views-frames 1.7.0__tar.gz → 1.8.0__tar.gz

{views_frames-1.7.0 → views_frames-1.8.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: views-frames
-Version: 1.7.0
+Version: 1.8.0
 Summary: The VIEWS platform data-contract layer: immutable array+identifier frames (numpy only, root of the dependency DAG).
 Project-URL: Homepage, https://github.com/views-platform/views-frames
 Project-URL: Repository, https://github.com/views-platform/views-frames
@@ -22,6 +22,12 @@ Requires-Python: >=3.10
 Requires-Dist: numpy<3,>=1.26
 Provides-Extra: arrow
 Requires-Dist: pyarrow<20,>=14; extra == 'arrow'
+Provides-Extra: docs
+Requires-Dist: jupyterlab<5,>=4; extra == 'docs'
+Requires-Dist: matplotlib<4,>=3.8; extra == 'docs'
+Requires-Dist: nbmake<2,>=1.5; extra == 'docs'
+Requires-Dist: pyarrow<20,>=14; extra == 'docs'
+Requires-Dist: scipy<2,>=1.11; extra == 'docs'
 Description-Content-Type: text/markdown
 
 # views-frames
@@ -249,7 +255,13 @@ makes it safe to depend on from everywhere (SDP).
 3. **Immutable value objects.** A frame is validated at construction and then
    treated as read-only. Operations (`collapse`, `select`, `with_metadata`)
    **return new frames**; they never mutate in place. (Directly forbids the
-   C-184 cross-repo-mutation anti-pattern.) **Copy-vs-view:** structural and
+   C-184 cross-repo-mutation anti-pattern.) **Enforced for the index, by
+   convention for the value buffer:** the identifier arrays (`time`/`unit`) are
+   write-protected (`setflags(write=False)`); the `values` buffer is left
+   **writeable on purpose** — so structural ops can share it zero-copy — and is
+   immutable *by convention*: mutating `.values` in place is unsupported and may
+   silently corrupt buffer-sharing frames (ADR-025 / register C-63; enforcing it
+   is a deferred MAJOR-rider). **Copy-vs-view:** structural and
    metadata-only operations (`with_metadata`, contiguous `select`) return frames
    that **share** the underlying `values` buffer (numpy view / zero-copy), and a
    `mmap`-backed frame stays `mmap`-backed — a new frame must never copy a

{views_frames-1.7.0 → views_frames-1.8.0}/README.md

@@ -223,7 +223,13 @@ makes it safe to depend on from everywhere (SDP).
 3. **Immutable value objects.** A frame is validated at construction and then
    treated as read-only. Operations (`collapse`, `select`, `with_metadata`)
    **return new frames**; they never mutate in place. (Directly forbids the
-   C-184 cross-repo-mutation anti-pattern.) **Copy-vs-view:** structural and
+   C-184 cross-repo-mutation anti-pattern.) **Enforced for the index, by
+   convention for the value buffer:** the identifier arrays (`time`/`unit`) are
+   write-protected (`setflags(write=False)`); the `values` buffer is left
+   **writeable on purpose** — so structural ops can share it zero-copy — and is
+   immutable *by convention*: mutating `.values` in place is unsupported and may
+   silently corrupt buffer-sharing frames (ADR-025 / register C-63; enforcing it
+   is a deferred MAJOR-rider). **Copy-vs-view:** structural and
    metadata-only operations (`with_metadata`, contiguous `select`) return frames
    that **share** the underlying `values` buffer (numpy view / zero-copy), and a
    `mmap`-backed frame stays `mmap`-backed — a new frame must never copy a

{views_frames-1.7.0 → views_frames-1.8.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "views-frames"
-version = "1.7.0"
+version = "1.8.0"
 description = "The VIEWS platform data-contract layer: immutable array+identifier frames (numpy only, root of the dependency DAG)."
 authors = [
     { name = "Simon Polichinel von der Maase", email = "simmaa@prio.org" },
@@ -39,6 +39,22 @@ Changelog = "https://github.com/views-platform/views-frames/blob/main/CHANGELOG.
 # Optional serialization extra — pyarrow is allowed ONLY behind io/ (README §3.1).
 [project.optional-dependencies]
 arrow = ["pyarrow>=14,<20"]
+# Optional docs/notebooks extra — plotting + jupyter for the showcase notebooks
+# (notebooks/, an un-gated dev artifact outside src/). NEVER runtime dependencies;
+# self-references [arrow] so `uv sync --extra docs` also enables the parquet round-trip
+# demo in notebooks/01_frames.ipynb. matplotlib/scipy are notebook-only (the core is
+# numpy-only); these are imported by notebooks, never by the package.
+docs = [
+    "views-frames[arrow]",
+    "matplotlib>=3.8,<4",
+    "scipy>=1.11,<2",
+    "jupyterlab>=4,<5",
+    # nbmake drives the non-blocking notebook-execution CI check (issue #151): it just
+    # runs the notebooks end-to-end to catch frozen-API drift. A test tool, but it rides
+    # in [docs] so the single `uv sync --extra docs` provisions everything the notebooks
+    # job needs (kernel + plotting + the checker).
+    "nbmake>=1.5,<2",
+]
 
