Annotations#

Hide imports 
%load_ext autoreload
%autoreload 2

import os

import dimcat as dc
import ms3
import plotly.express as px
from dimcat import groupers, plotting

import utils
Hide source 
RESULTS_PATH = os.path.abspath(os.path.join(utils.OUTPUT_FOLDER, "overview"))
os.makedirs(RESULTS_PATH, exist_ok=True)


def make_output_path(
    filename: str,
    extension=None,
    path=RESULTS_PATH,
) -> str:
    return utils.make_output_path(filename=filename, extension=extension, path=path)


def save_figure_as(
    fig, filename, formats=("png", "pdf"), directory=RESULTS_PATH, **kwargs
):
    if formats is not None:
        for fmt in formats:
            plotting.write_image(fig, filename, directory, format=fmt, **kwargs)
    else:
        plotting.write_image(fig, filename, directory, **kwargs)

Loading data

Hide source 
D = utils.get_dataset("mozart_piano_sonatas", corpus_release="v2.3")
package = D.inputs.get_package()
package_info = package._package.custom
git_tag = package_info.get("git_tag")
utils.print_heading("Data and software versions")
print("The Annotated Mozart Sonatas: Score, Harmony, and Cadence version v2.3")
print(f"Datapackage '{package.package_name}' @ {git_tag}")
print(f"dimcat version {dc.__version__}\n")
D

Data and software versions
--------------------------

The Annotated Mozart Sonatas: Score, Harmony, and Cadence version v2.3
Datapackage 'mozart_piano_sonatas' @ v2.3
dimcat version 3.4.0

Dataset
=======
{'inputs': {'basepath': None,
            'packages': {'mozart_piano_sonatas': ["'mozart_piano_sonatas.measures' "
                                                  '(MuseScoreFacetName.MuseScoreMeasures)',
                                                  "'mozart_piano_sonatas.notes' (MuseScoreFacetName.MuseScoreNotes)",
                                                  "'mozart_piano_sonatas.expanded' "
                                                  '(MuseScoreFacetName.MuseScoreHarmonies)',
                                                  "'mozart_piano_sonatas.chords' (MuseScoreFacetName.MuseScoreChords)",
                                                  "'mozart_piano_sonatas.metadata' (FeatureName.Metadata)"]}},
 'outputs': {'basepath': None, 'packages': {}},
 'pipeline': []}

filtered_D = D.apply_step("HasHarmonyLabelsFilter")
all_metadata = filtered_D.get_metadata()

assert len(all_metadata) > 0, "No pieces selected for analysis."
chronological_corpus_names = all_metadata.get_corpus_names()

DCML harmony labels#

Hide source 
all_annotations = filtered_D.get_feature("DcmlAnnotations")
is_annotated_mask = all_metadata.label_count > 0
is_annotated_index = all_metadata.index[is_annotated_mask]
annotated_notes = filtered_D.get_feature("notes").subselect(is_annotated_index)
print(f"The annotated pieces have {len(annotated_notes)} notes.")

The annotated pieces have 104774 notes.

all_chords = filtered_D.get_feature("harmonylabels")
print(
    f"{len(all_annotations)} annotations, of which {len(all_chords)} are harmony labels."
)

15236 annotations, of which 14995 are harmony labels.

Harmony labels#

Unigrams#

For computing unigram statistics, the tokens need to be grouped by their occurrence within a major or a minor key because this changes their meaning. To that aim, the annotated corpus needs to be sliced into contiguous localkey segments which are then grouped into a major (is_minor=False) and a minor group.

