def test_doubleml_exception_confint():
dml_plr_confint = DoubleMLPLR(dml_data, ml_g, ml_m)
msg = 'joint must be True or False. Got 1.'
with pytest.raises(TypeError, match=msg):
dml_plr_confint.confint(joint=1)
msg = "The confidence level must be of float type. 5% of type <class 'str'> was passed."
with pytest.raises(TypeError, match=msg):
dml_plr_confint.confint(level='5%')
msg = r'The confidence level must be in \(0,1\). 0.0 was passed.'
with pytest.raises(ValueError, match=msg):
dml_plr_confint.confint(level=0.)
msg = r'Apply fit\(\) before confint\(\).'
with pytest.raises(ValueError, match=msg):
dml_plr_confint.confint()
msg = r'Apply fit\(\) & bootstrap\(\) before confint\(joint=True\).'
with pytest.raises(ValueError, match=msg):
dml_plr_confint.confint(joint=True)
dml_plr_confint.fit() # error message should still appear till bootstrap was applied as well
with pytest.raises(ValueError, match=msg):
dml_plr_confint.confint(joint=True)
dml_plr_confint.bootstrap()
df_ci = dml_plr_confint.confint(joint=True)
assert isinstance(df_ci, pd.DataFrame)
def test_doubleml_exception_no_cross_fit():
msg = 'Estimation without cross-fitting not supported for n_folds > 2.'
with pytest.raises(AssertionError, match=msg):
_ = DoubleMLPLR(dml_data, ml_g, ml_m, apply_cross_fitting=False)
def test_doubleml_exception_bootstrap():
dml_plr_boot = DoubleMLPLR(dml_data, ml_g, ml_m)
msg = r'Apply fit\(\) before bootstrap\(\).'
with pytest.raises(ValueError, match=msg):
dml_plr_boot.bootstrap()
dml_plr_boot.fit()
msg = 'Method must be "Bayes", "normal" or "wild". Got Gaussian.'
with pytest.raises(ValueError, match=msg):
dml_plr_boot.bootstrap(method='Gaussian')
msg = "The number of bootstrap replications must be of int type. 500 of type <class 'str'> was passed."
with pytest.raises(TypeError, match=msg):
dml_plr_boot.bootstrap(n_rep_boot='500')
msg = 'The number of bootstrap replications must be positive. 0 was passed.'
with pytest.raises(ValueError, match=msg):
dml_plr_boot.bootstrap(n_rep_boot=0)
import pandas as pd
import numpy as np
from doubleml import DoubleMLPLR, DoubleMLIRM, DoubleMLIIVM, DoubleMLPLIV, DoubleMLData, DoubleMLClusterData
from doubleml.datasets import make_plr_CCDDHNR2018, make_irm_data, make_pliv_CHS2015, make_iivm_data,\
make_pliv_multiway_cluster_CKMS2021
from sklearn.linear_model import Lasso, LogisticRegression
from sklearn.base import BaseEstimator
np.random.seed(3141)
dml_data = make_plr_CCDDHNR2018(n_obs=10)
ml_g = Lasso()
ml_m = Lasso()
ml_r = Lasso()
dml_plr = DoubleMLPLR(dml_data, ml_g, ml_m)
dml_data_irm = make_irm_data(n_obs=10)
dml_data_iivm = make_iivm_data(n_obs=10)
dml_data_pliv = make_pliv_CHS2015(n_obs=10, dim_z=1)
dml_cluster_data_pliv = make_pliv_multiway_cluster_CKMS2021(N=10, M=10)
(x, y, d, z) = make_iivm_data(n_obs=30, return_type="array")
y[y > 0] = 1
y[y < 0] = 0
dml_data_irm_binary_outcome = DoubleMLData.from_arrays(x, y, d)
dml_data_iivm_binary_outcome = DoubleMLData.from_arrays(x, y, d, z)
@pytest.mark.ci
def test_doubleml_exception_data():
msg = 'The data must be of DoubleMLData type.'
def test_doubleml_warning_crossfitting_onefold():
msg = 'apply_cross_fitting is set to False. Cross-fitting is not supported for n_folds = 1.'
