def test_simulation_func(input_vault, test_id):
"""This test runs a random selection of test regression tests from
our regression test battery.
"""
(
model_spec_init_dict,
random_model_params_df,
exog_educ_shares,
exog_child_age_shares,
exog_partner_shares,
exog_exper_shares_pt,
exog_exper_shares_ft,
exog_child_info,
exog_partner_arrival_info,
exog_partner_separation_info,
expected_df_sim_func,
expected_df_sim_sol,
) = input_vault[test_id]
exog_educ_shares.to_pickle("test.soepy.educ.shares.pkl")
exog_child_age_shares.to_pickle("test.soepy.child.age.shares.pkl")
exog_child_info.to_pickle("test.soepy.child.pkl")
exog_partner_shares.to_pickle("test.soepy.partner.shares.pkl")
exog_exper_shares_pt.to_pickle("test.soepy.pt.exp.shares.pkl")
exog_exper_shares_ft.to_pickle("test.soepy.ft.exp.shares.pkl")
exog_partner_arrival_info.to_pickle("test.soepy.partner.arrival.pkl")
exog_partner_separation_info.to_pickle("test.soepy.partner.separation.pkl")
calculated_df = simulate(random_model_params_df, model_spec_init_dict)
pd.testing.assert_series_equal(
expected_df_sim_func,
calculated_df.sum(axis=0),
)
cleanup()
def update_sim_objectes():
vault_file = TEST_RESOURCES_DIR / "regression_vault.soepy.pkl"
vault = {}
with open(vault_file, "rb") as file:
tests_sim_func = pickle.load(file)
for i in range(0, 100):
print(i)
(
model_spec_init_dict,
random_model_params_df,
exog_educ_shares,
exog_child_age_shares,
exog_partner_shares,
exog_exper_shares_pt,
exog_exper_shares_ft,
exog_child_info,
exog_partner_arrival_info,
exog_partner_separation_info,
expected_df_sim_func,
expected_df_sim_sol,
) = tests_sim_func[i]
exog_educ_shares.to_pickle("test.soepy.educ.shares.pkl")
exog_child_age_shares.to_pickle("test.soepy.child.age.shares.pkl")
exog_child_info.to_pickle("test.soepy.child.pkl")
exog_partner_shares.to_pickle("test.soepy.partner.shares.pkl")
exog_exper_shares_pt.to_pickle("test.soepy.pt.exp.shares.pkl")
exog_exper_shares_ft.to_pickle("test.soepy.ft.exp.shares.pkl")
exog_partner_arrival_info.to_pickle("test.soepy.partner.arrival.pkl")
exog_partner_separation_info.to_pickle("test.soepy.partner.separation.pkl")
calculated_df_sim = simulate(random_model_params_df, model_spec_init_dict)
vault[i] = (
model_spec_init_dict,
random_model_params_df,
exog_educ_shares,
exog_child_age_shares,
exog_partner_shares,
exog_exper_shares_pt,
exog_exper_shares_ft,
exog_child_info,
exog_partner_arrival_info,
exog_partner_separation_info,
calculated_df_sim.sum(axis=0),
expected_df_sim_sol,
)
with open(vault_file, "wb") as file:
pickle.dump(vault, file)
cleanup(options="regression")
def test_simulation_func_exp(input_vault, test_id):
"""This test runs a random selection of test regression tests from
our regression test battery.
"""
(
model_spec_init_dict,
random_model_params_df,
exog_educ_shares,
exog_child_age_shares,
exog_partner_shares,
exog_exper_shares_pt,
exog_exper_shares_ft,
exog_child_info,
exog_partner_arrival_info,
exog_partner_separation_info,
expected_df_sim_func,
expected_df_sim_sol,
) = input_vault[test_id]
exog_educ_shares.to_pickle("test.soepy.educ.shares.pkl")
exog_child_age_shares.to_pickle("test.soepy.child.age.shares.pkl")
exog_child_info.to_pickle("test.soepy.child.pkl")
exog_partner_shares.to_pickle("test.soepy.partner.shares.pkl")
exog_exper_shares_pt.to_pickle("test.soepy.pt.exp.shares.pkl")
exog_exper_shares_ft.to_pickle("test.soepy.ft.exp.shares.pkl")
exog_partner_arrival_info.to_pickle("test.soepy.partner.arrival.pkl")
exog_partner_separation_info.to_pickle("test.soepy.partner.separation.pkl")
#
calculated_df_false = simulate(random_model_params_df,
model_spec_init_dict,
is_expected=False)
for edu_type in ["low", "middle", "high"]:
random_model_params_df.loc[(
"exp_returns_p_bias", f"gamma_p_bias_{edu_type}"), "value"] = (
random_model_params_df.loc[("exp_returns_p",
f"gamma_p_{edu_type}"), "value"] /
random_model_params_df.loc[("exp_returns_f",
f"gamma_f_{edu_type}"), "value"])
calculated_df_true = simulate(random_model_params_df,
model_spec_init_dict,
is_expected=True)
pd.testing.assert_series_equal(
calculated_df_false.sum(axis=0),
calculated_df_true.sum(axis=0),
)
cleanup()
def create_vault(num_test=1000, seed=123456):
"""This function creates our regression vault."""