 [dependency-groups]
 dev = [
@@ -76,9 +92,10 @@ show_missing = true
 [tool.ruff]
 line-length = 88
 target-version = "py310"
-# research/ is the volatile estimator lab (outside the frozen, gated src/); it is
-# not held to the leaf's lint/format bar.
-extend-exclude = ["research"]
+# research/ is the volatile estimator lab and notebooks/ holds the un-gated showcase
+# notebooks + their helper (notebooks/_synthetic.py) — both sit outside the frozen,
+# gated src/ and are not held to the leaf's lint/format bar.
+extend-exclude = ["research", "notebooks"]
 
 [tool.ruff.lint]
 select = ["E", "F", "I", "N", "UP", "B", "A", "C4", "SIM"]
@@ -87,11 +104,13 @@ select = ["E", "F", "I", "N", "UP", "B", "A", "C4", "SIM"]
 # The falsification stubs assert against the README via long, literal regexes
 # whose lines cannot wrap without changing their semantics.
 "tests/test_falsification_*.py" = ["E501"]
-# The reconciliation parity tests + their oracle-regeneration scripts are
-# faithfully relocated from views-postprocessing (Epic 11 / ADR-023); their dense
-# numpy/dict-comprehension assertions are kept verbatim rather than re-wrapped.
+# The reconciliation parity tests are faithfully relocated from views-postprocessing
+# (Epic 11 / ADR-023); their dense numpy/dict-comprehension assertions are kept verbatim
+# rather than re-wrapped.
 "tests/test_reconciliation_*.py" = ["E501"]
-"scripts/gen_reconciliation_*.py" = ["E501"]
+# The dev/ops scripts (oracle regeneration; the reconciliation parity verifier) are not
+# CI-run and carry dense numpy one-liners + report f-strings; not held to the wrap bar.
+"scripts/*.py" = ["E501"]
 
 [tool.mypy]
 python_version = "3.10"

{views_frames-1.7.0 → views_frames-1.8.0}/src/views_frames_reconcile/__init__.py

@@ -7,5 +7,18 @@ should be added as sibling modules, not by modifying ``proportional``.
 
 from views_frames_reconcile.module import ReconciliationModule
 from views_frames_reconcile.proportional import reconcile_proportional
+from views_frames_reconcile.result import (
+    ALIGNED_DRAWS,
+    METHOD_PROPORTIONAL,
+    POINT_BROADCAST,
+    ReconciliationResult,
+)
 
-__all__ = ["ReconciliationModule", "reconcile_proportional"]
+__all__ = [
+    "ALIGNED_DRAWS",
+    "METHOD_PROPORTIONAL",
+    "POINT_BROADCAST",
+    "ReconciliationModule",
+    "ReconciliationResult",
+    "reconcile_proportional",
+]

{views_frames-1.7.0 → views_frames-1.8.0}/src/views_frames_reconcile/conformance.py

@@ -66,7 +66,10 @@ def assert_reconcile_contract(
         rows = (pg_time == t) & (cm_units == c)
         in_sum = pgm_frame.values[rows].sum(axis=0)  # (S,)
         out_sum = out.values[rows].sum(axis=0)  # (S,)
-        total = cm_frame.values[cm_pos[(int(t), int(c))]]  # (S,)
+        # cm may be a point (sample_count == 1, broadcast inside reconcile) or aligned
+        # draws — broadcast its per-(time, country) total to the draw axis either way.
+        cm_total = cm_frame.values[cm_pos[(int(t), int(c))]]
+        total = np.broadcast_to(cm_total, out_sum.shape)
         active = in_sum != 0
         np.testing.assert_allclose(
             out_sum[active], total[active], rtol=1e-4, atol=1e-3

