1. generate_example_systems.py - Fixed incorrect file name in error message: Zeitreihen2020.csv → tmy_dresden.csv

  2. clustering/base.py clusters() - Now validates dimensions for all variables, not just the first one, and checks for consistency between variables
  3. clustering/base.py cluster_structure_from_mapping() - Fixed cluster occurrence mapping to handle non-contiguous cluster IDs by using max(unique_clusters) + 1 instead of len(unique_clusters) for n_clusters

Author: FBumann

docs/notebooks/data/generate_example_systems.py

@@ -66,7 +66,7 @@ def _get_weather() -> pd.DataFrame:
             _weather = load_weather()
         except FileNotFoundError as e:
             raise FileNotFoundError(
-                f'Weather data file not found. Ensure Zeitreihen2020.csv exists in {DATA_DIR}. Original error: {e}'
+                f'Weather data file not found. Ensure tmy_dresden.csv exists in {DATA_DIR}/raw. Original error: {e}'
             ) from e
     return _weather
 

flixopt/clustering/base.py

@@ -892,16 +892,26 @@ def clusters(
         n_clusters = int(cs.n_clusters) if isinstance(cs.n_clusters, (int, np.integer)) else int(cs.n_clusters.values)
         timesteps_per_cluster = cs.timesteps_per_cluster
 
-        # Check dimensions of aggregated data
-        sample_var = aggregated_data[resolved_variables[0]]
-        has_cluster_dim = 'cluster' in sample_var.dims
-        extra_dims = [d for d in sample_var.dims if d not in ('time', 'cluster')]
-        if extra_dims:
-            raise ValueError(
-                f'clusters() requires data with only time (or cluster, time) dimensions. '
-                f'Found extra dimensions: {extra_dims}. '
-                f'Use select={{{extra_dims[0]!r}: <value>}} to select a specific {extra_dims[0]}.'
-            )
+        # Check dimensions of all variables for consistency
+        has_cluster_dim = None
+        for var in resolved_variables:
+            da = aggregated_data[var]
+            var_has_cluster = 'cluster' in da.dims
+            extra_dims = [d for d in da.dims if d not in ('time', 'cluster')]
+            if extra_dims:
+                raise ValueError(
+                    f'clusters() requires data with only time (or cluster, time) dimensions. '
+                    f'Variable {var!r} has extra dimensions: {extra_dims}. '
+                    f'Use select={{{extra_dims[0]!r}: <value>}} to select a specific {extra_dims[0]}.'
+                )
+            if has_cluster_dim is None:
+                has_cluster_dim = var_has_cluster
+            elif has_cluster_dim != var_has_cluster:
+                raise ValueError(
+                    f'All variables must have consistent dimensions. '
+                    f'Variable {var!r} has {"" if var_has_cluster else "no "}cluster dimension, '
+                    f'but previous variables {"do" if has_cluster_dim else "do not"}.'
+                )
 
         # Build Dataset with cluster dimension, using labels with occurrence counts
         # Check if cluster_occurrences has extra dims
@@ -1147,11 +1157,11 @@ def create_cluster_structure_from_mapping(
 
     # Count occurrences of each cluster
     unique_clusters = np.unique(cluster_order)
+    n_clusters = int(unique_clusters.max()) + 1 if len(unique_clusters) > 0 else 0
     occurrences = {}
     for c in unique_clusters:
         occurrences[int(c)] = sum(1 for x in cluster_order if x == c)
 
-    n_clusters = len(unique_clusters)
     cluster_occurrences_da = xr.DataArray(
         [occurrences.get(c, 0) for c in range(n_clusters)],
         dims=['cluster'],