np.random.seed(seed)
seeds = np.random.randint(0, 1000, size=num_test)
vault = TEST_RESOURCES_DIR / "regression_vault.soepy.pkl"
tests = []
for counter, seed in enumerate(seeds):
np.random.seed(seed)
(
model_spec_init_dict,
random_model_params_df,
exog_educ_shares,
exog_child_age_shares,
exog_partner_shares,
exog_exper_shares_pt,
exog_exper_shares_ft,
exog_child_info,
exog_partner_arrival_info,
exog_partner_separation_info,
) = random_init()
df = simulate("test.soepy.pkl", "test.soepy.yml")
tests += [
(
model_spec_init_dict,
random_model_params_df,
exog_educ_shares,
exog_child_age_shares,
exog_partner_shares,
exog_exper_shares_pt,
exog_exper_shares_ft,
exog_child_info,
exog_partner_arrival_info,
exog_partner_separation_info,
df,
)
]
cleanup("regression")
with open(vault, "wb") as file:
pickle.dump(tests, file)
def check_vault(num_test):
"""This function runs another simulation for each init file in our regression vault.
"""
vault = TEST_RESOURCES_DIR / "regression_vault.soepy.pkl"
with open(vault, "rb") as file:
tests = pickle.load(file)
for test in tests[:num_test]:
init_dict, expected_df = test
calculated_df = simulate(init_dict)
for col in expected_df.columns.tolist():
expected_df[col].equals(calculated_df[col])
cleanup("regression")
def create_vault(num_test=1000, seed=123456):
"""This function creates our regression vault."""
np.random.seed(seed)
seeds = np.random.randint(0, 1000, size=num_test)
vault = TEST_RESOURCES_DIR / "regression_vault.soepy.pkl"
tests = []
for counter, seed in enumerate(seeds):
np.random.seed(seed)
init_dict = random_init()
df = simulate("test.soepy.yml")
tests += [(init_dict, df)]
cleanup("regression")
with open(vault, "wb") as file:
pickle.dump(tests, file)
def check_vault(num_test):
"""This function runs another simulation for each init file in our regression vault."""
vault = TEST_RESOURCES_DIR / "regression_vault.soepy.pkl"
with open(vault, "rb") as file:
tests = pickle.load(file)
for test in tests[:num_test]:
(
model_spec_init_dict,
random_model_params_df,
exog_educ_shares,
exog_child_age_shares,
exog_partner_shares,
exog_exper_shares_pt,
exog_exper_shares_ft,
exog_child_info,
exog_partner_arrival_info,
exog_partner_separation_info,
expected_df,
) = test
exog_educ_shares.to_pickle("test.soepy.educ.shares.pkl")
exog_child_age_shares.to_pickle("test.soepy.child.age.shares.pkl")
exog_child_info.to_pickle("test.soepy.child.pkl")
exog_partner_shares.to_pickle("test.soepy.partner.shares.pkl")
exog_exper_shares_pt.to_pickle("test.soepy.pt.exp.shares.pkl")
exog_exper_shares_ft.to_pickle("test.soepy.ft.exp.shares.pkl")
exog_partner_arrival_info.to_pickle("test.soepy.partner.arrival.pkl")
exog_partner_separation_info.to_pickle("test.soepy.partner.separation.pkl")
calculated_df = simulate(random_model_params_df, model_spec_init_dict)
for col in expected_df.columns.tolist():
expected_df[col].equals(calculated_df[col])
cleanup("regression")
import soepy
from development.tests.auxiliary.auxiliary import cleanup
# Generate simulated dataset
data_frame = soepy.simulate("toy_model_init_file_03_3types.pkl",
"model_spec_init.yml")
data_frame = soepy.simulate("toy_model_init_file_03_1type.pkl",
"model_spec_init.yml")
cleanup()
def test_pyth_simulate(input_vault, test_id):
"""This test runs a random selection of test regression tests from
our regression test battery.
