dfm-python 0.5.58__tar.gz → 0.5.59__tar.gz

{dfm_python-0.5.58 → dfm_python-0.5.59}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dfm-python
-Version: 0.5.58
+Version: 0.5.59
 Summary: Dynamic Factor Model (DFM) estimation and forecasting in Python
 Project-URL: Homepage, https://github.com/yourusername/dfm-python
 Project-URL: Documentation, https://github.com/yourusername/dfm-python#readme
@@ -18,6 +18,7 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Scientific/Engineering
 Requires-Python: >=3.10
+Requires-Dist: build>=1.4.0
 Requires-Dist: einops>=0.8.1
 Requires-Dist: hydra-core>=1.3.2
 Requires-Dist: matplotlib>=3.5.0

{dfm_python-0.5.58 → dfm_python-0.5.59}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "dfm-python"
-version = "0.5.58"
+version = "0.5.59"
 description = "Dynamic Factor Model (DFM) estimation and forecasting in Python"
 readme = "README.md"
 requires-python = ">=3.10"
@@ -20,6 +20,7 @@ classifiers = [
     "Topic :: Scientific/Engineering",
 ]
 dependencies = [
+    "build>=1.4.0",
     "einops>=0.8.1",
     "hydra-core>=1.3.2",
     "matplotlib>=3.5.0",

{dfm_python-0.5.58 → dfm_python-0.5.59}/src/dfm_python/functional/em.py

@@ -1233,7 +1233,7 @@ def em_step(
         _logger.info(f"    E-step: Running Kalman filter + smoother (T={T}, N={N}, m={m}, ~{ops_estimate:.1f}B ops)...")
         _logger.info(f"    E-step: Filter is fast (~1s), but smooth may take 5-7 minutes (bottleneck)")
     EZ, V_smooth, VVsmooth, loglik = kalman_filter.filter_and_smooth(X_masked)
-    
+
     # Keep float64 for numerical stability (prevents V_smooth accumulation overflow)
     # Do NOT convert to float32 - maintain float64 precision throughout M-step
     # Float64 is critical for large state spaces (m=183) and long time series (T=2135)

{dfm_python-0.5.58 → dfm_python-0.5.59}/src/dfm_python/models/dfm.py

@@ -1319,7 +1319,33 @@ class DFM(BaseFactorModel):
         
         # Run filter and smooth on new data
         y_masked = np.ma.masked_invalid(data_new)
-        Z_new, V_smooth_new, _, _ = kalman_new.filter_and_smooth(y_masked)
+
+        # ------------------------------------------------------------------
+        # IMPORTANT (pykalman quirk):
+        # pykalman.KalmanFilter._parse_observations() transposes when input has
+        # shape (1, n_dim_obs), interpreting it as (n_dim_obs, 1). For our
+        # update() case, (1, N) means 1 timestep with N series. This transpose
+        # causes n_dim_obs=1 and breaks CholeskyKalmanFilter internals.
+        #
+        # Workaround: for a single new timestep, use filter_update() directly
+        # with a 1D observation vector (n_dim_obs,), avoiding _parse_observations.
+        # ------------------------------------------------------------------
+        if hasattr(data_new, "shape") and len(data_new.shape) == 2 and int(data_new.shape[0]) == 1:
+            pk = getattr(kalman_new, "_pykalman", None)
+            if pk is None:
+                raise ModelNotTrainedError("Kalman filter not initialized for update()")
+
+            # 1D observation vector for this timestep
+            obs = np.ma.masked_invalid(data_new[0])
+            next_mean, _next_cov = pk.filter_update(
+                filtered_state_mean=Z_last,
+                filtered_state_covariance=V_last,
+                observation=obs,
+            )
+            Z_new = np.asarray(next_mean, dtype=DEFAULT_DTYPE)[np.newaxis, :]
+            V_smooth_new = None
+        else:
+            Z_new, V_smooth_new, _, _ = kalman_new.filter_and_smooth(y_masked)
         
