Fix docs/choosing_estimator.rst HAD snippet (block7) for CI

The HeterogeneousAdoptionDiD example snippet in choosing_estimator.rst
failed the Pure Python Fallback CI job (test_doc_snippets.py
::test_doc_snippet[choosing_estimator:block7]) due to three latent
drift bugs from PR igerber#389 (docs-rtd-audit):

1. Missing aggregate='event_study' on both did_had_pretest_workflow
   and HAD.fit calls — default aggregate='overall' requires exactly 2
   periods, but the doc-snippet test framework's namespace `data`
   (built via generate_staggered_data) has 10 periods.

2. Used the namespace's generic `data` variable, which has nonzero
   dose in every period (rng.choice from {0.0, 0.5, 1.0, 2.0}). HAD
   requires D=0 for all units in at least one pre-period.

3. `print(f"Estimate: {results.att:.3f}")` formatted att as a scalar,
   but under aggregate='event_study' results.att is a numpy array.

Fix: rewrite the snippet to construct its own HAD-shape panel inline
(mirrors how block6 handles ContinuousDiD with its own data
generator); thread aggregate='event_study' through both calls;
iterate the per-horizon att array for output.

Pre-existing on origin/main; surfaced on this PR's CI re-run after
the rebase. Other failing snippets (troubleshooting:block18, :block20,
r_comparison:block6, :block7) are also pre-existing on main but are
out of scope for this PR.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

Author: igerber

docs/choosing_estimator.rst

@@ -392,17 +392,36 @@ before estimation; see :doc:`api/had` for the full API and SE-regime contract.
 
 .. code-block:: python
 
+   import numpy as np
+   import pandas as pd
    from diff_diff import HeterogeneousAdoptionDiD, did_had_pretest_workflow
 
-   pretests = did_had_pretest_workflow(data, outcome_col='y', unit_col='unit',
-                                       time_col='period', dose_col='dose')
+   # Build a HAD-shape panel: D=0 in pre-periods (t < F), D > 0 only at F+.
+   rng = np.random.default_rng(42)
+   G, F, T = 200, 4, 5
+   doses = rng.beta(0.5, 1.0, size=G)
+   rows = []
+   for g in range(G):
+       for t in range(1, T + 1):
+           y = (rng.normal()
+                + (doses[g] + doses[g] ** 2) * (t >= F)
+                + rng.normal(0, 0.5))
+           d = doses[g] if t >= F else 0.0
+           rows.append({'unit': g, 'period': t, 'y': y, 'dose': d})
+   had_data = pd.DataFrame(rows)
+
+   pretests = did_had_pretest_workflow(had_data, outcome_col='y', unit_col='unit',
+                                       time_col='period', dose_col='dose',
+                                       aggregate='event_study')
 
    est = HeterogeneousAdoptionDiD()
-   results = est.fit(data, outcome_col='y', unit_col='unit',
-                     time_col='period', dose_col='dose')
+   results = est.fit(had_data, outcome_col='y', unit_col='unit',
+                     time_col='period', dose_col='dose',
+                     aggregate='event_study')
 
-   print(f"Resolved estimand: {results.target_parameter}")
-   print(f"Estimate: {results.att:.3f}")
+   # Event-study results: per-horizon WAS at each event time
+   for e, att in zip(results.event_times, results.att):
+       print(f"  e={e}: {att:.3f}")
 
 Efficient DiD
 ~~~~~~~~~~~~~