dfm-python 0.5.56__tar.gz → 0.5.57__tar.gz

{dfm_python-0.5.56 → dfm_python-0.5.57}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dfm-python
-Version: 0.5.56
+Version: 0.5.57
 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
@@ -8,7 +8,6 @@ Project-URL: Repository, https://github.com/yourusername/dfm-python
 Project-URL: Issues, https://github.com/yourusername/dfm-python/issues
 Author: Minkey Chang
 License: MIT
-License-File: LICENSE
 Keywords: dfm,dynamic-factor-model,econometrics,forecasting,time-series
 Classifier: Development Status :: 4 - Beta
 Classifier: Intended Audience :: Science/Research
@@ -176,7 +175,7 @@ dfm-python/
 │   └── dfm_python/
 │       ├── models/          # Model implementations (DFM, DDFM, KDFM)
 │       ├── config/           # Configuration schemas
-│       ├── datamodule/       # PyTorch Lightning DataModules
+│       ├── datamodule/       # Data loading and preprocessing modules
 │       ├── trainer/          # Training procedures
 │       ├── ssm/              # State-space model components
 │       ├── dataset/          # Data loading and preprocessing
@@ -194,7 +193,7 @@ dfm-python/
 - **Structural identification**: Learnable structural shock identification (Cholesky, full, low-rank)
 - **Efficient computation**: Krylov FFT for O(T log T) forward pass
 - **Direct IRF computation**: Avoids numerical error accumulation
-- **Gradient descent training**: Uses PyTorch Lightning for training
+- **Gradient descent training**: Uses PyTorch for training with custom logging
 
 ### DFM (Dynamic Factor Model)
 
@@ -207,7 +206,7 @@ dfm-python/
 
 - **Nonlinear encoder**: Neural network encoder for nonlinear factor extraction
 - **MCMC training**: Denoising training procedure
-- **PyTorch-based**: Full PyTorch implementation with Lightning support
+- **PyTorch-based**: Full PyTorch implementation with custom logging system
 
 ## IRF Analysis: KDFM's PRIMARY CONTRIBUTION
 

{dfm_python-0.5.56 → dfm_python-0.5.57}/README.md

@@ -118,7 +118,7 @@ dfm-python/
 │   └── dfm_python/
 │       ├── models/          # Model implementations (DFM, DDFM, KDFM)
 │       ├── config/           # Configuration schemas
-│       ├── datamodule/       # PyTorch Lightning DataModules
+│       ├── datamodule/       # Data loading and preprocessing modules
 │       ├── trainer/          # Training procedures
 │       ├── ssm/              # State-space model components
 │       ├── dataset/          # Data loading and preprocessing
@@ -136,7 +136,7 @@ dfm-python/
 - **Structural identification**: Learnable structural shock identification (Cholesky, full, low-rank)
 - **Efficient computation**: Krylov FFT for O(T log T) forward pass
 - **Direct IRF computation**: Avoids numerical error accumulation
-- **Gradient descent training**: Uses PyTorch Lightning for training
+- **Gradient descent training**: Uses PyTorch for training with custom logging
 
 ### DFM (Dynamic Factor Model)
 
@@ -149,7 +149,7 @@ dfm-python/
 
 - **Nonlinear encoder**: Neural network encoder for nonlinear factor extraction
 - **MCMC training**: Denoising training procedure
-- **PyTorch-based**: Full PyTorch implementation with Lightning support
+- **PyTorch-based**: Full PyTorch implementation with custom logging system
 
 ## IRF Analysis: KDFM's PRIMARY CONTRIBUTION
 

{dfm_python-0.5.56 → dfm_python-0.5.57}/config/ddfm_macro.yaml

@@ -26,29 +26,30 @@ target_scaler: standard  # Scaler for target series: 'standard', 'robust', 'minm
 
