dml-core 0.13.0

Double / debiased machine learning for causal inference in Rust
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180

//! External nuisance predictions: refitting with a first fit's own
//! predictions supplied externally reproduces the estimates exactly, and the
//! externally predicted learners have no out-of-sample loss.

use dml_core::{
    Apo, Did, DidCs, DidScore, DmlData, DmlFit, ExternalPredictions, Iivm, Irm, IrmScore,
    LogisticRegression, Ols, Pliv, PlivScore, Plr, PlrScore,
};
use ndarray::{Array1, Array2};
use rand::{Rng, SeedableRng};
use rand_chacha::ChaCha8Rng;

/// `(y, d, x, z, t)`.
type Arrays = (
    Array1<f64>,
    Array1<f64>,
    Array2<f64>,
    Array1<f64>,
    Array1<f64>,
);

fn data(n: usize, seed: u64) -> Arrays {
    let mut rng = ChaCha8Rng::seed_from_u64(seed);
    let x = Array2::from_shape_fn((n, 3), |_| rng.gen::<f64>() * 2.0 - 1.0);
    let (mut y, mut d, mut z, mut t) = (
        Array1::zeros(n),
        Array1::zeros(n),
        Array1::zeros(n),
        Array1::zeros(n),
    );
    for i in 0..n {
        z[i] = f64::from(rng.gen::<f64>() < 0.5);
        d[i] = f64::from(rng.gen::<f64>() < 0.3 + 0.3 * z[i] + 0.1 * x[[i, 0]]);
        t[i] = f64::from(rng.gen::<f64>() < 0.5);
        y[i] = d[i] + x[[i, 0]] - 0.5 * x[[i, 1]] + 0.3 * t[i] + rng.gen::<f64>();
    }
    (y, d, x, z, t)
}

/// Every prediction of `fit` (treatment 0) as external predictions.
fn all_external(fit: &DmlFit, names: &[&str]) -> ExternalPredictions {
    names.iter().fold(ExternalPredictions::new(), |e, name| {
        let p = fit
            .predictions(name)
            .unwrap_or_else(|| panic!("no predictions {name}"));
        e.with(0, *name, p.slice(ndarray::s![.., .., 0]).to_owned())
    })
}

fn assert_same(a: &DmlFit, b: &DmlFit) {
    for (x, y) in a.all_coef().iter().zip(b.all_coef()) {
        assert!((x - y).abs() < 1e-12, "coef {x} vs {y}");
    }
    for (x, y) in a.all_se().iter().zip(b.all_se()) {
        assert!((x - y).abs() < 1e-12, "se {x} vs {y}");
    }
}

#[test]
fn external_predictions_reproduce_every_linear_model() {
    let (y, d, x, z, t) = data(400, 1);
    let base = DmlData::new(y.clone(), d.clone(), x.clone()).unwrap();

    let plr = Plr::new(Ols::new(), Ols::new()).n_rep(2);
    let fit = plr.fit(&base).unwrap();
    let ext = all_external(&fit, &["ml_l", "ml_m"]);
    let refit = plr
        .fit(&base.clone().with_external_predictions(ext))
        .unwrap();
    assert_same(&fit, &refit);
    assert!(refit.nuisance_loss("ml_l").is_none() && refit.nuisance_loss("ml_m").is_none());

    // Partially external: only ml_m supplied, ml_l still fitted (and evaluated).
    let plr_iv = Plr::new(Ols::new(), Ols::new()).score(PlrScore::IvType);
    let fit = plr_iv.fit(&base).unwrap();
    let ext = all_external(&fit, &["ml_m", "ml_g"]);
    let refit = plr_iv
        .fit(&base.clone().with_external_predictions(ext))
        .unwrap();
    assert_same(&fit, &refit);
    assert!(refit.nuisance_loss("ml_l").is_some() && refit.nuisance_loss("ml_m").is_none());

    for score in [IrmScore::Ate, IrmScore::Atte] {
        let irm = Irm::new(Ols::new(), LogisticRegression::default()).score(score);
        let fit = irm.fit(&base).unwrap();
        let refit = irm
            .fit(
                &base
                    .clone()
                    .with_external_predictions(all_external(&fit, &["ml_g0", "ml_g1", "ml_m"])),
            )
            .unwrap();
        assert_same(&fit, &refit);
    }

    // APO needs a treatment with several levels (its other-level model sees D).
    let levels = &d + &z;
    let multi = DmlData::new(y.clone(), levels, x.clone()).unwrap();
    let apo = Apo::new(Ols::new(), LogisticRegression::default(), 1.0);
    let fit = apo.fit(&multi).unwrap();
    let refit =
        apo.fit(&multi.clone().with_external_predictions(all_external(
            &fit,
            &["ml_g_d_lvl0", "ml_g_d_lvl1", "ml_m"],
        )))
        .unwrap();
    assert_same(&fit, &refit);

    let with_z = base.clone().with_instrument(z).unwrap();
    let pliv = Pliv::new(Ols::new(), Ols::new(), Ols::new()).score(PlivScore::IvType);
    let fit = pliv.fit(&with_z).unwrap();
    let refit = pliv
        .fit(
            &with_z
                .clone()
                .with_external_predictions(all_external(&fit, &["ml_l", "ml_m", "ml_r", "ml_g"])),
        )
        .unwrap();
    assert_same(&fit, &refit);

    let iivm = Iivm::new(
        Ols::new(),
        LogisticRegression::default(),
        LogisticRegression::default(),
    );
    let fit = iivm.fit(&with_z).unwrap();
    let names = ["ml_g0", "ml_g1", "ml_m", "ml_r0", "ml_r1"];
    let refit = iivm
        .fit(
            &with_z
                .clone()
                .with_external_predictions(all_external(&fit, &names)),
        )
        .unwrap();
    assert_same(&fit, &refit);

    let did = Did::new(Ols::new(), LogisticRegression::default()).score(DidScore::Observational);
    let fit = did.fit(&base).unwrap();
    let refit = did
        .fit(
            &base
                .clone()
                .with_external_predictions(all_external(&fit, &["ml_g0", "ml_g1", "ml_m"])),
        )
        .unwrap();
    assert_same(&fit, &refit);

    let cs = base.clone().with_time_indicator(t).unwrap();
    let didcs = DidCs::new(Ols::new(), LogisticRegression::default());
    let fit = didcs.fit(&cs).unwrap();
    let names = [
        "ml_g_d0_t0",
        "ml_g_d0_t1",
        "ml_g_d1_t0",
        "ml_g_d1_t1",
        "ml_m",
    ];
    let refit = didcs
        .fit(
            &cs.clone()
                .with_external_predictions(all_external(&fit, &names)),
        )
        .unwrap();
    assert_same(&fit, &refit);
}

#[test]
fn external_predictions_are_checked() {
    let (y, d, x, _, _) = data(100, 2);
    let base = DmlData::new(y, d, x).unwrap();
    let wrong = ExternalPredictions::new().with(0, "ml_l", Array2::zeros((99, 1)));
    let err = Plr::new(Ols::new(), Ols::new()).fit(&base.clone().with_external_predictions(wrong));
    assert!(err.is_err());
    // One column but two repetitions.
    let short = ExternalPredictions::new().with_vector(0, "ml_l", Array1::zeros(100));
    assert!(Plr::new(Ols::new(), Ols::new())
        .n_rep(2)
        .fit(&base.with_external_predictions(short))
        .is_err());
}