views_frames-1.8.0/src/views_frames_reconcile/module.py

@@ -0,0 +1,120 @@
+"""Frames-native reconciliation orchestration (epic #31, story #36).
+
+`ReconciliationModule` holds the injected `(time, priogrid_gid) -> country_id`
+mapping (geography is injected, never embedded — views-frames ADR-014) and
+applies it: `reconcile(cm_frame, pgm_frame)` validates the inputs and scales the
+grid forecasts to the country totals, returning a **new** pgm frame (de-mutated,
+C-184).
+
+**SRP:** orchestration only — the scaling math is the leaf (`proportional`), the
+grouping is `grouping`, the guards are `validation`, the I/O is `frames`. No
+torch, no pandas, no viewser, no wandb: the original's `ProcessPoolExecutor` and
+WandB alerting are dropped (numpy is fast; there is no GPU). If scale ever needs
+parallelism, add it behind this same interface (OCP). Multi-target inputs are
+reconciled by calling `reconcile` once per target.
+"""
+
+from __future__ import annotations
+
+from typing import Any
+
+import numpy as np
+from numpy.typing import NDArray
+
+from views_frames import PredictionFrame
+from views_frames_reconcile.grouping import reconcile_pgm_to_cm
+from views_frames_reconcile.result import (
+    ALIGNED_DRAWS,
+    METHOD_PROPORTIONAL,
+    POINT_BROADCAST,
+    ReconciliationResult,
+)
+from views_frames_reconcile.validation import validate_reconciliation_inputs
+
+
+def _broadcast_point_country(
+    cm_frame: PredictionFrame, n_samples: int
+) -> PredictionFrame:
+    """Tile a point country forecast (``sample_count == 1``) across ``n_samples`` draws.
+
+    Bit-identical to the WET broadcast pipeline-core's ``align_country_to_grid`` does
+    (views-frames#143): the single column is repeated, so every draw is rescaled to the
+    same total. It lives in the orchestrator so the leaf ``proportional`` and the
+    parity-frozen ``grouping`` hot loop stay **untouched** — the equal-count path is
+    byte-for-byte identical and only ``sample_count == 1`` takes this new path.
+    """
+    tiled = np.tile(np.asarray(cm_frame.values, dtype=np.float32), (1, n_samples))
+    return PredictionFrame(tiled, cm_frame.index, cm_frame.metadata)
+
+
+class ReconciliationModule:
+    """Reconcile pgm forecasts to cm country totals (one target per call)."""
+
+    def __init__(
+        self,
+        map_keys: NDArray[np.integer[Any]] | object,
+        map_vals: NDArray[np.integer[Any]] | object,
+    ) -> None:
+        """Inject the `(time, priogrid_gid) -> country_id` mapping.
+
+        Args:
+            map_keys: ``(M, 2)`` int array of ``(time, priogrid_gid)`` pairs.
+            map_vals: ``(M,)`` int ``country_id`` for each key.
+
+        Raises:
+            ValueError: ``map_keys`` is not ``(M, 2)`` or ``map_vals`` is not
+                length ``M``.
+        """
+        keys = np.asarray(map_keys)
+        vals = np.asarray(map_vals)
+        if keys.ndim != 2 or keys.shape[1] != 2:
+            raise ValueError("map_keys must be an (M, 2) array of (time, priogrid_gid)")
+        if vals.shape != (keys.shape[0],):
+            raise ValueError("map_vals must be a length-M array aligned to map_keys")
+        self._map_keys = keys
+        self._map_vals = vals
+
+    def reconcile_result(
+        self, cm_frame: PredictionFrame, pgm_frame: PredictionFrame
+    ) -> ReconciliationResult:
+        """Reconcile, also reporting the mode — a ``ReconciliationResult``.
+
+        A **point** country (``cm.sample_count == 1``) is broadcast across the grid's
+        draws before reconciling (mode ``point-broadcast``); an **aligned** country
+        (``cm.sample_count == S``) scales draw-for-draw (mode ``aligned-draws``, the
+        documented per-draw approximation). Any other count fails loud.
+
+        The mode is **returned**, never stamped on the leaf's generic ``FrameMetadata``
+        (ADR-020 / register C-47 — the leaf carries no reconciliation vocabulary; see
+        ``result.py``).
+
+        Raises:
+            ValueError: the inputs fail validation (level / sample-count — cm must be 1
+                or pgm's ``S`` / time coverage / missing country forecast).
+        """
+        validate_reconciliation_inputs(
+            cm_frame, pgm_frame, self._map_keys, self._map_vals
+        )
+        if cm_frame.sample_count != pgm_frame.sample_count:
+            cm = _broadcast_point_country(cm_frame, pgm_frame.sample_count)
+            mode = POINT_BROADCAST
+        else:
+            cm = cm_frame
+            mode = ALIGNED_DRAWS
+        frame = reconcile_pgm_to_cm(pgm_frame, cm, self._map_keys, self._map_vals)
+        return ReconciliationResult(frame=frame, mode=mode, method=METHOD_PROPORTIONAL)
+
+    def reconcile(
+        self, cm_frame: PredictionFrame, pgm_frame: PredictionFrame
+    ) -> PredictionFrame:
+        """Validate the inputs, then return a new pgm frame reconciled to cm totals.
+
+        Point/aligned handling and fail-loud are as :meth:`reconcile_result`; this
+        returns only the reconciled frame. Call :meth:`reconcile_result` when you also
+        need the reconciliation *mode* (point-broadcast vs aligned-draws).
+
+        Raises:
+            ValueError: the inputs fail validation (level / sample-count — cm must be 1
+                or pgm's ``S`` / time coverage / missing country forecast).
+        """
+        return self.reconcile_result(cm_frame, pgm_frame).frame