with pytest.warns(UserWarning, match=msg):
_ = DoubleMLPLR(dml_data, ml_g, ml_m, apply_cross_fitting=True, n_folds=1)
def test_doubleml_draw_vs_set():
np.random.seed(3141)
dml_plr_set = DoubleMLPLR(dml_data, ml_g, ml_m, n_folds=7, n_rep=8)
dml_plr_drawn = DoubleMLPLR(dml_data,
ml_g,
ml_m,
n_folds=1,
n_rep=1,
apply_cross_fitting=False)
dml_plr_set.set_sample_splitting(dml_plr_drawn.smpls)
_assert_resampling_pars(dml_plr_drawn, dml_plr_set)
dml_plr_set.set_sample_splitting(dml_plr_drawn.smpls[0])
_assert_resampling_pars(dml_plr_drawn, dml_plr_set)
dml_plr_set.set_sample_splitting(dml_plr_drawn.smpls[0][0])
_assert_resampling_pars(dml_plr_drawn, dml_plr_set)
dml_plr_drawn = DoubleMLPLR(dml_data,
ml_g,
ml_m,
n_folds=2,
n_rep=1,
apply_cross_fitting=False)
dml_plr_set.set_sample_splitting(dml_plr_drawn.smpls)
_assert_resampling_pars(dml_plr_drawn, dml_plr_set)
dml_plr_set.set_sample_splitting(dml_plr_drawn.smpls[0])
_assert_resampling_pars(dml_plr_drawn, dml_plr_set)
dml_plr_set.set_sample_splitting(dml_plr_drawn.smpls[0][0])
_assert_resampling_pars(dml_plr_drawn, dml_plr_set)
dml_plr_drawn = DoubleMLPLR(dml_data,
ml_g,
ml_m,
n_folds=2,
n_rep=1,
apply_cross_fitting=True)
dml_plr_set.set_sample_splitting(dml_plr_drawn.smpls)
_assert_resampling_pars(dml_plr_drawn, dml_plr_set)
dml_plr_set.set_sample_splitting(dml_plr_drawn.smpls[0])
_assert_resampling_pars(dml_plr_drawn, dml_plr_set)
dml_plr_drawn = DoubleMLPLR(dml_data,
ml_g,
ml_m,
n_folds=5,
n_rep=1,
apply_cross_fitting=True)
dml_plr_set.set_sample_splitting(dml_plr_drawn.smpls)
_assert_resampling_pars(dml_plr_drawn, dml_plr_set)
dml_plr_set.set_sample_splitting(dml_plr_drawn.smpls[0])
_assert_resampling_pars(dml_plr_drawn, dml_plr_set)
dml_plr_drawn = DoubleMLPLR(dml_data,
ml_g,
ml_m,
n_folds=5,
n_rep=3,
apply_cross_fitting=True)
dml_plr_set.set_sample_splitting(dml_plr_drawn.smpls)
_assert_resampling_pars(dml_plr_drawn, dml_plr_set)
dml_plr_drawn = DoubleMLPLR(dml_data,
ml_g,
ml_m,
n_folds=2,
n_rep=4,
apply_cross_fitting=False)
dml_plr_set.set_sample_splitting(dml_plr_drawn.smpls)
_assert_resampling_pars(dml_plr_drawn, dml_plr_set)
import pytest
import pandas as pd
import numpy as np
from doubleml import DoubleMLPLR, DoubleMLIRM, DoubleMLIIVM, DoubleMLPLIV
from doubleml.datasets import make_plr_CCDDHNR2018, make_irm_data, make_pliv_CHS2015, make_iivm_data
from sklearn.linear_model import Lasso, LogisticRegression
np.random.seed(3141)
dml_data_plr = make_plr_CCDDHNR2018(n_obs=100)
dml_data_pliv = make_pliv_CHS2015(n_obs=100, dim_z=1)
dml_data_irm = make_irm_data(n_obs=100)
dml_data_iivm = make_iivm_data(n_obs=100)
dml_plr = DoubleMLPLR(dml_data_plr, Lasso(), Lasso())
dml_pliv = DoubleMLPLIV(dml_data_pliv, Lasso(), Lasso(), Lasso())
dml_irm = DoubleMLIRM(dml_data_irm, Lasso(), LogisticRegression())
dml_iivm = DoubleMLIIVM(dml_data_iivm, Lasso(), LogisticRegression(),
LogisticRegression())
@pytest.mark.ci
@pytest.mark.parametrize('dml_obj, cls', [(dml_plr, DoubleMLPLR),
(dml_pliv, DoubleMLPLIV),
(dml_irm, DoubleMLIRM),
(dml_iivm, DoubleMLIIVM)])
def test_plr_return_types(dml_obj, cls):
# ToDo: A second test case with multiple treatment variables would be helpful
assert isinstance(dml_obj.__str__(), str)
assert isinstance(dml_obj.summary, pd.DataFrame)
import pytest
import numpy as np
from doubleml import DoubleMLPLR
from doubleml.datasets import make_plr_CCDDHNR2018
from sklearn.linear_model import Lasso
np.random.seed(3141)
dml_data = make_plr_CCDDHNR2018(n_obs=10)
ml_g = Lasso()
ml_m = Lasso()
