riantr/moonbit_dowhy/estimators

README
- ::causal_graphCausalModel::causal_graph
- ::dataCausalModel::data
- ::estimate_effectCausalModel::estimate_effect
- ::identified_estimandCausalModel::identified_estimand
- ::identify_effectCausalModel::identify_effect
- ::newCausalModel::new
- ::refute_estimateCausalModel::refute_estimate

riantr/moonbit_dowhy/estimators does not have a README file

CausalEstimator

pub struct CausalEstimator {
  target_estimand : @riantr/moonbit_dowhy/identifiers.IdentifiedEstimand
IdentifiedEstimand
  kind : EstimatorKind
  weighting_scheme : WeightingScheme
  min_ps_score : Double
  max_ps_score : Double
  num_strata : Int
  clipping_threshold : Int
  instrument_name : String
  rd_variable_name : String
  rd_threshold_value : Double
  rd_bandwidth : Double
  rd_local_data : @riantr/moonbit_dowhy/api.DataFrame
DataFrame?
  model : @riantr/moonbit_dowhy/utils.OlsFit
OlsFit
  glm_model : @riantr/moonbit_dowhy/utils.GlmFit
GlmFit
  glm_family : @riantr/moonbit_dowhy/utils.GlmFamily
GlmFamily
  encoders : @riantr/moonbit_dowhy/api.Encoders
Encoders
  features : Array[String]
  propensities : Array[Double]
  propensity_beta : Array[Double]
  adjustment_names : Array[String]
  effect_modifier_names : Array[String]
  treatment_name : String
  outcome_name : String
  treatment_value : Double
  control_value : Double
  confidence_level : Double
  num_simulations : Int
  sample_size_fraction : Double
  compute_confidence_intervals : Bool
  test_significance : Bool
}

A causal estimator.

The estimator owns the identified estimand and the state that fit produced; estimate_effect turns a data frame into a CausalEstimate.

CausalEstimator::adjustment_set

source

fn CausalEstimator::adjustment_set(self : CausalEstimator) -> Array[String]

The adjustment variables the estimator uses.

CausalEstimator::doubly_robust

source

fn CausalEstimator::doubly_robust(estimand : @riantr/moonbit_dowhy/identifiers.IdentifiedEstimand
IdentifiedEstimand, min_ps_score : Double, max_ps_score : Double) -> CausalEstimator

A doubly robust estimator.

CausalEstimator::estimand

source

fn CausalEstimator::estimand(self : CausalEstimator) -> @riantr/moonbit_dowhy/identifiers.IdentifiedEstimand
IdentifiedEstimand

The estimand the estimator was built for.

CausalEstimator::estimate_effect

source

fn CausalEstimator::estimate_effect(self : CausalEstimator, data : @riantr/moonbit_dowhy/api.DataFrame
DataFrame, treatment_value : Double, control_value : Double, target_units : String) -> @riantr/moonbit_dowhy/model.CausalEstimate
CausalEstimate

Estimate the treatment effect.

target_units is one of "ate", "att" or "atc".

CausalEstimator::estimator_kind

source

fn CausalEstimator::estimator_kind(self : CausalEstimator) -> EstimatorKind

The algorithm of the estimator.

CausalEstimator::fit

source

fn CausalEstimator::fit(self : CausalEstimator, data : @riantr/moonbit_dowhy/api.DataFrame
DataFrame, effect_modifier_names : Array[String]) -> Unit

Fit the estimator on the given data.

The estimator remembers the adjustment variables of its estimand, fits the model it needs and stores the propensity scores when it uses them.

CausalEstimator::generalized_linear_model

source

fn CausalEstimator::generalized_linear_model(estimand : @riantr/moonbit_dowhy/identifiers.IdentifiedEstimand
IdentifiedEstimand, family : @riantr/moonbit_dowhy/utils.GlmFamily
GlmFamily) -> CausalEstimator

A generalised linear model estimator for the given estimand.

The family decides the link of the model: a binomial family fits a logistic regression, a poisson family fits a count model and the gaussian family fits an ordinary least squares model.

CausalEstimator::instrumental_variable

source

fn CausalEstimator::instrumental_variable(estimand : @riantr/moonbit_dowhy/identifiers.IdentifiedEstimand
IdentifiedEstimand, instrument_name : String) -> CausalEstimator

An instrumental variable estimator.

CausalEstimator::intervene

source

fn CausalEstimator::intervene(self : CausalEstimator, value : Double, data : @riantr/moonbit_dowhy/api.DataFrame
DataFrame) -> Double

The mean outcome of the intervention do(treatment = value).

This is the port of the do operator of the upstream estimators: the treatment is set to the given value in every row of the data and the model predicts the outcome of the modified data.

CausalEstimator::linear_regression

source

fn CausalEstimator::linear_regression(estimand : @riantr/moonbit_dowhy/identifiers.IdentifiedEstimand
IdentifiedEstimand) -> CausalEstimator

An ordinary least squares estimator for the given estimand.

CausalEstimator::outcome

source

fn CausalEstimator::outcome(self : CausalEstimator) -> String

The outcome column the estimator uses.

