dml_core/
lib.rs

1//! # dml-core
2//!
3//! Double / debiased machine learning (Chernozhukov et al., 2018) in Rust.
4//!
5//! ## Models
6//!
7//! - [`Plr`]: partially linear regression (partialling-out or IV-type score)
8//! - [`Irm`]: interactive regression model for a binary treatment (ATE / ATTE)
9//! - [`Pliv`]: partially linear IV regression
10//! - [`Iivm`]: interactive IV model, local average treatment effect (LATE) with a binary instrument
11//! - [`Did`] / [`DidCs`]: doubly robust difference-in-differences for panel data and
12//!   repeated cross-sections (Sant'Anna & Zhao, 2020)
13//! - [`StaggeredDid`]: DID with staggered adoption, group-time effects `ATT(g, t)` and their
14//!   aggregation by cohort, calendar time or event time (Callaway & Sant'Anna, 2021)
15//!
16//! All of them have scores that are linear in θ and share one engine
17//! ([`fit_model`]): repeated cross-fitting, DML2 estimation, standard errors,
18//! confidence intervals, a multiplier [`Bootstrap`] for joint inference and
19//! multiple-testing adjustment. New scores plug in via [`LinearScoreModel`].
20//!
21//! ## Heterogeneous effects
22//!
23//! - [`SLearner`], [`TLearner`], [`XLearner`], [`RLearner`], [`DrLearner`]: CATE meta-learners
24//! - [`Blp`]: best linear predictor of the CATE and group average effects (GATE) with
25//!   robust inference, from [`DrLearner`] fits or [`DmlFit::cate`] / [`DmlFit::gate`]
26//!
27//! ## Building blocks
28//!
29//! - [`DmlData`]: outcome `y`, one or more treatments `d`, covariates `x`, optional instrument `z`
30//! - [`Regressor`] / [`Classifier`]: plug-in nuisance learners
31//!   ([`Ols`], [`Lasso`], [`LogisticRegression`], [`RandomForestRegressor`],
32//!   [`RandomForestClassifier`] built in)
33//! - [`KFold`] / [`SampleSplitting`]: reproducible sample splitting
34//!
35//! ```
36//! use dml_core::{DmlData, Ols, Plr};
37//! use ndarray::{Array1, Array2};
38//!
39//! let n = 200;
40//! let x = Array2::from_shape_fn((n, 2), |(i, j)| ((i * 7 + j * 3) % 11) as f64);
41//! let d: Array1<f64> = (0..n).map(|i| x[[i, 0]] + ((i * 13) % 5) as f64).collect();
42//! let y: Array1<f64> = (0..n).map(|i| 0.5 * d[i] - x[[i, 1]] + ((i * 17) % 3) as f64).collect();
43//!
44//! let fit = Plr::new(Ols::new(), Ols::new()).n_folds(5).seed(42).fit(&DmlData::new(y, d, x)?)?;
45//! assert!((fit.coef()[0] - 0.5).abs() < 0.1);
46//! let ci = fit.confint(0.95)?; // shape (n_treat, 2)
47//! # let _ = ci;
48//! # Ok::<(), dml_core::DmlError>(())
49//! ```
50
51pub mod blp;
52pub mod bootstrap;
53pub mod cate;
54pub mod crossfit;
55pub mod data;
56pub mod error;
57pub mod fit;
58pub mod learner;
59pub(crate) mod linalg;
60pub mod model;
61pub mod score;
62pub mod staggered;
63pub mod stats;
64
65pub use blp::Blp;
66pub use bootstrap::{Bootstrap, BootstrapMethod};
67pub use cate::{CateFit, DrLearner, RLearner, SLearner, TLearner, XLearner};
68pub use crossfit::{
69    cross_fit_predict, cross_fit_predict_proba, cross_fit_predict_proba_subset,
70    cross_fit_predict_subset, Fold, KFold, SampleSplitting,
71};
72pub use data::DmlData;
73pub use error::{DmlError, Result};
74pub use fit::{fit_model, DmlFit, PAdjust};
75pub use learner::{
76    Classifier, Lasso, LogisticRegression, MaxFeatures, Ols, RandomForestClassifier,
77    RandomForestRegressor, Regressor,
78};
79pub use model::{
80    Did, DidCs, DidScore, Iivm, Irm, IrmScore, LinearScoreModel, Pliv, Plr, PlrScore,
81    ScoreEstimate, ScoreInput,
82};
83pub use score::LinearScore;
84pub use staggered::{
85    Aggregation, ControlGroup, DidAggregation, GroupTime, GtCombinations, PanelData, StaggeredDid,
86    StaggeredDidFit,
87};
dml_core/lib.rs

dml_core/
lib.rs