 # Frequency mapping for mixed-frequency macro data
 # Clock is weekly (w), so monthly series are slower frequency
-# All frequencies must be explicitly specified
+# Grouped format: frequencies are specified as lists grouped by frequency code
 # Reduced set for faster testing (~50% reduction: 12 monthly series kept from original ~24)
 frequency:
   # Monthly series (slower than weekly clock) - typically end-of-month observations
   # Essential series for testing
-  KOEMPTOTO: m  # Total employment (monthly)
-  KOHWRWEMP: m  # Hours worked (monthly)
-  KOIMPCONA: m  # Investment, Construction (monthly)
-  KOWRCCNSE: m  # Consumption (monthly)
-  KOCONPRCF: m  # Production (monthly)
-  KOCPCOREF: m  # Consumer prices (monthly)
-  KOCPEXFEF: m  # Export prices (monthly)
-  KOCREU..A: m  # Credit (monthly)
-  KOLRLTHH: m  # Interest rates (monthly)
-  KOBSIHAPR: m  # Business survey (monthly)
-  KOCNFCONR: m  # Confidence (monthly)
-  # Target series
-  KOEQUIPTE: m  # Investment, Equipment (monthly, target series)
+  m:
+    - KOEMPTOTO  # Total employment (monthly)
+    - KOHWRWEMP  # Hours worked (monthly)
+    - KOIMPCONA  # Investment, Construction (monthly)
+    - KOWRCCNSE  # Consumption (monthly)
+    - KOCONPRCF  # Production (monthly)
+    - KOCPCOREF  # Consumer prices (monthly)
+    - KOCPEXFEF  # Export prices (monthly)
+    - KOCREU..A  # Credit (monthly)
+    - KOLRLTHH  # Interest rates (monthly)
+    - KOBSIHAPR  # Business survey (monthly)
+    - KOCNFCONR  # Confidence (monthly)
+    - KOEQUIPTE  # Investment, Equipment (monthly, target series)
   # Weekly series (same as clock frequency)
-  KORFBEV: w  # Retail, Food & Beverages (weekly)
-  KORWHLS: w  # Retail, Wholesale (weekly)
-  KORMCMP: w  # Retail, Miscellaneous & Comparison (weekly)
-  KORELEC: w  # Retail, Electronics (weekly)
-  KORCNST: w  # Retail, Construction (weekly)
-  KORMACH: w  # Retail, Machinery (weekly)
-  KOROCOINF: w  # Retail, Other Consumer & Information (weekly)
+  w:
+    - KORFBEV  # Retail, Food & Beverages (weekly)
+    - KORWHLS  # Retail, Wholesale (weekly)
+    - KORMCMP  # Retail, Miscellaneous & Comparison (weekly)
+    - KORELEC  # Retail, Electronics (weekly)
+    - KORCNST  # Retail, Construction (weekly)
+    - KORMACH  # Retail, Machinery (weekly)
+    - KOROCOINF  # Retail, Other Consumer & Information (weekly)

{dfm_python-0.5.56 → dfm_python-0.5.57}/config/dfm_macro.yaml

@@ -55,30 +55,32 @@ blocks:
 
