Minor fixes

README.md

@@ -3,8 +3,6 @@
 [![PyPI wheel](https://img.shields.io/pypi/wheel/econml.svg)](https://pypi.org/project/econml/)
 [![Supported Python versions](https://img.shields.io/pypi/pyversions/econml.svg)](https://pypi.org/project/econml/)
 
-
-
 <h1>
 <a href="https://econml.azurewebsites.net/">
 <img src="doc/econml-logo-icon.png" width="80px" align="left" style="margin-right: 10px;", alt="econml-logo"> 
@@ -51,6 +49,8 @@ For information on use cases and background material on causal inference and het
 
 # News
 
+If you'd like to contribute to this project, see the [Help Wanted](#help-wanted) section below.
+
 **February 12, 2024:** Release v0.15.0, see release notes [here](https://github.com/py-why/EconML/releases/tag/v0.15.0)
 
 <details><summary>Previous releases</summary>
@@ -665,11 +665,15 @@ You can get started by cloning this repository. We use
 We rely on some recent features of setuptools, so make sure to upgrade to a recent version with
 `pip install setuptools --upgrade`. Then from your local copy of the repository you can run `pip install -e .` to get started (but depending on what you're doing you might want to install with extras instead, like `pip install -e .[plt]` if you want to use matplotlib integration, or you can use `pip install -e .[all]` to include all extras).
 
+## Help wanted
+
+If you're looking to contribute to the project, we have a number of issues tagged with the [`help wanted`](https://github.com/py-why/EconML/issues?q=is%3Aopen+is%3Aissue+label%3A%22help+wanted%22) label that are valuable improvements to the library that our team currently does not have time to prioritize where we would greatly appreciate community-initiated PRs.
+
 ## Running the tests
 
-This project uses [pytest](https://docs.pytest.org/) for testing. To run tests locally after installing the package, you can use `pip install pytest-runner` followed by `python setup.py pytest`.
+This project uses [pytest](https://docs.pytest.org/) for testing. To run all tests locally after installing the package, you can use `pip install pytest-runner` followed by `python setup.py pytest`.
 
-We have added pytest marks to some tests to make it easier to run a subset, and you can set the PYTEST_ADDOPTS environment variable to take advantage of this. For instance, you can set it to `-m "not (notebook or automl)"` to skip notebook and automl tests that have some additional dependencies. 
+However, running all tests can be very time-consuming, so you may prefer to run just a relevant subset of tests when developing locally. The easiest way to do this is to rely on `pytest`'s compatibility with `unittest`, so you can just run `python -m unittest econml.tests.test_module` to run all tests in a given module, or `python -m unittest econml.tests.test_module.TestClass` to run all tests in a given class. You can also run `python -m unittest econml.tests.test_module.TestClass.test_method` to run a single test method.
 
 ## Generating the documentation
 
@@ -691,6 +695,8 @@ We use GitHub Actions to build and publish the package and documentation. To cr
 
 # Blogs and Publications
 
+* May 2021: [Be Careful When Interpreting Predictive Models in Search of Causal Insights](https://towardsdatascience.com/be-careful-when-interpreting-predictive-models-in-search-of-causal-insights-e68626e664b6)
+
 * June 2019: [Treatment Effects with Instruments paper](https://arxiv.org/pdf/1905.10176.pdf)
 
 * May 2019: [Open Data Science Conference Workshop](https://odsc.com/speakers/machine-learning-estimation-of-heterogeneous-treatment-effect-the-microsoft-econml-library/) 

econml/_ensemble/_ensemble.py

@@ -13,9 +13,14 @@
 import numpy as np
 from abc import ABCMeta, abstractmethod
 from sklearn.base import BaseEstimator, clone
-from sklearn.utils import _print_elapsed_time
 from sklearn.utils import check_random_state
 from joblib import effective_n_jobs
+from packaging.version import parse
+import sklearn
+if parse(sklearn.__version__) < parse("1.5"):
+ from sklearn.utils import _print_elapsed_time
+else:
+ from sklearn.utils._user_interface import _print_elapsed_time
 
 
 def _fit_single_estimator(estimator, X, y, sample_weight=None,

econml/dml/causal_forest.py

@@ -567,7 +567,7 @@ class CausalForestDML(_BaseDML):
  ate_ : ndarray of shape (n_outcomes, n_treatments)
  The average constant marginal treatment effect of each treatment for each outcome,
  averaged over the training data and with a doubly robust correction. Available only
- when `discrete_treatment=True` and `oob=True`.
+ when `discrete_treatment=True` and `drate=True`.
  ate_stderr_ : ndarray of shape (n_outcomes, n_treatments)
  The standard error of the `ate_` attribute.
  feature_importances_ : ndarray of shape (n_features,)
@@ -997,7 +997,7 @@ def att__inference(self, *, T):
  Inference results information for the `att_` attribute, which is the average
  constant marginal treatment effect of each treatment for each outcome, averaged
  over the training data treated with treatment T and with a doubly robust correction.
- Available only when `discrete_treatment=True` and `oob=True`.
+ Available only when `discrete_treatment=True` and `drate=True`.
  """
  return NormalInferenceResults(d_t=self._d_t[0] if self._d_t else 1,
  d_y=self._d_y[0] if self._d_y else 1,

econml/policy/_drlearner.py

@@ -854,7 +854,8 @@ def _gen_drpolicy_learner(self):
  cv=self.cv,
  mc_iters=self.mc_iters,
  mc_agg=self.mc_agg,
- model_final=PolicyForest(max_depth=self.max_depth,
+ model_final=PolicyForest(n_estimators=self.n_estimators,
+ max_depth=self.max_depth,
  min_samples_split=self.min_samples_split,
  min_samples_leaf=self.min_samples_leaf,
  min_weight_fraction_leaf=self.min_weight_fraction_leaf,

econml/solutions/causal_analysis/_causal_analysis.py

@@ -30,7 +30,12 @@
 # TODO: this utility is documented but internal; reimplement?
 from sklearn.utils import _safe_indexing
 # TODO: this utility is even less public...
-from sklearn.utils import _get_column_indices
+from packaging.version import parse
+import sklearn
+if parse(sklearn.__version__) < parse("1.5"):
+ from sklearn.utils import _get_column_indices
+else:
+ from sklearn.utils._indexing import _get_column_indices
 
 
 class _CausalInsightsConstants:

econml/tests/test_policy_forest.py

@@ -321,8 +321,8 @@ def test_non_standard_input(self,):
  model_propensity=DummyClassifier(strategy='uniform'),
  featurizer=PolynomialFeatures(degree=1, include_bias=False),
  cv=GroupKFold(n_splits=2),
- n_estimators=20, n_jobs=1, random_state=123).fit(y, T, X=X,
- groups=groups)
+ n_estimators=100, n_jobs=1, random_state=123).fit(y, T, X=X,
+  groups=groups)
  mask = np.abs(Xraw[:, 0]) > .1
  np.testing.assert_allclose(pred[mask], forest.predict(Xraw[mask]))
  np.testing.assert_allclose(pred_val[mask, 1] - pred_val[mask, 0],

pyproject.toml

@@ -20,9 +20,9 @@ classifiers = [
  "Operating System :: POSIX :: Linux"
 ]
 dependencies = [
- "numpy",
+ "numpy<2",
  "scipy > 1.4.0",
- "scikit-learn >= 1.0, < 1.5",
+ "scikit-learn >= 1.0, < 1.6",
  "sparse",
  "joblib >= 0.13.0",
  "statsmodels >= 0.10",