"""
(
model_spec_init_dict,
random_model_params_df,
exog_educ_shares,
exog_child_age_shares,
exog_partner_shares,
exog_exper_shares_pt,
exog_exper_shares_ft,
exog_child_info,
exog_partner_arrival_info,
exog_partner_separation_info,
expected_df_sim_func,
expected_df_sim_sol,
) = input_vault[test_id]
exog_educ_shares.to_pickle("test.soepy.educ.shares.pkl")
exog_child_age_shares.to_pickle("test.soepy.child.age.shares.pkl")
exog_child_info.to_pickle("test.soepy.child.pkl")
exog_partner_shares.to_pickle("test.soepy.partner.shares.pkl")
exog_exper_shares_pt.to_pickle("test.soepy.pt.exp.shares.pkl")
exog_exper_shares_ft.to_pickle("test.soepy.ft.exp.shares.pkl")
exog_partner_arrival_info.to_pickle("test.soepy.partner.arrival.pkl")
exog_partner_separation_info.to_pickle("test.soepy.partner.separation.pkl")
model_params_df, model_params = read_model_params_init(random_model_params_df)
model_spec = read_model_spec_init(model_spec_init_dict, model_params_df)
prob_educ_level = gen_prob_educ_level_vector(model_spec)
prob_child_age = gen_prob_child_init_age_vector(model_spec)
prob_partner_present = gen_prob_partner_present_vector(model_spec)
prob_exp_ft = gen_prob_init_exp_vector(
model_spec, model_spec.ft_exp_shares_file_name
)
prob_exp_pt = gen_prob_init_exp_vector(
model_spec, model_spec.pt_exp_shares_file_name
)
prob_child = gen_prob_child_vector(model_spec)
prob_partner = gen_prob_partner(model_spec)
(
states,
indexer,
covariates,
child_age_update_rule,
child_state_indexes,
) = create_state_space_objects(model_spec)
# Obtain model solution
non_employment_consumption_resources, emaxs = pyth_solve(
states,
covariates,
child_state_indexes,
model_params,
model_spec,
prob_child,
prob_partner,
False,
)
# Simulate
calculated_df = pyth_simulate(
model_params,
model_spec,
states,
indexer,
emaxs,
covariates,
non_employment_consumption_resources,
child_age_update_rule,
prob_educ_level,
prob_child_age,
prob_partner_present,
prob_exp_ft,
prob_exp_pt,
prob_child,
prob_partner,
is_expected=False,
)
pd.testing.assert_series_equal(
calculated_df.sum(axis=0),
expected_df_sim_sol,
)
cleanup()
def update_solve_objectes():
vault_file = TEST_RESOURCES_DIR / "regression_vault.soepy.pkl"
vault = {}
with open(vault_file, "rb") as file:
tests_sim_func = pickle.load(file)
for i in range(0, 100):
print(i)
(
model_spec_init_dict,
random_model_params_df,
exog_educ_shares,
exog_child_age_shares,
exog_partner_shares,
exog_exper_shares_pt,
exog_exper_shares_ft,
exog_child_info,
exog_partner_arrival_info,
exog_partner_separation_info,
expected_df_sim_func,
expected_df_sim_sol,
) = tests_sim_func[i]
exog_educ_shares.to_pickle("test.soepy.educ.shares.pkl")
exog_child_age_shares.to_pickle("test.soepy.child.age.shares.pkl")
exog_child_info.to_pickle("test.soepy.child.pkl")
exog_partner_shares.to_pickle("test.soepy.partner.shares.pkl")
exog_exper_shares_pt.to_pickle("test.soepy.pt.exp.shares.pkl")
exog_exper_shares_ft.to_pickle("test.soepy.ft.exp.shares.pkl")
exog_partner_arrival_info.to_pickle("test.soepy.partner.arrival.pkl")
exog_partner_separation_info.to_pickle("test.soepy.partner.separation.pkl")
model_params_df, model_params = read_model_params_init(random_model_params_df)
model_spec = read_model_spec_init(model_spec_init_dict, model_params_df)
prob_educ_level = gen_prob_educ_level_vector(model_spec)
prob_child_age = gen_prob_child_init_age_vector(model_spec)
prob_partner_present = gen_prob_partner_present_vector(model_spec)
prob_exp_ft = gen_prob_init_exp_vector(
model_spec, model_spec.ft_exp_shares_file_name
)
prob_exp_pt = gen_prob_init_exp_vector(
model_spec, model_spec.pt_exp_shares_file_name
)
prob_child = gen_prob_child_vector(model_spec)
prob_partner = gen_prob_partner(model_spec)
# Create state space
(
states,
indexer,
covariates,
child_age_update_rule,
child_state_indexes,
) = create_state_space_objects(model_spec)
# Obtain model solution
non_employment_consumption_resources, emaxs = pyth_solve(
states,
covariates,
child_state_indexes,
model_params,
model_spec,
prob_child,
prob_partner,
False,
)
# Simulate
calculated_df_sim_sol = pyth_simulate(
model_params,
model_spec,
states,
indexer,
emaxs,
covariates,
non_employment_consumption_resources,
child_age_update_rule,
prob_educ_level,
prob_child_age,
prob_partner_present,
prob_exp_ft,
prob_exp_pt,
prob_child,
prob_partner,
is_expected=False,
)
vault[i] = (
model_spec_init_dict,
random_model_params_df,
exog_educ_shares,
exog_child_age_shares,
exog_partner_shares,
exog_exper_shares_pt,
exog_exper_shares_ft,
exog_child_info,
exog_partner_arrival_info,
exog_partner_separation_info,
expected_df_sim_func,
calculated_df_sim_sol.sum(axis=0),
)
with open(vault_file, "wb") as file:
pickle.dump(vault, file)
cleanup(options="regression")