feat: adds Metadata.get_corpus_names() to retrieve the names in chron…

…ological order

src/dimcat/data/resources/features.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 import logging
-from typing import Iterable, List, Optional, Tuple
+from typing import Callable, Iterable, List, Optional, Tuple
 
 import frictionless as fl
 import marshmallow as mm
@@ -20,6 +20,7 @@
 from dimcat.data.resources.utils import (
     boolean_is_minor_column_to_mode,
     condense_dataframe_by_groups,
+    get_corpus_display_name,
     join_df_on_index,
     make_adjacency_groups,
     merge_ties,
@@ -63,6 +64,20 @@ def get_composition_years(
         result = years.groupby(group_cols).mean()
         return result
 
+    def get_corpus_names(
+        self,
+        func: Callable[[str], str] = get_corpus_display_name,
+    ):
+        """Returns the corpus names in chronological order, based on their pieces' mean composition years.
+        If ``func`` is specify, the function will be applied to each corpus name. This is useful for prettifying
+        the names, e.g. by removing underscores.
+        """
+        mean_composition_years = self.get_composition_years(group_cols="corpus")
+        sorted_corpus_names = mean_composition_years.sort_values().index.to_list()
+        if func is None:
+            return sorted_corpus_names
+        return [func(corp) for corp in sorted_corpus_names]
+
 
 # region Annotations
 AUXILIARY_HARMONYLABEL_COLUMNS = [
@@ -876,7 +891,9 @@ def _format_dataframe(self, feature_df: D) -> D:
         group_keys, _ = make_adjacency_groups(
             feature_df.localkey, groupby=groupby_levels
         )
-        feature_df = condense_dataframe_by_groups(feature_df, group_keys)
+        feature_df = condense_dataframe_by_groups(
+            feature_df, group_keys, logger=self.logger
+        )
         return self._sort_columns(feature_df)
 
 

src/dimcat/data/resources/utils.py

@@ -5,6 +5,7 @@
 import os
 import warnings
 from collections import Counter
+from functools import cache
 from operator import itemgetter
 from pprint import pformat
 from typing import (
@@ -51,6 +52,52 @@
 FALSY_VALUES = Boolean.falsy
 
 
+DCML_CORPUS_NAMES: Dict[str, str] = {
+    "ABC": "Beethoven String Quartets",
+    "bach_en_fr_suites": "Bach Suites",
+    "bach_solo": "Bach Solo",
+    "bartok_bagatelles": "Bartok Bagatelles",
+    "beethoven_piano_sonatas": "Beethoven Sonatas",
+    "c_schumann_lieder": "C Schumann Lieder",
+    "chopin_mazurkas": "Chopin Mazurkas",
+    "corelli": "Corelli Trio Sonatas",
+    "couperin_clavecin": "Couperin Clavecin",
+    "couperin_concerts": "Couperin Concerts Royaux",
+    "cpe_bach_keyboard": "CPE Bach Keyboard",
+    "debussy_suite_bergamasque": "Debussy Suite Bergamasque",
+    "dvorak_silhouettes": "Dvořák Silhouettes",
+    "frescobaldi_fiori_musicali": "Frescobaldi Fiori Musicali",
+    "gastoldi_baletti": "Gastoldi Baletti",
+    "grieg_lyric_pieces": "Grieg Lyric Pieces",
+    "handel_keyboard": "Handel Keyboard",
+    "jc_bach_sonatas": "JC Bach Sonatas",
+    "kleine_geistliche_konzerte": "Schütz Kleine Geistliche Konzerte",
+    "kozeluh_sonatas": "Kozeluh Sonatas",
+    "liszt_pelerinage": "Liszt Années",
+    "mahler_kindertotenlieder": "Mahler Kindertotenlieder",
+    "medtner_tales": "Medtner Tales",
+    "mendelssohn_quartets": "Mendelssohn Quartets",
+    "monteverdi_madrigals": "Monteverdi Madrigals",
+    "mozart_piano_sonatas": "Mozart Piano Sonatas",
+    "pergolesi_stabat_mater": "Pergolesi Stabat Mater",
+    "peri_euridice": "Peri Euridice",
+    "pleyel_quartets": "Pleyel Quartets",
+    "poulenc_mouvements_perpetuels": "Poulenc Mouvements Perpetuels",
+    "rachmaninoff_piano": "Rachmaninoff Piano",
+    "ravel_piano": "Ravel Piano",
+    "scarlatti_sonatas": "Scarlatti Sonatas",
+    "schubert_dances": "Schubert Dances",
+    "schubert_winterreise": "Schubert Winterreise",
+    "schulhoff_suite_dansante_en_jazz": "Schulhoff Suite Dansante En Jazz",
+    "schumann_kinderszenen": "R Schumann Kinderszenen",
+    "schumann_liederkreis": "R Schumann Liederkreis",
+    "sweelinck_keyboard": "Sweelinck Keyboard",
+    "tchaikovsky_seasons": "Tchaikovsky Seasons",
+    "wagner_overtures": "Wagner Overtures",
+    "wf_bach_sonatas": "WF Bach Sonatas",
+}
+
+
 def align_with_grouping(
     df: pd.DataFrame, grouping: DimcatIndex | pd.MultiIndex, sort_index: bool = True
 ) -> pd.DataFrame:
@@ -320,6 +367,17 @@ def fl_fields2pandas_params(fields: List[fl.Field]) -> Tuple[dict, dict, list]:
     return dtype, converters, parse_dates
 
 
+@cache
+def get_corpus_display_name(repo_name: str) -> str:
+    """Looks up a repository name in the CORPUS_NAMES constant. If not present,
+    the repo name is returned as title case.
+    """
+    name = DCML_CORPUS_NAMES.get(repo_name, "")
+    if name == "":
+        name = " ".join(s.title() for s in repo_name.split("_"))
+    return name
+
+
 def get_existing_normpath(fl_resource) -> str:
     """Get the normpath of a frictionless resource, raising an exception if it does not exist.
 

src/dimcat/plotting.py

@@ -22,8 +22,7 @@
 )
 """Fixed category colors for cadence labels."""
 
-PLOTLY_COLOR_SCALES = ColorscaleValidator().named_colorscales
-COLOR_SCALE_NAMES: List[str] = sorted(PLOTLY_COLOR_SCALES.keys())
+COLOR_SCALE_NAMES: List[str] = sorted(ColorscaleValidator().named_colorscales.keys())
 CS: TypeAlias = Literal[tuple(COLOR_SCALE_NAMES)]