Annotations

Show imports 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

Show source 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

Show source Hide source

D = utils.get_dataset("handel_keyboard", corpus_release="v2.4")
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("Georg Friedrich Händel – Grobschmied Variations (The Harmonious Blacksmith), HWV 430 version v2.4")
print(f"Datapackage '{package.package_name}' @ {git_tag}")
print(f"dimcat version {dc.__version__}\n")
D

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

Georg Friedrich Händel – Grobschmied Variations (The Harmonious Blacksmith), HWV 430 version v2.4
Datapackage 'handel_keyboard' @ v2.4
dimcat version 3.4.0

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

Show source 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 1721 notes.

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

346 annotations, of which 346 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 7 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 / 218.0 = 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
	chord_and_mode	scale_degrees	duration_qb	proportion	proportion_%
rank
1	I, major	(1, 3, 5)	59.50	0.272936	27.29 %
2	I6, major	(3, 5, 1)	35.00	0.160550	16.06 %
3	V, major	(5, 7, 2)	19.25	0.088303	8.83 %
4	IV, major	(4, 6, 1)	17.00	0.077982	7.8 %
5	V6, major	(7, 2, 5)	9.00	0.041284	4.13 %
6	I/V, major	(5, 7, 2)	8.00	0.036697	3.67 %
7	ii6/V, major	(1, 3, 6)	6.00	0.027523	2.75 %
8	V7, major	(5, 7, 2, 4)	5.50	0.025229	2.52 %
9	ii6, major	(4, 6, 2)	4.50	0.020642	2.06 %
10	V/V, major	(2, #4, 6)	4.50	0.020642	2.06 %
11	viio6, major	(2, 4, 7)	3.50	0.016055	1.61 %
12	V2, major	(4, 5, 7, 2)	3.00	0.013761	1.38 %
13	V65, major	(7, 2, 4, 5)	3.00	0.013761	1.38 %
14	ii, major	(2, 4, 6)	3.00	0.013761	1.38 %
15	V(64), major	(5, 1, 3)	3.00	0.013761	1.38 %
16	I6/V, major	(7, 2, 5)	3.00	0.013761	1.38 %
17	vi, major	(6, 1, 3)	2.75	0.012615	1.26 %
18	V(4), major	(5, 1, 2)	2.50	0.011468	1.15 %
19	ii65/V, major	(1, 3, 5, 6)	2.50	0.011468	1.15 %
20	iii6, major	(5, 7, 3)	2.50	0.011468	1.15 %
21	vi/V, major	(3, 5, 7)	2.00	0.009174	0.92 %
22	IV6, major	(6, 1, 4)	1.50	0.006881	0.69 %
23	ii/V, major	(6, 1, 3)	1.00	0.004587	0.46 %
24	V(64)/V, major	(2, 5, 7)	1.00	0.004587	0.46 %
25	V2/V, major	(1, 2, #4, 6)	1.00	0.004587	0.46 %
26	V6(4), major	(1, 2, 5)	1.00	0.004587	0.46 %
27	IV(9), major	(4, 6, 1)	1.00	0.004587	0.46 %
28	V7/V, major	(2, #4, 6, 1)	1.00	0.004587	0.46 %
29	viio, major	(7, 2, 4)	1.00	0.004587	0.46 %
30	IV64, major	(1, 4, 6)	1.00	0.004587	0.46 %
31	IV6/V, major	(3, 5, 1)	1.00	0.004587	0.46 %
32	ii65, major	(4, 6, 1, 2)	1.00	0.004587	0.46 %
33	viio6/V, major	(6, 1, #4)	1.00	0.004587	0.46 %
34	I6(11), major	(3, 5, 1)	1.00	0.004587	0.46 %
35	vii%43, major	(4, 6, 7, 2)	1.00	0.004587	0.46 %
36	ii7, major	(2, 4, 6, 1)	0.50	0.002294	0.23 %
37	iii%65/V, major	(2, 4, 6, 7)	0.50	0.002294	0.23 %
38	iii, major	(3, 5, 7)	0.50	0.002294	0.23 %
39	V64/V, major	(6, 2, #4)	0.50	0.002294	0.23 %
40	vi6, major	(1, 3, 6)	0.50	0.002294	0.23 %
41	vi7, major	(6, 1, 3, 5)	0.50	0.002294	0.23 %
42	vii%65, major	(2, 4, 6, 7)	0.50	0.002294	0.23 %
43	V43, major	(2, 4, 5, 7)	0.50	0.002294	0.23 %
44	viio64, major	(4, 7, 2)	0.50	0.002294	0.23 %

chords_by_mode.apply_step("Counter")

					count
mode	corpus	piece	chord_and_mode	scale_degrees
major	handel_keyboard	hwv430d_Grobschmied_Aria	I, major	(1, 3, 5)	12
			I6, major	(3, 5, 1)	8
			V6, major	(7, 2, 5)	4
			ii6/V, major	(1, 3, 6)	4
			V, major	(5, 7, 2)	3
		...	...	...	...
		hwv430d_Grobschmied_Var5	ii6/V, major	(1, 3, 6)	2
			I/V, major	(5, 7, 2)	2
			ii, major	(2, 4, 6)	1
			V65, major	(7, 2, 4, 5)	1
			viio6, major	(2, 4, 7)	1