 # Frequency mapping for mixed-frequency macro data
 # Clock is weekly (w), so monthly series are slower frequency
-# All frequencies must be explicitly specified
+# Grouped format: frequencies are specified as lists grouped by frequency code
 # Reduced set for faster testing (~50% reduction: 18 monthly series kept from original ~36)
 frequency:
   # Monthly series (slower than weekly clock) - typically end-of-month observations
   # Block_Real series
-  KOEMPTOTO: m  # Total employment (monthly)
-  KOHWRWEMP: m  # Hours worked (monthly)
-  KOIMPCONA: m  # Investment, Construction (monthly)
-  KOWRCCNSE: m  # Consumption (monthly)
-  KOCONPRCF: m  # Production (monthly)
-  # Block_Prices_Financial series
-  KOCPCOREF: m  # Consumer prices (monthly)
-  KOCPEXFEF: m  # Export prices (monthly)
-  KOCREU..A: m  # Credit (monthly)
-  KOLRLTHH: m  # Interest rates (monthly)
-  KOBSIHAPR: m  # Business survey (monthly)
-  KOCNFCONR: m  # Confidence (monthly)
-  # Target series
-  KOEQUIPTE: m  # Investment, Equipment (monthly, target series)
+  m:
+    - KOEMPTOTO  # Total employment (monthly)
+    - KOHWRWEMP  # Hours worked (monthly)
+    - KOIMPCONA  # Investment, Construction (monthly)
+    - KOWRCCNSE  # Consumption (monthly)
+    - KOCONPRCF  # Production (monthly)
+    # Block_Prices_Financial series
+    - KOCPCOREF  # Consumer prices (monthly)
+    - KOCPEXFEF  # Export prices (monthly)
+    - KOCREU..A  # Credit (monthly)
+    - KOLRLTHH  # Interest rates (monthly)
+    - KOBSIHAPR  # Business survey (monthly)
+    - KOCNFCONR  # Confidence (monthly)
+    # Target series
+    - KOEQUIPTE  # Investment, Equipment (monthly, target series)
   # Weekly series (same as clock frequency)
-  KORFBEV: w  # Retail, Food & Beverages (weekly)
-  KORWHLS: w  # Retail, Wholesale (weekly)
-  KORMCMP: w  # Retail, Miscellaneous & Comparison (weekly)
-  KORELEC: w  # Retail, Electronics (weekly)
-  KORCNST: w  # Retail, Construction (weekly)
-  KORMACH: w  # Retail, Machinery (weekly)
-  KOROCOINF: w  # Retail, Other Consumer & Information (weekly)
+  w:
+    - KORFBEV  # Retail, Food & Beverages (weekly)
+    - KORWHLS  # Retail, Wholesale (weekly)
+    - KORMCMP  # Retail, Miscellaneous & Comparison (weekly)
+    - KORELEC  # Retail, Electronics (weekly)
+    - KORCNST  # Retail, Construction (weekly)
+    - KORMACH  # Retail, Machinery (weekly)
+    - KOROCOINF  # Retail, Other Consumer & Information (weekly)

{dfm_python-0.5.56 → dfm_python-0.5.57}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "dfm-python"
-version = "0.5.56"
+version = "0.5.57"
 description = "Dynamic Factor Model (DFM) estimation and forecasting in Python"
 readme = "README.md"
 requires-python = ">=3.10"
@@ -83,6 +83,7 @@ packages = [
 exclude = [
     "test_venv",
     "test_venv/**",
+    "LICENSE",
 ]
 
 [dependency-groups]

{dfm_python-0.5.56 → dfm_python-0.5.57}/src/dfm_python/config/__init__.py

@@ -10,7 +10,7 @@ Note: Series are specified via frequency dict mapping column names to frequencie
 from .schema import (
     BaseModelConfig, DFMConfig, DDFMConfig,
     BaseResult, DFMResult, DDFMResult,
-    DFMFitParams, DDFMFitParams, FitParams,  # FitParams is backward compatibility alias
+    DFMStateSpaceParams, DDFMStateSpaceParams,
 )
 # DEFAULT_BLOCK_NAME is imported lazily where needed to avoid circular imports
 from .constants import (
@@ -46,8 +46,6 @@ from .types import (
     ForecastResult,
     CoefficientMatrix,
     CovarianceMatrix,
-    IRFArray,
-    CompanionMatrix,
     SeriesID,
     Frequency,
     DatasetName,
@@ -58,7 +56,6 @@ from .types import (
     ResultDict,
     ForecastDict,
     MetricsDict,
-    IRFResultDict,
     CheckpointDict,
     ConfigDict,
     Device,
@@ -107,9 +104,8 @@ __all__ = [
     # 'DEFAULT_BLOCK_NAME',  # Removed to avoid circular import - import directly from functional.dfm_block
     # Model-specific configs (from schema.py)
     'DFMConfig', 'DDFMConfig',
-    # Parameter overrides
-    'DFMFitParams', 'DDFMFitParams',
-    'FitParams',  # Backward compatibility alias
+    # State-space parameters
+    'DFMStateSpaceParams', 'DDFMStateSpaceParams',
     # Model-specific results (from results.py)
     'DFMResult', 'DDFMResult',
     # Utilities
@@ -139,8 +135,6 @@ __all__ = [
     'ForecastResult',
     'CoefficientMatrix',
     'CovarianceMatrix',
-    'IRFArray',
-    'CompanionMatrix',
     'SeriesID',
     'Frequency',
     'DatasetName',
@@ -151,7 +145,6 @@ __all__ = [
     'ResultDict',
     'ForecastDict',
     'MetricsDict',
-    'IRFResultDict',
     'CheckpointDict',
     'ConfigDict',
     'Device',

