Skip to content

Fix GitHub Actions CI #6

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 6 commits into from
Jun 15, 2022
Merged

Fix GitHub Actions CI #6

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
f9833f6
install xgboost which is used in the unit tests of DoubleML
MalteKurz Jun 14, 2022
55de8b6
only run the serverless tests
MalteKurz Jun 14, 2022
e368ad8
use kwargs only to call the initializer of super classes
MalteKurz Jun 15, 2022
1f97643
remove unused imports
MalteKurz Jun 15, 2022
a3868df
rename nuisance parts; deactivate IV-type score; #7
MalteKurz Jun 15, 2022
fdc7db9
minimum required DoubleML version due to API changes
MalteKurz Jun 15, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions .github/workflows/pytest.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,9 +45,9 @@ jobs:
- name: Install dependencies
run: |
python -m pip install --upgrade pip
python -m pip install pytest
python -m pip install pytest xgboost
pip install -r requirements.txt
pip install .
- name: Test with pytest
run: |
pytest
pytest doubleml_serverless/
30 changes: 15 additions & 15 deletions doubleml_serverless/double_ml_iivm_aws_lambda.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,22 +26,22 @@ def __init__(self,
draw_sample_splitting=True,
apply_cross_fitting=True):
DoubleMLIIVM.__init__(self,
obj_dml_data,
ml_g,
ml_m,
ml_r,
n_folds,
n_rep,
score,
subgroups,
dml_procedure,
trimming_rule,
trimming_threshold,
draw_sample_splitting,
apply_cross_fitting)
obj_dml_data=obj_dml_data,
ml_g=ml_g,
ml_m=ml_m,
ml_r=ml_r,
n_folds=n_folds,
n_rep=n_rep,
score=score,
subgroups=subgroups,
dml_procedure=dml_procedure,
trimming_rule=trimming_rule,
trimming_threshold=trimming_threshold,
draw_sample_splitting=draw_sample_splitting,
apply_cross_fitting=apply_cross_fitting)
DoubleMLLambda.__init__(self,
lambda_function_name,
aws_region)
lambda_function_name=lambda_function_name,
aws_region=aws_region)

def _ml_nuisance_aws_lambda(self, cv_params):
assert self._dml_data.n_treat == 1
Expand Down
27 changes: 13 additions & 14 deletions doubleml_serverless/double_ml_irm_aws_lambda.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,4 @@
from doubleml import DoubleMLIRM
import numpy as np
from sklearn.utils import check_X_y

from ._helper import _get_cond_smpls
Expand All @@ -24,20 +23,20 @@ def __init__(self,
draw_sample_splitting=True,
apply_cross_fitting=True):
DoubleMLIRM.__init__(self,
obj_dml_data,
ml_g,
ml_m,
n_folds,
n_rep,
score,
dml_procedure,
trimming_rule,
trimming_threshold,
draw_sample_splitting,
apply_cross_fitting)
obj_dml_data=obj_dml_data,
ml_g=ml_g,
ml_m=ml_m,
n_folds=n_folds,
n_rep=n_rep,
score=score,
dml_procedure=dml_procedure,
trimming_rule=trimming_rule,
trimming_threshold=trimming_threshold,
draw_sample_splitting=draw_sample_splitting,
apply_cross_fitting=apply_cross_fitting)
DoubleMLLambda.__init__(self,
lambda_function_name,
aws_region)
lambda_function_name=lambda_function_name,
aws_region=aws_region)

def _ml_nuisance_aws_lambda(self, cv_params):
assert self._dml_data.n_treat == 1
Expand Down
37 changes: 19 additions & 18 deletions doubleml_serverless/double_ml_pliv_aws_lambda.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@ def __init__(self,
lambda_function_name,
aws_region,
obj_dml_data,
ml_g,
ml_l,
ml_m,
ml_r,
n_folds=5,
Expand All @@ -21,19 +21,19 @@ def __init__(self,
draw_sample_splitting=True,
apply_cross_fitting=True):
DoubleMLPLIV.__init__(self,
obj_dml_data,
ml_g,
ml_m,
ml_r,
n_folds,
n_rep,
score,
dml_procedure,
draw_sample_splitting,
apply_cross_fitting)
obj_dml_data=obj_dml_data,
ml_l=ml_l,
ml_m=ml_m,
ml_r=ml_r,
n_folds=n_folds,
n_rep=n_rep,
score=score,
dml_procedure=dml_procedure,
draw_sample_splitting=draw_sample_splitting,
apply_cross_fitting=apply_cross_fitting)
DoubleMLLambda.__init__(self,
lambda_function_name,
aws_region)
lambda_function_name=lambda_function_name,
aws_region=aws_region)

def _ml_nuisance_aws_lambda(self, cv_params):
assert self._dml_data.n_treat == 1
Expand All @@ -47,12 +47,12 @@ def _ml_nuisance_aws_lambda(self, cv_params):

payload = self._dml_data.get_payload()

payload_ml_g = payload.copy()
payload_ml_l = payload.copy()
payload_ml_m = payload.copy()
payload_ml_r = payload.copy()

