v0.4.0 fix z1&z2 bug

src/CausalEGM/__init__.py

@@ -1,3 +1,3 @@
-__version__ = '0.3.4'
+__version__ = '0.4.0'
 from .causalEGM import CausalEGM, VariationalCausalEGM
 from .util import Base_sampler, Semi_acic_sampler, Sim_Hirano_Imbens_sampler, Sim_Sun_sampler, Sim_Colangelo_sampler, Semi_Twins_sampler

src/CausalEGM/cli.py

@@ -20,7 +20,7 @@ def main(args=None):
                         help="whether use binary treatment setting.")
 
     #model hypterparameters
-    parser.add_argument('-z_dims', dest='z_dims', type=int, nargs='+', default=[3,3,6,6],
+    parser.add_argument('-z_dims', dest='z_dims', type=int, nargs='+', default=[3,6,3,6],
                         help='Latent dimensions of the four encoder outputs e(V)_0~3.')
     parser.add_argument('-lr', dest='lr', type=float, default=0.0002,
                         help="Learning rate for the optimizer (default: 0.0002).")
@@ -75,4 +75,4 @@ def main(args=None):
                 startoff=args.startoff, save_format=args.save_format)
 
 if __name__ == "__main__":
-   main()
+    main()

src/setup.py

@@ -2,11 +2,11 @@
 
 setuptools.setup(
     name="CausalEGM", 
-    version="0.3.4",
+    version="0.4.0",
     author="Qiao Liu",
     author_email="liuqiao@stanford.edu",
-    description="CausalEGM: a general causal inference framework by encoding generative modeling",
-    long_description="Understanding and characterizing causal effect has become essential in observational studies while it is still challenging if the confounders are high-dimensional. In this article, we develop a general framework CausalEGM, for estimating causal effect by encoding generative modeling, which can be applied in both binary and continuous treatment settings. In the potential outcome framework with unconfoundedness, we build a bidirectional transformation between the high-dimensional confounders space and a low-dimensional latent space where the density is known (e.g., Gaussian). Through this, CausalEGM enables simultaneously decoupling the dependencies of confounders on both treatment and outcome, and mapping the confounders to the low-dimensional latent space. By conditioning on the low-dimensional latent features, CausalEGM is able to estimate the causal effect for each individual or estimate the average causal effect within a population. Our theoretical analysis shows that the excess risk for CausalEGM can be bounded through empirical process theory. Under an assumption on encoder-decoder networks, the consistency of the estimate can also be guaranteed. In a series of experiments, CausalEGM demonstrates superior performance against existing methods in both binary and continuous settings. Specifically, we find CausalEGM to be substantially more powerful than competing methods in the presence of large sample size and high dimensional confounders. CausalEGM is freely available at https://github.com/SUwonglab/CausalEGM.",
+    description="CausalEGM: an encoding generative modeling approach to dimension reduction and covariate adjustment in causal inference with observational studies",
+    long_description="In this article, we develop CausalEGM, a deep learning framework for nonlinear dimension reduction and generative modeling of the dependency among covariate features affecting treatment and response. CausalEGM can be used for estimating causal effects in both binary and continuous treatment settings. By learning a bidirectional transformation between the high-dimensional covariate space and a low-dimensional latent space and then modeling the dependencies of different subsets of the latent variables on the treatment and response, CausalEGM can extract the latent covariate features that affect both treatment and response. By conditioning on these features, one can mitigate the confounding effect of the high dimensional covariate on the estimation of the causal relation between treatment and response. In a series of experiments, the proposed method is shown to achieve superior performance over existing methods in both binary and continuous treatment settings. The improvement is substantial when the sample size is large and the covariate is of high dimension. Finally, we established excess risk bounds and consistency results for our method, and discuss how our approach is related to and improves upon other dimension reduction approaches in causal inference. CausalEGM is freely available at https://github.com/SUwonglab/CausalEGM.",
     long_description_content_type="text/markdown",
     url="https://github.com/SUwonglab/CausalEGM",
     packages=setuptools.find_packages(),