root_durations = (
    all_chords[all_chords.root.between(-5, 6)]
    .groupby(["root", "chord_type"])
    .duration_qb.sum()
)
# sort by stacked bar length:
# root_durations = root_durations.sort_values(key=lambda S: S.index.get_level_values(0).map(S.groupby(level=0).sum()),
# ascending=False)
bar_data = root_durations.reset_index()
bar_data.root = bar_data.root.map(ms3.fifths2iv)
fig = px.bar(
    bar_data,
    x="root",
    y="duration_qb",
    color="chord_type",
    title="Distribution of chord types over chord roots",
    labels=dict(
        root="Chord root expressed as interval above the local (or secondary) tonic",
        duration_qb="duration in quarter notes",
        chord_type="chord type",
    ),
)
fig.update_layout(**utils.STD_LAYOUT)
save_figure_as(fig, "chord_type_distribution_over_scale_degrees_absolute_stacked_bars")
fig.show()

relative_roots = all_chords[
    ["numeral", "duration_qb", "relativeroot", "localkey_is_minor", "chord_type"]
].copy()
relative_roots["relativeroot_resolved"] = ms3.transform(
    relative_roots, ms3.resolve_relative_keys, ["relativeroot", "localkey_is_minor"]
)
has_rel = relative_roots.relativeroot_resolved.notna()
relative_roots.loc[has_rel, "localkey_is_minor"] = relative_roots.loc[
    has_rel, "relativeroot_resolved"
].str.islower()
relative_roots["root"] = ms3.transform(
    relative_roots, ms3.roman_numeral2fifths, ["numeral", "localkey_is_minor"]
)
chord_type_frequency = all_chords.chord_type.value_counts()
replace_rare = ms3.map_dict(
    {t: "other" for t in chord_type_frequency[chord_type_frequency < 500].index}
)
relative_roots["type_reduced"] = relative_roots.chord_type.map(replace_rare)
# is_special = relative_roots.chord_type.isin(('It', 'Ger', 'Fr'))
# relative_roots.loc[is_special, 'root'] = -4

root_durations = (
    relative_roots.groupby(["root", "type_reduced"])
    .duration_qb.sum()
    .sort_values(ascending=False)
)
bar_data = root_durations.reset_index()
bar_data.root = bar_data.root.map(ms3.fifths2iv)
root_order = (
    bar_data.groupby("root")
    .duration_qb.sum()
    .sort_values(ascending=False)
    .index.to_list()
)
fig = px.bar(
    bar_data,
    x="root",
    y="duration_qb",
    color="type_reduced",
    barmode="group",
    log_y=True,
    color_discrete_map=utils.TYPE_COLORS,
    category_orders=dict(
        root=root_order,
        type_reduced=relative_roots.type_reduced.value_counts().index.to_list(),
    ),
    labels=dict(
        root="intervallic difference between chord root to the local or secondary tonic",
        duration_qb="duration in quarter notes",
        type_reduced="chord type",
    ),
    width=1000,
    height=400,
)
fig.update_layout(
    **utils.STD_LAYOUT,
    legend=dict(
        orientation="h",
        xanchor="right",
        x=1,
        y=1,
    ),
)
save_figure_as(fig, "chord_type_distribution_over_scale_degrees_absolute_grouped_bars")
fig.show()

print(
    f"Reduced to {len(set(bar_data.iloc[:,:2].itertuples(index=False, name=None)))} types. "
    f"Paper cites the sum of types in major and types in minor (see below), treating them as distinct."
)

Reduced to 33 types. Paper cites the sum of types in major and types in minor (see below), treating them as distinct.

dim_or_aug = bar_data[
    bar_data.root.str.startswith("a") | bar_data.root.str.startswith("d")
].duration_qb.sum()
complete = bar_data.duration_qb.sum()
print(
    f"On diminished or augmented scale degrees: {dim_or_aug} / {complete} = {dim_or_aug / complete}"
)

On diminished or augmented scale degrees: 0.0 / 22408.25 = 0.0

chords_by_mode = groupers.ModeGrouper().process(all_chords)
chords_by_mode.format = "scale_degree"