{dfm_python-0.5.56 → dfm_python-0.5.57}/src/dfm_python/config/adapter.py

@@ -118,7 +118,12 @@ def _extract_frequency_dict(
     data: Dict[str, Any],
     clock: str = DEFAULT_CLOCK_FREQUENCY
 ) -> Optional[Dict[str, str]]:
-    """Extract frequency dict from data, handling both new API and legacy formats.
+    """Extract frequency dict from data, handling multiple formats.
+    
+    Supports:
+    1. Grouped format: {'w': [series1, series2, ...], 'm': [series3, ...]}
+    2. Individual format: {'series1': 'w', 'series2': 'm', ...}
+    3. Legacy format: {'series': [{'series_id': ..., 'frequency': ...}, ...]}
     
     Parameters
     ----------
@@ -132,12 +137,63 @@ def _extract_frequency_dict(
     Optional[Dict[str, str]]
         Frequency dict mapping column names to frequencies, or None if not found
     """
-    if 'frequency' in data:
-        # New API: frequency dict directly
-        return data['frequency']
-    elif 'series' in data:
-        # Legacy: convert series list/dict to frequency dict
-        return _convert_series_to_frequency_dict(data['series'], clock)
+    if 'frequency' not in data:
+        # Legacy: check for 'series' key
+        if 'series' in data:
+            return _convert_series_to_frequency_dict(data['series'], clock)
+        return None
+    
+    freq_data = data['frequency']
+    
+    # Check if it's in grouped format: {'w': [...], 'm': [...]}
+    if _is_dict_like(freq_data):
+        from .constants import VALID_FREQUENCIES
+        
+        # Check if all keys are valid frequency codes (grouped format)
+        keys_are_frequencies = all(
+            isinstance(k, str) and k in VALID_FREQUENCIES 
+            for k in freq_data.keys()
+        )
+        
+        # Check if values are lists (grouped format)
+        values_are_lists = all(
+            isinstance(v, (list, tuple)) for v in freq_data.values()
+        )
+        
+        if keys_are_frequencies and values_are_lists:
+            # Grouped format: convert to individual format
+            result = {}
+            for freq, series_list in freq_data.items():
+                if not isinstance(series_list, (list, tuple)):
+                    _raise_config_error(
+                        f"Frequency '{freq}' must map to a list of series names, got {type(series_list)}"
+                    )
+                for series_name in series_list:
+                    if not isinstance(series_name, str):
+                        _raise_config_error(
+                            f"Series names must be strings, got {type(series_name)} in frequency '{freq}'"
+                        )
+                    if series_name in result:
+                        _raise_config_error(
+                            f"Series '{series_name}' appears in multiple frequency groups"
+                        )
+                    result[series_name] = freq
+            return result
+        else:
+            # Individual format: already in correct format, validate structure
+            result = {}
+            for series_name, freq in freq_data.items():
+                if not isinstance(series_name, str):
+                    _raise_config_error(
+                        f"Frequency dict keys must be strings (series names), got {type(series_name)}"
+                    )
+                if not isinstance(freq, str):
+                    _raise_config_error(
+                        f"Frequency dict values must be strings (frequency codes), got {type(freq)} for series '{series_name}'"
+                    )
+                result[series_name] = freq
+            return result
+    
     return None
 
