dml_core/
data.rs

1use std::borrow::Cow;
2
3use ndarray::{concatenate, Array1, Array2, ArrayView1, ArrayView2, Axis};
4
5use crate::error::{DmlError, Result};
6
7/// Data for a DML model.
8///
9/// - `y`: outcome, length `n`
10/// - `d`: one or more treatments, shape `(n, k)` (continuous or 0/1)
11/// - `x`: covariates / confounders, shape `(n, p)`
12/// - `z`: optional instrument, length `n` (for [`Pliv`](crate::Pliv) and, binary, [`Iivm`](crate::Iivm))
13/// - `t`: optional 0/1 time-period indicator (for repeated cross-sections, [`DidCs`](crate::DidCs))
14///
15/// With several treatments each one is estimated in turn, and the other
16/// treatments are added to the covariates (as in DoubleML).
17#[derive(Debug, Clone)]
18pub struct DmlData {
19    y: Array1<f64>,
20    d: Array2<f64>,
21    x: Array2<f64>,
22    z: Option<Array1<f64>>,
23    t: Option<Array1<f64>>,
24    treatment_names: Vec<String>,
25}
26
27fn all_finite<'a>(mut values: impl Iterator<Item = &'a f64>) -> bool {
28    values.all(|v| v.is_finite())
29}
30
31impl DmlData {
32    /// Single treatment.
33    pub fn new(y: Array1<f64>, d: Array1<f64>, x: Array2<f64>) -> Result<Self> {
34        let n = d.len();
35        let d = d.into_shape_with_order((n, 1)).expect("1-D to (n, 1)");
36        Self::with_treatments(y, d, x)
37    }
38
39    /// Several treatments, one per column of `d`.
40    pub fn with_treatments(y: Array1<f64>, d: Array2<f64>, x: Array2<f64>) -> Result<Self> {
41        let n = y.len();
42        if n < 2 {
43            return Err(DmlError::InvalidArgument(
44                "need at least 2 observations".into(),
45            ));
46        }
47        if d.nrows() != n || x.nrows() != n {
48            return Err(DmlError::DimensionMismatch(format!(
49                "y has {n} rows, d has {}, x has {}",
50                d.nrows(),
51                x.nrows()
52            )));
53        }
54        if d.ncols() == 0 {
55            return Err(DmlError::InvalidArgument(
56                "need at least one treatment".into(),
57            ));
58        }
59        if !all_finite(y.iter()) || !all_finite(d.iter()) || !all_finite(x.iter()) {
60            return Err(DmlError::InvalidArgument(
61                "data contains NaN or infinite values".into(),
62            ));
63        }
64        let treatment_names = if d.ncols() == 1 {
65            vec!["d".to_string()]
66        } else {
67            (0..d.ncols()).map(|j| format!("d{j}")).collect()
68        };
69        Ok(Self {
70            y,
71            d,
72            x,
73            z: None,
74            t: None,
75            treatment_names,
76        })
77    }
78
79    /// Attach an instrument `z` (required by [`Pliv`](crate::Pliv)).
80    pub fn with_instrument(mut self, z: Array1<f64>) -> Result<Self> {
81        if z.len() != self.n_obs() {
82            return Err(DmlError::DimensionMismatch(format!(
83                "z has {} rows, expected {}",
84                z.len(),
85                self.n_obs()
86            )));
87        }
88        if !all_finite(z.iter()) {
89            return Err(DmlError::InvalidArgument(
90                "instrument contains NaN or infinite values".into(),
91            ));
92        }
93        self.z = Some(z);
94        Ok(self)
95    }
96
97    /// Attach a 0/1 time-period indicator (post-period = 1), required by
98    /// [`DidCs`](crate::DidCs) for repeated cross-sections.
99    pub fn with_time_indicator(mut self, t: Array1<f64>) -> Result<Self> {
100        if t.len() != self.n_obs() {
101            return Err(DmlError::DimensionMismatch(format!(
102                "t has {} rows, expected {}",
103                t.len(),
104                self.n_obs()
105            )));
106        }
107        if !is_binary(t.view()) {
108            return Err(DmlError::InvalidArgument(
109                "time indicator must contain only 0 and 1".into(),
110            ));
111        }
112        self.t = Some(t);
113        Ok(self)
114    }
115
116    /// Names shown in summaries (default `d`, or `d0`, `d1`, …).
117    pub fn with_treatment_names<S: Into<String>>(
118        mut self,
119        names: impl IntoIterator<Item = S>,
120    ) -> Result<Self> {
121        let names: Vec<String> = names.into_iter().map(Into::into).collect();
122        if names.len() != self.n_treat() {
123            return Err(DmlError::DimensionMismatch(format!(
124                "{} names for {} treatments",
125                names.len(),
126                self.n_treat()
127            )));
128        }
129        self.treatment_names = names;
130        Ok(self)
131    }
132
133    pub fn n_obs(&self) -> usize {
134        self.y.len()
135    }
136
137    pub fn n_features(&self) -> usize {
138        self.x.ncols()
139    }
140
141    pub fn n_treat(&self) -> usize {
142        self.d.ncols()
143    }
144
145    pub fn y(&self) -> ArrayView1<'_, f64> {
146        self.y.view()
147    }
148
149    /// All treatments, shape `(n, k)`.