{views_frames-1.7.0 → views_frames-1.8.0}/src/views_frames_reconcile/proportional.py

@@ -10,9 +10,12 @@ This is a *faithful, numpy-only* port of views-reporting's
 ``ForecastReconciler.reconcile_forecast`` (torch), migrated here because the
 algorithm belongs in post-processing, not reporting (views-reporting issue #72).
 It is intentionally the **same** method — a pragmatic per-draw approximation, not
-principled joint probabilistic reconciliation. The upgrade to the latter is
-tracked as **C-37** and is deliberately deferred until this port's parity with
-the original is proven and the move is wired.
+principled joint probabilistic reconciliation. The upgrade to the latter is designed
+in **ADR-024** (register **C-62**; the cross-repo lineage is views-postprocessing
+C-37) and is deliberately **deferred**: per-draw pairing of independently-trained
+grid and country draws has no shared draw identity, so the principled method waits on
+a defined draw-identity/coupling contract and a consumer that needs calibrated joint
+tails.
 
 No torch, no pandas — numpy only.
 """

views_frames-1.8.0/src/views_frames_reconcile/result.py

@@ -0,0 +1,55 @@
+"""The reconciliation result — the reconciled frame plus *how* it was produced (#144).
+
+The reconciliation **mode** (`point-broadcast` vs `aligned-draws`) and **method** are
+reported here, on a reconcile-package result object — deliberately **not** stamped onto
+the leaf's generic ``FrameMetadata``. That header is governed *generic-only* (ADR-020 /
+register C-47): the numpy leaf carries provenance meaningful for *any* frame (`run_id`,
+`data_version`) and must never carry domain/operation vocabulary it cannot know — as
+evaluation provenance lives in views-evaluation's ``MetricFrame``, not the leaf.
+Reconciliation is a sibling operation, so its provenance is reported by the sibling.
+
+A caller that needs the mode reads it off :class:`ReconciliationResult`
+(``ReconciliationModule.reconcile_result``); a caller that only needs the frame uses
+``ReconciliationModule.reconcile``, which returns the frame directly.
+
+The mode reflects **what this reconcile call did** (broadcast a point, or scaled aligned
+draws) — not upstream provenance: a caller that pre-tiles a point country to ``S`` draws
+before calling reconciles in ``aligned-draws`` mode. The string values match
+pipeline-core's ``reconcile_frames`` constants verbatim, so the *vocabulary* is shared
+across the repos that produce and consume the mode.
+"""
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+
+from views_frames import PredictionFrame
+
+#: Mode — the call **broadcast a point**: the country arrived as a point
+#: (``cm.sample_count == 1``) against a multi-draw grid and was tiled across the grid's
+#: ``S`` draws (every draw rescaled to the same total).
+POINT_BROADCAST = "point-broadcast"
+#: Mode — the call **scaled aligned draws**: the country already carried the grid's draw
+#: count (``cm.sample_count == S``) and was scaled draw-for-draw — the per-draw
+#: approximation (the principled joint upgrade is a separate design, #145). The mode
+#: describes *what this call did*: a point against a single-draw grid, or a point the
+#: caller pre-tiled to ``S``, also reads as aligned-draws (nothing was broadcast).
+ALIGNED_DRAWS = "aligned-draws"
+#: The reconciliation algorithm — top-down proportional, per draw.
+METHOD_PROPORTIONAL = "proportional"
+
+
+@dataclass(frozen=True)
+class ReconciliationResult:
+    """A reconciled grid frame plus how it was produced.
+
+    Attributes:
+        frame: the reconciled pgm ``PredictionFrame`` (identical to what ``reconcile``
+            returns).
+        mode: :data:`POINT_BROADCAST` or :data:`ALIGNED_DRAWS`.
+        method: the reconciliation method, e.g. :data:`METHOD_PROPORTIONAL`.
+    """
+
+    frame: PredictionFrame
+    mode: str
+    method: str