 

{dfm_python-0.5.56 → dfm_python-0.5.57}/src/dfm_python/config/constants.py

@@ -23,7 +23,7 @@ DEFAULT_MIN_DELTA = 1e-6  # Minimum change for improvement
 # ============================================================================
 
 # Minimum eigenvalues and variances
-MIN_EIGENVALUE = 1e-8  # Minimum eigenvalue for positive definite matrices
+MIN_EIGENVALUE = 1e-6  # Minimum eigenvalue for positive definite matrices (increased from 1e-8 for better conditioning)
 MIN_DIAGONAL_VARIANCE = 1e-8  # Minimum variance for diagonal elements
 MIN_OBSERVATION_NOISE = 1e-4  # Minimum observation noise for measurement error (used in EM updates)
 DEFAULT_DDFM_OBSERVATION_NOISE = 1e-15  # Default observation noise for DDFM state-space (matches original TensorFlow)
@@ -33,7 +33,7 @@ MIN_STD_FOR_SCALE_CHECK = 1e-10  # Minimum standard deviation for scale ratio co
 DEFAULT_VARIANCE_FALLBACK = 1.0  # Default variance fallback value for numerical stability
 
 # Maximum eigenvalues
-MAX_EIGENVALUE = 1e6  # Maximum eigenvalue cap
+MAX_EIGENVALUE = 1e3  # Maximum eigenvalue cap (reduced to 1e3 to improve condition number: 1e3/1e-6 = 1e9)
 
 # Eigenvalue stability thresholds
 DEFAULT_EIGENVALUE_MAX_MAGNITUDE = 1.0  # Default maximum eigenvalue magnitude for stability checks
@@ -217,6 +217,7 @@ DEFAULT_START_DATE = datetime(2000, 1, 1)
 # Default window size for DDFM
 DEFAULT_WINDOW_SIZE = 100
 DEFAULT_TENT_KERNEL_SIZE = 5  # Default tent kernel size for slower-frequency series aggregation
+DEFAULT_TENT_KERNEL_REGULARIZATION_MULTIPLIER = 100.0  # Regularization multiplier for tent kernel series (handles ill-conditioning)
 # Note: DEFAULT_BATCH_SIZE is defined above (line 88) as 32 for general neural networks
 # Use DEFAULT_DDFM_WINDOW_SIZE (100) for DDFM-specific window size (time-step batch size)
 
@@ -284,7 +285,7 @@ DEFAULT_PROGRESS_LOG_INTERVAL = 5  # Default progress logging interval for EM al
 # Precision Defaults
 # ============================================================================
 
-DEFAULT_DTYPE = np.float32  # Default numpy dtype for arrays
+DEFAULT_DTYPE = np.float64  # Default numpy dtype for arrays (float64 for better numerical stability)
 
 # PyTorch dtype (matches DEFAULT_DTYPE)
 try:
@@ -518,7 +519,6 @@ __all__ = [
     'MIN_VARIABLES',
     'MIN_SHAPE_FOR_AR2',
     'MIN_DDFM_TIME_STEPS',
-    'MIN_SHAPE_FOR_AR2',
     'MIN_DDFM_DATASET_SIZE_WARNING',
     'MIN_ITER_FOR_DELTA_COMPUTATION',
     'DEFAULT_MIN_ITER_FOR_CONVERGENCE_CHECK',
@@ -546,6 +546,7 @@ __all__ = [
     'DEFAULT_LOG_INTERVAL',
     'DEFAULT_PROGRESS_LOG_INTERVAL',
     'DEFAULT_TENT_KERNEL_SIZE',
+    'DEFAULT_TENT_KERNEL_REGULARIZATION_MULTIPLIER',
     'MAX_ERROR_ITEMS',
     # IRF
     'DEFAULT_IRF_HORIZON',