150    pub fn d(&self) -> ArrayView2<'_, f64> {
151        self.d.view()
152    }
153
154    /// Treatment `j`.
155    pub fn treatment(&self, j: usize) -> ArrayView1<'_, f64> {
156        self.d.column(j)
157    }
158
159    pub fn x(&self) -> ArrayView2<'_, f64> {
160        self.x.view()
161    }
162
163    pub fn z(&self) -> Option<ArrayView1<'_, f64>> {
164        self.z.as_ref().map(|z| z.view())
165    }
166
167    /// The 0/1 time-period indicator, if attached.
168    pub fn time(&self) -> Option<ArrayView1<'_, f64>> {
169        self.t.as_ref().map(|t| t.view())
170    }
171
172    pub fn treatment_names(&self) -> &[String] {
173        &self.treatment_names
174    }
175
176    /// Covariates used when estimating the effect of treatment `j`: `x` plus
177    /// the other treatment columns. Borrowed when there is only one treatment.
178    ///
179    /// (`Cow` = "clone on write": either a borrowed view or an owned matrix.)
180    pub fn covariates_for(&self, j: usize) -> Cow<'_, Array2<f64>> {
181        if self.n_treat() == 1 {
182            return Cow::Borrowed(&self.x);
183        }
184        let others: Vec<usize> = (0..self.n_treat()).filter(|&k| k != j).collect();
185        let d_other = self.d.select(Axis(1), &others);
186        Cow::Owned(concatenate![Axis(1), self.x, d_other])
187    }
188
189    /// True when every value of treatment `j` is exactly 0 or 1.
190    pub fn is_binary_treatment(&self, j: usize) -> bool {
191        is_binary(self.d.column(j))
192    }
193}
194
195/// True when every value is exactly 0 or 1.
196pub(crate) fn is_binary(v: ArrayView1<'_, f64>) -> bool {
197    v.iter().all(|&x| x == 0.0 || x == 1.0)
198}
199
200/// Gather `v[idx]` into a new array.
201pub(crate) fn gather(v: ArrayView1<'_, f64>, idx: &[usize]) -> Array1<f64> {
202    idx.iter().map(|&i| v[i]).collect()
203}
204
205#[cfg(test)]
206mod tests {
207    use super::*;
208    use ndarray::array;
209
210    #[test]
211    fn rejects_mismatched_lengths() {
212        let err = DmlData::new(array![1.0, 2.0], array![0.0], array![[1.0], [2.0]]).unwrap_err();
213        assert!(matches!(err, DmlError::DimensionMismatch(_)));
214    }
215
216    #[test]
217    fn rejects_nan() {
218        let err = DmlData::new(
219            array![1.0, f64::NAN],
220            array![0.0, 1.0],
221            array![[1.0], [2.0]],
222        )
223        .unwrap_err();
224        assert!(matches!(err, DmlError::InvalidArgument(_)));
225    }
226
227    #[test]
228    fn detects_binary_treatment() {
229        let data = DmlData::new(array![1.0, 2.0], array![0.0, 1.0], array![[1.0], [2.0]]).unwrap();
230        assert!(data.is_binary_treatment(0));
231    }
232
233    #[test]
234    fn other_treatments_become_covariates() {
235        let d = array![[1.0, 10.0, 100.0], [2.0, 20.0, 200.0]];
236        let data = DmlData::with_treatments(array![0.0, 1.0], d, array![[5.0], [6.0]]).unwrap();
237        assert_eq!(data.treatment_names(), ["d0", "d1", "d2"]);
238        assert_eq!(
239            *data.covariates_for(1),
240            array![[5.0, 1.0, 100.0], [6.0, 2.0, 200.0]]
241        );
242        assert!(matches!(data.covariates_for(0), Cow::Owned(_)));
243    }
244
245    #[test]
246    fn time_indicator_must_be_binary() {
247        let data = DmlData::new(array![1.0, 2.0], array![0.0, 1.0], array![[1.0], [2.0]]).unwrap();
248        assert!(data.clone().with_time_indicator(array![0.0, 2.0]).is_err());
249        assert!(data.clone().with_time_indicator(array![1.0]).is_err());
250        assert!(data
251            .with_time_indicator(array![0.0, 1.0])
252            .unwrap()
253            .time()
254            .is_some());
255    }
256
257    #[test]
258    fn instrument_length_checked() {
259        let data = DmlData::new(array![1.0, 2.0], array![0.0, 1.0], array![[1.0], [2.0]]).unwrap();
260        assert!(data.clone().with_instrument(array![1.0]).is_err());
261        assert!(data
262            .with_instrument(array![1.0, 0.0])
263            .unwrap()
264            .z()
265            .is_some());
266    }
267}
dml_core/data.rs

dml_core/
data.rs
