Overview#

This notebook gives a general overview of the features included in the dataset.

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

D = utils.get_dataset("wf_bach_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("Wilhelm Friedemann Bach – Piano Sonatas version v2.3")
print(f"Datapackage '{package.package_name}' @ {git_tag}")
print(f"dimcat version {dc.__version__}\n")
D

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

Wilhelm Friedemann Bach – Piano Sonatas version v2.3
Datapackage 'wf_bach_sonatas' @ v2.3
dimcat version 3.4.0

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

filtered_D = filters.HasHarmonyLabelsFilter(keep_values=[True]).process(D)
all_metadata = filtered_D.get_metadata()
assert len(all_metadata) > 0, "No pieces selected for analysis."
all_metadata

		TimeSig	KeySig	last_mc	last_mn	length_qb	last_mc_unfolded	last_mn_unfolded	length_qb_unfolded	volta_mcs	all_notes_qb	...	originalFormat	P86 (composer)	musicbrainz	viaf	imslp	pdf	staff_1_ambitus	staff_1_instrument	staff_2_ambitus	staff_2_instrument
corpus	piece
wf_bach_sonatas	F001_n08a	{1: '4/4'}	{1: 0}	63	63	252.0	126	126	504.0	()	602.75	...	cap	Q107277	https://musicbrainz.org/work/4cf167ee-4601-4d0...	<NA>	https://imslp.org/wiki/Keyboard_Sonata_in_C_ma...	https://imslp.org/wiki/Special:ReverseLookup/3838	52-89 (E3-F6)	Piano	33-76 (A1-E5)	Piano
	F001_n08b	{1: '3/4'}	{1: 0}	42	40	126.0	40	40	120.0	(8], [9]], [[17], [18)	237.00	...	cap	Q107277	https://musicbrainz.org/work/fd2561b4-869d-4af...	<NA>	https://imslp.org/wiki/Keyboard_Sonata_in_C_ma...	https://imslp.org/wiki/Special:ReverseLookup/3838	60-86 (C4-D6)	Piano	36-71 (C2-B4)	Piano
	F001_n08c	{1: '3/8', 17: '3/4', 18: '3/8', 81: '3/4', 82...	{1: 0}	101	101	154.5	202	202	309.0	()	390.50	...	cap	Q107277	https://musicbrainz.org/work/32703d10-01ac-4e5...	<NA>	https://imslp.org/wiki/Keyboard_Sonata_in_C_ma...	https://imslp.org/wiki/Special:ReverseLookup/3838	59-88 (B3-E6)	Piano	31-69 (G1-A4)	Piano
	F002_n07a	{1: '4/4'}	{1: 0}	64	62	256.0	124	124	496.0	(20], [21]], [[63], [64)	400.25	...	cap	Q107277	https://musicbrainz.org/work/90fefc58-8ebe-46e...	https://viaf.org/viaf/6344152502815710800004	https://imslp.org/wiki/Keyboard_Sonata_in_C_ma...	https://imslp.org/wiki/Special:ReverseLookup/3837	58-85 (A#3-C#6)	Piano	37-69 (C#2-A4)	Piano
	F002_n07b	{1: '3/4'}	{1: 0}	44	44	132.0	44	44	132.0	()	312.75	...	cap	Q107277	https://musicbrainz.org/work/3ff1582c-3fea-429...	https://viaf.org/viaf/6344152502815710800004	https://imslp.org/wiki/Keyboard_Sonata_in_C_ma...	https://imslp.org/wiki/Special:ReverseLookup/3837	58-86 (Bb3-D6)	Piano	40-67 (E2-G4)	Piano
	F002_n07c	{1: '3/4'}	{1: 0}	68	66	204.0	156	156	468.0	(24], [25]], [[67], [68)	416.25	...	cap	Q107277	https://musicbrainz.org/work/d4a16857-8e9c-455...	https://viaf.org/viaf/6344152502815710800004	https://imslp.org/wiki/Keyboard_Sonata_in_C_ma...	https://imslp.org/wiki/Special:ReverseLookup/3837	55-88 (G3-E6)	Piano	36-72 (C2-C5)	Piano
	F003_n04a	{1: '2/4'}	{1: 2}	85	83	166.0	170	166	332.0	()	431.79	...	cap	Q107277	https://musicbrainz.org/work/1be761f0-fbb7-4d8...	https://viaf.org/viaf/185957894	https://imslp.org/wiki/Keyboard_Sonata_in_D_ma...	https://imslp.org/wiki/Special:ReverseLookup/3834	47-86 (B2-D6)	Piano	38-76 (D2-E5)	Piano
	F003_n04b	{1: '3/4'}	{1: 2}	64	64	192.0	128	128	384.0	()	538.50	...	cap	Q107277	https://musicbrainz.org/work/b5ac6def-d156-4a8...	https://viaf.org/viaf/185957894	https://imslp.org/wiki/Keyboard_Sonata_in_D_ma...	https://imslp.org/wiki/Special:ReverseLookup/3834	54-85 (F#3-C#6)	Piano	40-71 (E2-B4)	Piano
	F003_n04c	{1: '2/2'}	{1: 2}	110	108	432.0	220	216	864.0	()	1107.92	...	cap	Q107277	https://musicbrainz.org/work/e8ab4cdb-56dc-4b8...	https://viaf.org/viaf/185957894	https://imslp.org/wiki/Keyboard_Sonata_in_D_ma...	https://imslp.org/wiki/Special:ReverseLookup/3834	55-86 (G3-D6)	Piano	35-74 (B1-D5)	Piano