{dfm_python-0.5.56 → dfm_python-0.5.57}/src/dfm_python/config/schema/__init__.py

@@ -9,15 +9,11 @@ Note: Series are specified via frequency dict mapping column names to frequencie
 
 from .model import BaseModelConfig, DFMConfig, DDFMConfig
 from .results import BaseResult, DFMResult, DDFMResult
-from .params import DFMFitParams, DDFMFitParams
-
-# Backward compatibility alias
-FitParams = DFMFitParams
+from .params import DFMStateSpaceParams, DDFMStateSpaceParams
 
 __all__ = [
     'BaseModelConfig', 'DFMConfig', 'DDFMConfig',
     'BaseResult', 'DFMResult', 'DDFMResult',
-    'DFMFitParams', 'DDFMFitParams',
-    'FitParams',  # Backward compatibility alias
+    'DFMStateSpaceParams', 'DDFMStateSpaceParams',
 ]
 

dfm_python-0.5.57/src/dfm_python/config/schema/block.py

@@ -0,0 +1,122 @@
+"""Block structure configuration for DFM.
+
+This module defines the BlockStructure dataclass used to group block-related
+parameters in EM algorithm, replacing long conditional checks with a single
+optional parameter.
+"""
+
+from dataclasses import dataclass, field
+from typing import Optional, Dict, List
+import numpy as np
+
+
+@dataclass
+class BlockStructure:
+    """Block structure configuration for EM algorithm.
+    
+    Groups all block-related parameters together to simplify function signatures
+    and replace long conditional checks.
+    
+    Attributes
+    ----------
+    blocks : np.ndarray
+        Block structure array (N x n_blocks)
+    r : np.ndarray
+        Number of factors per block (n_blocks,)
+    p : int
+        VAR lag order
+    p_plus_one : int
+        State dimension per factor. This is equal to max_lag_size = max(p + 1, tent_kernel_size).
+        The name "p_plus_one" is used for backward compatibility with the EM algorithm interface.
+        In the model code, this is called "max_lag_size" to more clearly indicate it accounts
+        for tent kernel size when tent_kernel_size > p + 1.
+    n_clock_freq : int
+        Number of clock-frequency series
+    idio_indicator : np.ndarray
+        Idiosyncratic component indicator (N,)
+    R_mat : np.ndarray, optional
+        Tent kernel constraint matrix for mixed-frequency data
+    q : np.ndarray, optional
+        Tent kernel constraint vector for mixed-frequency data
+    n_slower_freq : int, optional
+        Number of slower-frequency series
+    tent_weights_dict : dict, optional
+        Dictionary mapping frequency pairs to tent weights
+    
+    Cached indices (computed once, reused across EM iterations):
+    _cached_unique_blocks : List[np.ndarray], optional
+        Unique block patterns (cached)
+    _cached_unique_indices : List[int], optional
+        Indices of unique block patterns (cached)
+    _cached_bl_idxM : List[np.ndarray], optional
+        Clock-frequency factor loadings indices per unique block pattern (cached)
+    _cached_bl_idxQ : List[np.ndarray], optional
+        Slower-frequency factor loadings indices per unique block pattern (cached)
+    _cached_R_con : np.ndarray, optional
+        Block diagonal constraint matrix (cached)
+    _cached_q_con : np.ndarray, optional
+        Constraint vector (cached)
+    _cached_total_factor_dim : int, optional
+        Total factor state dimension (cached)
+    _cached_idio_indicator_M : np.ndarray, optional
+        Clock-frequency idiosyncratic component indicator (cached)
+    _cached_n_idio_M : int, optional
+        Number of clock-frequency idiosyncratic components (cached)
+    _cached_c_idio_indicator : np.ndarray, optional
+        Cumulative sum of idiosyncratic component indicator (cached)
+    _cached_rp1 : int, optional
+        Start of idiosyncratic components in state space (cached)
+    """
+    blocks: np.ndarray
+    r: np.ndarray
+    p: int
+    p_plus_one: int
+    n_clock_freq: int
+    idio_indicator: np.ndarray
+    R_mat: Optional[np.ndarray] = None
+    q: Optional[np.ndarray] = None
+    n_slower_freq: Optional[int] = None
+    tent_weights_dict: Optional[Dict[str, np.ndarray]] = None
+    
+    # Cached indices (computed once, reused across EM iterations)
+    _cached_unique_blocks: Optional[List[np.ndarray]] = field(default=None, init=False, repr=False)
+    _cached_unique_indices: Optional[List[int]] = field(default=None, init=False, repr=False)
+    _cached_bl_idxM: Optional[List[np.ndarray]] = field(default=None, init=False, repr=False)
+    _cached_bl_idxQ: Optional[List[np.ndarray]] = field(default=None, init=False, repr=False)
+    _cached_R_con: Optional[np.ndarray] = field(default=None, init=False, repr=False)
+    _cached_q_con: Optional[np.ndarray] = field(default=None, init=False, repr=False)
+    _cached_total_factor_dim: Optional[int] = field(default=None, init=False, repr=False)
+    _cached_idio_indicator_M: Optional[np.ndarray] = field(default=None, init=False, repr=False)
+    _cached_n_idio_M: Optional[int] = field(default=None, init=False, repr=False)
+    _cached_c_idio_indicator: Optional[np.ndarray] = field(default=None, init=False, repr=False)
+    _cached_rp1: Optional[int] = field(default=None, init=False, repr=False)
+    
+    def is_valid(self) -> bool:
+        """Check if block structure is valid (all required fields are not None)."""
+        return (
+            self.blocks is not None
+            and self.r is not None
+            and self.p is not None
+            and self.p_plus_one is not None
+            and self.n_clock_freq is not None
+            and self.idio_indicator is not None
+        )
+    
+    def has_cached_indices(self) -> bool:
+        """Check if block structure indices are cached."""
+        return self._cached_unique_blocks is not None
+    
+    def clear_cache(self) -> None:
+        """Clear all cached indices to ensure clean state for new training runs."""
+        self._cached_unique_blocks = None
+        self._cached_unique_indices = None
+        self._cached_bl_idxM = None
+        self._cached_bl_idxQ = None
+        self._cached_R_con = None
+        self._cached_q_con = None
+        self._cached_total_factor_dim = None
+        self._cached_idio_indicator_M = None
+        self._cached_n_idio_M = None
+        self._cached_c_idio_indicator = None
+        self._cached_rp1 = None
+