CausalEstimator::propensity_score_matching

source

fn CausalEstimator::propensity_score_matching(estimand : @riantr/moonbit_dowhy/identifiers.IdentifiedEstimand
IdentifiedEstimand) -> CausalEstimator

A propensity score matching estimator.

CausalEstimator::propensity_score_stratification

source

fn CausalEstimator::propensity_score_stratification(estimand : @riantr/moonbit_dowhy/identifiers.IdentifiedEstimand
IdentifiedEstimand, num_strata : Int, clipping_threshold : Int) -> CausalEstimator

A propensity score stratification estimator.

CausalEstimator::propensity_score_weighting

source

fn CausalEstimator::propensity_score_weighting(estimand : @riantr/moonbit_dowhy/identifiers.IdentifiedEstimand
IdentifiedEstimand, min_ps_score : Double, max_ps_score : Double, scheme : WeightingScheme) -> CausalEstimator

An inverse propensity score weighting estimator.

CausalEstimator::propensity_scores

source

fn CausalEstimator::propensity_scores(self : CausalEstimator) -> Array[Double]

The propensity scores the estimator computed.

CausalEstimator::regression_discontinuity

source

fn CausalEstimator::regression_discontinuity(estimand : @riantr/moonbit_dowhy/identifiers.IdentifiedEstimand
IdentifiedEstimand, rd_variable_name : String, rd_threshold_value : Double, rd_bandwidth : Double) -> CausalEstimator

A regression discontinuity estimator.

CausalEstimator::set_compute_confidence_intervals

source

fn CausalEstimator::set_compute_confidence_intervals(self : CausalEstimator, compute : Bool) -> Unit

Ask the estimator to compute the confidence intervals.

CausalEstimator::set_confidence_level

source

fn CausalEstimator::set_confidence_level(self : CausalEstimator, level : Double) -> Unit

Set the confidence level of the intervals.

CausalEstimator::set_estimand

source

fn CausalEstimator::set_estimand(self : CausalEstimator, estimand : @riantr/moonbit_dowhy/identifiers.IdentifiedEstimand
IdentifiedEstimand) -> Unit

Replace the estimand the estimator was built for.

The refuters use this to estimate a different effect with the same estimator.

CausalEstimator::set_num_simulations

source

fn CausalEstimator::set_num_simulations(self : CausalEstimator, num_simulations : Int) -> Unit

Set the number of bootstrap simulations.

CausalEstimator::set_sample_size_fraction

source

fn CausalEstimator::set_sample_size_fraction(self : CausalEstimator, fraction : Double) -> Unit

Set the fraction of the sample a bootstrap resample takes.

CausalEstimator::set_test_significance

source

fn CausalEstimator::set_test_significance(self : CausalEstimator, do_test : Bool) -> Unit

Ask the estimator to test the significance of the estimate.

CausalEstimator::treatment

source

fn CausalEstimator::treatment(self : CausalEstimator) -> String

The treatment column the estimator uses.

CausalEstimator::two_stage_regression

source

fn CausalEstimator::two_stage_regression(estimand : @riantr/moonbit_dowhy/identifiers.IdentifiedEstimand
IdentifiedEstimand) -> CausalEstimator

A two stage regression estimator.

CausalEstimator::with_estimand

source

fn CausalEstimator::with_estimand(self : CausalEstimator, estimand : @riantr/moonbit_dowhy/identifiers.IdentifiedEstimand
IdentifiedEstimand) -> CausalEstimator

A copy of the estimator that estimates a different estimand.

The refuters use this to re-estimate the effect with the same algorithm on modified data. The copy starts without any fitted state, so the estimator that was handed in keeps the model and the adjustment set it was fitted with.

EstimatorKind

source

pub enum EstimatorKind {
  LinearRegression
  PropensityScoreWeighting
  PropensityScoreMatching
  PropensityScoreStratification
  DoublyRobust
  InstrumentalVariable
  TwoStageRegression
  RegressionDiscontinuity
  GeneralizedLinearModel
}

The estimator family that DoWhy offers.

The kind decides which algorithm fit and estimate_effect run; the estimator itself keeps the fitted state, exactly like the Python classes inherit from CausalEstimator.

WeightingScheme

source

pub enum WeightingScheme {
  IpsWeight
  IpsStabilizedWeight
  IpsNormalizedWeight
}

The weighting scheme of the propensity score weighting estimator.

WeightingScheme::ips_normalized_weight

source

fn WeightingScheme::ips_normalized_weight() -> WeightingScheme

The normalised inverse propensity score weighting scheme.

WeightingScheme::ips_stabilized_weight

source

fn WeightingScheme::ips_stabilized_weight() -> WeightingScheme

The stabilised inverse propensity score weighting scheme.

WeightingScheme::ips_weight

source

fn WeightingScheme::ips_weight() -> WeightingScheme

The inverse propensity score weighting scheme.

WeightingScheme::name

source

fn WeightingScheme::name(self : WeightingScheme) -> String

The name of the weighting scheme.