9 rows × 55 columns

mean_composition_years = utils.corpus_mean_composition_years(all_metadata)
chronological_order = mean_composition_years.index.to_list()
corpus_colors = dict(zip(chronological_order, utils.CORPUS_COLOR_SCALE))
corpus_names = {
    corp: utils.get_corpus_display_name(corp) for corp in chronological_order
}
chronological_corpus_names = list(corpus_names.values())
corpus_name_colors = {
    corpus_names[corp]: color for corp, color in corpus_colors.items()
}

mean_composition_years

corpus
wf_bach_sonatas    1762.166667
Name: mean_composition_year, dtype: float64

Composition dates#

This section relies on the dataset’s metadata.

valid_composed_start = pd.to_numeric(all_metadata.composed_start, errors="coerce")
valid_composed_end = pd.to_numeric(all_metadata.composed_end, errors="coerce")
print(
    f"Composition dates range from {int(valid_composed_start.min())} {valid_composed_start.idxmin()} "
    f"to {int(valid_composed_end.max())} {valid_composed_end.idxmax()}."
)

Composition dates range from 1745 ('wf_bach_sonatas', 'F003_n04a') to 1784 ('wf_bach_sonatas', 'F002_n07a').

Mean composition years per corpus#

def make_summary(metadata_df):
    piece_is_annotated = metadata_df.label_count > 0
    return metadata_df[piece_is_annotated].copy()