{dfm_python-0.5.56 → dfm_python-0.5.57}/src/dfm_python/config/schema/model.py

@@ -91,7 +91,9 @@ class BaseModelConfig:
     - Data preprocessing (missing data handling)
     
     Series Configuration:
-    - Provide `frequency` dict: {'column_name': 'frequency_code'} to specify per-series frequencies
+    - Provide `frequency` dict in one of two formats:
+      1. Grouped format: {'w': [series1, series2, ...], 'm': [series3, ...]} (recommended for large configs)
+      2. Individual format: {'series1': 'w', 'series2': 'm', ...} (backward compatible)
     - If `frequency` is None, all columns will use `clock` frequency
     - If a column is missing from `frequency` dict, it will use `clock` frequency
     - When data is loaded, missing columns in `frequency` dict are automatically added with `clock` frequency
@@ -103,7 +105,14 @@ class BaseModelConfig:
     
     Examples
     --------
-    >>> # With explicit frequency mapping
+    >>> # With grouped frequency mapping (recommended for large configs)
+    >>> config = DFMConfig(
+    ...     frequency={'q': ['gdp'], 'm': ['unemployment', 'interest_rate']},
+    ...     clock='m',
+    ...     blocks={...}
+    ... )
+    >>> 
+    >>> # With individual frequency mapping (backward compatible)
     >>> config = DFMConfig(
     ...     frequency={'gdp': 'q', 'unemployment': 'm', 'interest_rate': 'm'},
     ...     clock='m',