dml_plr = DoubleMLPLR(dml_data,
ml_g,
ml_m,
n_folds=7,
n_rep=8,
draw_sample_splitting=False)
def _assert_resampling_pars(dml_obj0, dml_obj1):
assert dml_obj0.n_folds == dml_obj1.n_folds
assert dml_obj0.n_rep == dml_obj1.n_rep
assert dml_obj0.apply_cross_fitting == dml_obj1.apply_cross_fitting
_assert_smpls_equal(dml_obj0.smpls, dml_obj1.smpls,
dml_obj0.apply_cross_fitting)
def _assert_smpls_equal(smpls0, smpls1, apply_cross_fitting=True):
assert len(smpls0) == len(smpls1)
for i_rep, _ in enumerate(smpls0):
import pytest
import numpy as np
from doubleml import DoubleMLPLR, DoubleMLIRM, DoubleMLIIVM, DoubleMLPLIV
from doubleml.datasets import make_plr_CCDDHNR2018, make_irm_data, make_pliv_CHS2015, make_iivm_data
from sklearn.linear_model import Lasso, LogisticRegression
np.random.seed(3141)
dml_data_plr = make_plr_CCDDHNR2018(n_obs=100)
dml_data_pliv = make_pliv_CHS2015(n_obs=100, dim_z=1)
dml_data_irm = make_irm_data(n_obs=100)
dml_data_iivm = make_iivm_data(n_obs=100)
dml_plr = DoubleMLPLR(dml_data_plr, Lasso(), Lasso())
dml_pliv = DoubleMLPLIV(dml_data_pliv, Lasso(), Lasso(), Lasso())
dml_irm = DoubleMLIRM(dml_data_irm, Lasso(), LogisticRegression())
dml_iivm = DoubleMLIIVM(dml_data_iivm, Lasso(), LogisticRegression(),
LogisticRegression())
def _assert_resampling_default_settings(dml_obj):
assert dml_obj.n_folds == 5
assert dml_obj.n_rep == 1
assert dml_obj.draw_sample_splitting
assert dml_obj.apply_cross_fitting
@pytest.mark.ci
def test_plr_defaults():
_assert_resampling_default_settings(dml_plr)
import pytest
import numpy as np
from doubleml import DoubleMLPLR, DoubleMLIRM, DoubleMLIIVM, DoubleMLPLIV
from doubleml.datasets import make_plr_CCDDHNR2018, make_irm_data, make_pliv_CHS2015, make_iivm_data
from sklearn.linear_model import Lasso, LogisticRegression
np.random.seed(3141)
dml_data_plr = make_plr_CCDDHNR2018(n_obs=100)
dml_data_pliv = make_pliv_CHS2015(n_obs=100, dim_z=1)
dml_data_irm = make_irm_data(n_obs=100)
dml_data_iivm = make_iivm_data(n_obs=100)
dml_plr = DoubleMLPLR(dml_data_plr, Lasso(), Lasso())
dml_plr.fit()
dml_pliv = DoubleMLPLIV(dml_data_pliv, Lasso(), Lasso(), Lasso())
dml_pliv.fit()
dml_irm = DoubleMLIRM(dml_data_irm, Lasso(), LogisticRegression())
dml_irm.fit()
dml_iivm = DoubleMLIIVM(dml_data_iivm, Lasso(), LogisticRegression(),
LogisticRegression())
dml_iivm.fit()
# fit models with callable scores
plr_score = dml_plr._score_elements
dml_plr_callable_score = DoubleMLPLR(dml_data_plr,
Lasso(),
Lasso(),
score=plr_score,
draw_sample_splitting=False)
def test_doubleml_exception_p_adjust():
dml_plr_p_adjust = DoubleMLPLR(dml_data, ml_g, ml_m)
msg = r'Apply fit\(\) before p_adjust\(\).'
with pytest.raises(ValueError, match=msg):
dml_plr_p_adjust.p_adjust()
dml_plr_p_adjust.fit()
msg = r'Apply fit\(\) & bootstrap\(\) before p_adjust'
with pytest.raises(ValueError, match=msg):
dml_plr_p_adjust.p_adjust(method='romano-wolf')
dml_plr_p_adjust.bootstrap()
p_val = dml_plr_p_adjust.p_adjust(method='romano-wolf')
assert isinstance(p_val, pd.DataFrame)
msg = "The p_adjust method must be of str type. 0.05 of type <class 'float'> was passed."
with pytest.raises(TypeError, match=msg):
dml_plr_p_adjust.p_adjust(method=0.05)
def test_doubleml_exception_smpls():
msg = ('Sample splitting not specified. '
r'Either draw samples via .draw_sample splitting\(\) or set external samples via .set_sample_splitting\(\).')
dml_plr_no_smpls = DoubleMLPLR(dml_data, ml_g, ml_m, draw_sample_splitting=False)
with pytest.raises(ValueError, match=msg):
_ = dml_plr_no_smpls.smpls