summary

		TimeSig	KeySig	last_mc	last_mn	length_qb	last_mc_unfolded	last_mn_unfolded	length_qb_unfolded	volta_mcs	all_notes_qb	...	originalFormat	P86 (composer)	musicbrainz	viaf	imslp	pdf	staff_1_ambitus	staff_1_instrument	staff_2_ambitus	staff_2_instrument
corpus	piece
wf_bach_sonatas	F001_n08a	{1: '4/4'}	{1: 0}	63	63	252.0	126	126	504.0	()	602.75	...	cap	Q107277	https://musicbrainz.org/work/4cf167ee-4601-4d0...	<NA>	https://imslp.org/wiki/Keyboard_Sonata_in_C_ma...	https://imslp.org/wiki/Special:ReverseLookup/3838	52-89 (E3-F6)	Piano	33-76 (A1-E5)	Piano
	F001_n08b	{1: '3/4'}	{1: 0}	42	40	126.0	40	40	120.0	(8], [9]], [[17], [18)	237.00	...	cap	Q107277	https://musicbrainz.org/work/fd2561b4-869d-4af...	<NA>	https://imslp.org/wiki/Keyboard_Sonata_in_C_ma...	https://imslp.org/wiki/Special:ReverseLookup/3838	60-86 (C4-D6)	Piano	36-71 (C2-B4)	Piano
	F001_n08c	{1: '3/8', 17: '3/4', 18: '3/8', 81: '3/4', 82...	{1: 0}	101	101	154.5	202	202	309.0	()	390.50	...	cap	Q107277	https://musicbrainz.org/work/32703d10-01ac-4e5...	<NA>	https://imslp.org/wiki/Keyboard_Sonata_in_C_ma...	https://imslp.org/wiki/Special:ReverseLookup/3838	59-88 (B3-E6)	Piano	31-69 (G1-A4)	Piano
	F002_n07a	{1: '4/4'}	{1: 0}	64	62	256.0	124	124	496.0	(20], [21]], [[63], [64)	400.25	...	cap	Q107277	https://musicbrainz.org/work/90fefc58-8ebe-46e...	https://viaf.org/viaf/6344152502815710800004	https://imslp.org/wiki/Keyboard_Sonata_in_C_ma...	https://imslp.org/wiki/Special:ReverseLookup/3837	58-85 (A#3-C#6)	Piano	37-69 (C#2-A4)	Piano
	F002_n07b	{1: '3/4'}	{1: 0}	44	44	132.0	44	44	132.0	()	312.75	...	cap	Q107277	https://musicbrainz.org/work/3ff1582c-3fea-429...	https://viaf.org/viaf/6344152502815710800004	https://imslp.org/wiki/Keyboard_Sonata_in_C_ma...	https://imslp.org/wiki/Special:ReverseLookup/3837	58-86 (Bb3-D6)	Piano	40-67 (E2-G4)	Piano
	F002_n07c	{1: '3/4'}	{1: 0}	68	66	204.0	156	156	468.0	(24], [25]], [[67], [68)	416.25	...	cap	Q107277	https://musicbrainz.org/work/d4a16857-8e9c-455...	https://viaf.org/viaf/6344152502815710800004	https://imslp.org/wiki/Keyboard_Sonata_in_C_ma...	https://imslp.org/wiki/Special:ReverseLookup/3837	55-88 (G3-E6)	Piano	36-72 (C2-C5)	Piano
	F003_n04a	{1: '2/4'}	{1: 2}	85	83	166.0	170	166	332.0	()	431.79	...	cap	Q107277	https://musicbrainz.org/work/1be761f0-fbb7-4d8...	https://viaf.org/viaf/185957894	https://imslp.org/wiki/Keyboard_Sonata_in_D_ma...	https://imslp.org/wiki/Special:ReverseLookup/3834	47-86 (B2-D6)	Piano	38-76 (D2-E5)	Piano
	F003_n04b	{1: '3/4'}	{1: 2}	64	64	192.0	128	128	384.0	()	538.50	...	cap	Q107277	https://musicbrainz.org/work/b5ac6def-d156-4a8...	https://viaf.org/viaf/185957894	https://imslp.org/wiki/Keyboard_Sonata_in_D_ma...	https://imslp.org/wiki/Special:ReverseLookup/3834	54-85 (F#3-C#6)	Piano	40-71 (E2-B4)	Piano
	F003_n04c	{1: '2/2'}	{1: 2}	110	108	432.0	220	216	864.0	()	1107.92	...	cap	Q107277	https://musicbrainz.org/work/e8ab4cdb-56dc-4b8...	https://viaf.org/viaf/185957894	https://imslp.org/wiki/Keyboard_Sonata_in_D_ma...	https://imslp.org/wiki/Special:ReverseLookup/3834	55-86 (G3-D6)	Piano	35-74 (B1-D5)	Piano

9 rows × 55 columns

Composition years histogram#

Dimensions#

Overview#

def make_overview_table(groupby, group_name="pieces"):
    n_groups = groupby.size().rename(group_name)
    absolute_numbers = dict(
        measures=groupby.last_mn.sum(),
        length=groupby.length_qb.sum(),
        notes=groupby.n_onsets.sum(),
        labels=groupby.label_count.sum(),
    )
    absolute = pd.DataFrame.from_dict(absolute_numbers)
    absolute = pd.concat([n_groups, absolute], axis=1)
    sum_row = pd.DataFrame(absolute.sum(), columns=["sum"]).T
    absolute = pd.concat([absolute, sum_row])
    return absolute


absolute = make_overview_table(summary.groupby("workTitle"))
# print(absolute.astype(int).to_markdown())
absolute.astype(int)

	pieces	measures	length	notes	labels
Keyboard Sonata in C major	6	376	1124	4957	924
Keyboard Sonata in D major	3	255	790	3594	829
sum	9	631	1914	8551	1753

def summarize_dataset(D):
    all_metadata = D.get_metadata()
    summary = make_summary(all_metadata)
    return make_overview_table(summary.groupby(level=0))


corpus_summary = summarize_dataset(D)
print(corpus_summary.astype(int).to_markdown())

|                 |   pieces |   measures |   length |   notes |   labels |
|:----------------|---------:|-----------:|---------:|--------:|---------:|
| wf_bach_sonatas |        9 |        631 |     1914 |    8551 |     1753 |
| sum             |        9 |        631 |     1914 |    8551 |     1753 |

Measures#

all_measures = D.get_feature("measures")
print(
    f"{len(all_measures.index)} measures over {len(all_measures.groupby(level=[0,1]))} files."
)
all_measures.head()