         # Update model state: append new factors and data
         # Concatenate new factors to existing result.Z
@@ -1509,6 +1535,18 @@ class DFM(BaseFactorModel):
         except (ModelNotInitializedError, AttributeError):
             pass
         target_series, target_indices = resolve_target_series(dataset, series_ids, result, self.__class__.__name__)
+
+        # Fallback: If no Dataset is attached, use config.target_series.
+        # This is needed for checkpoints used in external pipelines where dataset.pkl
+        # is missing or not attached to the model instance.
+        if (target_series is None or len(target_series) == 0 or target_indices is None) and getattr(self, "_config", None) is not None:
+            cfg_ts = getattr(self._config, "target_series", None)
+            if cfg_ts is not None:
+                cfg_ts_list = cfg_ts if isinstance(cfg_ts, list) else [cfg_ts]
+                cfg_indices = [series_ids.index(t) for t in cfg_ts_list if series_ids is not None and t in series_ids]
+
+                if cfg_indices:
+                    target_series, target_indices = cfg_ts_list, cfg_indices
         
         if target_series is None or len(target_series) == 0:
             raise ValueError(
@@ -1747,19 +1785,36 @@ class DFM(BaseFactorModel):
             raise FileNotFoundError(f"Checkpoint file not found: {path}")
         
         # Try loading with error handling for corrupted files
+        # NOTE: Our training pipeline typically saves with joblib (for speed/compression),
+        # but older checkpoints may be plain pickle. Support both.
+        checkpoint = None
         try:
-            with open(path, 'rb') as f:
-                checkpoint = pickle.load(f)
-        except (pickle.UnpicklingError, EOFError, ValueError) as e:
-            raise RuntimeError(
-                f"Failed to load checkpoint from {path}. "
-                f"The file may be corrupted. Error: {e}. "
-                f"Try re-training the model to generate a new checkpoint."
-            ) from e
+            import joblib  # local import to avoid hard dependency at import-time
+            checkpoint = joblib.load(path)
+        except Exception:
+            # Fallback to plain pickle
+            try:
+                with open(path, 'rb') as f:
+                    checkpoint = pickle.load(f)
+            except (pickle.UnpicklingError, EOFError, ValueError) as e:
+                raise RuntimeError(
+                    f"Failed to load checkpoint from {path}. "
+                    f"The file may be corrupted or saved in an unsupported format. Error: {e}. "
+                    f"Try re-training the model to generate a new checkpoint."
+                ) from e
         
         # Use checkpoint config if not provided
         if config is None:
             config = checkpoint.get('config')
+
+        # If target_series was stored separately in the checkpoint (common in our pipeline),
+        # inject it into config so predict() can resolve targets without a Dataset attached.
+        try:
+            ckpt_target_series = checkpoint.get('target_series')
+            if config is not None and getattr(config, 'target_series', None) is None and ckpt_target_series is not None:
+                config.target_series = ckpt_target_series if isinstance(ckpt_target_series, list) else [ckpt_target_series]
+        except Exception:
+            pass
         
         # Get model state (new format preferred, fallback to old format)
         model_state = checkpoint.get('model_state')

{dfm_python-0.5.58 → dfm_python-0.5.59}/src/dfm_python/ssm/kalman.py

@@ -204,7 +204,7 @@ class DFMKalmanFilter:
                 "DFMKalmanFilter parameters not initialized. "
                 "Call update_parameters() first."
             )
-        
+
         # Get filtered states first (needed for smoother)
         transition_offsets = getattr(self._pykalman, 'transition_offsets', None)
         observation_offsets = getattr(self._pykalman, 'observation_offsets', None)
@@ -241,7 +241,7 @@ class DFMKalmanFilter:
         
         # Run filter
         predicted_state_means, predicted_state_covariances, _, filtered_state_means, filtered_state_covariances = run_filter()
-        
+
         filter_time = time_module.time() - filter_start
         _logger.info(f"    Filter: Completed in {filter_time:.2f}s ({filter_time/T*1000:.2f}ms/timestep)")
         