111 rows × 1 columns

chords_by_mode.format = "scale_degree"
chords_by_mode.get_default_analysis().make_ranking_table()

mode	major
	chord_and_mode	scale_degrees	duration_qb	proportion	proportion_%
rank
1	I, major	(1, 3, 5)	59.50	0.272936	27.29 %
2	I6, major	(3, 5, 1)	35.00	0.160550	16.06 %
3	V, major	(5, 7, 2)	19.25	0.088303	8.83 %
4	IV, major	(4, 6, 1)	17.00	0.077982	7.8 %
5	V6, major	(7, 2, 5)	9.00	0.041284	4.13 %
6	I/V, major	(5, 7, 2)	8.00	0.036697	3.67 %
7	ii6/V, major	(1, 3, 6)	6.00	0.027523	2.75 %
8	V7, major	(5, 7, 2, 4)	5.50	0.025229	2.52 %
9	ii6, major	(4, 6, 2)	4.50	0.020642	2.06 %
10	V/V, major	(2, #4, 6)	4.50	0.020642	2.06 %
11	viio6, major	(2, 4, 7)	3.50	0.016055	1.61 %
12	V2, major	(4, 5, 7, 2)	3.00	0.013761	1.38 %
13	V65, major	(7, 2, 4, 5)	3.00	0.013761	1.38 %
14	ii, major	(2, 4, 6)	3.00	0.013761	1.38 %
15	V(64), major	(5, 1, 3)	3.00	0.013761	1.38 %
16	I6/V, major	(7, 2, 5)	3.00	0.013761	1.38 %
17	vi, major	(6, 1, 3)	2.75	0.012615	1.26 %
18	V(4), major	(5, 1, 2)	2.50	0.011468	1.15 %
19	ii65/V, major	(1, 3, 5, 6)	2.50	0.011468	1.15 %
20	iii6, major	(5, 7, 3)	2.50	0.011468	1.15 %
21	vi/V, major	(3, 5, 7)	2.00	0.009174	0.92 %
22	IV6, major	(6, 1, 4)	1.50	0.006881	0.69 %
23	ii/V, major	(6, 1, 3)	1.00	0.004587	0.46 %
24	V(64)/V, major	(2, 5, 7)	1.00	0.004587	0.46 %
25	V2/V, major	(1, 2, #4, 6)	1.00	0.004587	0.46 %
26	V6(4), major	(1, 2, 5)	1.00	0.004587	0.46 %
27	IV(9), major	(4, 6, 1)	1.00	0.004587	0.46 %
28	V7/V, major	(2, #4, 6, 1)	1.00	0.004587	0.46 %
29	viio, major	(7, 2, 4)	1.00	0.004587	0.46 %
30	IV64, major	(1, 4, 6)	1.00	0.004587	0.46 %
31	IV6/V, major	(3, 5, 1)	1.00	0.004587	0.46 %
32	ii65, major	(4, 6, 1, 2)	1.00	0.004587	0.46 %
33	viio6/V, major	(6, 1, #4)	1.00	0.004587	0.46 %
34	I6(11), major	(3, 5, 1)	1.00	0.004587	0.46 %
35	vii%43, major	(4, 6, 7, 2)	1.00	0.004587	0.46 %
36	ii7, major	(2, 4, 6, 1)	0.50	0.002294	0.23 %
37	iii%65/V, major	(2, 4, 6, 7)	0.50	0.002294	0.23 %
38	iii, major	(3, 5, 7)	0.50	0.002294	0.23 %
39	V64/V, major	(6, 2, #4)	0.50	0.002294	0.23 %
40	vi6, major	(1, 3, 6)	0.50	0.002294	0.23 %
41	vi7, major	(6, 1, 3, 5)	0.50	0.002294	0.23 %
42	vii%65, major	(2, 4, 6, 7)	0.50	0.002294	0.23 %
43	V43, major	(2, 4, 5, 7)	0.50	0.002294	0.23 %
44	viio64, major	(4, 7, 2)	0.50	0.002294	0.23 %

unigram_proportions.plot_grouped()