Whole dataset#

unigram_proportions = chords_by_mode.get_default_analysis()
unigram_proportions.make_ranking_table()
mode major minor
chord_and_mode scale_degrees duration_qb proportion proportion_% chord_and_mode scale_degrees duration_qb proportion proportion_%
rank
1 I, major (1, 3, 5) 4259.375000 0.232166 23.22 % i, minor (1, 3, 5) 899.00 0.221320 22.13 %
2 V7, major (5, 7, 2, 4) 1595.000000 0.086939 8.69 % V, minor (5, #7, 2) 456.50 0.112383 11.24 %
3 V, major (5, 7, 2) 1545.250000 0.084227 8.42 % V7, minor (5, #7, 2, 4) 271.25 0.066777 6.68 %
4 I6, major (3, 5, 1) 1442.583333 0.078631 7.86 % i6, minor (3, 5, 1) 251.50 0.061915 6.19 %
5 ii6, major (4, 6, 2) 946.500000 0.051591 5.16 % V(64), minor (5, 1, 3) 152.25 0.037482 3.75 %
... ... ... ... ... ... ... ... ... ... ...
368 IV(2), major (5, 6, 1) 0.500000 0.000027 0.0 % NaN NaN NaN NaN NaN
369 IM7, major (1, 3, 5, 7) 0.500000 0.000027 0.0 % NaN NaN NaN NaN NaN
370 V65/V/vi, major (#2, #4, 6, 7) 0.500000 0.000027 0.0 % NaN NaN NaN NaN NaN
371 v2, major (4, 5, b7, 2) 0.500000 0.000027 0.0 % NaN NaN NaN NaN NaN
372 V64/IV, major (5, 1, 3) 0.125000 0.000007 0.0 % NaN NaN NaN NaN NaN

372 rows × 10 columns

chords_by_mode.apply_step("Counter")
count
mode corpus piece chord_and_mode scale_degrees
major mozart_piano_sonatas K279-1 I, major (1, 3, 5) 42
I6, major (3, 5, 1) 21
V7, major (5, 7, 2, 4) 21
ii6, major (4, 6, 2) 20
V, major (5, 7, 2) 16
... ... ... ... ... ...
minor mozart_piano_sonatas K576-3 i, minor (1, 3, 5) 1
V65/V, minor (#4, #6, 1, 2) 1
V, minor (5, #7, 2) 1
#viio6, minor (2, 4, #7) 1
ii65, minor (4, #6, 1, 2) 1

2970 rows × 1 columns

chords_by_mode.format = "scale_degree"
chords_by_mode.get_default_analysis().make_ranking_table()
mode major minor
chord_and_mode scale_degrees duration_qb proportion proportion_% chord_and_mode scale_degrees duration_qb proportion proportion_%
rank
1 I, major (1, 3, 5) 4259.375000 0.232166 23.22 % i, minor (1, 3, 5) 899.00 0.221320 22.13 %
2 V7, major (5, 7, 2, 4) 1595.000000 0.086939 8.69 % V, minor (5, #7, 2) 456.50 0.112383 11.24 %
3 V, major (5, 7, 2) 1545.250000 0.084227 8.42 % V7, minor (5, #7, 2, 4) 271.25 0.066777 6.68 %
4 I6, major (3, 5, 1) 1442.583333 0.078631 7.86 % i6, minor (3, 5, 1) 251.50 0.061915 6.19 %
5 ii6, major (4, 6, 2) 946.500000 0.051591 5.16 % V(64), minor (5, 1, 3) 152.25 0.037482 3.75 %
... ... ... ... ... ... ... ... ... ... ...
368 IV(2), major (5, 6, 1) 0.500000 0.000027 0.0 % NaN NaN NaN NaN NaN
369 IM7, major (1, 3, 5, 7) 0.500000 0.000027 0.0 % NaN NaN NaN NaN NaN
370 V65/V/vi, major (#2, #4, 6, 7) 0.500000 0.000027 0.0 % NaN NaN NaN NaN NaN
371 v2, major (4, 5, b7, 2) 0.500000 0.000027 0.0 % NaN NaN NaN NaN NaN
372 V64/IV, major (5, 1, 3) 0.125000 0.000007 0.0 % NaN NaN NaN NaN NaN

372 rows × 10 columns

unigram_proportions.plot_grouped()