing.assert_array_equal(df.Y0, df.U0)
np.testing.assert_array_equal(df.Y[df.D == 1], df.U1[df.D == 1])
np.testing.assert_array_equal(df.Y[df.D == 0], df.U0[df.D == 0])
elif i == 'TREATED':
y_untreated = pd.DataFrame.sum(dict_['UNTREATED']['all'] * x, axis=1) + df.U0
np.testing.assert_array_almost_equal(df.Y0, y_untreated, decimal=5)
np.testing.assert_array_equal(df.Y1, df.U1)
elif i == 'UNTREATED':
y_treated = pd.DataFrame.sum(dict_['TREATED']['all'] * x, axis=1) + df.U1
np.testing.assert_array_almost_equal(df.Y1, y_treated, decimal=5)
np.testing.assert_array_equal(df.Y0, df.U0)
else:
y_treated = pd.DataFrame.sum(dict_['TREATED']['all'] * x, axis=1) + df.U1
y_untreated = pd.DataFrame.sum(dict_['UNTREATED']['all'] * x, axis=1) + df.U0
np.testing.assert_array_almost_equal(df.Y1, y_treated, decimal=5)
np.testing.assert_array_almost_equal(df.Y0, y_untreated, decimal=5)
np.testing.assert_array_equal(df.Y[df.D == 1], df.Y1[df.D == 1])
np.testing.assert_array_equal(df.Y[df.D == 0], df.Y0[df.D == 0])
np.testing.assert_array_almost_equal(df.V, (df.UC - df.U1 + df.U0))
def test3():
"""The fourth test checks whether the simulation process works if there are only
treated or untreated Agents by setting the number of agents to one. Additionally the
test checks if the start values for the estimation process are set to the init-
ialization file values due to perfect separation.
"""
constr = dict()
constr["AGENTS"], constr["DETERMINISTIC"] = 1, False
for _ in range(10):
generate_random_dict(constr)
dict_ = read("test.grmpy.yml")
df = simulate("test.grmpy.yml")
start = start_values(dict_, df, "auto")
np.testing.assert_equal(dict_["AUX"]["init_values"][:(-6)],
start[:(-4)])
def test6():
"""Additionally to test5 this test checks if the comparison file provides the expected
output when maxiter is set to zero and the estimation process uses the initialization file
values as start values.
"""
for _ in range(5):
constr = dict()
constr['DETERMINISTIC'], constr['MAXITER'], constr[
'AGENTS'] = False, 0, 10000
constr['START'], constr['SAME_SIZE'] = 'init', True
dict_ = generate_random_dict(constr)
dict_['DIST']['all'][1], dict_['DIST']['all'][5] = 0.0, 1.0
print_dict(dict_)
simulate('test.grmpy.ini')
estimate('test.grmpy.ini')
dict_ = read_desc('comparison.grmpy.txt')
for key_ in ['All', 'Treated', 'Untreated']:
np.testing.assert_equal(len(set(dict_[key_]['Number'])), 1)
np.testing.assert_almost_equal(
dict_[key_]['Observed Sample'],
dict_[key_]['Simulated Sample (finish)'], 0.001)
np.testing.assert_array_almost_equal(
dict_[key_]['Simulated Sample (finish)'],
dict_[key_]['Simulated Sample (start)'], 0.001)
def test3():
"""The fourth test checks whether the simulation process works if there are only treated or un-
treated Agents by setting the number of agents to one. Additionally the test checks if the start
values for the estimation process are set to the initialization file values due to perfect
separation.
"""
constr = dict()
constr['AGENTS'], constr['DETERMINISTIC'] = 1, False
for _ in range(10):
generate_random_dict(constr)
dict_ = read('test.grmpy.ini')
df = simulate('test.grmpy.ini')
start = start_values(dict_, df, 'auto')
np.testing.assert_equal(dict_['AUX']['init_values'][:(-6)],
start[:(-4)])
def test10():
"""This test checks if the start_values function returns the init file values if the start
option is set to init.
"""
for _ in range(10):
constr = dict()
constr['DETERMINISTIC'] = False
generate_random_dict(constr)
dict_ = read('test.grmpy.ini')
true = []
for key_ in ['TREATED', 'UNTREATED', 'CHOICE']:
true += list(dict_[key_]['all'])
df = simulate('test.grmpy.ini')
x0 = start_values(dict_, df, 'init')[:-4]
np.testing.assert_array_equal(true, x0)
def test9():
"""This test checks if the start_values function returns the init file values if the
start option is set to init.
"""
for _ in range(10):
constr = dict()
constr["DETERMINISTIC"] = False
generate_random_dict(constr)
dict_ = read("test.grmpy.yml")
true = []
for key_ in ["TREATED", "UNTREATED", "CHOICE"]:
true += list(dict_[key_]["params"])
df = simulate("test.grmpy.yml")
x0 = start_values(dict_, df, "init")[:-4]
np.testing.assert_array_equal(true, x0)
def test_common_support():
"""
Test whether common support is indeed zero if treatment propensity
is 0.5 for everyone.
"""
fname = TEST_RESOURCES_DIR + "/tutorial.grmpy.yml"
data = simulate(fname)
dict_ = read(fname)
prop_score = pd.Series(np.ones(len(data))) * 0.5
data.loc[:, "prop_score"] = prop_score
estimated_support = _define_common_support(dict_, data)
expected_support = [0.5, 0.5]
np.testing.assert_equal(estimated_support, expected_support)
def test11():
"""This test checks if the refactor auxiliary function returns an unchanged init file if the
maximum number of iterations is set to zero.
"""
for _ in range(10):
constr = dict()
constr['DETERMINISTIC'], constr['AGENTS'] = False, 1000
constr['MAXITER'], constr['START'] = 0, 'init'
generate_random_dict(constr)
init_dict = read('test.grmpy.ini')
df = simulate('test.grmpy.ini')
start = start_values(init_dict, df, 'init')
start = backward_transformation(start)
rslt = estimate('test.grmpy.ini')
np.testing.assert_equal(start, rslt['AUX']['x_internal'])
def create_vault(num_tests=100, seed=123):
"""This function creates a new regression vault."""
np.random.seed(seed)
tests = []
for _ in range(num_tests):
dict_ = generate_random_dict()
init_dict = read("test.grmpy.yml")
df = simulate("test.grmpy.yml")
_, X1, X0, Z1, Z0, Y1, Y0 = process_data(df, init_dict)
x0 = start_values(init_dict, df, "init")
criteria = calculate_criteria(init_dict, X1, X0, Z1, Z0, Y1, Y0, x0)
stat = np.sum(df.sum())
tests += [(stat, dict_, criteria)]
cleanup()
json.dump(tests, open("regression_vault.grmpy.json", "w"))