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("chopin_mazurkas", corpus_release="v3.2")
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("Frédéric Chopin – Mazurkas version v3.2")
print(f"Datapackage '{package.package_name}' @ {git_tag}")
print(f"dimcat version {dc.__version__}\n")
D

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

Frédéric Chopin – Mazurkas version v3.2
Datapackage 'chopin_mazurkas' @ v3.2
dimcat version 3.4.0

Dataset
=======
{'inputs': {'basepath': None,
            'packages': {'chopin_mazurkas': ["'chopin_mazurkas.measures' (MuseScoreFacetName.MuseScoreMeasures)",
                                             "'chopin_mazurkas.notes' (MuseScoreFacetName.MuseScoreNotes)",
                                             "'chopin_mazurkas.expanded' (MuseScoreFacetName.MuseScoreHarmonies)",
                                             "'chopin_mazurkas.chords' (MuseScoreFacetName.MuseScoreChords)",
                                             "'chopin_mazurkas.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 57373 notes.

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

9084 annotations, of which 8957 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 43 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: 64.25 / 14604.25 = 0.004399404282999812

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) 2184.00 0.254976 25.5 % i, minor (1, 3, 5) 1221.750000 0.202318 20.23 %
2 V7, major (5, 7, 2, 4) 1282.75 0.149758 14.98 % V7, minor (5, #7, 2, 4) 625.416667 0.103567 10.36 %
3 V, major (5, 7, 2) 445.00 0.051953 5.2 % V, minor (5, #7, 2) 446.500000 0.073939 7.39 %
4 IV, major (4, 6, 1) 347.25 0.040541 4.05 % III, minor (3, 5, 7) 142.000000 0.023515 2.35 %
5 V7/V, major (2, #4, 6, 1) 225.75 0.026356 2.64 % I, minor (1, #3, 5) 129.250000 0.021403 2.14 %
... ... ... ... ... ... ... ... ... ... ...
456 iio, major (2, 4, b6) 0.50 0.000058 0.01 % NaN NaN NaN NaN NaN
457 ii%65/vi, major (2, 4, 6, 7) 0.50 0.000058 0.01 % NaN NaN NaN NaN NaN
458 iio/vi, major (7, 2, 4) 0.50 0.000058 0.01 % NaN NaN NaN NaN NaN
459 IM7, major (1, 3, 5, 7) 0.50 0.000058 0.01 % NaN NaN NaN NaN NaN
460 V7/V/vi, major (7, #2, #4, 6) 0.25 0.000029 0.0 % NaN NaN NaN NaN NaN

460 rows × 10 columns

chords_by_mode.apply_step("Counter")
count
mode corpus piece chord_and_mode scale_degrees
major chopin_mazurkas BI105-3op30-3 V7, major (5, 7, 2, 4) 18
I, major (1, 3, 5) 17
V(64)/vi, major (3, 6, 1) 5
i, major (1, b3, 5) 4
V7(b9), major (5, 7, 2, 4) 4
... ... ... ... ... ...
minor chopin_mazurkas BI89-4op24-4 V(13), minor (5, #7, 2) 1
III(7), minor (3, 5, 7) 1
I/V, minor (5, #7, 2) 1
I(9), minor (1, #3, 5) 1
Ger6, minor (6, 1, 3, #4) 1

2311 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) 2184.00 0.254976 25.5 % i, minor (1, 3, 5) 1221.750000 0.202318 20.23 %
2 V7, major (5, 7, 2, 4) 1282.75 0.149758 14.98 % V7, minor (5, #7, 2, 4) 625.416667 0.103567 10.36 %
3 V, major (5, 7, 2) 445.00 0.051953 5.2 % V, minor (5, #7, 2) 446.500000 0.073939 7.39 %
4 IV, major (4, 6, 1) 347.25 0.040541 4.05 % III, minor (3, 5, 7) 142.000000 0.023515 2.35 %
5 V7/V, major (2, #4, 6, 1) 225.75 0.026356 2.64 % I, minor (1, #3, 5) 129.250000 0.021403 2.14 %
... ... ... ... ... ... ... ... ... ... ...
456 iio, major (2, 4, b6) 0.50 0.000058 0.01 % NaN NaN NaN NaN NaN
457 ii%65/vi, major (2, 4, 6, 7) 0.50 0.000058 0.01 % NaN NaN NaN NaN NaN
458 iio/vi, major (7, 2, 4) 0.50 0.000058 0.01 % NaN NaN NaN NaN NaN
459 IM7, major (1, 3, 5, 7) 0.50 0.000058 0.01 % NaN NaN NaN NaN NaN
460 V7/V/vi, major (7, #2, #4, 6) 0.25 0.000029 0.0 % NaN NaN NaN NaN NaN

460 rows × 10 columns

unigram_proportions.plot_grouped()