635 measures over 9 files.

			mc	mn	quarterbeats	duration_qb	keysig	timesig	act_dur	mc_offset	numbering_offset	dont_count	barline	breaks	repeats	next	volta	markers	jump_bwd	jump_fwd	play_until
corpus	piece	i
wf_bach_sonatas	F001_n08a	0	1	1	0	4.0	0	4/4	1	0	<NA>	<NA>	<NA>	<NA>	firstMeasure	(2,)	<NA>	<NA>	<NA>	<NA>	<NA>
		1	2	2	4	4.0	0	4/4	1	0	<NA>	<NA>	<NA>	<NA>	<NA>	(3,)	<NA>	<NA>	<NA>	<NA>	<NA>
		2	3	3	8	4.0	0	4/4	1	0	<NA>	<NA>	<NA>	line	<NA>	(4,)	<NA>	<NA>	<NA>	<NA>	<NA>
		3	4	4	12	4.0	0	4/4	1	0	<NA>	<NA>	<NA>	<NA>	<NA>	(5,)	<NA>	<NA>	<NA>	<NA>	<NA>
		4	5	5	16	4.0	0	4/4	1	0	<NA>	<NA>	<NA>	<NA>	<NA>	(6,)	<NA>	<NA>	<NA>	<NA>	<NA>

all_measures.get_default_analysis().plot_grouped()

Harmony labels#

All symbols, independent of the local key (the mode of which changes their semantics).

try:
    all_annotations = D.get_feature("harmonylabels").df
except Exception:
    all_annotations = pd.DataFrame()
n_annotations = len(all_annotations.index)
includes_annotations = n_annotations > 0
if includes_annotations:
    display(all_annotations.head())
    print(f"Concatenated annotation tables contains {all_annotations.shape[0]} rows.")
    no_chord = all_annotations.root.isna()
    if no_chord.sum() > 0:
        print(
            f"{no_chord.sum()} of them are not chords. Their values are:"
            f" {all_annotations.label[no_chord].value_counts(dropna=False).to_dict()}"
        )
    all_chords = all_annotations[~no_chord].copy()
    print(
        f"Dataset contains {all_chords.shape[0]} tokens and {len(all_chords.chord.unique())} types over "
        f"{len(all_chords.groupby(level=[0,1]))} documents."
    )
    all_annotations["corpus_name"] = all_annotations.index.get_level_values(0).map(
        utils.get_corpus_display_name
    )
    all_chords["corpus_name"] = all_chords.index.get_level_values(0).map(
        utils.get_corpus_display_name
    )
else:
    print("Dataset contains no annotations.")

			mc	mn	quarterbeats	duration_qb	mc_onset	mn_onset	timesig	staff	voice	volta	...	numeral_or_applied_to_numeral	intervals_over_bass	intervals_over_root	scale_degrees	scale_degrees_and_mode	scale_degrees_major	scale_degrees_minor	globalkey	localkey	chord
corpus	piece	i
wf_bach_sonatas	F001_n08a	0	1	1	0	4.0	0	0	4/4	2	1	<NA>	...	I	(M3, P5)	(M3, P5)	(1, 3, 5)	(1, 3, 5), major	(1, 3, 5)	(1, #3, 5)	C	I	I
		1	2	2	4	2.0	0	0	4/4	2	1	<NA>	...	IV	(P4, M6)	(M3, P5)	(1, 4, 6)	(1, 4, 6), major	(1, 4, 6)	(1, 4, #6)	C	I	IV64
		2	2	2	6	0.5	1/2	1/2	4/4	2	1	<NA>	...	I	(P4, M6)	(P4, M6)	(1, 4, 6)	(1, 4, 6), major	(1, 4, 6)	(1, 4, #6)	C	I	I(64)
		3	2	2	13/2	1.5	5/8	5/8	4/4	2	1	<NA>	...	I	(M3, P5)	(M3, P5)	(1, 3, 5)	(1, 3, 5), major	(1, 3, 5)	(1, #3, 5)	C	I	I
		4	3	3	8	2.0	0	0	4/4	2	1	<NA>	...	V	(M3, P5, m7)	(M3, P5, m7)	(5, 7, 2, 4)	(5, 7, 2, 4), major	(5, 7, 2, 4)	(5, #7, 2, 4)	C	I	V7

5 rows × 52 columns

Concatenated annotation tables contains 1724 rows.
Dataset contains 1724 tokens and 314 types over 9 documents.