DEFAULT_CONFIDENCE_LEVEL

source

let DEFAULT_CONFIDENCE_LEVEL : Double

The default confidence level.

DEFAULT_NUMBER_OF_SIMULATIONS_CI

source

let DEFAULT_NUMBER_OF_SIMULATIONS_CI : Int

The default number of simulations used for the confidence intervals.

DEFAULT_NUMBER_OF_SIMULATIONS_STAT_TEST

source

let DEFAULT_NUMBER_OF_SIMULATIONS_STAT_TEST : Int

The default number of simulations used for the significance test.

NUM_QUANTILES_TO_DISCRETIZE_CONT_COLS

source

let NUM_QUANTILES_TO_DISCRETIZE_CONT_COLS : Int

The default number of quantiles a continuous effect modifier is split into.

Source Files

Install

Download zip

MoonBit port of DoWhy 0.14 (PyWhy). Causal graph construction and analysis, effect identification (backdoor / frontdoor / complete adjustment), estimation (linear regression, generalized linear model, propensity score weighting / matching / stratification, doubly robust, instrumental variable, two stage, regression discontinuity), refutation (bootstrap, placebo treatment, data subset, dummy outcome, unobserved common cause), intervention sampling (do samplers), temporal graphs, causal discovery (the PC algorithm with the Fisher-z test) and the portable core of the graphical causal models (the p-value merging, the bootstrap confidence intervals, the Kullback-Leibler divergences, the density estimators, the Shapley values, the independence tests, the prediction models, the causal mechanisms, the fitting of a causal model and the what-if queries (the interventional samples, the counterfactual samples and the average causal effect). Pure MoonBit with zero external runtime dependencies.

causal-inferencedowhycausal-graphcausal-discoverybackdoorfrontdoorpropensity-scoretreatment-effectrefutationidentifiersestimatorsshapley-valuesindependence-teststructural-causal-modelcausal-mechanismwhat-ifcounterfactual

riantr

MIT

gitee.com/ren-yongxiang/moonbit_doWhy

Updated 2 hours ago

20 downloads

Site source Report issue Modules Skills Build queue Statistics

#CausalEstimator

#CausalEstimator::adjustment_set

#CausalEstimator::doubly_robust

#CausalEstimator::estimand

#CausalEstimator::estimate_effect

#CausalEstimator::estimator_kind

#CausalEstimator::fit

#CausalEstimator::generalized_linear_model

#CausalEstimator::instrumental_variable

#CausalEstimator::intervene

#CausalEstimator::linear_regression

#CausalEstimator::outcome

#CausalEstimator::propensity_score_matching

#CausalEstimator::propensity_score_stratification

#CausalEstimator::propensity_score_weighting

#CausalEstimator::propensity_scores

#CausalEstimator::regression_discontinuity

#CausalEstimator::set_compute_confidence_intervals

#CausalEstimator::set_confidence_level

#CausalEstimator::set_estimand

#CausalEstimator::set_num_simulations

#CausalEstimator::set_sample_size_fraction

#CausalEstimator::set_test_significance

#CausalEstimator::treatment

#CausalEstimator::two_stage_regression

#CausalEstimator::with_estimand

#EstimatorKind

#WeightingScheme

#WeightingScheme::ips_normalized_weight

#WeightingScheme::ips_stabilized_weight

#WeightingScheme::ips_weight

#WeightingScheme::name

#DEFAULT_CONFIDENCE_LEVEL

#DEFAULT_NUMBER_OF_SIMULATIONS_CI

#DEFAULT_NUMBER_OF_SIMULATIONS_STAT_TEST

#NUM_QUANTILES_TO_DISCRETIZE_CONT_COLS

Source Files

CausalEstimator

CausalEstimator::adjustment_set

CausalEstimator::doubly_robust

CausalEstimator::estimand

CausalEstimator::estimate_effect

CausalEstimator::estimator_kind

CausalEstimator::fit

CausalEstimator::generalized_linear_model

CausalEstimator::instrumental_variable

CausalEstimator::intervene

CausalEstimator::linear_regression

CausalEstimator::outcome

CausalEstimator::propensity_score_matching

CausalEstimator::propensity_score_stratification

CausalEstimator::propensity_score_weighting

CausalEstimator::propensity_scores

CausalEstimator::regression_discontinuity

CausalEstimator::set_compute_confidence_intervals

CausalEstimator::set_confidence_level

CausalEstimator::set_estimand

CausalEstimator::set_num_simulations

CausalEstimator::set_sample_size_fraction

CausalEstimator::set_test_significance

CausalEstimator::treatment

CausalEstimator::two_stage_regression

CausalEstimator::with_estimand

EstimatorKind

WeightingScheme

WeightingScheme::ips_normalized_weight

WeightingScheme::ips_stabilized_weight

WeightingScheme::ips_weight

WeightingScheme::name

DEFAULT_CONFIDENCE_LEVEL

DEFAULT_NUMBER_OF_SIMULATIONS_CI

DEFAULT_NUMBER_OF_SIMULATIONS_STAT_TEST

NUM_QUANTILES_TO_DISCRETIZE_CONT_COLS