Flatten submit package structure

submit/model/c0.py

@@ -0,0 +1,57 @@
+"""C0: observed statistics and mask baseline from E题V2, table 5.9."""
+from __future__ import annotations
+
+import numpy as np
+from sklearn.linear_model import LogisticRegression, Ridge
+
+MODALITIES = ("text", "audio", "vision")
+
+
+def sample_statistics(arrays: dict[str, np.ndarray], mask: np.ndarray) -> np.ndarray:
+    """Mean, standard deviation, missing fraction and longest gap per modality."""
+    mask = np.asarray(mask, dtype=bool)
+    if mask.ndim != 3 or mask.shape[-1] != 3:
+        raise ValueError("mask must have shape (N, T, 3)")
+    parts = []
+    for index, name in enumerate(MODALITIES):
+        x = np.asarray(arrays[name], dtype=np.float32)
+        if x.shape[:2] != mask.shape[:2]:
+            raise ValueError(f"{name}: feature and mask shapes disagree")
+        visible = mask[:, :, index]
+        count = visible.sum(axis=1, keepdims=True)
+        mean = (x * visible[:, :, None]).sum(axis=1) / np.maximum(count, 1)
+        variance = (((x - mean[:, None, :]) ** 2) * visible[:, :, None]).sum(axis=1) / np.maximum(count, 1)
+        missing = 1.0 - visible.mean(axis=1, keepdims=True)
+        max_gap = []
+        for row in visible:
+            longest = current = 0
+            for observed in row:
+                current = 0 if observed else current + 1
+                longest = max(longest, current)
+            max_gap.append(longest / max(len(row), 1))
+        parts.extend((mean, np.sqrt(variance), missing, np.asarray(max_gap, np.float32)[:, None]))
+    return np.concatenate(parts, axis=1).astype(np.float32)
+
+
+class C0:
+    """Logistic polarity classifier and Ridge intensity regressor."""
+
+    def __init__(self) -> None:
+        self.classifier = LogisticRegression(C=0.05, max_iter=2500, random_state=20260924)
+        self.regressor = Ridge(alpha=25.0)
+
+    def fit(self, arrays: dict[str, np.ndarray], mask: np.ndarray,
+            polarity: np.ndarray, intensity: np.ndarray) -> "C0":
+        features = sample_statistics(arrays, mask)
+        self.classifier.fit(features, polarity)
+        self.regressor.fit(features, intensity)
+        return self
+
+    def predict(self, arrays: dict[str, np.ndarray], mask: np.ndarray) -> dict[str, np.ndarray]:
+        features = sample_statistics(arrays, mask)
+        probabilities = np.zeros((len(features), 3), np.float64)
+        probabilities[:, self.classifier.classes_] = self.classifier.predict_proba(features)
+        return {
+            "probabilities": probabilities,
+            "intensity": np.clip(self.regressor.predict(features), -3.0, 3.0),
+        }