_attach_learner(payload_ml_g,
'ml_g', self.learner['ml_g'],
_attach_learner(payload_ml_l,
'ml_l', self.learner['ml_l'],
self._dml_data.y_col, self._dml_data.x_cols)

_attach_learner(payload_ml_m,
Expand All @@ -63,7 +63,7 @@ def _ml_nuisance_aws_lambda(self, cv_params):
'ml_r', self.learner['ml_r'],
self._dml_data.d_cols[0], self._dml_data.x_cols)

payloads = _attach_smpls([payload_ml_g, payload_ml_m, payload_ml_r],
payloads = _attach_smpls([payload_ml_l, payload_ml_m, payload_ml_r],
[self.smpls, self.smpls, self.smpls],
self.n_folds,
self.n_rep,
Expand All @@ -80,9 +80,10 @@ def _ml_nuisance_aws_lambda(self, cv_params):
# compute score elements
self._psi_a[:, i_rep, self._i_treat], self._psi_b[:, i_rep, self._i_treat] = \
self._score_elements(y, z, d,
preds['ml_g'][:, i_rep],
preds['ml_l'][:, i_rep],
preds['ml_m'][:, i_rep],
preds['ml_r'][:, i_rep],
None,
self.smpls[i_rep])

return
38 changes: 19 additions & 19 deletions doubleml_serverless/double_ml_plr_aws_lambda.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,17 +1,16 @@
from doubleml import DoubleMLPLR
import numpy as np
from sklearn.utils import check_X_y

from .double_ml_aws_lambda import DoubleMLLambda
from ._helper import _attach_learner, _attach_smpls, _extract_preds
from ._helper import _attach_learner, _attach_smpls


class DoubleMLPLRServerless(DoubleMLPLR, DoubleMLLambda):
def __init__(self,
lambda_function_name,
aws_region,
obj_dml_data,
ml_g,
ml_l,
ml_m,
n_folds=5,
n_rep=1,
Expand All @@ -20,18 +19,18 @@ def __init__(self,
draw_sample_splitting=True,
apply_cross_fitting=True):
DoubleMLPLR.__init__(self,
obj_dml_data,
ml_g,
ml_m,
n_folds,
n_rep,
score,
dml_procedure,
draw_sample_splitting,
apply_cross_fitting)
obj_dml_data=obj_dml_data,
ml_l=ml_l,
ml_m=ml_m,
n_folds=n_folds,
n_rep=n_rep,
score=score,
dml_procedure=dml_procedure,
draw_sample_splitting=draw_sample_splitting,
apply_cross_fitting=apply_cross_fitting)
DoubleMLLambda.__init__(self,
lambda_function_name,
aws_region)
lambda_function_name=lambda_function_name,
aws_region=aws_region)

def _ml_nuisance_aws_lambda(self, cv_params):
assert self._dml_data.n_treat == 1
Expand All @@ -42,18 +41,18 @@ def _ml_nuisance_aws_lambda(self, cv_params):

payload = self._dml_data.get_payload()

payload_ml_g = payload.copy()
payload_ml_l = payload.copy()
payload_ml_m = payload.copy()

_attach_learner(payload_ml_g,
'ml_g', self.learner['ml_g'],
_attach_learner(payload_ml_l,
'ml_l', self.learner['ml_l'],
self._dml_data.y_col, self._dml_data.x_cols)

_attach_learner(payload_ml_m,
'ml_m', self.learner['ml_m'],
self._dml_data.d_cols[0], self._dml_data.x_cols)

payloads = _attach_smpls([payload_ml_g, payload_ml_m],
payloads = _attach_smpls([payload_ml_l, payload_ml_m],
[self.smpls, self.smpls],
self.n_folds,
self.n_rep,
Expand All @@ -70,8 +69,9 @@ def _ml_nuisance_aws_lambda(self, cv_params):
# compute score elements
self._psi_a[:, i_rep, self._i_treat], self._psi_b[:, i_rep, self._i_treat] = \
self._score_elements(y, d,
preds['ml_g'][:, i_rep],
preds['ml_l'][:, i_rep],
preds['ml_m'][:, i_rep],
None,
self.smpls[i_rep])

return
20 changes: 10 additions & 10 deletions doubleml_serverless/tests/test_pliv.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,16 +58,16 @@ def dml_pliv_fixture(generate_data_pliv, idx, learner, score, dml_procedure):
x_cols = data.columns[data.columns.str.startswith('X')].tolist()

# Set machine learning methods for m & g
ml_g = clone(learner)
ml_l = clone(learner)
ml_m = clone(learner)
ml_r = clone(learner)

np.random.seed(3141)
dml_data_json = dml_lambda.DoubleMLDataJson(data, 'y', ['d'], x_cols, 'Z1')
dml_pliv_lambda = DoubleMLPLIVServerlessLocal('local', 'local',
dml_data_json,
ml_g, ml_m, ml_r,
n_folds,
ml_l, ml_m, ml_r,
n_folds=n_folds,
score=score,
dml_procedure=dml_procedure)