{views_frames-1.7.0 → views_frames-1.8.0}/src/views_frames_reconcile/validation.py

@@ -6,7 +6,8 @@ buried in the orchestrator. The original's intents map as:
 
   - dataset type checks            -> spatial-level guard (cm@CM, pgm@PGM)
   - same time steps + exact overlap -> identical set of time values
-  - (per-draw scaling needs it)     -> equal `sample_count`
+  - (per-draw scaling needs it)     -> equal `sample_count`, or a point cm
+                                       (`sample_count == 1`) broadcast across the draws
   - valid countries                 -> every (time, country) the grid maps to has
                                        a country forecast in the cm frame
 
@@ -44,10 +45,11 @@ def validate_reconciliation_inputs(
         raise ValueError(
             f"grid frame must be at SpatialLevel.PGM, got {pgm_frame.index.level}"
         )
-    if cm_frame.sample_count != pgm_frame.sample_count:
+    if cm_frame.sample_count not in (1, pgm_frame.sample_count):
         raise ValueError(
-            f"sample-count mismatch: cm has {cm_frame.sample_count}, "
-            f"pgm has {pgm_frame.sample_count}"
+            f"sample-count mismatch: cm has {cm_frame.sample_count}, pgm has "
+            f"{pgm_frame.sample_count}; cm must be 1 (point, broadcast across draws) "
+            f"or {pgm_frame.sample_count} (aligned draws)"
         )
 
     cm_times = {int(t) for t in np.unique(cm_frame.index.time)}

views_frames-1.7.0/src/views_frames_reconcile/module.py

@@ -1,68 +0,0 @@
-"""Frames-native reconciliation orchestration (epic #31, story #36).
-
-`ReconciliationModule` holds the injected `(time, priogrid_gid) -> country_id`
-mapping (geography is injected, never embedded — views-frames ADR-014) and
-applies it: `reconcile(cm_frame, pgm_frame)` validates the inputs and scales the
-grid forecasts to the country totals, returning a **new** pgm frame (de-mutated,
-C-184).
-
-**SRP:** orchestration only — the scaling math is the leaf (`proportional`), the
-grouping is `grouping`, the guards are `validation`, the I/O is `frames`. No
-torch, no pandas, no viewser, no wandb: the original's `ProcessPoolExecutor` and
-WandB alerting are dropped (numpy is fast; there is no GPU). If scale ever needs
-parallelism, add it behind this same interface (OCP). Multi-target inputs are
-reconciled by calling `reconcile` once per target.
-"""
-
-from __future__ import annotations
-
-from typing import Any
-
-import numpy as np
-from numpy.typing import NDArray
-
-from views_frames import PredictionFrame
-from views_frames_reconcile.grouping import reconcile_pgm_to_cm
-from views_frames_reconcile.validation import validate_reconciliation_inputs
-
-
-class ReconciliationModule:
-    """Reconcile pgm forecasts to cm country totals (one target per call)."""
-
-    def __init__(
-        self,
-        map_keys: NDArray[np.integer[Any]] | object,
-        map_vals: NDArray[np.integer[Any]] | object,
-    ) -> None:
-        """Inject the `(time, priogrid_gid) -> country_id` mapping.
-
-        Args:
-            map_keys: ``(M, 2)`` int array of ``(time, priogrid_gid)`` pairs.
-            map_vals: ``(M,)`` int ``country_id`` for each key.
-
-        Raises:
-            ValueError: ``map_keys`` is not ``(M, 2)`` or ``map_vals`` is not
-                length ``M``.
-        """
-        keys = np.asarray(map_keys)
-        vals = np.asarray(map_vals)
-        if keys.ndim != 2 or keys.shape[1] != 2:
-            raise ValueError("map_keys must be an (M, 2) array of (time, priogrid_gid)")
-        if vals.shape != (keys.shape[0],):
-            raise ValueError("map_vals must be a length-M array aligned to map_keys")
-        self._map_keys = keys
-        self._map_vals = vals
-
-    def reconcile(
-        self, cm_frame: PredictionFrame, pgm_frame: PredictionFrame
-    ) -> PredictionFrame:
-        """Validate the inputs, then return a new pgm frame reconciled to cm totals.
-
-        Raises:
-            ValueError: the inputs fail validation (level / sample-count / time
-                coverage / missing country forecast).
-        """
-        validate_reconciliation_inputs(
-            cm_frame, pgm_frame, self._map_keys, self._map_vals
-        )
-        return reconcile_pgm_to_cm(pgm_frame, cm_frame, self._map_keys, self._map_vals)