@@ -266,7 +266,7 @@ class DFMKalmanFilter:
                 # This is much cheaper than full eigendecomposition (O(m²) vs O(m³))
                 from ..config.constants import MIN_EIGENVALUE
                 regularization = max(1e-6, MIN_EIGENVALUE * 100)  # 1e-4 for stability
-                
+
                 _logger.info(f"    Smooth: Stabilizing {len(predicted_state_covariances)} covariance matrices "
                             f"(regularization={regularization:.2e})")
                 

{dfm_python-0.5.58 → dfm_python-0.5.59}/uv.lock

@@ -270,6 +270,22 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/b9/fa/123043af240e49752f1c4bd24da5053b6bd00cad78c2be53c0d1e8b975bc/backports.tarfile-1.2.0-py3-none-any.whl", hash = "sha256:77e284d754527b01fb1e6fa8a1afe577858ebe4e9dad8919e34c862cb399bc34", size = 30181, upload-time = "2024-05-28T17:01:53.112Z" },
 ]
 
+[[package]]
+name = "build"
+version = "1.4.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "colorama", marker = "os_name == 'nt'" },
+    { name = "importlib-metadata", marker = "python_full_version < '3.10.2'" },
+    { name = "packaging" },
+    { name = "pyproject-hooks" },
+    { name = "tomli", marker = "python_full_version < '3.11'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/42/18/94eaffda7b329535d91f00fe605ab1f1e5cd68b2074d03f255c7d250687d/build-1.4.0.tar.gz", hash = "sha256:f1b91b925aa322be454f8330c6fb48b465da993d1e7e7e6fa35027ec49f3c936", size = 50054, upload-time = "2026-01-08T16:41:47.696Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/c5/0d/84a4380f930db0010168e0aa7b7a8fed9ba1835a8fbb1472bc6d0201d529/build-1.4.0-py3-none-any.whl", hash = "sha256:6a07c1b8eb6f2b311b96fcbdbce5dab5fe637ffda0fd83c9cac622e927501596", size = 24141, upload-time = "2026-01-08T16:41:46.453Z" },
+]
+
 [[package]]
 name = "certifi"
 version = "2025.11.12"
@@ -859,9 +875,10 @@ wheels = [
 
 [[package]]
 name = "dfm-python"
-version = "0.5.56"
+version = "0.5.59"
 source = { editable = "." }
 dependencies = [
+    { name = "build" },
     { name = "einops" },
     { name = "hydra-core" },
     { name = "matplotlib" },
@@ -914,6 +931,7 @@ dev = [
 
 [package.metadata]
 requires-dist = [
+    { name = "build", specifier = ">=1.4.0" },
     { name = "dfm-python", extras = ["hydra", "db", "dev", "deep", "transform"], marker = "extra == 'all'" },
     { name = "einops", specifier = ">=0.8.1" },
     { name = "hydra-core", specifier = ">=1.3.2" },
@@ -2801,6 +2819,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/10/5e/1aa9a93198c6b64513c9d7752de7422c06402de6600a8767da1524f9570b/pyparsing-3.2.5-py3-none-any.whl", hash = "sha256:e38a4f02064cf41fe6593d328d0512495ad1f3d8a91c4f73fc401b3079a59a5e", size = 113890, upload-time = "2025-09-21T04:11:04.117Z" },
 ]
 
+[[package]]
+name = "pyproject-hooks"
+version = "1.2.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/e7/82/28175b2414effca1cdac8dc99f76d660e7a4fb0ceefa4b4ab8f5f6742925/pyproject_hooks-1.2.0.tar.gz", hash = "sha256:1e859bd5c40fae9448642dd871adf459e5e2084186e8d2c2a79a824c970da1f8", size = 19228, upload-time = "2024-09-29T09:24:13.293Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/bd/24/12818598c362d7f300f18e74db45963dbcb85150324092410c8b49405e42/pyproject_hooks-1.2.0-py3-none-any.whl", hash = "sha256:9e5c6bfa8dcc30091c74b0cf803c81fdd29d94f01992a7707bc97babb1141913", size = 10216, upload-time = "2024-09-29T09:24:11.978Z" },
+]
+
 [[package]]
 name = "pytest"
 version = "9.0.1"