Expand All @@ -76,8 +76,8 @@ def dml_pliv_fixture(generate_data_pliv, idx, learner, score, dml_procedure):
np.random.seed(3141)
dml_data = dml.DoubleMLData(data, 'y', ['d'], x_cols, 'Z1')
dml_pliv = dml.DoubleMLPLIV(dml_data,
ml_g, ml_m, ml_r,
n_folds,
ml_l, ml_m, ml_r,
n_folds=n_folds,
score=score,
dml_procedure=dml_procedure)

Expand Down Expand Up @@ -140,7 +140,7 @@ def dml_pliv_scaling_fixture(generate_data_pliv, idx, learner, score, dml_proced
x_cols = data.columns[data.columns.str.startswith('X')].tolist()

# Set machine learning methods for m & g
ml_g = clone(learner)
ml_l = clone(learner)
ml_m = clone(learner)
ml_r = clone(learner)

Expand All @@ -149,8 +149,8 @@ def dml_pliv_scaling_fixture(generate_data_pliv, idx, learner, score, dml_proced
np.random.seed(3141)
dml_pliv_folds = DoubleMLPLIVServerlessLocal('local', 'local',
dml_data_json,
ml_g, ml_m, ml_r,
n_folds,
ml_l, ml_m, ml_r,
n_folds=n_folds,
score=score,
dml_procedure=dml_procedure)

Expand All @@ -159,8 +159,8 @@ def dml_pliv_scaling_fixture(generate_data_pliv, idx, learner, score, dml_proced
np.random.seed(3141)
dml_pliv_reps = DoubleMLPLIVServerlessLocal('local', 'local',
dml_data_json,
ml_g, ml_m, ml_r,
n_folds,
ml_l, ml_m, ml_r,
n_folds=n_folds,
score=score,
dml_procedure=dml_procedure)

Expand Down
22 changes: 11 additions & 11 deletions doubleml_serverless/tests/test_plr.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,7 +32,7 @@ def learner(request):


@pytest.fixture(scope='module',
params=['IV-type', 'partialling out'])
params=['partialling out'])
def score(request):
return request.param

Expand All @@ -58,15 +58,15 @@ def dml_plr_fixture(generate_data_plr, idx, learner, score, dml_procedure):
x_cols = data.columns[data.columns.str.startswith('X')].tolist()

# Set machine learning methods for m & g
ml_g = clone(learner)
ml_l = clone(learner)
ml_m = clone(learner)

np.random.seed(3141)
dml_data_json = dml_lambda.DoubleMLDataJson(data, 'y', ['d'], x_cols)
dml_plr_lambda = DoubleMLPLRServerlessLocal('local', 'local',
dml_data_json,
ml_g, ml_m,
n_folds,
ml_l, ml_m,
n_folds=n_folds,
score=score,
dml_procedure=dml_procedure)

Expand All @@ -75,8 +75,8 @@ def dml_plr_fixture(generate_data_plr, idx, learner, score, dml_procedure):
np.random.seed(3141)
dml_data = dml.DoubleMLData(data, 'y', ['d'], x_cols)
dml_plr = dml.DoubleMLPLR(dml_data,
ml_g, ml_m,
n_folds,
ml_l, ml_m,
n_folds=n_folds,
score=score,
dml_procedure=dml_procedure)

Expand Down Expand Up @@ -139,16 +139,16 @@ def dml_plr_scaling_fixture(generate_data_plr, idx, learner, score, dml_procedur
x_cols = data.columns[data.columns.str.startswith('X')].tolist()

# Set machine learning methods for m & g
ml_g = clone(learner)
ml_l = clone(learner)
ml_m = clone(learner)

dml_data_json = dml_lambda.DoubleMLDataJson(data, 'y', ['d'], x_cols)

np.random.seed(3141)
dml_plr_folds = DoubleMLPLRServerlessLocal('local', 'local',
dml_data_json,
ml_g, ml_m,
n_folds,
ml_l, ml_m,
n_folds=n_folds,
score=score,
dml_procedure=dml_procedure)

Expand All @@ -157,8 +157,8 @@ def dml_plr_scaling_fixture(generate_data_plr, idx, learner, score, dml_procedur
np.random.seed(3141)
dml_plr_reps = DoubleMLPLRServerlessLocal('local', 'local',
dml_data_json,
ml_g, ml_m,
n_folds,
ml_l, ml_m,
n_folds=n_folds,
score=score,
dml_procedure=dml_procedure)

Expand Down
2 changes: 1 addition & 1 deletion requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
DoubleML>=0.2.2
DoubleML>=0.5.0
joblib
numpy
pandas
Expand Down
2 changes: 1 addition & 1 deletion setup.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@
url='https://github.com/DoubleML/doubleml-serverless',
packages=find_packages(exclude=['aws_lambda_app*']),
install_requires=[
'DoubleML>=0.2.2',
'DoubleML>=0.5.0',
'joblib',
'numpy',
'pandas',
Expand Down