Pass Solver and n_iter parameters in the model estimation step

[ravitejar]

Do Why model estimation runs for a really long time while displaying warning messages such as below. I know other solvers like liblinear will have a quicker solution. How do I pass these parameters through the DoWhy package?

/home/ec2-user/anaconda3/envs/python3/lib/python3.6/site-packages/sklearn/utils/validation.py:63: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel(). return f(*args, **kwargs) /home/ec2-user/anaconda3/envs/python3/lib/python3.6/site-packages/sklearn/linear_model/_logistic.py:765: ConvergenceWarning: lbfgs failed to converge (status=1): STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in: https://scikit-learn.org/stable/modules/preprocessing.html Please also refer to the documentation for alternative solver options: https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression extra_warning_msg=_LOGISTIC_SOLVER_CONVERGENCE_MSG)

Code:: model = CausalModel( data=df_new, treatment="treatment" , outcome="y", common_causes=X_new.columns.tolist())

identified_estimand = model.identify_effect()

estimate_matching = model.estimate_effect(identified_estimand, method_name="backdoor.propensity_score_matching")

[amit-sharma]

This is a good idea. I can implement this in the next PR.

[ravitejar]

Would it be possible to add the 'balanced' parameter of the Logistic Regression model as well? This solves the problem of imbalanced treatment labels to some extent

[ravitejar]

What is the target launch date for this enhancement?

[amit-sharma]

thanks for your patience @ravitejar . Had planned it for v0.8 but we missed the target. This should be added within the next month to main, and then available in the subsequent release.